diff --git a/.devcontainer/README.md b/.devcontainer/README.md index 2b18630a21..359e2e5aef 100644 --- a/.devcontainer/README.md +++ b/.devcontainer/README.md @@ -1,23 +1,26 @@ # Development with devcontainer + This project includes a devcontainer configuration that allows you to open the project in a container with a fully configured development environment. Both frontend and backend environments are initialized when the container is started. + ## GitHub Codespaces + [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langgenius/dify) you can simply click the button above to open this project in GitHub Codespaces. For more info, check out the [GitHub documentation](https://docs.github.com/en/free-pro-team@latest/github/developing-online-with-codespaces/creating-a-codespace#creating-a-codespace). - ## VS Code Dev Containers + [![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langgenius/dify) if you have VS Code installed, you can click the button above to open this project in VS Code Dev Containers. You can learn more in the [Dev Containers documentation](https://code.visualstudio.com/docs/devcontainers/containers). - ## Pros of Devcontainer + Unified Development Environment: By using devcontainers, you can ensure that all developers are developing in the same environment, reducing the occurrence of "it works on my machine" type of issues. Quick Start: New developers can set up their development environment in a few simple steps, without spending a lot of time on environment configuration. @@ -25,11 +28,13 @@ Quick Start: New developers can set up their development environment in a few si Isolation: Devcontainers isolate your project from your host operating system, reducing the chance of OS updates or other application installations impacting the development environment. ## Cons of Devcontainer + Learning Curve: For developers unfamiliar with Docker and VS Code, using devcontainers may be somewhat complex. Performance Impact: While usually minimal, programs running inside a devcontainer may be slightly slower than those running directly on the host. ## Troubleshooting + if you see such error message when you open this project in codespaces: ![Alt text](troubleshooting.png) diff --git a/.env.example b/.env.example deleted file mode 100644 index 3e95f2e982..0000000000 --- a/.env.example +++ /dev/null @@ -1,1197 +0,0 @@ -# ------------------------------ -# Environment Variables for API service & worker -# ------------------------------ - -# ------------------------------ -# Common Variables -# ------------------------------ - -# The backend URL of the console API, -# used to concatenate the authorization callback. -# If empty, it is the same domain. -# Example: https://api.console.dify.ai -CONSOLE_API_URL= - -# The front-end URL of the console web, -# used to concatenate some front-end addresses and for CORS configuration use. -# If empty, it is the same domain. -# Example: https://console.dify.ai -CONSOLE_WEB_URL= - -# Service API Url, -# used to display Service API Base Url to the front-end. -# If empty, it is the same domain. -# Example: https://api.dify.ai -SERVICE_API_URL= - -# WebApp API backend Url, -# used to declare the back-end URL for the front-end API. -# If empty, it is the same domain. -# Example: https://api.app.dify.ai -APP_API_URL= - -# WebApp Url, -# used to display WebAPP API Base Url to the front-end. -# If empty, it is the same domain. -# Example: https://app.dify.ai -APP_WEB_URL= - -# File preview or download Url prefix. -# used to display File preview or download Url to the front-end or as Multi-model inputs; -# Url is signed and has expiration time. -# Setting FILES_URL is required for file processing plugins. -# - For https://example.com, use FILES_URL=https://example.com -# - For http://example.com, use FILES_URL=http://example.com -# Recommendation: use a dedicated domain (e.g., https://upload.example.com). -# Alternatively, use http://:5001 or http://api:5001, -# ensuring port 5001 is externally accessible (see docker-compose.yaml). -FILES_URL= - -# INTERNAL_FILES_URL is used for plugin daemon communication within Docker network. -# Set this to the internal Docker service URL for proper plugin file access. -# Example: INTERNAL_FILES_URL=http://api:5001 -INTERNAL_FILES_URL= - -# ------------------------------ -# Server Configuration -# ------------------------------ - -# The log level for the application. -# Supported values are `DEBUG`, `INFO`, `WARNING`, `ERROR`, `CRITICAL` -LOG_LEVEL=INFO -# Log file path -LOG_FILE=/app/logs/server.log -# Log file max size, the unit is MB -LOG_FILE_MAX_SIZE=20 -# Log file max backup count -LOG_FILE_BACKUP_COUNT=5 -# Log dateformat -LOG_DATEFORMAT=%Y-%m-%d %H:%M:%S -# Log Timezone -LOG_TZ=UTC - -# Debug mode, default is false. -# It is recommended to turn on this configuration for local development -# to prevent some problems caused by monkey patch. -DEBUG=false - -# Flask debug mode, it can output trace information at the interface when turned on, -# which is convenient for debugging. -FLASK_DEBUG=false - -# Enable request logging, which will log the request and response information. -# And the log level is DEBUG -ENABLE_REQUEST_LOGGING=False - -# A secret key that is used for securely signing the session cookie -# and encrypting sensitive information on the database. -# You can generate a strong key using `openssl rand -base64 42`. -SECRET_KEY=sk-9f73s3ljTXVcMT3Blb3ljTqtsKiGHXVcMT3BlbkFJLK7U - -# Password for admin user initialization. -# If left unset, admin user will not be prompted for a password -# when creating the initial admin account. -# The length of the password cannot exceed 30 characters. -INIT_PASSWORD= - -# Deployment environment. -# Supported values are `PRODUCTION`, `TESTING`. Default is `PRODUCTION`. -# Testing environment. There will be a distinct color label on the front-end page, -# indicating that this environment is a testing environment. -DEPLOY_ENV=PRODUCTION - -# Whether to enable the version check policy. -# If set to empty, https://updates.dify.ai will be called for version check. -CHECK_UPDATE_URL=https://updates.dify.ai - -# Used to change the OpenAI base address, default is https://api.openai.com/v1. -# When OpenAI cannot be accessed in China, replace it with a domestic mirror address, -# or when a local model provides OpenAI compatible API, it can be replaced. -OPENAI_API_BASE=https://api.openai.com/v1 - -# When enabled, migrations will be executed prior to application startup -# and the application will start after the migrations have completed. -MIGRATION_ENABLED=true - -# File Access Time specifies a time interval in seconds for the file to be accessed. -# The default value is 300 seconds. -FILES_ACCESS_TIMEOUT=300 - -# Access token expiration time in minutes -ACCESS_TOKEN_EXPIRE_MINUTES=60 - -# Refresh token expiration time in days -REFRESH_TOKEN_EXPIRE_DAYS=30 - -# The maximum number of active requests for the application, where 0 means unlimited, should be a non-negative integer. -APP_MAX_ACTIVE_REQUESTS=0 -APP_MAX_EXECUTION_TIME=1200 - -# ------------------------------ -# Container Startup Related Configuration -# Only effective when starting with docker image or docker-compose. -# ------------------------------ - -# API service binding address, default: 0.0.0.0, i.e., all addresses can be accessed. -DIFY_BIND_ADDRESS=0.0.0.0 - -# API service binding port number, default 5001. -DIFY_PORT=5001 - -# The number of API server workers, i.e., the number of workers. -# Formula: number of cpu cores x 2 + 1 for sync, 1 for Gevent -# Reference: https://docs.gunicorn.org/en/stable/design.html#how-many-workers -SERVER_WORKER_AMOUNT=1 - -# Defaults to gevent. If using windows, it can be switched to sync or solo. -SERVER_WORKER_CLASS=gevent - -# Default number of worker connections, the default is 10. -SERVER_WORKER_CONNECTIONS=10 - -# Similar to SERVER_WORKER_CLASS. -# If using windows, it can be switched to sync or solo. -CELERY_WORKER_CLASS= - -# Request handling timeout. The default is 200, -# it is recommended to set it to 360 to support a longer sse connection time. -GUNICORN_TIMEOUT=360 - -# The number of Celery workers. The default is 1, and can be set as needed. -CELERY_WORKER_AMOUNT= - -# Flag indicating whether to enable autoscaling of Celery workers. -# -# Autoscaling is useful when tasks are CPU intensive and can be dynamically -# allocated and deallocated based on the workload. -# -# When autoscaling is enabled, the maximum and minimum number of workers can -# be specified. The autoscaling algorithm will dynamically adjust the number -# of workers within the specified range. -# -# Default is false (i.e., autoscaling is disabled). -# -# Example: -# CELERY_AUTO_SCALE=true -CELERY_AUTO_SCALE=false - -# The maximum number of Celery workers that can be autoscaled. -# This is optional and only used when autoscaling is enabled. -# Default is not set. -CELERY_MAX_WORKERS= - -# The minimum number of Celery workers that can be autoscaled. -# This is optional and only used when autoscaling is enabled. -# Default is not set. -CELERY_MIN_WORKERS= - -# API Tool configuration -API_TOOL_DEFAULT_CONNECT_TIMEOUT=10 -API_TOOL_DEFAULT_READ_TIMEOUT=60 - -# ------------------------------- -# Datasource Configuration -# -------------------------------- -ENABLE_WEBSITE_JINAREADER=true -ENABLE_WEBSITE_FIRECRAWL=true -ENABLE_WEBSITE_WATERCRAWL=true - -# ------------------------------ -# Database Configuration -# The database uses PostgreSQL. Please use the public schema. -# It is consistent with the configuration in the 'db' service below. -# ------------------------------ - -DB_USERNAME=postgres -DB_PASSWORD=difyai123456 -DB_HOST=db -DB_PORT=5432 -DB_DATABASE=dify -# The size of the database connection pool. -# The default is 30 connections, which can be appropriately increased. -SQLALCHEMY_POOL_SIZE=30 -# Database connection pool recycling time, the default is 3600 seconds. -SQLALCHEMY_POOL_RECYCLE=3600 -# Whether to print SQL, default is false. -SQLALCHEMY_ECHO=false -# If True, will test connections for liveness upon each checkout -SQLALCHEMY_POOL_PRE_PING=false -# Whether to enable the Last in first out option or use default FIFO queue if is false -SQLALCHEMY_POOL_USE_LIFO=false - -# Maximum number of connections to the database -# Default is 100 -# -# Reference: https://www.postgresql.org/docs/current/runtime-config-connection.html#GUC-MAX-CONNECTIONS -POSTGRES_MAX_CONNECTIONS=100 - -# Sets the amount of shared memory used for postgres's shared buffers. -# Default is 128MB -# Recommended value: 25% of available memory -# Reference: https://www.postgresql.org/docs/current/runtime-config-resource.html#GUC-SHARED-BUFFERS -POSTGRES_SHARED_BUFFERS=128MB - -# Sets the amount of memory used by each database worker for working space. -# Default is 4MB -# -# Reference: https://www.postgresql.org/docs/current/runtime-config-resource.html#GUC-WORK-MEM -POSTGRES_WORK_MEM=4MB - -# Sets the amount of memory reserved for maintenance activities. -# Default is 64MB -# -# Reference: https://www.postgresql.org/docs/current/runtime-config-resource.html#GUC-MAINTENANCE-WORK-MEM -POSTGRES_MAINTENANCE_WORK_MEM=64MB - -# Sets the planner's assumption about the effective cache size. -# Default is 4096MB -# -# Reference: https://www.postgresql.org/docs/current/runtime-config-query.html#GUC-EFFECTIVE-CACHE-SIZE -POSTGRES_EFFECTIVE_CACHE_SIZE=4096MB - -# ------------------------------ -# Redis Configuration -# This Redis configuration is used for caching and for pub/sub during conversation. -# ------------------------------ - -REDIS_HOST=redis -REDIS_PORT=6379 -REDIS_USERNAME= -REDIS_PASSWORD=difyai123456 -REDIS_USE_SSL=false -REDIS_DB=0 - -# Whether to use Redis Sentinel mode. -# If set to true, the application will automatically discover and connect to the master node through Sentinel. -REDIS_USE_SENTINEL=false - -# List of Redis Sentinel nodes. If Sentinel mode is enabled, provide at least one Sentinel IP and port. -# Format: `:,:,:` -REDIS_SENTINELS= -REDIS_SENTINEL_SERVICE_NAME= -REDIS_SENTINEL_USERNAME= -REDIS_SENTINEL_PASSWORD= -REDIS_SENTINEL_SOCKET_TIMEOUT=0.1 - -# List of Redis Cluster nodes. If Cluster mode is enabled, provide at least one Cluster IP and port. -# Format: `:,:,:` -REDIS_USE_CLUSTERS=false -REDIS_CLUSTERS= -REDIS_CLUSTERS_PASSWORD= - -# ------------------------------ -# Celery Configuration -# ------------------------------ - -# Use redis as the broker, and redis db 1 for celery broker. -# Format as follows: `redis://:@:/` -# Example: redis://:difyai123456@redis:6379/1 -# If use Redis Sentinel, format as follows: `sentinel://:@:/` -# Example: sentinel://localhost:26379/1;sentinel://localhost:26380/1;sentinel://localhost:26381/1 -CELERY_BROKER_URL=redis://:difyai123456@redis:6379/1 -BROKER_USE_SSL=false - -# If you are using Redis Sentinel for high availability, configure the following settings. -CELERY_USE_SENTINEL=false -CELERY_SENTINEL_MASTER_NAME= -CELERY_SENTINEL_PASSWORD= -CELERY_SENTINEL_SOCKET_TIMEOUT=0.1 - -# ------------------------------ -# CORS Configuration -# Used to set the front-end cross-domain access policy. -# ------------------------------ - -# Specifies the allowed origins for cross-origin requests to the Web API, -# e.g. https://dify.app or * for all origins. -WEB_API_CORS_ALLOW_ORIGINS=* - -# Specifies the allowed origins for cross-origin requests to the console API, -# e.g. https://cloud.dify.ai or * for all origins. -CONSOLE_CORS_ALLOW_ORIGINS=* - -# ------------------------------ -# File Storage Configuration -# ------------------------------ - -# The type of storage to use for storing user files. -STORAGE_TYPE=opendal - -# Apache OpenDAL Configuration -# The configuration for OpenDAL consists of the following format: OPENDAL__. -# You can find all the service configurations (CONFIG_NAME) in the repository at: https://github.com/apache/opendal/tree/main/core/src/services. -# Dify will scan configurations starting with OPENDAL_ and automatically apply them. -# The scheme name for the OpenDAL storage. -OPENDAL_SCHEME=fs -# Configurations for OpenDAL Local File System. -OPENDAL_FS_ROOT=storage - -# ClickZetta Volume Configuration (for storage backend) -# To use ClickZetta Volume as storage backend, set STORAGE_TYPE=clickzetta-volume -# Note: ClickZetta Volume will reuse the existing CLICKZETTA_* connection parameters - -# Volume type selection (three types available): -# - user: Personal/small team use, simple config, user-level permissions -# - table: Enterprise multi-tenant, smart routing, table-level + user-level permissions -# - external: Data lake integration, external storage connection, volume-level + storage-level permissions -CLICKZETTA_VOLUME_TYPE=user - -# External Volume name (required only when TYPE=external) -CLICKZETTA_VOLUME_NAME= - -# Table Volume table prefix (used only when TYPE=table) -CLICKZETTA_VOLUME_TABLE_PREFIX=dataset_ - -# Dify file directory prefix (isolates from other apps, recommended to keep default) -CLICKZETTA_VOLUME_DIFY_PREFIX=dify_km - -# S3 Configuration -# -S3_ENDPOINT= -S3_REGION=us-east-1 -S3_BUCKET_NAME=difyai -S3_ACCESS_KEY= -S3_SECRET_KEY= -# Whether to use AWS managed IAM roles for authenticating with the S3 service. -# If set to false, the access key and secret key must be provided. -S3_USE_AWS_MANAGED_IAM=false - -# Azure Blob Configuration -# -AZURE_BLOB_ACCOUNT_NAME=difyai -AZURE_BLOB_ACCOUNT_KEY=difyai -AZURE_BLOB_CONTAINER_NAME=difyai-container -AZURE_BLOB_ACCOUNT_URL=https://.blob.core.windows.net - -# Google Storage Configuration -# -GOOGLE_STORAGE_BUCKET_NAME=your-bucket-name -GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64= - -# The Alibaba Cloud OSS configurations, -# -ALIYUN_OSS_BUCKET_NAME=your-bucket-name -ALIYUN_OSS_ACCESS_KEY=your-access-key -ALIYUN_OSS_SECRET_KEY=your-secret-key -ALIYUN_OSS_ENDPOINT=https://oss-ap-southeast-1-internal.aliyuncs.com -ALIYUN_OSS_REGION=ap-southeast-1 -ALIYUN_OSS_AUTH_VERSION=v4 -# Don't start with '/'. OSS doesn't support leading slash in object names. -ALIYUN_OSS_PATH=your-path - -# Tencent COS Configuration -# -TENCENT_COS_BUCKET_NAME=your-bucket-name -TENCENT_COS_SECRET_KEY=your-secret-key -TENCENT_COS_SECRET_ID=your-secret-id -TENCENT_COS_REGION=your-region -TENCENT_COS_SCHEME=your-scheme - -# Oracle Storage Configuration -# -OCI_ENDPOINT=https://your-object-storage-namespace.compat.objectstorage.us-ashburn-1.oraclecloud.com -OCI_BUCKET_NAME=your-bucket-name -OCI_ACCESS_KEY=your-access-key -OCI_SECRET_KEY=your-secret-key -OCI_REGION=us-ashburn-1 - -# Huawei OBS Configuration -# -HUAWEI_OBS_BUCKET_NAME=your-bucket-name -HUAWEI_OBS_SECRET_KEY=your-secret-key -HUAWEI_OBS_ACCESS_KEY=your-access-key -HUAWEI_OBS_SERVER=your-server-url - -# Volcengine TOS Configuration -# -VOLCENGINE_TOS_BUCKET_NAME=your-bucket-name -VOLCENGINE_TOS_SECRET_KEY=your-secret-key -VOLCENGINE_TOS_ACCESS_KEY=your-access-key -VOLCENGINE_TOS_ENDPOINT=your-server-url -VOLCENGINE_TOS_REGION=your-region - -# Baidu OBS Storage Configuration -# -BAIDU_OBS_BUCKET_NAME=your-bucket-name -BAIDU_OBS_SECRET_KEY=your-secret-key -BAIDU_OBS_ACCESS_KEY=your-access-key -BAIDU_OBS_ENDPOINT=your-server-url - -# Supabase Storage Configuration -# -SUPABASE_BUCKET_NAME=your-bucket-name -SUPABASE_API_KEY=your-access-key -SUPABASE_URL=your-server-url - -# ------------------------------ -# Vector Database Configuration -# ------------------------------ - -# The type of vector store to use. -# Supported values are `weaviate`, `qdrant`, `milvus`, `myscale`, `relyt`, `pgvector`, `pgvecto-rs`, `chroma`, `opensearch`, `oracle`, `tencent`, `elasticsearch`, `elasticsearch-ja`, `analyticdb`, `couchbase`, `vikingdb`, `oceanbase`, `opengauss`, `tablestore`,`vastbase`,`tidb`,`tidb_on_qdrant`,`baidu`,`lindorm`,`huawei_cloud`,`upstash`, `matrixone`. -VECTOR_STORE=weaviate - -# The Weaviate endpoint URL. Only available when VECTOR_STORE is `weaviate`. -WEAVIATE_ENDPOINT=http://weaviate:8080 -WEAVIATE_API_KEY=WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih - -# The Qdrant endpoint URL. Only available when VECTOR_STORE is `qdrant`. -QDRANT_URL=http://qdrant:6333 -QDRANT_API_KEY=difyai123456 -QDRANT_CLIENT_TIMEOUT=20 -QDRANT_GRPC_ENABLED=false -QDRANT_GRPC_PORT=6334 -QDRANT_REPLICATION_FACTOR=1 - -# Milvus configuration. Only available when VECTOR_STORE is `milvus`. -# The milvus uri. -MILVUS_URI=http://host.docker.internal:19530 -MILVUS_DATABASE= -MILVUS_TOKEN= -MILVUS_USER= -MILVUS_PASSWORD= -MILVUS_ENABLE_HYBRID_SEARCH=False -MILVUS_ANALYZER_PARAMS= - -# MyScale configuration, only available when VECTOR_STORE is `myscale` -# For multi-language support, please set MYSCALE_FTS_PARAMS with referring to: -# https://myscale.com/docs/en/text-search/#understanding-fts-index-parameters -MYSCALE_HOST=myscale -MYSCALE_PORT=8123 -MYSCALE_USER=default -MYSCALE_PASSWORD= -MYSCALE_DATABASE=dify -MYSCALE_FTS_PARAMS= - -# Couchbase configurations, only available when VECTOR_STORE is `couchbase` -# The connection string must include hostname defined in the docker-compose file (couchbase-server in this case) -COUCHBASE_CONNECTION_STRING=couchbase://couchbase-server -COUCHBASE_USER=Administrator -COUCHBASE_PASSWORD=password -COUCHBASE_BUCKET_NAME=Embeddings -COUCHBASE_SCOPE_NAME=_default - -# pgvector configurations, only available when VECTOR_STORE is `pgvector` -PGVECTOR_HOST=pgvector -PGVECTOR_PORT=5432 -PGVECTOR_USER=postgres -PGVECTOR_PASSWORD=difyai123456 -PGVECTOR_DATABASE=dify -PGVECTOR_MIN_CONNECTION=1 -PGVECTOR_MAX_CONNECTION=5 -PGVECTOR_PG_BIGM=false -PGVECTOR_PG_BIGM_VERSION=1.2-20240606 - -# vastbase configurations, only available when VECTOR_STORE is `vastbase` -VASTBASE_HOST=vastbase -VASTBASE_PORT=5432 -VASTBASE_USER=dify -VASTBASE_PASSWORD=Difyai123456 -VASTBASE_DATABASE=dify -VASTBASE_MIN_CONNECTION=1 -VASTBASE_MAX_CONNECTION=5 - -# pgvecto-rs configurations, only available when VECTOR_STORE is `pgvecto-rs` -PGVECTO_RS_HOST=pgvecto-rs -PGVECTO_RS_PORT=5432 -PGVECTO_RS_USER=postgres -PGVECTO_RS_PASSWORD=difyai123456 -PGVECTO_RS_DATABASE=dify - -# analyticdb configurations, only available when VECTOR_STORE is `analyticdb` -ANALYTICDB_KEY_ID=your-ak -ANALYTICDB_KEY_SECRET=your-sk -ANALYTICDB_REGION_ID=cn-hangzhou -ANALYTICDB_INSTANCE_ID=gp-ab123456 -ANALYTICDB_ACCOUNT=testaccount -ANALYTICDB_PASSWORD=testpassword -ANALYTICDB_NAMESPACE=dify -ANALYTICDB_NAMESPACE_PASSWORD=difypassword -ANALYTICDB_HOST=gp-test.aliyuncs.com -ANALYTICDB_PORT=5432 -ANALYTICDB_MIN_CONNECTION=1 -ANALYTICDB_MAX_CONNECTION=5 - -# TiDB vector configurations, only available when VECTOR_STORE is `tidb_vector` -TIDB_VECTOR_HOST=tidb -TIDB_VECTOR_PORT=4000 -TIDB_VECTOR_USER= -TIDB_VECTOR_PASSWORD= -TIDB_VECTOR_DATABASE=dify - -# Matrixone vector configurations. -MATRIXONE_HOST=matrixone -MATRIXONE_PORT=6001 -MATRIXONE_USER=dump -MATRIXONE_PASSWORD=111 -MATRIXONE_DATABASE=dify - -# Tidb on qdrant configuration, only available when VECTOR_STORE is `tidb_on_qdrant` -TIDB_ON_QDRANT_URL=http://127.0.0.1 -TIDB_ON_QDRANT_API_KEY=dify -TIDB_ON_QDRANT_CLIENT_TIMEOUT=20 -TIDB_ON_QDRANT_GRPC_ENABLED=false -TIDB_ON_QDRANT_GRPC_PORT=6334 -TIDB_PUBLIC_KEY=dify -TIDB_PRIVATE_KEY=dify -TIDB_API_URL=http://127.0.0.1 -TIDB_IAM_API_URL=http://127.0.0.1 -TIDB_REGION=regions/aws-us-east-1 -TIDB_PROJECT_ID=dify -TIDB_SPEND_LIMIT=100 - -# Chroma configuration, only available when VECTOR_STORE is `chroma` -CHROMA_HOST=127.0.0.1 -CHROMA_PORT=8000 -CHROMA_TENANT=default_tenant -CHROMA_DATABASE=default_database -CHROMA_AUTH_PROVIDER=chromadb.auth.token_authn.TokenAuthClientProvider -CHROMA_AUTH_CREDENTIALS= - -# Oracle configuration, only available when VECTOR_STORE is `oracle` -ORACLE_USER=dify -ORACLE_PASSWORD=dify -ORACLE_DSN=oracle:1521/FREEPDB1 -ORACLE_CONFIG_DIR=/app/api/storage/wallet -ORACLE_WALLET_LOCATION=/app/api/storage/wallet -ORACLE_WALLET_PASSWORD=dify -ORACLE_IS_AUTONOMOUS=false - -# relyt configurations, only available when VECTOR_STORE is `relyt` -RELYT_HOST=db -RELYT_PORT=5432 -RELYT_USER=postgres -RELYT_PASSWORD=difyai123456 -RELYT_DATABASE=postgres - -# open search configuration, only available when VECTOR_STORE is `opensearch` -OPENSEARCH_HOST=opensearch -OPENSEARCH_PORT=9200 -OPENSEARCH_SECURE=true -OPENSEARCH_VERIFY_CERTS=true -OPENSEARCH_AUTH_METHOD=basic -OPENSEARCH_USER=admin -OPENSEARCH_PASSWORD=admin -# If using AWS managed IAM, e.g. Managed Cluster or OpenSearch Serverless -OPENSEARCH_AWS_REGION=ap-southeast-1 -OPENSEARCH_AWS_SERVICE=aoss - -# tencent vector configurations, only available when VECTOR_STORE is `tencent` -TENCENT_VECTOR_DB_URL=http://127.0.0.1 -TENCENT_VECTOR_DB_API_KEY=dify -TENCENT_VECTOR_DB_TIMEOUT=30 -TENCENT_VECTOR_DB_USERNAME=dify -TENCENT_VECTOR_DB_DATABASE=dify -TENCENT_VECTOR_DB_SHARD=1 -TENCENT_VECTOR_DB_REPLICAS=2 -TENCENT_VECTOR_DB_ENABLE_HYBRID_SEARCH=false - -# ElasticSearch configuration, only available when VECTOR_STORE is `elasticsearch` -ELASTICSEARCH_HOST=0.0.0.0 -ELASTICSEARCH_PORT=9200 -ELASTICSEARCH_USERNAME=elastic -ELASTICSEARCH_PASSWORD=elastic -KIBANA_PORT=5601 - -# baidu vector configurations, only available when VECTOR_STORE is `baidu` -BAIDU_VECTOR_DB_ENDPOINT=http://127.0.0.1:5287 -BAIDU_VECTOR_DB_CONNECTION_TIMEOUT_MS=30000 -BAIDU_VECTOR_DB_ACCOUNT=root -BAIDU_VECTOR_DB_API_KEY=dify -BAIDU_VECTOR_DB_DATABASE=dify -BAIDU_VECTOR_DB_SHARD=1 -BAIDU_VECTOR_DB_REPLICAS=3 - -# VikingDB configurations, only available when VECTOR_STORE is `vikingdb` -VIKINGDB_ACCESS_KEY=your-ak -VIKINGDB_SECRET_KEY=your-sk -VIKINGDB_REGION=cn-shanghai -VIKINGDB_HOST=api-vikingdb.xxx.volces.com -VIKINGDB_SCHEMA=http -VIKINGDB_CONNECTION_TIMEOUT=30 -VIKINGDB_SOCKET_TIMEOUT=30 - -# Lindorm configuration, only available when VECTOR_STORE is `lindorm` -LINDORM_URL=http://lindorm:30070 -LINDORM_USERNAME=lindorm -LINDORM_PASSWORD=lindorm -LINDORM_QUERY_TIMEOUT=1 - -# OceanBase Vector configuration, only available when VECTOR_STORE is `oceanbase` -OCEANBASE_VECTOR_HOST=oceanbase -OCEANBASE_VECTOR_PORT=2881 -OCEANBASE_VECTOR_USER=root@test -OCEANBASE_VECTOR_PASSWORD=difyai123456 -OCEANBASE_VECTOR_DATABASE=test -OCEANBASE_CLUSTER_NAME=difyai -OCEANBASE_MEMORY_LIMIT=6G -OCEANBASE_ENABLE_HYBRID_SEARCH=false - -# opengauss configurations, only available when VECTOR_STORE is `opengauss` -OPENGAUSS_HOST=opengauss -OPENGAUSS_PORT=6600 -OPENGAUSS_USER=postgres -OPENGAUSS_PASSWORD=Dify@123 -OPENGAUSS_DATABASE=dify -OPENGAUSS_MIN_CONNECTION=1 -OPENGAUSS_MAX_CONNECTION=5 -OPENGAUSS_ENABLE_PQ=false - -# huawei cloud search service vector configurations, only available when VECTOR_STORE is `huawei_cloud` -HUAWEI_CLOUD_HOSTS=https://127.0.0.1:9200 -HUAWEI_CLOUD_USER=admin -HUAWEI_CLOUD_PASSWORD=admin - -# Upstash Vector configuration, only available when VECTOR_STORE is `upstash` -UPSTASH_VECTOR_URL=https://xxx-vector.upstash.io -UPSTASH_VECTOR_TOKEN=dify - -# TableStore Vector configuration -# (only used when VECTOR_STORE is tablestore) -TABLESTORE_ENDPOINT=https://instance-name.cn-hangzhou.ots.aliyuncs.com -TABLESTORE_INSTANCE_NAME=instance-name -TABLESTORE_ACCESS_KEY_ID=xxx -TABLESTORE_ACCESS_KEY_SECRET=xxx - -# Clickzetta configuration, only available when VECTOR_STORE is `clickzetta` -CLICKZETTA_USERNAME= -CLICKZETTA_PASSWORD= -CLICKZETTA_INSTANCE= -CLICKZETTA_SERVICE=api.clickzetta.com -CLICKZETTA_WORKSPACE=quick_start -CLICKZETTA_VCLUSTER=default_ap -CLICKZETTA_SCHEMA=dify -CLICKZETTA_BATCH_SIZE=100 -CLICKZETTA_ENABLE_INVERTED_INDEX=true -CLICKZETTA_ANALYZER_TYPE=chinese -CLICKZETTA_ANALYZER_MODE=smart -CLICKZETTA_VECTOR_DISTANCE_FUNCTION=cosine_distance - -# ------------------------------ -# Knowledge Configuration -# ------------------------------ - -# Upload file size limit, default 15M. -UPLOAD_FILE_SIZE_LIMIT=15 - -# The maximum number of files that can be uploaded at a time, default 5. -UPLOAD_FILE_BATCH_LIMIT=5 - -# ETL type, support: `dify`, `Unstructured` -# `dify` Dify's proprietary file extraction scheme -# `Unstructured` Unstructured.io file extraction scheme -ETL_TYPE=dify - -# Unstructured API path and API key, needs to be configured when ETL_TYPE is Unstructured -# Or using Unstructured for document extractor node for pptx. -# For example: http://unstructured:8000/general/v0/general -UNSTRUCTURED_API_URL= -UNSTRUCTURED_API_KEY= -SCARF_NO_ANALYTICS=true - -# ------------------------------ -# Model Configuration -# ------------------------------ - -# The maximum number of tokens allowed for prompt generation. -# This setting controls the upper limit of tokens that can be used by the LLM -# when generating a prompt in the prompt generation tool. -# Default: 512 tokens. -PROMPT_GENERATION_MAX_TOKENS=512 - -# The maximum number of tokens allowed for code generation. -# This setting controls the upper limit of tokens that can be used by the LLM -# when generating code in the code generation tool. -# Default: 1024 tokens. -CODE_GENERATION_MAX_TOKENS=1024 - -# Enable or disable plugin based token counting. If disabled, token counting will return 0. -# This can improve performance by skipping token counting operations. -# Default: false (disabled). -PLUGIN_BASED_TOKEN_COUNTING_ENABLED=false - -# ------------------------------ -# Multi-modal Configuration -# ------------------------------ - -# The format of the image/video/audio/document sent when the multi-modal model is input, -# the default is base64, optional url. -# The delay of the call in url mode will be lower than that in base64 mode. -# It is generally recommended to use the more compatible base64 mode. -# If configured as url, you need to configure FILES_URL as an externally accessible address so that the multi-modal model can access the image/video/audio/document. -MULTIMODAL_SEND_FORMAT=base64 -# Upload image file size limit, default 10M. -UPLOAD_IMAGE_FILE_SIZE_LIMIT=10 -# Upload video file size limit, default 100M. -UPLOAD_VIDEO_FILE_SIZE_LIMIT=100 -# Upload audio file size limit, default 50M. -UPLOAD_AUDIO_FILE_SIZE_LIMIT=50 - -# ------------------------------ -# Sentry Configuration -# Used for application monitoring and error log tracking. -# ------------------------------ -SENTRY_DSN= - -# API Service Sentry DSN address, default is empty, when empty, -# all monitoring information is not reported to Sentry. -# If not set, Sentry error reporting will be disabled. -API_SENTRY_DSN= -# API Service The reporting ratio of Sentry events, if it is 0.01, it is 1%. -API_SENTRY_TRACES_SAMPLE_RATE=1.0 -# API Service The reporting ratio of Sentry profiles, if it is 0.01, it is 1%. -API_SENTRY_PROFILES_SAMPLE_RATE=1.0 - -# Web Service Sentry DSN address, default is empty, when empty, -# all monitoring information is not reported to Sentry. -# If not set, Sentry error reporting will be disabled. -WEB_SENTRY_DSN= - -# ------------------------------ -# Notion Integration Configuration -# Variables can be obtained by applying for Notion integration: https://www.notion.so/my-integrations -# ------------------------------ - -# Configure as "public" or "internal". -# Since Notion's OAuth redirect URL only supports HTTPS, -# if deploying locally, please use Notion's internal integration. -NOTION_INTEGRATION_TYPE=public -# Notion OAuth client secret (used for public integration type) -NOTION_CLIENT_SECRET= -# Notion OAuth client id (used for public integration type) -NOTION_CLIENT_ID= -# Notion internal integration secret. -# If the value of NOTION_INTEGRATION_TYPE is "internal", -# you need to configure this variable. -NOTION_INTERNAL_SECRET= - -# ------------------------------ -# Mail related configuration -# ------------------------------ - -# Mail type, support: resend, smtp, sendgrid -MAIL_TYPE=resend - -# Default send from email address, if not specified -# If using SendGrid, use the 'from' field for authentication if necessary. -MAIL_DEFAULT_SEND_FROM= - -# API-Key for the Resend email provider, used when MAIL_TYPE is `resend`. -RESEND_API_URL=https://api.resend.com -RESEND_API_KEY=your-resend-api-key - - -# SMTP server configuration, used when MAIL_TYPE is `smtp` -SMTP_SERVER= -SMTP_PORT=465 -SMTP_USERNAME= -SMTP_PASSWORD= -SMTP_USE_TLS=true -SMTP_OPPORTUNISTIC_TLS=false - -# Sendgid configuration -SENDGRID_API_KEY= - -# ------------------------------ -# Others Configuration -# ------------------------------ - -# Maximum length of segmentation tokens for indexing -INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=4000 - -# Member invitation link valid time (hours), -# Default: 72. -INVITE_EXPIRY_HOURS=72 - -# Reset password token valid time (minutes), -RESET_PASSWORD_TOKEN_EXPIRY_MINUTES=5 - -# The sandbox service endpoint. -CODE_EXECUTION_ENDPOINT=http://sandbox:8194 -CODE_EXECUTION_API_KEY=dify-sandbox -CODE_MAX_NUMBER=9223372036854775807 -CODE_MIN_NUMBER=-9223372036854775808 -CODE_MAX_DEPTH=5 -CODE_MAX_PRECISION=20 -CODE_MAX_STRING_LENGTH=80000 -CODE_MAX_STRING_ARRAY_LENGTH=30 -CODE_MAX_OBJECT_ARRAY_LENGTH=30 -CODE_MAX_NUMBER_ARRAY_LENGTH=1000 -CODE_EXECUTION_CONNECT_TIMEOUT=10 -CODE_EXECUTION_READ_TIMEOUT=60 -CODE_EXECUTION_WRITE_TIMEOUT=10 -TEMPLATE_TRANSFORM_MAX_LENGTH=80000 - -# Workflow runtime configuration -WORKFLOW_MAX_EXECUTION_STEPS=500 -WORKFLOW_MAX_EXECUTION_TIME=1200 -WORKFLOW_CALL_MAX_DEPTH=5 -MAX_VARIABLE_SIZE=204800 -WORKFLOW_PARALLEL_DEPTH_LIMIT=3 -WORKFLOW_FILE_UPLOAD_LIMIT=10 - -# Workflow storage configuration -# Options: rdbms, hybrid -# rdbms: Use only the relational database (default) -# hybrid: Save new data to object storage, read from both object storage and RDBMS -WORKFLOW_NODE_EXECUTION_STORAGE=rdbms - -# Repository configuration -# Core workflow execution repository implementation -CORE_WORKFLOW_EXECUTION_REPOSITORY=core.repositories.sqlalchemy_workflow_execution_repository.SQLAlchemyWorkflowExecutionRepository - -# Core workflow node execution repository implementation -CORE_WORKFLOW_NODE_EXECUTION_REPOSITORY=core.repositories.sqlalchemy_workflow_node_execution_repository.SQLAlchemyWorkflowNodeExecutionRepository - -# API workflow node execution repository implementation -API_WORKFLOW_NODE_EXECUTION_REPOSITORY=repositories.sqlalchemy_api_workflow_node_execution_repository.DifyAPISQLAlchemyWorkflowNodeExecutionRepository - -# API workflow run repository implementation -API_WORKFLOW_RUN_REPOSITORY=repositories.sqlalchemy_api_workflow_run_repository.DifyAPISQLAlchemyWorkflowRunRepository - -# HTTP request node in workflow configuration -HTTP_REQUEST_NODE_MAX_BINARY_SIZE=10485760 -HTTP_REQUEST_NODE_MAX_TEXT_SIZE=1048576 -HTTP_REQUEST_NODE_SSL_VERIFY=True - -# Respect X-* headers to redirect clients -RESPECT_XFORWARD_HEADERS_ENABLED=false - -# SSRF Proxy server HTTP URL -SSRF_PROXY_HTTP_URL=http://ssrf_proxy:3128 -# SSRF Proxy server HTTPS URL -SSRF_PROXY_HTTPS_URL=http://ssrf_proxy:3128 - -# Maximum loop count in the workflow -LOOP_NODE_MAX_COUNT=100 - -# The maximum number of tools that can be used in the agent. -MAX_TOOLS_NUM=10 - -# Maximum number of Parallelism branches in the workflow -MAX_PARALLEL_LIMIT=10 - -# The maximum number of iterations for agent setting -MAX_ITERATIONS_NUM=99 - -# ------------------------------ -# Environment Variables for web Service -# ------------------------------ - -# The timeout for the text generation in millisecond -TEXT_GENERATION_TIMEOUT_MS=60000 - -# Allow rendering unsafe URLs which have "data:" scheme. -ALLOW_UNSAFE_DATA_SCHEME=false - -# ------------------------------ -# Environment Variables for db Service -# ------------------------------ - -# The name of the default postgres user. -POSTGRES_USER=${DB_USERNAME} -# The password for the default postgres user. -POSTGRES_PASSWORD=${DB_PASSWORD} -# The name of the default postgres database. -POSTGRES_DB=${DB_DATABASE} -# postgres data directory -PGDATA=/var/lib/postgresql/data/pgdata - -# ------------------------------ -# Environment Variables for sandbox Service -# ------------------------------ - -# The API key for the sandbox service -SANDBOX_API_KEY=dify-sandbox -# The mode in which the Gin framework runs -SANDBOX_GIN_MODE=release -# The timeout for the worker in seconds -SANDBOX_WORKER_TIMEOUT=15 -# Enable network for the sandbox service -SANDBOX_ENABLE_NETWORK=true -# HTTP proxy URL for SSRF protection -SANDBOX_HTTP_PROXY=http://ssrf_proxy:3128 -# HTTPS proxy URL for SSRF protection -SANDBOX_HTTPS_PROXY=http://ssrf_proxy:3128 -# The port on which the sandbox service runs -SANDBOX_PORT=8194 - -# ------------------------------ -# Environment Variables for weaviate Service -# (only used when VECTOR_STORE is weaviate) -# ------------------------------ -WEAVIATE_PERSISTENCE_DATA_PATH=/var/lib/weaviate -WEAVIATE_QUERY_DEFAULTS_LIMIT=25 -WEAVIATE_AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED=true -WEAVIATE_DEFAULT_VECTORIZER_MODULE=none -WEAVIATE_CLUSTER_HOSTNAME=node1 -WEAVIATE_AUTHENTICATION_APIKEY_ENABLED=true -WEAVIATE_AUTHENTICATION_APIKEY_ALLOWED_KEYS=WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih -WEAVIATE_AUTHENTICATION_APIKEY_USERS=hello@dify.ai -WEAVIATE_AUTHORIZATION_ADMINLIST_ENABLED=true -WEAVIATE_AUTHORIZATION_ADMINLIST_USERS=hello@dify.ai - -# ------------------------------ -# Environment Variables for Chroma -# (only used when VECTOR_STORE is chroma) -# ------------------------------ - -# Authentication credentials for Chroma server -CHROMA_SERVER_AUTHN_CREDENTIALS=difyai123456 -# Authentication provider for Chroma server -CHROMA_SERVER_AUTHN_PROVIDER=chromadb.auth.token_authn.TokenAuthenticationServerProvider -# Persistence setting for Chroma server -CHROMA_IS_PERSISTENT=TRUE - -# ------------------------------ -# Environment Variables for Oracle Service -# (only used when VECTOR_STORE is oracle) -# ------------------------------ -ORACLE_PWD=Dify123456 -ORACLE_CHARACTERSET=AL32UTF8 - -# ------------------------------ -# Environment Variables for milvus Service -# (only used when VECTOR_STORE is milvus) -# ------------------------------ -# ETCD configuration for auto compaction mode -ETCD_AUTO_COMPACTION_MODE=revision -# ETCD configuration for auto compaction retention in terms of number of revisions -ETCD_AUTO_COMPACTION_RETENTION=1000 -# ETCD configuration for backend quota in bytes -ETCD_QUOTA_BACKEND_BYTES=4294967296 -# ETCD configuration for the number of changes before triggering a snapshot -ETCD_SNAPSHOT_COUNT=50000 -# MinIO access key for authentication -MINIO_ACCESS_KEY=minioadmin -# MinIO secret key for authentication -MINIO_SECRET_KEY=minioadmin -# ETCD service endpoints -ETCD_ENDPOINTS=etcd:2379 -# MinIO service address -MINIO_ADDRESS=minio:9000 -# Enable or disable security authorization -MILVUS_AUTHORIZATION_ENABLED=true - -# ------------------------------ -# Environment Variables for pgvector / pgvector-rs Service -# (only used when VECTOR_STORE is pgvector / pgvector-rs) -# ------------------------------ -PGVECTOR_PGUSER=postgres -# The password for the default postgres user. -PGVECTOR_POSTGRES_PASSWORD=difyai123456 -# The name of the default postgres database. -PGVECTOR_POSTGRES_DB=dify -# postgres data directory -PGVECTOR_PGDATA=/var/lib/postgresql/data/pgdata - -# ------------------------------ -# Environment Variables for opensearch -# (only used when VECTOR_STORE is opensearch) -# ------------------------------ -OPENSEARCH_DISCOVERY_TYPE=single-node -OPENSEARCH_BOOTSTRAP_MEMORY_LOCK=true -OPENSEARCH_JAVA_OPTS_MIN=512m -OPENSEARCH_JAVA_OPTS_MAX=1024m -OPENSEARCH_INITIAL_ADMIN_PASSWORD=Qazwsxedc!@#123 -OPENSEARCH_MEMLOCK_SOFT=-1 -OPENSEARCH_MEMLOCK_HARD=-1 -OPENSEARCH_NOFILE_SOFT=65536 -OPENSEARCH_NOFILE_HARD=65536 - -# ------------------------------ -# Environment Variables for Nginx reverse proxy -# ------------------------------ -NGINX_SERVER_NAME=_ -NGINX_HTTPS_ENABLED=false -# HTTP port -NGINX_PORT=80 -# SSL settings are only applied when HTTPS_ENABLED is true -NGINX_SSL_PORT=443 -# if HTTPS_ENABLED is true, you're required to add your own SSL certificates/keys to the `./nginx/ssl` directory -# and modify the env vars below accordingly. -NGINX_SSL_CERT_FILENAME=dify.crt -NGINX_SSL_CERT_KEY_FILENAME=dify.key -NGINX_SSL_PROTOCOLS=TLSv1.1 TLSv1.2 TLSv1.3 - -# Nginx performance tuning -NGINX_WORKER_PROCESSES=auto -NGINX_CLIENT_MAX_BODY_SIZE=100M -NGINX_KEEPALIVE_TIMEOUT=65 - -# Proxy settings -NGINX_PROXY_READ_TIMEOUT=3600s -NGINX_PROXY_SEND_TIMEOUT=3600s - -# Set true to accept requests for /.well-known/acme-challenge/ -NGINX_ENABLE_CERTBOT_CHALLENGE=false - -# ------------------------------ -# Certbot Configuration -# ------------------------------ - -# Email address (required to get certificates from Let's Encrypt) -CERTBOT_EMAIL=your_email@example.com - -# Domain name -CERTBOT_DOMAIN=your_domain.com - -# certbot command options -# i.e: --force-renewal --dry-run --test-cert --debug -CERTBOT_OPTIONS= - -# ------------------------------ -# Environment Variables for SSRF Proxy -# ------------------------------ -SSRF_HTTP_PORT=3128 -SSRF_COREDUMP_DIR=/var/spool/squid -SSRF_REVERSE_PROXY_PORT=8194 -SSRF_SANDBOX_HOST=sandbox -SSRF_DEFAULT_TIME_OUT=5 -SSRF_DEFAULT_CONNECT_TIME_OUT=5 -SSRF_DEFAULT_READ_TIME_OUT=5 -SSRF_DEFAULT_WRITE_TIME_OUT=5 - -# ------------------------------ -# docker env var for specifying vector db type at startup -# (based on the vector db type, the corresponding docker -# compose profile will be used) -# if you want to use unstructured, add ',unstructured' to the end -# ------------------------------ -COMPOSE_PROFILES=${VECTOR_STORE:-weaviate} - -# ------------------------------ -# Docker Compose Service Expose Host Port Configurations -# ------------------------------ -EXPOSE_NGINX_PORT=80 -EXPOSE_NGINX_SSL_PORT=443 - -# ---------------------------------------------------------------------------- -# ModelProvider & Tool Position Configuration -# Used to specify the model providers and tools that can be used in the app. -# ---------------------------------------------------------------------------- - -# Pin, include, and exclude tools -# Use comma-separated values with no spaces between items. -# Example: POSITION_TOOL_PINS=bing,google -POSITION_TOOL_PINS= -POSITION_TOOL_INCLUDES= -POSITION_TOOL_EXCLUDES= - -# Pin, include, and exclude model providers -# Use comma-separated values with no spaces between items. -# Example: POSITION_PROVIDER_PINS=openai,openllm -POSITION_PROVIDER_PINS= -POSITION_PROVIDER_INCLUDES= -POSITION_PROVIDER_EXCLUDES= - -# CSP https://developer.mozilla.org/en-US/docs/Web/HTTP/CSP -CSP_WHITELIST= - -# Enable or disable create tidb service job -CREATE_TIDB_SERVICE_JOB_ENABLED=false - -# Maximum number of submitted thread count in a ThreadPool for parallel node execution -MAX_SUBMIT_COUNT=100 - -# The maximum number of top-k value for RAG. -TOP_K_MAX_VALUE=10 - -# ------------------------------ -# Plugin Daemon Configuration -# ------------------------------ - -DB_PLUGIN_DATABASE=dify_plugin -EXPOSE_PLUGIN_DAEMON_PORT=5002 -PLUGIN_DAEMON_PORT=5002 -PLUGIN_DAEMON_KEY=lYkiYYT6owG+71oLerGzA7GXCgOT++6ovaezWAjpCjf+Sjc3ZtU+qUEi -PLUGIN_DAEMON_URL=http://plugin_daemon:5002 -PLUGIN_MAX_PACKAGE_SIZE=52428800 -PLUGIN_PPROF_ENABLED=false - -PLUGIN_DEBUGGING_HOST=0.0.0.0 -PLUGIN_DEBUGGING_PORT=5003 -EXPOSE_PLUGIN_DEBUGGING_HOST=localhost -EXPOSE_PLUGIN_DEBUGGING_PORT=5003 - -# If this key is changed, DIFY_INNER_API_KEY in plugin_daemon service must also be updated or agent node will fail. -PLUGIN_DIFY_INNER_API_KEY=QaHbTe77CtuXmsfyhR7+vRjI/+XbV1AaFy691iy+kGDv2Jvy0/eAh8Y1 -PLUGIN_DIFY_INNER_API_URL=http://api:5001 - -ENDPOINT_URL_TEMPLATE=http://localhost/e/{hook_id} - -MARKETPLACE_ENABLED=true -MARKETPLACE_API_URL=https://marketplace.dify.ai - -FORCE_VERIFYING_SIGNATURE=true - -PLUGIN_PYTHON_ENV_INIT_TIMEOUT=120 -PLUGIN_MAX_EXECUTION_TIMEOUT=600 -# PIP_MIRROR_URL=https://pypi.tuna.tsinghua.edu.cn/simple -PIP_MIRROR_URL= - -# https://github.com/langgenius/dify-plugin-daemon/blob/main/.env.example -# Plugin storage type, local aws_s3 tencent_cos azure_blob aliyun_oss volcengine_tos -PLUGIN_STORAGE_TYPE=local -PLUGIN_STORAGE_LOCAL_ROOT=/app/storage -PLUGIN_WORKING_PATH=/app/storage/cwd -PLUGIN_INSTALLED_PATH=plugin -PLUGIN_PACKAGE_CACHE_PATH=plugin_packages -PLUGIN_MEDIA_CACHE_PATH=assets -# Plugin oss bucket -PLUGIN_STORAGE_OSS_BUCKET= -# Plugin oss s3 credentials -PLUGIN_S3_USE_AWS=false -PLUGIN_S3_USE_AWS_MANAGED_IAM=false -PLUGIN_S3_ENDPOINT= -PLUGIN_S3_USE_PATH_STYLE=false -PLUGIN_AWS_ACCESS_KEY= -PLUGIN_AWS_SECRET_KEY= -PLUGIN_AWS_REGION= -# Plugin oss azure blob -PLUGIN_AZURE_BLOB_STORAGE_CONTAINER_NAME= -PLUGIN_AZURE_BLOB_STORAGE_CONNECTION_STRING= -# Plugin oss tencent cos -PLUGIN_TENCENT_COS_SECRET_KEY= -PLUGIN_TENCENT_COS_SECRET_ID= -PLUGIN_TENCENT_COS_REGION= -# Plugin oss aliyun oss -PLUGIN_ALIYUN_OSS_REGION= -PLUGIN_ALIYUN_OSS_ENDPOINT= -PLUGIN_ALIYUN_OSS_ACCESS_KEY_ID= -PLUGIN_ALIYUN_OSS_ACCESS_KEY_SECRET= -PLUGIN_ALIYUN_OSS_AUTH_VERSION=v4 -PLUGIN_ALIYUN_OSS_PATH= -# Plugin oss volcengine tos -PLUGIN_VOLCENGINE_TOS_ENDPOINT= -PLUGIN_VOLCENGINE_TOS_ACCESS_KEY= -PLUGIN_VOLCENGINE_TOS_SECRET_KEY= -PLUGIN_VOLCENGINE_TOS_REGION= - -# ------------------------------ -# OTLP Collector Configuration -# ------------------------------ -ENABLE_OTEL=false -OTLP_TRACE_ENDPOINT= -OTLP_METRIC_ENDPOINT= -OTLP_BASE_ENDPOINT=http://localhost:4318 -OTLP_API_KEY= -OTEL_EXPORTER_OTLP_PROTOCOL= -OTEL_EXPORTER_TYPE=otlp -OTEL_SAMPLING_RATE=0.1 -OTEL_BATCH_EXPORT_SCHEDULE_DELAY=5000 -OTEL_MAX_QUEUE_SIZE=2048 -OTEL_MAX_EXPORT_BATCH_SIZE=512 -OTEL_METRIC_EXPORT_INTERVAL=60000 -OTEL_BATCH_EXPORT_TIMEOUT=10000 -OTEL_METRIC_EXPORT_TIMEOUT=30000 - -# Prevent Clickjacking -ALLOW_EMBED=false - -# Dataset queue monitor configuration -QUEUE_MONITOR_THRESHOLD=200 -# You can configure multiple ones, separated by commas. eg: test1@dify.ai,test2@dify.ai -QUEUE_MONITOR_ALERT_EMAILS= -# Monitor interval in minutes, default is 30 minutes -QUEUE_MONITOR_INTERVAL=30 diff --git a/.github/CODE_OF_CONDUCT.md b/.github/CODE_OF_CONDUCT.md index 47e2453f41..a59630d112 100644 --- a/.github/CODE_OF_CONDUCT.md +++ b/.github/CODE_OF_CONDUCT.md @@ -17,27 +17,25 @@ diverse, inclusive, and healthy community. Examples of behavior that contributes to a positive environment for our community include: -* Demonstrating empathy and kindness toward other people -* Being respectful of differing opinions, viewpoints, and experiences -* Giving and gracefully accepting constructive feedback -* Accepting responsibility and apologizing to those affected by our mistakes, +- Demonstrating empathy and kindness toward other people +- Being respectful of differing opinions, viewpoints, and experiences +- Giving and gracefully accepting constructive feedback +- Accepting responsibility and apologizing to those affected by our mistakes, and learning from the experience -* Focusing on what is best not just for us as individuals, but for the +- Focusing on what is best not just for us as individuals, but for the overall community Examples of unacceptable behavior include: -* The use of sexualized language or imagery, and sexual attention or +- The use of sexualized language or imagery, and sexual attention or advances of any kind -* Trolling, insulting or derogatory comments, and personal or political attacks -* Public or private harassment -* Publishing others' private information, such as a physical or email +- Trolling, insulting or derogatory comments, and personal or political attacks +- Public or private harassment +- Publishing others' private information, such as a physical or email address, without their explicit permission -* Other conduct which could reasonably be considered inappropriate in a +- Other conduct which could reasonably be considered inappropriate in a professional setting ## Language Policy To facilitate clear and effective communication, all discussions, comments, documentation, and pull requests in this project should be conducted in English. This ensures that all contributors can participate and collaborate effectively. - - diff --git a/.github/pull_request_template.md b/.github/pull_request_template.md index f4a5f754e0..aa5a50918a 100644 --- a/.github/pull_request_template.md +++ b/.github/pull_request_template.md @@ -1,8 +1,8 @@ > [!IMPORTANT] > > 1. Make sure you have read our [contribution guidelines](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) -> 2. Ensure there is an associated issue and you have been assigned to it -> 3. Use the correct syntax to link this PR: `Fixes #`. +> 1. Ensure there is an associated issue and you have been assigned to it +> 1. Use the correct syntax to link this PR: `Fixes #`. ## Summary @@ -12,7 +12,7 @@ | Before | After | |--------|-------| -| ... | ... | +| ... | ... | ## Checklist diff --git a/.github/workflows/api-tests.yml b/.github/workflows/api-tests.yml index 9c3daddbfc..63d681e7ed 100644 --- a/.github/workflows/api-tests.yml +++ b/.github/workflows/api-tests.yml @@ -47,7 +47,16 @@ jobs: - name: Run Unit tests run: | uv run --project api bash dev/pytest/pytest_unit_tests.sh - + - name: Run ty check + run: | + cd api + uv add --dev ty + uv run ty check || true + - name: Run pyrefly check + run: | + cd api + uv add --dev pyrefly + uv run pyrefly check || true - name: Coverage Summary run: | set -x diff --git a/.github/workflows/autofix.yml b/.github/workflows/autofix.yml index 152ff3b648..f5ba498c7d 100644 --- a/.github/workflows/autofix.yml +++ b/.github/workflows/autofix.yml @@ -23,6 +23,9 @@ jobs: uv run ruff check --fix-only . # Format code uv run ruff format . + - name: ast-grep + run: | + uvx --from ast-grep-cli sg --pattern 'db.session.query($WHATEVER).filter($HERE)' --rewrite 'db.session.query($WHATEVER).where($HERE)' -l py --update-all - uses: autofix-ci/action@635ffb0c9798bd160680f18fd73371e355b85f27 diff --git a/.github/workflows/style.yml b/.github/workflows/style.yml index 54f3f42a25..9aad9558b0 100644 --- a/.github/workflows/style.yml +++ b/.github/workflows/style.yml @@ -82,7 +82,7 @@ jobs: - name: Install pnpm uses: pnpm/action-setup@v4 with: - version: 10 + package_json_file: web/package.json run_install: false - name: Setup NodeJS @@ -95,10 +95,12 @@ jobs: - name: Web dependencies if: steps.changed-files.outputs.any_changed == 'true' + working-directory: ./web run: pnpm install --frozen-lockfile - name: Web style check if: steps.changed-files.outputs.any_changed == 'true' + working-directory: ./web run: pnpm run lint docker-compose-template: diff --git a/.github/workflows/translate-i18n-base-on-english.yml b/.github/workflows/translate-i18n-base-on-english.yml index 4b06174ee1..c004836808 100644 --- a/.github/workflows/translate-i18n-base-on-english.yml +++ b/.github/workflows/translate-i18n-base-on-english.yml @@ -46,7 +46,7 @@ jobs: - name: Install pnpm uses: pnpm/action-setup@v4 with: - version: 10 + package_json_file: web/package.json run_install: false - name: Set up Node.js @@ -59,10 +59,12 @@ jobs: - name: Install dependencies if: env.FILES_CHANGED == 'true' + working-directory: ./web run: pnpm install --frozen-lockfile - name: Generate i18n translations if: env.FILES_CHANGED == 'true' + working-directory: ./web run: pnpm run auto-gen-i18n ${{ env.FILE_ARGS }} - name: Create Pull Request diff --git a/.github/workflows/web-tests.yml b/.github/workflows/web-tests.yml index c3f8fdbaf6..d104d69947 100644 --- a/.github/workflows/web-tests.yml +++ b/.github/workflows/web-tests.yml @@ -35,7 +35,7 @@ jobs: if: steps.changed-files.outputs.any_changed == 'true' uses: pnpm/action-setup@v4 with: - version: 10 + package_json_file: web/package.json run_install: false - name: Setup Node.js @@ -48,8 +48,10 @@ jobs: - name: Install dependencies if: steps.changed-files.outputs.any_changed == 'true' + working-directory: ./web run: pnpm install --frozen-lockfile - name: Run tests if: steps.changed-files.outputs.any_changed == 'true' + working-directory: ./web run: pnpm test diff --git a/.gitignore b/.gitignore index 5c68d89a4d..30432c4302 100644 --- a/.gitignore +++ b/.gitignore @@ -197,6 +197,8 @@ sdks/python-client/dify_client.egg-info !.vscode/README.md pyrightconfig.json api/.vscode +# vscode Code History Extension +.history .idea/ diff --git a/.vscode/README.md b/.vscode/README.md index 26516f0540..87b45787c3 100644 --- a/.vscode/README.md +++ b/.vscode/README.md @@ -4,10 +4,10 @@ This `launch.json.template` file provides various debug configurations for the D ## How to Use -1. **Create `launch.json`**: If you don't have one, create a file named `launch.json` inside the `.vscode` directory. -2. **Copy Content**: Copy the entire content from `launch.json.template` into your newly created `launch.json` file. -3. **Select Debug Configuration**: Go to the Run and Debug view in VS Code / Cursor (Ctrl+Shift+D or Cmd+Shift+D). -4. **Start Debugging**: Select the desired configuration from the dropdown menu and click the green play button. +1. **Create `launch.json`**: If you don't have one, create a file named `launch.json` inside the `.vscode` directory. +1. **Copy Content**: Copy the entire content from `launch.json.template` into your newly created `launch.json` file. +1. **Select Debug Configuration**: Go to the Run and Debug view in VS Code / Cursor (Ctrl+Shift+D or Cmd+Shift+D). +1. **Start Debugging**: Select the desired configuration from the dropdown menu and click the green play button. ## Tips diff --git a/CLAUDE.md b/CLAUDE.md new file mode 100644 index 0000000000..fd437d7bf0 --- /dev/null +++ b/CLAUDE.md @@ -0,0 +1,88 @@ +# CLAUDE.md + +This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. + +## Project Overview + +Dify is an open-source platform for developing LLM applications with an intuitive interface combining agentic AI workflows, RAG pipelines, agent capabilities, and model management. + +The codebase consists of: + +- **Backend API** (`/api`): Python Flask application with Domain-Driven Design architecture +- **Frontend Web** (`/web`): Next.js 15 application with TypeScript and React 19 +- **Docker deployment** (`/docker`): Containerized deployment configurations + +## Development Commands + +### Backend (API) + +All Python commands must be prefixed with `uv run --project api`: + +```bash +# Start development servers +./dev/start-api # Start API server +./dev/start-worker # Start Celery worker + +# Run tests +uv run --project api pytest # Run all tests +uv run --project api pytest tests/unit_tests/ # Unit tests only +uv run --project api pytest tests/integration_tests/ # Integration tests + +# Code quality +./dev/reformat # Run all formatters and linters +uv run --project api ruff check --fix ./ # Fix linting issues +uv run --project api ruff format ./ # Format code +uv run --project api mypy . # Type checking +``` + +### Frontend (Web) + +```bash +cd web +pnpm lint # Run ESLint +pnpm eslint-fix # Fix ESLint issues +pnpm test # Run Jest tests +``` + +## Testing Guidelines + +### Backend Testing + +- Use `pytest` for all backend tests +- Write tests first (TDD approach) +- Test structure: Arrange-Act-Assert + +## Code Style Requirements + +### Python + +- Use type hints for all functions and class attributes +- No `Any` types unless absolutely necessary +- Implement special methods (`__repr__`, `__str__`) appropriately + +### TypeScript/JavaScript + +- Strict TypeScript configuration +- ESLint with Prettier integration +- Avoid `any` type + +## Important Notes + +- **Environment Variables**: Always use UV for Python commands: `uv run --project api ` +- **Comments**: Only write meaningful comments that explain "why", not "what" +- **File Creation**: Always prefer editing existing files over creating new ones +- **Documentation**: Don't create documentation files unless explicitly requested +- **Code Quality**: Always run `./dev/reformat` before committing backend changes + +## Common Development Tasks + +### Adding a New API Endpoint + +1. Create controller in `/api/controllers/` +1. Add service logic in `/api/services/` +1. Update routes in controller's `__init__.py` +1. Write tests in `/api/tests/` + +## Project-Specific Conventions + +- All async tasks use Celery with Redis as broker diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 5d4ba36485..fdc414b047 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -34,11 +34,11 @@ Don't forget to link an existing issue or open a new issue in the PR's descripti How we prioritize: - | Issue Type | Priority | - | ------------------------------------------------------------ | --------------- | - | Bugs in core functions (cloud service, cannot login, applications not working, security loopholes) | Critical | - | Non-critical bugs, performance boosts | Medium Priority | - | Minor fixes (typos, confusing but working UI) | Low Priority | +| Issue Type | Priority | +| ------------------------------------------------------------ | --------------- | +| Bugs in core functions (cloud service, cannot login, applications not working, security loopholes) | Critical | +| Non-critical bugs, performance boosts | Medium Priority | +| Minor fixes (typos, confusing but working UI) | Low Priority | ### Feature requests @@ -52,23 +52,25 @@ How we prioritize: How we prioritize: - | Feature Type | Priority | - | ------------------------------------------------------------ | --------------- | - | High-Priority Features as being labeled by a team member | High Priority | - | Popular feature requests from our [community feedback board](https://github.com/langgenius/dify/discussions/categories/feedbacks) | Medium Priority | - | Non-core features and minor enhancements | Low Priority | - | Valuable but not immediate | Future-Feature | +| Feature Type | Priority | +| ------------------------------------------------------------ | --------------- | +| High-Priority Features as being labeled by a team member | High Priority | +| Popular feature requests from our [community feedback board](https://github.com/langgenius/dify/discussions/categories/feedbacks) | Medium Priority | +| Non-core features and minor enhancements | Low Priority | +| Valuable but not immediate | Future-Feature | + ## Submitting your PR ### Pull Request Process 1. Fork the repository -2. Before you draft a PR, please create an issue to discuss the changes you want to make -3. Create a new branch for your changes -4. Please add tests for your changes accordingly -5. Ensure your code passes the existing tests -6. Please link the issue in the PR description, `fixes #` -7. Get merged! +1. Before you draft a PR, please create an issue to discuss the changes you want to make +1. Create a new branch for your changes +1. Please add tests for your changes accordingly +1. Ensure your code passes the existing tests +1. Please link the issue in the PR description, `fixes #` +1. Get merged! + ### Setup the project #### Frontend @@ -82,12 +84,14 @@ For setting up the backend service, kindly refer to our detailed [instructions]( #### Other things to note We recommend reviewing this document carefully before proceeding with the setup, as it contains essential information about: + - Prerequisites and dependencies - Installation steps - Configuration details - Common troubleshooting tips Feel free to reach out if you encounter any issues during the setup process. + ## Getting Help If you ever get stuck or get a burning question while contributing, simply shoot your queries our way via the related GitHub issue, or hop onto our [Discord](https://discord.gg/8Tpq4AcN9c) for a quick chat. diff --git a/CONTRIBUTING_CN.md b/CONTRIBUTING_CN.md index 69ae7071bb..c278c8fd7a 100644 --- a/CONTRIBUTING_CN.md +++ b/CONTRIBUTING_CN.md @@ -34,12 +34,11 @@ 优先级划分： - | 问题类型 | 优先级 | - | -------------------------------------------------- | ---------- | - | 核心功能 bug（云服务、登录失败、应用无法使用、安全漏洞） | 紧急 | - | 非关键 bug、性能优化 | 中等优先级 | - | 小修复（拼写错误、界面混乱但可用） | 低优先级 | - +| 问题类型 | 优先级 | +| -------------------------------------------------- | ---------- | +| 核心功能 bug（云服务、登录失败、应用无法使用、安全漏洞） | 紧急 | +| 非关键 bug、性能优化 | 中等优先级 | +| 小修复（拼写错误、界面混乱但可用） | 低优先级 | ### 功能请求 @@ -53,12 +52,12 @@ 优先级划分： - | 功能类型 | 优先级 | - | -------------------------------------------------- | ---------- | - | 被团队成员标记为高优先级的功能 | 高优先级 | - | 来自[社区反馈板](https://github.com/langgenius/dify/discussions/categories/feedbacks)的热门功能请求 | 中等优先级 | - | 非核心功能和小改进 | 低优先级 | - | 有价值但非紧急的功能 | 未来特性 | +| 功能类型 | 优先级 | +| -------------------------------------------------- | ---------- | +| 被团队成员标记为高优先级的功能 | 高优先级 | +| 来自[社区反馈板](https://github.com/langgenius/dify/discussions/categories/feedbacks)的热门功能请求 | 中等优先级 | +| 非核心功能和小改进 | 低优先级 | +| 有价值但非紧急的功能 | 未来特性 | ## 提交 PR @@ -67,12 +66,12 @@ ### PR 提交流程 1. Fork 本仓库 -2. 在提交 PR 之前，请先创建 issue 讨论你想要做的修改 -3. 为你的修改创建一个新的分支 -4. 请为你的修改添加相应的测试 -5. 确保你的代码能通过现有的测试 -6. 请在 PR 描述中关联相关 issue，格式为 `fixes #` -7. 等待合并！ +1. 在提交 PR 之前，请先创建 issue 讨论你想要做的修改 +1. 为你的修改创建一个新的分支 +1. 请为你的修改添加相应的测试 +1. 确保你的代码能通过现有的测试 +1. 请在 PR 描述中关联相关 issue，格式为 `fixes #` +1. 等待合并！ #### 前端 @@ -85,6 +84,7 @@ #### 其他注意事项 我们建议在开始设置之前仔细阅读本文档，因为它包含以下重要信息： + - 前置条件和依赖项 - 安装步骤 - 配置细节 diff --git a/CONTRIBUTING_DE.md b/CONTRIBUTING_DE.md index ddbf3abc55..f819e80bbb 100644 --- a/CONTRIBUTING_DE.md +++ b/CONTRIBUTING_DE.md @@ -32,11 +32,11 @@ Vergessen Sie nicht, in der PR-Beschreibung ein bestehendes Issue zu verlinken o Unsere Priorisierung: - | Fehlertyp | Priorität | - | ------------------------------------------------------------ | --------------- | - | Fehler in Kernfunktionen (Cloud-Service, Login nicht möglich, Anwendungen funktionieren nicht, Sicherheitslücken) | Kritisch | - | Nicht-kritische Fehler, Leistungsverbesserungen | Mittlere Priorität | - | Kleinere Korrekturen (Tippfehler, verwirrende aber funktionierende UI) | Niedrige Priorität | +| Fehlertyp | Priorität | +| ------------------------------------------------------------ | --------------- | +| Fehler in Kernfunktionen (Cloud-Service, Login nicht möglich, Anwendungen funktionieren nicht, Sicherheitslücken) | Kritisch | +| Nicht-kritische Fehler, Leistungsverbesserungen | Mittlere Priorität | +| Kleinere Korrekturen (Tippfehler, verwirrende aber funktionierende UI) | Niedrige Priorität | ### Feature-Anfragen @@ -50,24 +50,24 @@ Unsere Priorisierung: Unsere Priorisierung: - | Feature-Typ | Priorität | - | ------------------------------------------------------------ | --------------- | - | Hochprioritäre Features (durch Teammitglied gekennzeichnet) | Hohe Priorität | - | Beliebte Feature-Anfragen aus unserem [Community-Feedback-Board](https://github.com/langgenius/dify/discussions/categories/feedbacks) | Mittlere Priorität | - | Nicht-Kernfunktionen und kleinere Verbesserungen | Niedrige Priorität | - | Wertvoll, aber nicht dringend | Zukunfts-Feature | +| Feature-Typ | Priorität | +| ------------------------------------------------------------ | --------------- | +| Hochprioritäre Features (durch Teammitglied gekennzeichnet) | Hohe Priorität | +| Beliebte Feature-Anfragen aus unserem [Community-Feedback-Board](https://github.com/langgenius/dify/discussions/categories/feedbacks) | Mittlere Priorität | +| Nicht-Kernfunktionen und kleinere Verbesserungen | Niedrige Priorität | +| Wertvoll, aber nicht dringend | Zukunfts-Feature | ## Einreichen Ihres PRs ### Pull-Request-Prozess 1. Repository forken -2. Vor dem Erstellen eines PRs bitte ein Issue zur Diskussion der Änderungen erstellen -3. Einen neuen Branch für Ihre Änderungen erstellen -4. Tests für Ihre Änderungen hinzufügen -5. Sicherstellen, dass Ihr Code die bestehenden Tests besteht -6. Issue in der PR-Beschreibung verlinken (`fixes #`) -7. Auf den Merge warten! +1. Vor dem Erstellen eines PRs bitte ein Issue zur Diskussion der Änderungen erstellen +1. Einen neuen Branch für Ihre Änderungen erstellen +1. Tests für Ihre Änderungen hinzufügen +1. Sicherstellen, dass Ihr Code die bestehenden Tests besteht +1. Issue in der PR-Beschreibung verlinken (`fixes #`) +1. Auf den Merge warten! ### Projekt einrichten @@ -82,6 +82,7 @@ Für die Einrichtung des Backend-Service folgen Sie bitte unseren detaillierten #### Weitere Hinweise Wir empfehlen, dieses Dokument sorgfältig zu lesen, da es wichtige Informationen enthält über: + - Voraussetzungen und Abhängigkeiten - Installationsschritte - Konfigurationsdetails @@ -92,4 +93,3 @@ Bei Problemen während der Einrichtung können Sie sich gerne an uns wenden. ## Hilfe bekommen Wenn Sie beim Mitwirken Fragen haben oder nicht weiterkommen, stellen Sie Ihre Fragen einfach im entsprechenden GitHub Issue oder besuchen Sie unseren [Discord](https://discord.gg/8Tpq4AcN9c) für einen schnellen Austausch. - diff --git a/CONTRIBUTING_ES.md b/CONTRIBUTING_ES.md index 98cbb5b457..e19d958c65 100644 --- a/CONTRIBUTING_ES.md +++ b/CONTRIBUTING_ES.md @@ -34,11 +34,11 @@ No olvides vincular un issue existente o abrir uno nuevo en la descripción del Cómo priorizamos: - | Tipo de Issue | Prioridad | - | ------------------------------------------------------------ | --------------- | - | Errores en funciones principales (servicio en la nube, no poder iniciar sesión, aplicaciones que no funcionan, fallos de seguridad) | Crítica | - | Errores no críticos, mejoras de rendimiento | Prioridad Media | - | Correcciones menores (errores tipográficos, UI confusa pero funcional) | Prioridad Baja | +| Tipo de Issue | Prioridad | +| ------------------------------------------------------------ | --------------- | +| Errores en funciones principales (servicio en la nube, no poder iniciar sesión, aplicaciones que no funcionan, fallos de seguridad) | Crítica | +| Errores no críticos, mejoras de rendimiento | Prioridad Media | +| Correcciones menores (errores tipográficos, UI confusa pero funcional) | Prioridad Baja | ### Solicitudes de funcionalidades @@ -52,23 +52,25 @@ Cómo priorizamos: Cómo priorizamos: - | Tipo de Funcionalidad | Prioridad | - | ------------------------------------------------------------ | --------------- | - | Funcionalidades de alta prioridad etiquetadas por un miembro del equipo | Prioridad Alta | - | Solicitudes populares de funcionalidades de nuestro [tablero de comentarios de la comunidad](https://github.com/langgenius/dify/discussions/categories/feedbacks) | Prioridad Media | - | Funcionalidades no principales y mejoras menores | Prioridad Baja | - | Valiosas pero no inmediatas | Futura-Funcionalidad | +| Tipo de Funcionalidad | Prioridad | +| ------------------------------------------------------------ | --------------- | +| Funcionalidades de alta prioridad etiquetadas por un miembro del equipo | Prioridad Alta | +| Solicitudes populares de funcionalidades de nuestro [tablero de comentarios de la comunidad](https://github.com/langgenius/dify/discussions/categories/feedbacks) | Prioridad Media | +| Funcionalidades no principales y mejoras menores | Prioridad Baja | +| Valiosas pero no inmediatas | Futura-Funcionalidad | + ## Enviando tu PR ### Proceso de Pull Request 1. Haz un fork del repositorio -2. Antes de redactar un PR, por favor crea un issue para discutir los cambios que quieres hacer -3. Crea una nueva rama para tus cambios -4. Por favor añade pruebas para tus cambios en consecuencia -5. Asegúrate de que tu código pasa las pruebas existentes -6. Por favor vincula el issue en la descripción del PR, `fixes #` -7. ¡Fusiona tu código! +1. Antes de redactar un PR, por favor crea un issue para discutir los cambios que quieres hacer +1. Crea una nueva rama para tus cambios +1. Por favor añade pruebas para tus cambios en consecuencia +1. Asegúrate de que tu código pasa las pruebas existentes +1. Por favor vincula el issue en la descripción del PR, `fixes #` +1. ¡Fusiona tu código! + ### Configuración del proyecto #### Frontend @@ -82,12 +84,14 @@ Para configurar el servicio backend, por favor consulta nuestras [instrucciones #### Otras cosas a tener en cuenta Recomendamos revisar este documento cuidadosamente antes de proceder con la configuración, ya que contiene información esencial sobre: + - Requisitos previos y dependencias - Pasos de instalación - Detalles de configuración - Consejos comunes de solución de problemas No dudes en contactarnos si encuentras algún problema durante el proceso de configuración. + ## Obteniendo Ayuda -Si alguna vez te quedas atascado o tienes una pregunta urgente mientras contribuyes, simplemente envíanos tus consultas a través del issue relacionado de GitHub, o únete a nuestro [Discord](https://discord.gg/8Tpq4AcN9c) para una charla rápida. +Si alguna vez te quedas atascado o tienes una pregunta urgente mientras contribuyes, simplemente envíanos tus consultas a través del issue relacionado de GitHub, o únete a nuestro [Discord](https://discord.gg/8Tpq4AcN9c) para una charla rápida. diff --git a/CONTRIBUTING_FR.md b/CONTRIBUTING_FR.md index fc8410dfd6..335e943fcd 100644 --- a/CONTRIBUTING_FR.md +++ b/CONTRIBUTING_FR.md @@ -34,11 +34,11 @@ N'oubliez pas de lier un problème existant ou d'ouvrir un nouveau problème dan Comment nous priorisons : - | Type de Problème | Priorité | - | ------------------------------------------------------------ | --------------- | - | Bugs dans les fonctions principales (service cloud, impossibilité de se connecter, applications qui ne fonctionnent pas, failles de sécurité) | Critique | - | Bugs non critiques, améliorations de performance | Priorité Moyenne | - | Corrections mineures (fautes de frappe, UI confuse mais fonctionnelle) | Priorité Basse | +| Type de Problème | Priorité | +| ------------------------------------------------------------ | --------------- | +| Bugs dans les fonctions principales (service cloud, impossibilité de se connecter, applications qui ne fonctionnent pas, failles de sécurité) | Critique | +| Bugs non critiques, améliorations de performance | Priorité Moyenne | +| Corrections mineures (fautes de frappe, UI confuse mais fonctionnelle) | Priorité Basse | ### Demandes de fonctionnalités @@ -52,23 +52,25 @@ Comment nous priorisons : Comment nous priorisons : - | Type de Fonctionnalité | Priorité | - | ------------------------------------------------------------ | --------------- | - | Fonctionnalités hautement prioritaires étiquetées par un membre de l'équipe | Priorité Haute | - | Demandes populaires de fonctionnalités de notre [tableau de feedback communautaire](https://github.com/langgenius/dify/discussions/categories/feedbacks) | Priorité Moyenne | - | Fonctionnalités non essentielles et améliorations mineures | Priorité Basse | - | Précieuses mais non immédiates | Fonctionnalité Future | +| Type de Fonctionnalité | Priorité | +| ------------------------------------------------------------ | --------------- | +| Fonctionnalités hautement prioritaires étiquetées par un membre de l'équipe | Priorité Haute | +| Demandes populaires de fonctionnalités de notre [tableau de feedback communautaire](https://github.com/langgenius/dify/discussions/categories/feedbacks) | Priorité Moyenne | +| Fonctionnalités non essentielles et améliorations mineures | Priorité Basse | +| Précieuses mais non immédiates | Fonctionnalité Future | + ## Soumettre votre PR ### Processus de Pull Request 1. Forkez le dépôt -2. Avant de rédiger une PR, veuillez créer un problème pour discuter des changements que vous souhaitez apporter -3. Créez une nouvelle branche pour vos changements -4. Veuillez ajouter des tests pour vos changements en conséquence -5. Assurez-vous que votre code passe les tests existants -6. Veuillez lier le problème dans la description de la PR, `fixes #` -7. Faites fusionner votre code ! +1. Avant de rédiger une PR, veuillez créer un problème pour discuter des changements que vous souhaitez apporter +1. Créez une nouvelle branche pour vos changements +1. Veuillez ajouter des tests pour vos changements en conséquence +1. Assurez-vous que votre code passe les tests existants +1. Veuillez lier le problème dans la description de la PR, `fixes #` +1. Faites fusionner votre code ! + ### Configuration du projet #### Frontend @@ -82,12 +84,14 @@ Pour configurer le service backend, veuillez consulter nos [instructions détail #### Autres choses à noter Nous recommandons de revoir attentivement ce document avant de procéder à la configuration, car il contient des informations essentielles sur : + - Prérequis et dépendances - Étapes d'installation - Détails de configuration - Conseils courants de dépannage N'hésitez pas à nous contacter si vous rencontrez des problèmes pendant le processus de configuration. + ## Obtenir de l'aide -Si jamais vous êtes bloqué ou avez une question urgente en contribuant, envoyez-nous simplement vos questions via le problème GitHub concerné, ou rejoignez notre [Discord](https://discord.gg/8Tpq4AcN9c) pour une discussion rapide. +Si jamais vous êtes bloqué ou avez une question urgente en contribuant, envoyez-nous simplement vos questions via le problème GitHub concerné, ou rejoignez notre [Discord](https://discord.gg/8Tpq4AcN9c) pour une discussion rapide. diff --git a/CONTRIBUTING_JA.md b/CONTRIBUTING_JA.md index e991d0263e..2d0d79fc16 100644 --- a/CONTRIBUTING_JA.md +++ b/CONTRIBUTING_JA.md @@ -34,11 +34,11 @@ PRの説明には、既存のイシューへのリンクを含めるか、新し 優先順位の付け方： - | 問題の種類 | 優先度 | - | ------------------------------------------------------------ | --------- | - | コア機能のバグ（クラウドサービス、ログイン不可、アプリケーション不具合、セキュリティ脆弱性） | 最重要 | - | 重要度の低いバグ、パフォーマンス改善 | 中程度 | - | 軽微な修正（タイプミス、分かりにくいが動作するUI） | 低 | +| 問題の種類 | 優先度 | +| ------------------------------------------------------------ | --------- | +| コア機能のバグ（クラウドサービス、ログイン不可、アプリケーション不具合、セキュリティ脆弱性） | 最重要 | +| 重要度の低いバグ、パフォーマンス改善 | 中程度 | +| 軽微な修正（タイプミス、分かりにくいが動作するUI） | 低 | ### 機能リクエスト @@ -52,24 +52,24 @@ PRの説明には、既存のイシューへのリンクを含めるか、新し 優先順位の付け方： - | 機能の種類 | 優先度 | - | ------------------------------------------------------------ | --------- | - | チームメンバーによって高優先度とラベル付けされた機能 | 高 | - | [コミュニティフィードボード](https://github.com/langgenius/dify/discussions/categories/feedbacks)での人気の機能リクエスト | 中程度 | - | 非コア機能と軽微な改善 | 低 | - | 価値はあるが緊急性の低いもの | 将来対応 | +| 機能の種類 | 優先度 | +| ------------------------------------------------------------ | --------- | +| チームメンバーによって高優先度とラベル付けされた機能 | 高 | +| [コミュニティフィードボード](https://github.com/langgenius/dify/discussions/categories/feedbacks)での人気の機能リクエスト | 中程度 | +| 非コア機能と軽微な改善 | 低 | +| 価値はあるが緊急性の低いもの | 将来対応 | ## PRの提出 ### プルリクエストのプロセス 1. リポジトリをフォークする -2. PRを作成する前に、変更内容についてイシューで議論する -3. 変更用の新しいブランチを作成する -4. 変更に応じたテストを追加する -5. 既存のテストをパスすることを確認する -6. PRの説明文にイシューをリンクする（`fixes #`） -7. マージ完了！ +1. PRを作成する前に、変更内容についてイシューで議論する +1. 変更用の新しいブランチを作成する +1. 変更に応じたテストを追加する +1. 既存のテストをパスすることを確認する +1. PRの説明文にイシューをリンクする（`fixes #`） +1. マージ完了！ ### プロジェクトのセットアップ @@ -84,6 +84,7 @@ PRの説明には、既存のイシューへのリンクを含めるか、新し #### その他の注意点 セットアップを進める前に、以下の重要な情報が含まれているため、このドキュメントを注意深く確認することをお勧めします： + - 前提条件と依存関係 - インストール手順 - 設定の詳細 @@ -94,4 +95,3 @@ PRの説明には、既存のイシューへのリンクを含めるか、新し ## サポートを受ける 貢献中に行き詰まったり、緊急の質問がある場合は、関連するGitHubイシューで質問するか、[Discord](https://discord.gg/8Tpq4AcN9c)で気軽にチャットしてください。 - diff --git a/CONTRIBUTING_KR.md b/CONTRIBUTING_KR.md index 78d3f38c47..14b1c9a9ca 100644 --- a/CONTRIBUTING_KR.md +++ b/CONTRIBUTING_KR.md @@ -34,11 +34,11 @@ PR 설명에 기존 이슈를 연결하거나 새 이슈를 여는 것을 잊지 우선순위 결정 방법: - | 이슈 유형 | 우선순위 | - | ------------------------------------------------------------ | --------------- | - | 핵심 기능의 버그(클라우드 서비스, 로그인 불가, 애플리케이션 작동 불능, 보안 취약점) | 중대 | - | 비중요 버그, 성능 향상 | 중간 우선순위 | - | 사소한 수정(오타, 혼란스럽지만 작동하는 UI) | 낮은 우선순위 | +| 이슈 유형 | 우선순위 | +| ------------------------------------------------------------ | --------------- | +| 핵심 기능의 버그(클라우드 서비스, 로그인 불가, 애플리케이션 작동 불능, 보안 취약점) | 중대 | +| 비중요 버그, 성능 향상 | 중간 우선순위 | +| 사소한 수정(오타, 혼란스럽지만 작동하는 UI) | 낮은 우선순위 | ### 기능 요청 @@ -52,23 +52,25 @@ PR 설명에 기존 이슈를 연결하거나 새 이슈를 여는 것을 잊지 우선순위 결정 방법: - | 기능 유형 | 우선순위 | - | ------------------------------------------------------------ | --------------- | - | 팀 구성원에 의해 레이블이 지정된 고우선순위 기능 | 높은 우선순위 | - | 우리의 [커뮤니티 피드백 보드](https://github.com/langgenius/dify/discussions/categories/feedbacks)에서 인기 있는 기능 요청 | 중간 우선순위 | - | 비핵심 기능 및 사소한 개선 | 낮은 우선순위 | - | 가치 있지만 즉시 필요하지 않은 기능 | 미래 기능 | +| 기능 유형 | 우선순위 | +| ------------------------------------------------------------ | --------------- | +| 팀 구성원에 의해 레이블이 지정된 고우선순위 기능 | 높은 우선순위 | +| 우리의 [커뮤니티 피드백 보드](https://github.com/langgenius/dify/discussions/categories/feedbacks)에서 인기 있는 기능 요청 | 중간 우선순위 | +| 비핵심 기능 및 사소한 개선 | 낮은 우선순위 | +| 가치 있지만 즉시 필요하지 않은 기능 | 미래 기능 | + ## PR 제출하기 ### Pull Request 프로세스 1. 저장소를 포크하세요 -2. PR을 작성하기 전에, 변경하고자 하는 내용에 대해 논의하기 위한 이슈를 생성해 주세요 -3. 변경 사항을 위한 새 브랜치를 만드세요 -4. 변경 사항에 대한 테스트를 적절히 추가해 주세요 -5. 코드가 기존 테스트를 통과하는지 확인하세요 -6. PR 설명에 이슈를 연결해 주세요, `fixes #<이슈_번호>` -7. 병합 완료! +1. PR을 작성하기 전에, 변경하고자 하는 내용에 대해 논의하기 위한 이슈를 생성해 주세요 +1. 변경 사항을 위한 새 브랜치를 만드세요 +1. 변경 사항에 대한 테스트를 적절히 추가해 주세요 +1. 코드가 기존 테스트를 통과하는지 확인하세요 +1. PR 설명에 이슈를 연결해 주세요, `fixes #<이슈_번호>` +1. 병합 완료! + ### 프로젝트 설정하기 #### 프론트엔드 @@ -82,12 +84,14 @@ PR 설명에 기존 이슈를 연결하거나 새 이슈를 여는 것을 잊지 #### 기타 참고 사항 설정을 진행하기 전에 이 문서를 주의 깊게 검토하는 것을 권장합니다. 다음과 같은 필수 정보가 포함되어 있습니다: + - 필수 조건 및 종속성 - 설치 단계 - 구성 세부 정보 - 일반적인 문제 해결 팁 설정 과정에서 문제가 발생하면 언제든지 연락해 주세요. + ## 도움 받기 -기여하는 동안 막히거나 긴급한 질문이 있으면, 관련 GitHub 이슈를 통해 질문을 보내거나, 빠른 대화를 위해 우리의 [Discord](https://discord.gg/8Tpq4AcN9c)에 참여하세요. +기여하는 동안 막히거나 긴급한 질문이 있으면, 관련 GitHub 이슈를 통해 질문을 보내거나, 빠른 대화를 위해 우리의 [Discord](https://discord.gg/8Tpq4AcN9c)에 참여하세요. diff --git a/CONTRIBUTING_PT.md b/CONTRIBUTING_PT.md index 7347fd7f9c..aeabcad51f 100644 --- a/CONTRIBUTING_PT.md +++ b/CONTRIBUTING_PT.md @@ -34,11 +34,11 @@ Não se esqueça de vincular um problema existente ou abrir um novo problema na Como priorizamos: - | Tipo de Problema | Prioridade | - | ------------------------------------------------------------ | --------------- | - | Bugs em funções centrais (serviço em nuvem, não conseguir fazer login, aplicações não funcionando, falhas de segurança) | Crítica | - | Bugs não críticos, melhorias de desempenho | Prioridade Média | - | Correções menores (erros de digitação, interface confusa mas funcional) | Prioridade Baixa | +| Tipo de Problema | Prioridade | +| ------------------------------------------------------------ | --------------- | +| Bugs em funções centrais (serviço em nuvem, não conseguir fazer login, aplicações não funcionando, falhas de segurança) | Crítica | +| Bugs não críticos, melhorias de desempenho | Prioridade Média | +| Correções menores (erros de digitação, interface confusa mas funcional) | Prioridade Baixa | ### Solicitações de recursos @@ -52,23 +52,25 @@ Como priorizamos: Como priorizamos: - | Tipo de Recurso | Prioridade | - | ------------------------------------------------------------ | --------------- | - | Recursos de alta prioridade conforme rotulado por um membro da equipe | Prioridade Alta | - | Solicitações populares de recursos do nosso [quadro de feedback da comunidade](https://github.com/langgenius/dify/discussions/categories/feedbacks) | Prioridade Média | - | Recursos não essenciais e melhorias menores | Prioridade Baixa | - | Valiosos mas não imediatos | Recurso Futuro | +| Tipo de Recurso | Prioridade | +| ------------------------------------------------------------ | --------------- | +| Recursos de alta prioridade conforme rotulado por um membro da equipe | Prioridade Alta | +| Solicitações populares de recursos do nosso [quadro de feedback da comunidade](https://github.com/langgenius/dify/discussions/categories/feedbacks) | Prioridade Média | +| Recursos não essenciais e melhorias menores | Prioridade Baixa | +| Valiosos mas não imediatos | Recurso Futuro | + ## Enviando seu PR ### Processo de Pull Request 1. Faça um fork do repositório -2. Antes de elaborar um PR, por favor crie um problema para discutir as mudanças que você quer fazer -3. Crie um novo branch para suas alterações -4. Por favor, adicione testes para suas alterações conforme apropriado -5. Certifique-se de que seu código passa nos testes existentes -6. Por favor, vincule o problema na descrição do PR, `fixes #` -7. Faça o merge do seu código! +1. Antes de elaborar um PR, por favor crie um problema para discutir as mudanças que você quer fazer +1. Crie um novo branch para suas alterações +1. Por favor, adicione testes para suas alterações conforme apropriado +1. Certifique-se de que seu código passa nos testes existentes +1. Por favor, vincule o problema na descrição do PR, `fixes #` +1. Faça o merge do seu código! + ### Configurando o projeto #### Frontend @@ -82,12 +84,14 @@ Para configurar o serviço backend, por favor consulte nossas [instruções deta #### Outras coisas a observar Recomendamos revisar este documento cuidadosamente antes de prosseguir com a configuração, pois ele contém informações essenciais sobre: + - Pré-requisitos e dependências - Etapas de instalação - Detalhes de configuração - Dicas comuns de solução de problemas Sinta-se à vontade para entrar em contato se encontrar quaisquer problemas durante o processo de configuração. + ## Obtendo Ajuda -Se você ficar preso ou tiver uma dúvida urgente enquanto contribui, simplesmente envie suas perguntas através do problema relacionado no GitHub, ou entre no nosso [Discord](https://discord.gg/8Tpq4AcN9c) para uma conversa rápida. +Se você ficar preso ou tiver uma dúvida urgente enquanto contribui, simplesmente envie suas perguntas através do problema relacionado no GitHub, ou entre no nosso [Discord](https://discord.gg/8Tpq4AcN9c) para uma conversa rápida. diff --git a/CONTRIBUTING_TR.md b/CONTRIBUTING_TR.md index 681f05689b..d016802a53 100644 --- a/CONTRIBUTING_TR.md +++ b/CONTRIBUTING_TR.md @@ -34,11 +34,11 @@ PR açıklamasında mevcut bir sorunu bağlamayı veya yeni bir sorun açmayı u Nasıl önceliklendiriyoruz: - | Sorun Türü | Öncelik | - | ------------------------------------------------------------ | --------------- | - | Temel işlevlerdeki hatalar (bulut hizmeti, giriş yapamama, çalışmayan uygulamalar, güvenlik açıkları) | Kritik | - | Kritik olmayan hatalar, performans artışları | Orta Öncelik | - | Küçük düzeltmeler (yazım hataları, kafa karıştırıcı ama çalışan UI) | Düşük Öncelik | +| Sorun Türü | Öncelik | +| ------------------------------------------------------------ | --------------- | +| Temel işlevlerdeki hatalar (bulut hizmeti, giriş yapamama, çalışmayan uygulamalar, güvenlik açıkları) | Kritik | +| Kritik olmayan hatalar, performans artışları | Orta Öncelik | +| Küçük düzeltmeler (yazım hataları, kafa karıştırıcı ama çalışan UI) | Düşük Öncelik | ### Özellik İstekleri @@ -52,23 +52,25 @@ Nasıl önceliklendiriyoruz: Nasıl önceliklendiriyoruz: - | Özellik Türü | Öncelik | - | ------------------------------------------------------------ | --------------- | - | Bir ekip üyesi tarafından etiketlenen Yüksek Öncelikli Özellikler | Yüksek Öncelik | - | [Topluluk geri bildirim panosundan](https://github.com/langgenius/dify/discussions/categories/feedbacks) popüler özellik istekleri | Orta Öncelik | - | Temel olmayan özellikler ve küçük geliştirmeler | Düşük Öncelik | - | Değerli ama acil olmayan | Gelecek-Özellik | +| Özellik Türü | Öncelik | +| ------------------------------------------------------------ | --------------- | +| Bir ekip üyesi tarafından etiketlenen Yüksek Öncelikli Özellikler | Yüksek Öncelik | +| [Topluluk geri bildirim panosundan](https://github.com/langgenius/dify/discussions/categories/feedbacks) popüler özellik istekleri | Orta Öncelik | +| Temel olmayan özellikler ve küçük geliştirmeler | Düşük Öncelik | +| Değerli ama acil olmayan | Gelecek-Özellik | + ## PR'nizi Göndermek ### Pull Request Süreci 1. Depoyu fork edin -2. Bir PR taslağı oluşturmadan önce, yapmak istediğiniz değişiklikleri tartışmak için lütfen bir sorun oluşturun -3. Değişiklikleriniz için yeni bir dal oluşturun -4. Lütfen değişiklikleriniz için uygun testler ekleyin -5. Kodunuzun mevcut testleri geçtiğinden emin olun -6. Lütfen PR açıklamasında sorunu bağlayın, `fixes #` -7. Kodunuzu birleştirin! +1. Bir PR taslağı oluşturmadan önce, yapmak istediğiniz değişiklikleri tartışmak için lütfen bir sorun oluşturun +1. Değişiklikleriniz için yeni bir dal oluşturun +1. Lütfen değişiklikleriniz için uygun testler ekleyin +1. Kodunuzun mevcut testleri geçtiğinden emin olun +1. Lütfen PR açıklamasında sorunu bağlayın, `fixes #` +1. Kodunuzu birleştirin! + ### Projeyi Kurma #### Frontend @@ -82,12 +84,14 @@ Backend hizmetini kurmak için, lütfen `api/README.md` dosyasındaki detaylı [ #### Dikkat Edilecek Diğer Şeyler Kuruluma geçmeden önce bu belgeyi dikkatlice incelemenizi öneririz, çünkü şunlar hakkında temel bilgiler içerir: + - Ön koşullar ve bağımlılıklar - Kurulum adımları - Yapılandırma detayları - Yaygın sorun giderme ipuçları Kurulum süreci sırasında herhangi bir sorunla karşılaşırsanız bizimle iletişime geçmekten çekinmeyin. + ## Yardım Almak -Katkıda bulunurken takılırsanız veya yanıcı bir sorunuz olursa, sorularınızı ilgili GitHub sorunu aracılığıyla bize gönderin veya hızlı bir sohbet için [Discord'umuza](https://discord.gg/8Tpq4AcN9c) katılın. +Katkıda bulunurken takılırsanız veya yanıcı bir sorunuz olursa, sorularınızı ilgili GitHub sorunu aracılığıyla bize gönderin veya hızlı bir sohbet için [Discord'umuza](https://discord.gg/8Tpq4AcN9c) katılın. diff --git a/CONTRIBUTING_TW.md b/CONTRIBUTING_TW.md index a61ea918c5..5c4d7022fe 100644 --- a/CONTRIBUTING_TW.md +++ b/CONTRIBUTING_TW.md @@ -22,7 +22,7 @@ ### 錯誤回報 -> [!IMPORTANT] +> [!IMPORTANT]\ > 提交錯誤回報時，請務必包含以下資訊： - 清晰明確的標題 @@ -34,15 +34,15 @@ 優先順序評估： - | 議題類型 | 優先級 | - | -------- | ------ | - | 核心功能錯誤（雲端服務、無法登入、應用程式無法運作、安全漏洞） | 緊急 | - | 非緊急錯誤、效能優化 | 中等 | - | 次要修正（拼字錯誤、介面混淆但可運作） | 低 | +| 議題類型 | 優先級 | +| -------- | ------ | +| 核心功能錯誤（雲端服務、無法登入、應用程式無法運作、安全漏洞） | 緊急 | +| 非緊急錯誤、效能優化 | 中等 | +| 次要修正（拼字錯誤、介面混淆但可運作） | 低 | ### 功能請求 -> [!NOTE] +> [!NOTE]\ > 提交功能請求時，請務必包含以下資訊： - 清晰明確的標題 @@ -52,24 +52,24 @@ 優先順序評估： - | 功能類型 | 優先級 | - | -------- | ------ | - | 團隊成員標記為高優先級的功能 | 高 | - | 來自[社群回饋板](https://github.com/langgenius/dify/discussions/categories/feedbacks)的熱門功能請求 | 中 | - | 非核心功能和小幅改進 | 低 | - | 有價值但非急迫的功能 | 未來功能 | +| 功能類型 | 優先級 | +| -------- | ------ | +| 團隊成員標記為高優先級的功能 | 高 | +| 來自[社群回饋板](https://github.com/langgenius/dify/discussions/categories/feedbacks)的熱門功能請求 | 中 | +| 非核心功能和小幅改進 | 低 | +| 有價值但非急迫的功能 | 未來功能 | ## 提交 PR ### PR 流程 1. Fork 專案 -2. 在開始撰寫 PR 前，請先建立議題討論你想做的更改 -3. 為你的更改建立新分支 -4. 請為你的更改新增相應的測試 -5. 確保你的程式碼通過現有測試 -6. 請在 PR 描述中連結相關議題，使用 `fixes #` -7. 等待合併！ +1. 在開始撰寫 PR 前，請先建立議題討論你想做的更改 +1. 為你的更改建立新分支 +1. 請為你的更改新增相應的測試 +1. 確保你的程式碼通過現有測試 +1. 請在 PR 描述中連結相關議題，使用 `fixes #` +1. 等待合併！ ### 專案設定 @@ -84,6 +84,7 @@ #### 其他注意事項 我們建議在開始設定前仔細閱讀此文件，因為它包含以下重要資訊： + - 前置需求和相依性 - 安裝步驟 - 設定細節 @@ -94,4 +95,3 @@ ## 尋求協助 如果你在貢獻過程中遇到困難或有急切的問題，可以透過相關的 GitHub 議題詢問，或加入我們的 [Discord](https://discord.gg/8Tpq4AcN9c) 進行即時交流。 - diff --git a/CONTRIBUTING_VI.md b/CONTRIBUTING_VI.md index 807054acce..2ad431296a 100644 --- a/CONTRIBUTING_VI.md +++ b/CONTRIBUTING_VI.md @@ -22,7 +22,7 @@ Hãy tham gia, đóng góp và cùng nhau xây dựng điều tuyệt vời! ### Báo cáo lỗi -> [!QUAN TRỌNG] +> [!QUAN TRỌNG]\ > Vui lòng đảm bảo cung cấp các thông tin sau khi gửi báo cáo lỗi: - Tiêu đề rõ ràng và mô tả @@ -34,11 +34,11 @@ Hãy tham gia, đóng góp và cùng nhau xây dựng điều tuyệt vời! Cách chúng tôi ưu tiên: - | Loại vấn đề | Mức độ ưu tiên | - | ----------- | -------------- | - | Lỗi trong các chức năng cốt lõi (dịch vụ đám mây, không thể đăng nhập, ứng dụng không hoạt động, lỗ hổng bảo mật) | Quan trọng | - | Lỗi không nghiêm trọng, cải thiện hiệu suất | Ưu tiên trung bình | - | Sửa lỗi nhỏ (lỗi chính tả, UI gây nhầm lẫn nhưng vẫn hoạt động) | Ưu tiên thấp | +| Loại vấn đề | Mức độ ưu tiên | +| ----------- | -------------- | +| Lỗi trong các chức năng cốt lõi (dịch vụ đám mây, không thể đăng nhập, ứng dụng không hoạt động, lỗ hổng bảo mật) | Quan trọng | +| Lỗi không nghiêm trọng, cải thiện hiệu suất | Ưu tiên trung bình | +| Sửa lỗi nhỏ (lỗi chính tả, UI gây nhầm lẫn nhưng vẫn hoạt động) | Ưu tiên thấp | ### Yêu cầu tính năng @@ -52,24 +52,24 @@ Cách chúng tôi ưu tiên: Cách chúng tôi ưu tiên: - | Loại tính năng | Mức độ ưu tiên | - | -------------- | -------------- | - | Tính năng ưu tiên cao được gắn nhãn bởi thành viên nhóm | Ưu tiên cao | - | Yêu cầu tính năng phổ biến từ [bảng phản hồi cộng đồng](https://github.com/langgenius/dify/discussions/categories/feedbacks) | Ưu tiên trung bình | - | Tính năng không cốt lõi và cải tiến nhỏ | Ưu tiên thấp | - | Có giá trị nhưng không cấp bách | Tính năng tương lai | +| Loại tính năng | Mức độ ưu tiên | +| -------------- | -------------- | +| Tính năng ưu tiên cao được gắn nhãn bởi thành viên nhóm | Ưu tiên cao | +| Yêu cầu tính năng phổ biến từ [bảng phản hồi cộng đồng](https://github.com/langgenius/dify/discussions/categories/feedbacks) | Ưu tiên trung bình | +| Tính năng không cốt lõi và cải tiến nhỏ | Ưu tiên thấp | +| Có giá trị nhưng không cấp bách | Tính năng tương lai | ## Gửi PR của bạn ### Quy trình tạo Pull Request 1. Fork repository -2. Trước khi soạn PR, vui lòng tạo issue để thảo luận về các thay đổi bạn muốn thực hiện -3. Tạo nhánh mới cho các thay đổi của bạn -4. Vui lòng thêm test cho các thay đổi tương ứng -5. Đảm bảo code của bạn vượt qua các test hiện có -6. Vui lòng liên kết issue trong mô tả PR, `fixes #` -7. Được merge! +1. Trước khi soạn PR, vui lòng tạo issue để thảo luận về các thay đổi bạn muốn thực hiện +1. Tạo nhánh mới cho các thay đổi của bạn +1. Vui lòng thêm test cho các thay đổi tương ứng +1. Đảm bảo code của bạn vượt qua các test hiện có +1. Vui lòng liên kết issue trong mô tả PR, `fixes #` +1. Được merge! ### Thiết lập dự án @@ -84,6 +84,7 @@ Cách chúng tôi ưu tiên: #### Các điểm cần lưu ý khác Chúng tôi khuyến nghị xem xét kỹ tài liệu này trước khi tiến hành thiết lập, vì nó chứa thông tin thiết yếu về: + - Điều kiện tiên quyết và dependencies - Các bước cài đặt - Chi tiết cấu hình @@ -94,4 +95,3 @@ Chúng tôi khuyến nghị xem xét kỹ tài liệu này trước khi tiến h ## Nhận trợ giúp Nếu bạn bị mắc kẹt hoặc có câu hỏi cấp bách trong quá trình đóng góp, chỉ cần gửi câu hỏi của bạn thông qua issue GitHub liên quan, hoặc tham gia [Discord](https://discord.gg/8Tpq4AcN9c) của chúng tôi để trò chuyện nhanh. - diff --git a/README.md b/README.md index 775f6f351f..7e566a0b2f 100644 --- a/README.md +++ b/README.md @@ -185,7 +185,8 @@ All of Dify's offerings come with corresponding APIs, so you could effortlessly Use our [documentation](https://docs.dify.ai) for further references and more in-depth instructions. - **Dify for enterprise / organizations
** - We provide additional enterprise-centric features. [Log your questions for us through this chatbot](https://udify.app/chat/22L1zSxg6yW1cWQg) or [send us an email](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) to discuss enterprise needs.
+ We provide additional enterprise-centric features. [Log your questions for us through this chatbot](https://udify.app/chat/22L1zSxg6yW1cWQg) or [send us an email](mailto:business@dify.ai?subject=%5BGitHub%5DBusiness%20License%20Inquiry) to discuss enterprise needs.
+ > For startups and small businesses using AWS, check out [Dify Premium on AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) and deploy it to your own AWS VPC with one click. It's an affordable AMI offering with the option to create apps with custom logo and branding. ## Staying ahead @@ -225,20 +226,20 @@ Deploy Dify to AWS with [CDK](https://aws.amazon.com/cdk/) ##### AWS -- [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +- [AWS CDK by @KevinZhao (EKS based)](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +- [AWS CDK by @tmokmss (ECS based)](https://github.com/aws-samples/dify-self-hosted-on-aws) #### Using Alibaba Cloud Computing Nest -Quickly deploy Dify to Alibaba cloud with [Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88) +Quickly deploy Dify to Alibaba cloud with [Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88) #### Using Alibaba Cloud Data Management -One-Click deploy Dify to Alibaba Cloud with [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/) +One-Click deploy Dify to Alibaba Cloud with [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/) #### Deploy to AKS with Azure Devops Pipeline -One-Click deploy Dify to AKS with [Azure Devops Pipeline Helm Chart by @LeoZhang](https://github.com/Ruiruiz30/Dify-helm-chart-AKS) - +One-Click deploy Dify to AKS with [Azure Devops Pipeline Helm Chart by @LeoZhang](https://github.com/Ruiruiz30/Dify-helm-chart-AKS) ## Contributing diff --git a/README_AR.md b/README_AR.md index e7a4dbdb27..044ced98ed 100644 --- a/README_AR.md +++ b/README_AR.md @@ -52,7 +52,7 @@ مشروع Dify هو منصة تطوير تطبيقات الذكاء الصناعي مفتوحة المصدر. تجمع واجهته البديهية بين سير العمل الذكي بالذكاء الاصطناعي وخط أنابيب RAG وقدرات الوكيل وإدارة النماذج وميزات الملاحظة وأكثر من ذلك، مما يتيح لك الانتقال بسرعة من المرحلة التجريبية إلى الإنتاج. إليك قائمة بالميزات الأساسية:

-**1. سير العمل**: قم ببناء واختبار سير عمل الذكاء الاصطناعي القوي على قماش بصري، مستفيدًا من جميع الميزات التالية وأكثر. +**1. سير العمل**: قم ببناء واختبار سير عمل الذكاء الاصطناعي القوي على قماش بصري، مستفيدًا من جميع الميزات التالية وأكثر. **2. الدعم الشامل للنماذج**: تكامل سلس مع مئات من LLMs الخاصة / مفتوحة المصدر من عشرات من موفري التحليل والحلول المستضافة ذاتيًا، مما يغطي GPT و Mistral و Llama3 وأي نماذج متوافقة مع واجهة OpenAI API. يمكن العثور على قائمة كاملة بمزودي النموذج المدعومين [هنا](https://docs.dify.ai/getting-started/readme/model-providers). @@ -139,17 +139,17 @@ ## استخدام Dify - **سحابة
** -نحن نستضيف [خدمة Dify Cloud](https://dify.ai) لأي شخص لتجربتها بدون أي إعدادات. توفر كل قدرات النسخة التي تمت استضافتها ذاتيًا، وتتضمن 200 أمر GPT-4 مجانًا في خطة الصندوق الرملي. + نحن نستضيف [خدمة Dify Cloud](https://dify.ai) لأي شخص لتجربتها بدون أي إعدادات. توفر كل قدرات النسخة التي تمت استضافتها ذاتيًا، وتتضمن 200 أمر GPT-4 مجانًا في خطة الصندوق الرملي. - **استضافة ذاتية لنسخة المجتمع Dify
** -ابدأ سريعًا في تشغيل Dify في بيئتك باستخدام [دليل البدء السريع](#البدء السريع). -استخدم [توثيقنا](https://docs.dify.ai) للمزيد من المراجع والتعليمات الأعمق. + ابدأ سريعًا في تشغيل Dify في بيئتك باستخدام \[دليل البدء السريع\](#البدء السريع). + استخدم [توثيقنا](https://docs.dify.ai) للمزيد من المراجع والتعليمات الأعمق. - **مشروع Dify للشركات / المؤسسات
** -نحن نوفر ميزات إضافية مركزة على الشركات. [جدول اجتماع معنا](https://cal.com/guchenhe/30min) أو [أرسل لنا بريدًا إلكترونيًا](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) لمناقشة احتياجات الشركات.
+ نحن نوفر ميزات إضافية مركزة على الشركات. [جدول اجتماع معنا](https://cal.com/guchenhe/30min) أو [أرسل لنا بريدًا إلكترونيًا](mailto:business@dify.ai?subject=%5BGitHub%5DBusiness%20License%20Inquiry) لمناقشة احتياجات الشركات.
> بالنسبة للشركات الناشئة والشركات الصغيرة التي تستخدم خدمات AWS، تحقق من [Dify Premium على AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) ونشرها في شبكتك الخاصة على AWS VPC بنقرة واحدة. إنها عرض AMI بأسعار معقولة مع خيار إنشاء تطبيقات بشعار وعلامة تجارية مخصصة. -> + ## البقاء قدمًا قم بإضافة نجمة إلى Dify على GitHub وتلق تنبيهًا فوريًا بالإصدارات الجديدة. @@ -157,11 +157,11 @@ ![نجمنا](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4) ## البداية السريعة -> + > قبل تثبيت Dify، تأكد من أن جهازك يلبي الحد الأدنى من متطلبات النظام التالية: > ->- معالج >= 2 نواة ->- ذاكرة وصول عشوائي (RAM) >= 4 جيجابايت +> - معالج >= 2 نواة +> - ذاكرة وصول عشوائي (RAM) >= 4 جيجابايت
@@ -208,11 +208,13 @@ docker compose up -d ##### AWS -- [AWS CDK بواسطة @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +- [AWS CDK بواسطة @KevinZhao (EKS based)](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +- [AWS CDK بواسطة @tmokmss (ECS based)](https://github.com/aws-samples/dify-self-hosted-on-aws) #### استخدام Alibaba Cloud للنشر - [بسرعة نشر Dify إلى سحابة علي بابا مع عش الحوسبة السحابية علي بابا](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88) - + +[بسرعة نشر Dify إلى سحابة علي بابا مع عش الحوسبة السحابية علي بابا](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88) + #### استخدام Alibaba Cloud Data Management للنشر انشر ​​Dify على علي بابا كلاود بنقرة واحدة باستخدام [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/) @@ -221,7 +223,6 @@ docker compose up -d انشر Dify على AKS بنقرة واحدة باستخدام [Azure Devops Pipeline Helm Chart by @LeoZhang](https://github.com/Ruiruiz30/Dify-helm-chart-AKS) - ## المساهمة لأولئك الذين يرغبون في المساهمة، انظر إلى [دليل المساهمة](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) لدينا. @@ -236,6 +237,7 @@ docker compose up -d ## المجتمع والاتصال + - [مناقشة GitHub](https://github.com/langgenius/dify/discussions). الأفضل لـ: مشاركة التعليقات وطرح الأسئلة. - [المشكلات على GitHub](https://github.com/langgenius/dify/issues). الأفضل لـ: الأخطاء التي تواجهها في استخدام Dify.AI، واقتراحات الميزات. انظر [دليل المساهمة](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). - [Discord](https://discord.gg/FngNHpbcY7). الأفضل لـ: مشاركة تطبيقاتك والترفيه مع المجتمع. diff --git a/README_BN.md b/README_BN.md index e4da437eff..f5a19ab434 100644 --- a/README_BN.md +++ b/README_BN.md @@ -56,53 +56,55 @@ ডিফাই একটি ওপেন-সোর্স LLM অ্যাপ ডেভেলপমেন্ট প্ল্যাটফর্ম। এটি ইন্টুইটিভ ইন্টারফেস, এজেন্টিক AI ওয়ার্কফ্লো, RAG পাইপলাইন, এজেন্ট ক্যাপাবিলিটি, মডেল ম্যানেজমেন্ট, মনিটরিং সুবিধা এবং আরও অনেক কিছু একত্রিত করে, যা দ্রুত প্রোটোটাইপ থেকে প্রোডাকশন পর্যন্ত নিয়ে যেতে সহায়তা করে। ## কুইক স্টার্ট + +> ডিফাই ইনস্টল করার আগে, নিশ্চিত করুন যে আপনার মেশিন নিম্নলিখিত ন্যূনতম কনফিগারেশনের প্রয়োজনীয়তা পূরন করে : > -> ডিফাই ইনস্টল করার আগে, নিশ্চিত করুন যে আপনার মেশিন নিম্নলিখিত ন্যূনতম কনফিগারেশনের প্রয়োজনীয়তা পূরন করে : -> ->- সিপিউ >= 2 কোর ->- র‍্যাম >= 4 জিবি +> - সিপিউ >= 2 কোর +> - র‍্যাম >= 4 জিবি
ডিফাই সার্ভার চালু করার সবচেয়ে সহজ উপায় [docker compose](docker/docker-compose.yaml) মাধ্যমে। নিম্নলিখিত কমান্ডগুলো ব্যবহার করে ডিফাই চালানোর আগে, নিশ্চিত করুন যে আপনার মেশিনে [Docker](https://docs.docker.com/get-docker/) এবং [Docker Compose](https://docs.docker.com/compose/install/) ইনস্টল করা আছে : + ```bash cd dify cd docker cp .env.example .env docker compose up -d ``` + চালানোর পর, আপনি আপনার ব্রাউজারে [http://localhost/install](http://localhost/install)-এ ডিফাই ড্যাশবোর্ডে অ্যাক্সেস করতে পারেন এবং ইনিশিয়ালাইজেশন প্রক্রিয়া শুরু করতে পারেন। #### সাহায্যের খোঁজে -ডিফাই সেট আপ করতে সমস্যা হলে দয়া করে আমাদের [FAQ](https://docs.dify.ai/getting-started/install-self-hosted/faqs) দেখুন। যদি তবুও সমস্যা থেকে থাকে, তাহলে [কমিউনিটি এবং আমাদের](#community--contact) সাথে যোগাযোগ করুন। +ডিফাই সেট আপ করতে সমস্যা হলে দয়া করে আমাদের [FAQ](https://docs.dify.ai/getting-started/install-self-hosted/faqs) দেখুন। যদি তবুও সমস্যা থেকে থাকে, তাহলে [কমিউনিটি এবং আমাদের](#community--contact) সাথে যোগাযোগ করুন। > যদি আপনি ডিফাইতে অবদান রাখতে বা অতিরিক্ত উন্নয়ন করতে চান, আমাদের [সোর্স কোড থেকে ডিপ্লয়মেন্টের গাইড](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code) দেখুন। ## প্রধান ফিচারসমূহ **১. ওয়ার্কফ্লো**: - ভিজ্যুয়াল ক্যানভাসে AI ওয়ার্কফ্লো তৈরি এবং পরীক্ষা করুন, নিম্নলিখিত সব ফিচার এবং তার বাইরেও আরও অনেক কিছু ব্যবহার করে। +ভিজ্যুয়াল ক্যানভাসে AI ওয়ার্কফ্লো তৈরি এবং পরীক্ষা করুন, নিম্নলিখিত সব ফিচার এবং তার বাইরেও আরও অনেক কিছু ব্যবহার করে। -**২. মডেল সাপোর্ট**: - GPT, Mistral, Llama3, এবং যেকোনো OpenAI API-সামঞ্জস্যপূর্ণ মডেলসহ, কয়েক ডজন ইনফারেন্স প্রদানকারী এবং সেল্ফ-হোস্টেড সমাধান থেকে শুরু করে প্রোপ্রাইটরি/ওপেন-সোর্স LLM-এর সাথে সহজে ইন্টিগ্রেশন। সমর্থিত মডেল প্রদানকারীদের একটি সম্পূর্ণ তালিকা পাওয়া যাবে [এখানে](https://docs.dify.ai/getting-started/readme/model-providers)। +**২. মডেল সাপোর্ট**: +GPT, Mistral, Llama3, এবং যেকোনো OpenAI API-সামঞ্জস্যপূর্ণ মডেলসহ, কয়েক ডজন ইনফারেন্স প্রদানকারী এবং সেল্ফ-হোস্টেড সমাধান থেকে শুরু করে প্রোপ্রাইটরি/ওপেন-সোর্স LLM-এর সাথে সহজে ইন্টিগ্রেশন। সমর্থিত মডেল প্রদানকারীদের একটি সম্পূর্ণ তালিকা পাওয়া যাবে [এখানে](https://docs.dify.ai/getting-started/readme/model-providers)। ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3) -**3. প্রম্পট IDE**: - প্রম্পট তৈরি, মডেলের পারফরম্যান্স তুলনা এবং চ্যাট-বেজড অ্যাপে টেক্সট-টু-স্পিচের মতো বৈশিষ্ট্য যুক্ত করার জন্য ইন্টুইটিভ ইন্টারফেস। +**3. প্রম্পট IDE**: +প্রম্পট তৈরি, মডেলের পারফরম্যান্স তুলনা এবং চ্যাট-বেজড অ্যাপে টেক্সট-টু-স্পিচের মতো বৈশিষ্ট্য যুক্ত করার জন্য ইন্টুইটিভ ইন্টারফেস। **4. RAG পাইপলাইন**: - ডকুমেন্ট ইনজেশন থেকে শুরু করে রিট্রিভ পর্যন্ত সবকিছুই বিস্তৃত RAG ক্যাপাবিলিটির আওতাভুক্ত। PDF, PPT এবং অন্যান্য সাধারণ ডকুমেন্ট ফর্ম্যাট থেকে টেক্সট এক্সট্রাকশনের জন্য আউট-অফ-বক্স সাপোর্ট। +ডকুমেন্ট ইনজেশন থেকে শুরু করে রিট্রিভ পর্যন্ত সবকিছুই বিস্তৃত RAG ক্যাপাবিলিটির আওতাভুক্ত। PDF, PPT এবং অন্যান্য সাধারণ ডকুমেন্ট ফর্ম্যাট থেকে টেক্সট এক্সট্রাকশনের জন্য আউট-অফ-বক্স সাপোর্ট। -**5. এজেন্ট ক্যাপাবিলিটি**: - LLM ফাংশন কলিং বা ReAct উপর ভিত্তি করে এজেন্ট ডিফাইন করতে পারেন এবং এজেন্টের জন্য পূর্ব-নির্মিত বা কাস্টম টুলস যুক্ত করতে পারেন। Dify AI এজেন্টদের জন্য 50+ বিল্ট-ইন টুলস সরবরাহ করে, যেমন Google Search, DALL·E, Stable Diffusion এবং WolframAlpha। +**5. এজেন্ট ক্যাপাবিলিটি**: +LLM ফাংশন কলিং বা ReAct উপর ভিত্তি করে এজেন্ট ডিফাইন করতে পারেন এবং এজেন্টের জন্য পূর্ব-নির্মিত বা কাস্টম টুলস যুক্ত করতে পারেন। Dify AI এজেন্টদের জন্য 50+ বিল্ট-ইন টুলস সরবরাহ করে, যেমন Google Search, DALL·E, Stable Diffusion এবং WolframAlpha। -**6. এলএলএম-অপ্স**: - সময়ের সাথে সাথে অ্যাপ্লিকেশন লগ এবং পারফরম্যান্স মনিটর এবং বিশ্লেষণ করুন। প্রডাকশন ডেটা এবং annotation এর উপর ভিত্তি করে প্রম্পট, ডেটাসেট এবং মডেলগুলিকে ক্রমাগত উন্নত করতে পারেন। +**6. এলএলএম-অপ্স**: +সময়ের সাথে সাথে অ্যাপ্লিকেশন লগ এবং পারফরম্যান্স মনিটর এবং বিশ্লেষণ করুন। প্রডাকশন ডেটা এবং annotation এর উপর ভিত্তি করে প্রম্পট, ডেটাসেট এবং মডেলগুলিকে ক্রমাগত উন্নত করতে পারেন। **7. ব্যাকএন্ড-অ্যাজ-এ-সার্ভিস**: - ডিফাই-এর সমস্ত অফার সংশ্লিষ্ট API-সহ আছে, যাতে আপনি অনায়াসে ডিফাইকে আপনার নিজস্ব বিজনেস লজিকে ইন্টেগ্রেট করতে পারেন। +ডিফাই-এর সমস্ত অফার সংশ্লিষ্ট API-সহ আছে, যাতে আপনি অনায়াসে ডিফাইকে আপনার নিজস্ব বিজনেস লজিকে ইন্টেগ্রেট করতে পারেন। ## বৈশিষ্ট্য তুলনা @@ -172,17 +174,17 @@ docker compose up -d -## ডিফাই-এর ব্যবহার +## ডিফাই-এর ব্যবহার - **ক্লাউড
** -জিরো সেটাপে ব্যবহার করতে আমাদের [Dify Cloud](https://dify.ai) সার্ভিসটি ব্যবহার করতে পারেন। এখানে সেল্ফহোস্টিং-এর সকল ফিচার ও ক্যাপাবিলিটিসহ স্যান্ডবক্সে ২০০ জিপিটি-৪ কল ফ্রি পাবেন। + জিরো সেটাপে ব্যবহার করতে আমাদের [Dify Cloud](https://dify.ai) সার্ভিসটি ব্যবহার করতে পারেন। এখানে সেল্ফহোস্টিং-এর সকল ফিচার ও ক্যাপাবিলিটিসহ স্যান্ডবক্সে ২০০ জিপিটি-৪ কল ফ্রি পাবেন। - **সেল্ফহোস্টিং ডিফাই কমিউনিটি সংস্করণ
** -সেল্ফহোস্ট করতে এই [স্টার্টার গাইড](#quick-start) ব্যবহার করে দ্রুত আপনার এনভায়রনমেন্টে ডিফাই চালান। -আরো ইন-ডেপথ রেফারেন্সের জন্য [ডকুমেন্টেশন](https://docs.dify.ai) দেখেন। + সেল্ফহোস্ট করতে এই [স্টার্টার গাইড](#quick-start) ব্যবহার করে দ্রুত আপনার এনভায়রনমেন্টে ডিফাই চালান। + আরো ইন-ডেপথ রেফারেন্সের জন্য [ডকুমেন্টেশন](https://docs.dify.ai) দেখেন। - **এন্টারপ্রাইজ / প্রতিষ্ঠানের জন্য Dify
** -আমরা এন্টারপ্রাইজ/প্রতিষ্ঠান-কেন্দ্রিক সেবা প্রদান করে থাকি । [এই চ্যাটবটের মাধ্যমে আপনার প্রশ্নগুলি আমাদের জন্য লগ করুন।](https://udify.app/chat/22L1zSxg6yW1cWQg) অথবা [আমাদের ইমেল পাঠান](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) আপনার চাহিদা সম্পর্কে আলোচনা করার জন্য।
+ আমরা এন্টারপ্রাইজ/প্রতিষ্ঠান-কেন্দ্রিক সেবা প্রদান করে থাকি । [এই চ্যাটবটের মাধ্যমে আপনার প্রশ্নগুলি আমাদের জন্য লগ করুন।](https://udify.app/chat/22L1zSxg6yW1cWQg) অথবা [আমাদের ইমেল পাঠান](mailto:business@dify.ai?subject=%5BGitHub%5DBusiness%20License%20Inquiry) আপনার চাহিদা সম্পর্কে আলোচনা করার জন্য।
> AWS ব্যবহারকারী স্টার্টআপ এবং ছোট ব্যবসার জন্য, [AWS মার্কেটপ্লেসে Dify Premium](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) দেখুন এবং এক-ক্লিকের মাধ্যমে এটি আপনার নিজস্ব AWS VPC-তে ডিপ্লয় করুন। এটি একটি সাশ্রয়ী মূল্যের AMI অফার, যাতে কাস্টম লোগো এবং ব্র্যান্ডিং সহ অ্যাপ তৈরির সুবিধা আছে। @@ -194,10 +196,10 @@ GitHub-এ ডিফাইকে স্টার দিয়ে রাখুন ## Advanced Setup -যদি আপনার কনফিগারেশনটি কাস্টমাইজ করার প্রয়োজন হয়, তাহলে অনুগ্রহ করে আমাদের [.env.example](docker/.env.example) ফাইল দেখুন এবং আপনার `.env` ফাইলে সংশ্লিষ্ট মানগুলি আপডেট করুন। এছাড়াও, আপনার নির্দিষ্ট এনভায়রনমেন্ট এবং প্রয়োজনীয়তার উপর ভিত্তি করে আপনাকে `docker-compose.yaml` ফাইলে সমন্বয় করতে হতে পারে, যেমন ইমেজ ভার্সন পরিবর্তন করা, পোর্ট ম্যাপিং করা, অথবা ভলিউম মাউন্ট করা। +যদি আপনার কনফিগারেশনটি কাস্টমাইজ করার প্রয়োজন হয়, তাহলে অনুগ্রহ করে আমাদের [.env.example](docker/.env.example) ফাইল দেখুন এবং আপনার `.env` ফাইলে সংশ্লিষ্ট মানগুলি আপডেট করুন। এছাড়াও, আপনার নির্দিষ্ট এনভায়রনমেন্ট এবং প্রয়োজনীয়তার উপর ভিত্তি করে আপনাকে `docker-compose.yaml` ফাইলে সমন্বয় করতে হতে পারে, যেমন ইমেজ ভার্সন পরিবর্তন করা, পোর্ট ম্যাপিং করা, অথবা ভলিউম মাউন্ট করা। যেকোনো পরিবর্তন করার পর, অনুগ্রহ করে `docker-compose up -d` পুনরায় চালান। ভেরিয়েবলের সম্পূর্ণ তালিকা [এখানে] (https://docs.dify.ai/getting-started/install-self-hosted/environments) খুঁজে পেতে পারেন। -যদি আপনি একটি হাইলি এভেইলেবল সেটআপ কনফিগার করতে চান, তাহলে কমিউনিটি [Helm Charts](https://helm.sh/) এবং YAML ফাইল রয়েছে যা Dify কে Kubernetes-এ ডিপ্লয় করার প্রক্রিয়া বর্ণনা করে। +যদি আপনি একটি হাইলি এভেইলেবল সেটআপ কনফিগার করতে চান, তাহলে কমিউনিটি [Helm Charts](https://helm.sh/) এবং YAML ফাইল রয়েছে যা Dify কে Kubernetes-এ ডিপ্লয় করার প্রক্রিয়া বর্ণনা করে। - [Helm Chart by @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify) - [Helm Chart by @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm) @@ -206,7 +208,6 @@ GitHub-এ ডিফাইকে স্টার দিয়ে রাখুন - [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s) - [🚀 নতুন! YAML ফাইলসমূহ (Dify v1.6.0 সমর্থিত) তৈরি করেছেন @Zhoneym](https://github.com/Zhoneym/DifyAI-Kubernetes) - #### টেরাফর্ম ব্যবহার করে ডিপ্লয় [terraform](https://www.terraform.io/) ব্যবহার করে এক ক্লিকেই ক্লাউড প্ল্যাটফর্মে Dify ডিপ্লয় করুন। @@ -225,21 +226,21 @@ GitHub-এ ডিফাইকে স্টার দিয়ে রাখুন ##### AWS -- [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +- [AWS CDK by @KevinZhao (EKS based)](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +- [AWS CDK by @tmokmss (ECS based)](https://github.com/aws-samples/dify-self-hosted-on-aws) #### Alibaba Cloud ব্যবহার করে ডিপ্লয় - [Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88) +[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88) #### Alibaba Cloud Data Management ব্যবহার করে ডিপ্লয় - [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/) +[Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/) - #### AKS-এ ডিপ্লয় করার জন্য Azure Devops Pipeline ব্যবহার +#### AKS-এ ডিপ্লয় করার জন্য Azure Devops Pipeline ব্যবহার [Azure Devops Pipeline Helm Chart by @LeoZhang](https://github.com/Ruiruiz30/Dify-helm-chart-AKS) ব্যবহার করে Dify কে AKS-এ এক ক্লিকে ডিপ্লয় করুন - ## Contributing যারা কোড অবদান রাখতে চান, তাদের জন্য আমাদের [অবদান নির্দেশিকা] দেখুন (https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)। @@ -250,9 +251,9 @@ GitHub-এ ডিফাইকে স্টার দিয়ে রাখুন ## কমিউনিটি এবং যোগাযোগ - [GitHub Discussion](https://github.com/langgenius/dify/discussions) ফিডব্যাক এবং প্রতিক্রিয়া জানানোর মাধ্যম। -- [GitHub Issues](https://github.com/langgenius/dify/issues). Dify.AI ব্যবহার করে আপনি যেসব বাগের সম্মুখীন হন এবং ফিচার প্রস্তাবনা। আমাদের [অবদান নির্দেশিকা](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) দেখুন। -- [Discord](https://discord.gg/FngNHpbcY7) আপনার এপ্লিকেশন শেয়ার এবং কমিউনিটি আড্ডার মাধ্যম। -- [X(Twitter)](https://twitter.com/dify_ai) আপনার এপ্লিকেশন শেয়ার এবং কমিউনিটি আড্ডার মাধ্যম। +- [GitHub Issues](https://github.com/langgenius/dify/issues). Dify.AI ব্যবহার করে আপনি যেসব বাগের সম্মুখীন হন এবং ফিচার প্রস্তাবনা। আমাদের [অবদান নির্দেশিকা](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) দেখুন। +- [Discord](https://discord.gg/FngNHpbcY7) আপনার এপ্লিকেশন শেয়ার এবং কমিউনিটি আড্ডার মাধ্যম। +- [X(Twitter)](https://twitter.com/dify_ai) আপনার এপ্লিকেশন শেয়ার এবং কমিউনিটি আড্ডার মাধ্যম। **অবদানকারীদের তালিকা** @@ -264,7 +265,7 @@ GitHub-এ ডিফাইকে স্টার দিয়ে রাখুন [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date) -## নিরাপত্তা বিষয়ক +## নিরাপত্তা বিষয়ক আপনার গোপনীয়তা রক্ষা করতে, অনুগ্রহ করে GitHub-এ নিরাপত্তা সংক্রান্ত সমস্যা পোস্ট করা এড়িয়ে চলুন। পরিবর্তে, আপনার প্রশ্নগুলি ঠিকানায় পাঠান এবং আমরা আপনাকে আরও বিস্তারিত উত্তর প্রদান করব। diff --git a/README_CN.md b/README_CN.md index 82149519d3..1c40098034 100644 --- a/README_CN.md +++ b/README_CN.md @@ -48,8 +48,7 @@ README in বাংলা - -# +#
langgenius%2Fdify | 趋势转变 @@ -58,32 +57,31 @@ Dify 是一个开源的 LLM 应用开发平台。其直观的界面结合了 AI 工作流、RAG 管道、Agent、模型管理、可观测性功能等，让您可以快速从原型到生产。以下是其核心功能列表：

-**1. 工作流**: - 在画布上构建和测试功能强大的 AI 工作流程，利用以下所有功能以及更多功能。 +**1. 工作流**: +在画布上构建和测试功能强大的 AI 工作流程，利用以下所有功能以及更多功能。 -**2. 全面的模型支持**: - 与数百种专有/开源 LLMs 以及数十种推理提供商和自托管解决方案无缝集成，涵盖 GPT、Mistral、Llama3 以及任何与 OpenAI API 兼容的模型。完整的支持模型提供商列表可在[此处](https://docs.dify.ai/getting-started/readme/model-providers)找到。 +**2. 全面的模型支持**: +与数百种专有/开源 LLMs 以及数十种推理提供商和自托管解决方案无缝集成，涵盖 GPT、Mistral、Llama3 以及任何与 OpenAI API 兼容的模型。完整的支持模型提供商列表可在[此处](https://docs.dify.ai/getting-started/readme/model-providers)找到。 ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3) +**3. Prompt IDE**: +用于制作提示、比较模型性能以及向基于聊天的应用程序添加其他功能（如文本转语音）的直观界面。 -**3. Prompt IDE**: - 用于制作提示、比较模型性能以及向基于聊天的应用程序添加其他功能（如文本转语音）的直观界面。 +**4. RAG Pipeline**: +广泛的 RAG 功能，涵盖从文档摄入到检索的所有内容，支持从 PDF、PPT 和其他常见文档格式中提取文本的开箱即用的支持。 -**4. RAG Pipeline**: - 广泛的 RAG 功能，涵盖从文档摄入到检索的所有内容，支持从 PDF、PPT 和其他常见文档格式中提取文本的开箱即用的支持。 +**5. Agent 智能体**: +您可以基于 LLM 函数调用或 ReAct 定义 Agent，并为 Agent 添加预构建或自定义工具。Dify 为 AI Agent 提供了 50 多种内置工具，如谷歌搜索、DALL·E、Stable Diffusion 和 WolframAlpha 等。 -**5. Agent 智能体**: - 您可以基于 LLM 函数调用或 ReAct 定义 Agent，并为 Agent 添加预构建或自定义工具。Dify 为 AI Agent 提供了 50 多种内置工具，如谷歌搜索、DALL·E、Stable Diffusion 和 WolframAlpha 等。 - -**6. LLMOps**: - 随时间监视和分析应用程序日志和性能。您可以根据生产数据和标注持续改进提示、数据集和模型。 - -**7. 后端即服务**: - 所有 Dify 的功能都带有相应的 API，因此您可以轻松地将 Dify 集成到自己的业务逻辑中。 +**6. LLMOps**: +随时间监视和分析应用程序日志和性能。您可以根据生产数据和标注持续改进提示、数据集和模型。 +**7. 后端即服务**: +所有 Dify 的功能都带有相应的 API，因此您可以轻松地将 Dify 集成到自己的业务逻辑中。 ## 功能比较 + @@ -153,14 +151,15 @@ Dify 是一个开源的 LLM 应用开发平台。其直观的界面结合了 AI ## 使用 Dify - **云
** -我们提供[ Dify 云服务](https://dify.ai)，任何人都可以零设置尝试。它提供了自部署版本的所有功能，并在沙盒计划中包含 200 次免费的 GPT-4 调用。 + 我们提供[ Dify 云服务](https://dify.ai)，任何人都可以零设置尝试。它提供了自部署版本的所有功能，并在沙盒计划中包含 200 次免费的 GPT-4 调用。 - **自托管 Dify 社区版
** -使用这个[入门指南](#快速启动)快速在您的环境中运行 Dify。 -使用我们的[文档](https://docs.dify.ai)进行进一步的参考和更深入的说明。 + 使用这个[入门指南](#%E5%BF%AB%E9%80%9F%E5%90%AF%E5%8A%A8)快速在您的环境中运行 Dify。 + 使用我们的[文档](https://docs.dify.ai)进行进一步的参考和更深入的说明。 - **面向企业/组织的 Dify
** -我们提供额外的面向企业的功能。[给我们发送电子邮件](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)讨论企业需求。
+ 我们提供额外的面向企业的功能。[给我们发送电子邮件](mailto:business@dify.ai?subject=%5BGitHub%5DBusiness%20License%20Inquiry)讨论企业需求。
+ > 对于使用 AWS 的初创公司和中小型企业，请查看 [AWS Marketplace 上的 Dify 高级版](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6)，并使用一键部署到您自己的 AWS VPC。它是一个价格实惠的 AMI 产品，提供了使用自定义徽标和品牌创建应用程序的选项。 ## 保持领先 @@ -199,31 +198,37 @@ docker compose up -d 使用 [Helm Chart](https://helm.sh/) 版本或者 Kubernetes 资源清单（YAML），可以在 Kubernetes 上部署 Dify。 - [Helm Chart by @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify) + - [Helm Chart by @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm) + - [Helm Chart by @magicsong](https://github.com/magicsong/ai-charts) + - [YAML 文件 by @Winson-030](https://github.com/Winson-030/dify-kubernetes) + - [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s) - [🚀 NEW! YAML 文件 (支持 Dify v1.6.0) by @Zhoneym](https://github.com/Zhoneym/DifyAI-Kubernetes) - - #### 使用 Terraform 部署 使用 [terraform](https://www.terraform.io/) 一键将 Dify 部署到云平台 ##### Azure Global + - [Azure Terraform by @nikawang](https://github.com/nikawang/dify-azure-terraform) ##### Google Cloud + - [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform) #### 使用 AWS CDK 部署 使用 [CDK](https://aws.amazon.com/cdk/) 将 Dify 部署到 AWS -##### AWS -- [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +##### AWS + +- [AWS CDK by @KevinZhao (EKS based)](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +- [AWS CDK by @tmokmss (ECS based)](https://github.com/aws-samples/dify-self-hosted-on-aws) #### 使用 阿里云计算巢 部署 @@ -241,7 +246,6 @@ docker compose up -d [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date) - ## Contributing 对于那些想要贡献代码的人，请参阅我们的[贡献指南](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)。 @@ -261,10 +265,10 @@ docker compose up -d - [GitHub Discussion](https://github.com/langgenius/dify/discussions). 👉：分享您的应用程序并与社区交流。 - [GitHub Issues](https://github.com/langgenius/dify/issues)。👉：使用 Dify.AI 时遇到的错误和问题，请参阅[贡献指南](CONTRIBUTING.md)。 -- [电子邮件支持](mailto:hello@dify.ai?subject=[GitHub]Questions%20About%20Dify)。👉：关于使用 Dify.AI 的问题。 +- [电子邮件支持](mailto:hello@dify.ai?subject=%5BGitHub%5DQuestions%20About%20Dify)。👉：关于使用 Dify.AI 的问题。 - [Discord](https://discord.gg/FngNHpbcY7)。👉：分享您的应用程序并与社区交流。 - [X(Twitter)](https://twitter.com/dify_ai)。👉：分享您的应用程序并与社区交流。 -- [商业许可](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)。👉：有关商业用途许可 Dify.AI 的商业咨询。 +- [商业许可](mailto:business@dify.ai?subject=%5BGitHub%5DBusiness%20License%20Inquiry)。👉：有关商业用途许可 Dify.AI 的商业咨询。 ## 安全问题 diff --git a/README_DE.md b/README_DE.md index 2420ac0392..88c36019e3 100644 --- a/README_DE.md +++ b/README_DE.md @@ -56,10 +56,11 @@ Dify ist eine Open-Source-Plattform zur Entwicklung von LLM-Anwendungen. Ihre intuitive Benutzeroberfläche vereint agentenbasierte KI-Workflows, RAG-Pipelines, Agentenfunktionen, Modellverwaltung, Überwachungsfunktionen und mehr, sodass Sie schnell von einem Prototyp in die Produktion übergehen können. ## Schnellstart + > Bevor Sie Dify installieren, stellen Sie sicher, dass Ihr System die folgenden Mindestanforderungen erfüllt: -> ->- CPU >= 2 Core ->- RAM >= 4 GiB +> +> - CPU >= 2 Core +> - RAM >= 4 GiB
@@ -75,37 +76,38 @@ docker compose up -d Nachdem Sie den Server gestartet haben, können Sie über Ihren Browser auf das Dify Dashboard unter [http://localhost/install](http://localhost/install) zugreifen und den Initialisierungsprozess starten. #### Hilfe suchen + Bitte beachten Sie unsere [FAQ](https://docs.dify.ai/getting-started/install-self-hosted/faqs), wenn Sie Probleme bei der Einrichtung von Dify haben. Wenden Sie sich an [die Community und uns](#community--contact), falls weiterhin Schwierigkeiten auftreten. > Wenn Sie zu Dify beitragen oder zusätzliche Entwicklungen durchführen möchten, lesen Sie bitte unseren [Leitfaden zur Bereitstellung aus dem Quellcode](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code). ## Wesentliche Merkmale -**1. Workflow**: - Erstellen und testen Sie leistungsstarke KI-Workflows auf einer visuellen Oberfläche, wobei Sie alle der folgenden Funktionen und darüber hinaus nutzen können. -**2. Umfassende Modellunterstützung**: - Nahtlose Integration mit Hunderten von proprietären und Open-Source-LLMs von Dutzenden Inferenzanbietern und selbstgehosteten Lösungen, die GPT, Mistral, Llama3 und alle mit der OpenAI API kompatiblen Modelle abdecken. Eine vollständige Liste der unterstützten Modellanbieter finden Sie [hier](https://docs.dify.ai/getting-started/readme/model-providers). +**1. Workflow**: +Erstellen und testen Sie leistungsstarke KI-Workflows auf einer visuellen Oberfläche, wobei Sie alle der folgenden Funktionen und darüber hinaus nutzen können. +**2. Umfassende Modellunterstützung**: +Nahtlose Integration mit Hunderten von proprietären und Open-Source-LLMs von Dutzenden Inferenzanbietern und selbstgehosteten Lösungen, die GPT, Mistral, Llama3 und alle mit der OpenAI API kompatiblen Modelle abdecken. Eine vollständige Liste der unterstützten Modellanbieter finden Sie [hier](https://docs.dify.ai/getting-started/readme/model-providers). ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3) +**3. Prompt IDE**: +Intuitive Benutzeroberfläche zum Erstellen von Prompts, zum Vergleichen der Modellleistung und zum Hinzufügen zusätzlicher Funktionen wie Text-to-Speech in einer chatbasierten Anwendung. -**3. Prompt IDE**: - Intuitive Benutzeroberfläche zum Erstellen von Prompts, zum Vergleichen der Modellleistung und zum Hinzufügen zusätzlicher Funktionen wie Text-to-Speech in einer chatbasierten Anwendung. +**4. RAG Pipeline**: +Umfassende RAG-Funktionalitäten, die alles von der Dokumenteneinlesung bis zur -abfrage abdecken, mit sofort einsatzbereiter Unterstützung für die Textextraktion aus PDFs, PPTs und anderen gängigen Dokumentformaten. -**4. RAG Pipeline**: - Umfassende RAG-Funktionalitäten, die alles von der Dokumenteneinlesung bis zur -abfrage abdecken, mit sofort einsatzbereiter Unterstützung für die Textextraktion aus PDFs, PPTs und anderen gängigen Dokumentformaten. +**5. Fähigkeiten des Agenten**: +Sie können Agenten basierend auf LLM Function Calling oder ReAct definieren und vorgefertigte oder benutzerdefinierte Tools für den Agenten hinzufügen. Dify stellt über 50 integrierte Tools für KI-Agenten bereit, wie zum Beispiel Google Search, DALL·E, Stable Diffusion und WolframAlpha. -**5. Fähigkeiten des Agenten**: - Sie können Agenten basierend auf LLM Function Calling oder ReAct definieren und vorgefertigte oder benutzerdefinierte Tools für den Agenten hinzufügen. Dify stellt über 50 integrierte Tools für KI-Agenten bereit, wie zum Beispiel Google Search, DALL·E, Stable Diffusion und WolframAlpha. +**6. LLMOps**: +Überwachen und analysieren Sie Anwendungsprotokolle und die Leistung im Laufe der Zeit. Sie können kontinuierlich Prompts, Datensätze und Modelle basierend auf Produktionsdaten und Annotationen verbessern. -**6. LLMOps**: - Überwachen und analysieren Sie Anwendungsprotokolle und die Leistung im Laufe der Zeit. Sie können kontinuierlich Prompts, Datensätze und Modelle basierend auf Produktionsdaten und Annotationen verbessern. - -**7. Backend-as-a-Service**: - Alle Dify-Angebote kommen mit entsprechenden APIs, sodass Sie Dify mühelos in Ihre eigene Geschäftslogik integrieren können. +**7. Backend-as-a-Service**: +Alle Dify-Angebote kommen mit entsprechenden APIs, sodass Sie Dify mühelos in Ihre eigene Geschäftslogik integrieren können. ## Vergleich der Merkmale +
功能
@@ -175,15 +177,15 @@ Bitte beachten Sie unsere [FAQ](https://docs.dify.ai/getting-started/install-sel ## Dify verwenden - **Cloud
** -Wir hosten einen [Dify Cloud](https://dify.ai)-Service, den jeder ohne Einrichtung ausprobieren kann. Er bietet alle Funktionen der selbstgehosteten Version und beinhaltet 200 kostenlose GPT-4-Aufrufe im Sandbox-Plan. + Wir hosten einen [Dify Cloud](https://dify.ai)-Service, den jeder ohne Einrichtung ausprobieren kann. Er bietet alle Funktionen der selbstgehosteten Version und beinhaltet 200 kostenlose GPT-4-Aufrufe im Sandbox-Plan. - **Selbstgehostete Dify Community Edition
** -Starten Sie Dify schnell in Ihrer Umgebung mit diesem [Schnellstart-Leitfaden](#quick-start). Nutzen Sie unsere [Dokumentation](https://docs.dify.ai) für weiterführende Informationen und detaillierte Anweisungen. + Starten Sie Dify schnell in Ihrer Umgebung mit diesem [Schnellstart-Leitfaden](#quick-start). Nutzen Sie unsere [Dokumentation](https://docs.dify.ai) für weiterführende Informationen und detaillierte Anweisungen. - **Dify für Unternehmen / Organisationen
** -Wir bieten zusätzliche, unternehmensspezifische Funktionen. [Über diesen Chatbot können Sie uns Ihre Fragen mitteilen](https://udify.app/chat/22L1zSxg6yW1cWQg) oder [senden Sie uns eine E-Mail](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry), um Ihre unternehmerischen Bedürfnisse zu besprechen.
- > Für Startups und kleine Unternehmen, die AWS nutzen, schauen Sie sich [Dify Premium on AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) an und stellen Sie es mit nur einem Klick in Ihrer eigenen AWS VPC bereit. Es handelt sich um ein erschwingliches AMI-Angebot mit der Option, Apps mit individuellem Logo und Branding zu erstellen. + Wir bieten zusätzliche, unternehmensspezifische Funktionen. [Über diesen Chatbot können Sie uns Ihre Fragen mitteilen](https://udify.app/chat/22L1zSxg6yW1cWQg) oder [senden Sie uns eine E-Mail](mailto:business@dify.ai?subject=%5BGitHub%5DBusiness%20License%20Inquiry), um Ihre unternehmerischen Bedürfnisse zu besprechen.
+ > Für Startups und kleine Unternehmen, die AWS nutzen, schauen Sie sich [Dify Premium on AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) an und stellen Sie es mit nur einem Klick in Ihrer eigenen AWS VPC bereit. Es handelt sich um ein erschwingliches AMI-Angebot mit der Option, Apps mit individuellem Logo und Branding zu erstellen. ## Immer einen Schritt voraus @@ -191,7 +193,6 @@ Star Dify auf GitHub und lassen Sie sich sofort über neue Releases benachrichti ![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4) - ## Erweiterte Einstellungen Falls Sie die Konfiguration anpassen müssen, lesen Sie bitte die Kommentare in unserer [.env.example](docker/.env.example)-Datei und aktualisieren Sie die entsprechenden Werte in Ihrer `.env`-Datei. Zusätzlich müssen Sie eventuell Anpassungen an der `docker-compose.yaml`-Datei vornehmen, wie zum Beispiel das Ändern von Image-Versionen, Portzuordnungen oder Volumen-Mounts, je nach Ihrer spezifischen Einsatzumgebung und Ihren Anforderungen. Nachdem Sie Änderungen vorgenommen haben, starten Sie `docker-compose up -d` erneut. Eine vollständige Liste der verfügbaren Umgebungsvariablen finden Sie [hier](https://docs.dify.ai/getting-started/install-self-hosted/environments). @@ -210,19 +211,23 @@ Falls Sie eine hochverfügbare Konfiguration einrichten möchten, gibt es von de Stellen Sie Dify mit nur einem Klick mithilfe von [terraform](https://www.terraform.io/) auf einer Cloud-Plattform bereit. ##### Azure Global + - [Azure Terraform by @nikawang](https://github.com/nikawang/dify-azure-terraform) ##### Google Cloud + - [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform) #### Verwendung von AWS CDK für die Bereitstellung Bereitstellung von Dify auf AWS mit [CDK](https://aws.amazon.com/cdk/) -##### AWS -- [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +##### AWS -#### Alibaba Cloud +- [AWS CDK by @KevinZhao (EKS based)](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +- [AWS CDK by @tmokmss (ECS based)](https://github.com/aws-samples/dify-self-hosted-on-aws) + +#### Alibaba Cloud [Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88) @@ -234,20 +239,18 @@ Ein-Klick-Bereitstellung von Dify in der Alibaba Cloud mit [Alibaba Cloud Data M Stellen Sie Dify mit einem Klick in AKS bereit, indem Sie [Azure Devops Pipeline Helm Chart by @LeoZhang](https://github.com/Ruiruiz30/Dify-helm-chart-AKS) verwenden - ## Contributing Falls Sie Code beitragen möchten, lesen Sie bitte unseren [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). Gleichzeitig bitten wir Sie, Dify zu unterstützen, indem Sie es in den sozialen Medien teilen und auf Veranstaltungen und Konferenzen präsentieren. - > Wir suchen Mitwirkende, die dabei helfen, Dify in weitere Sprachen zu übersetzen – außer Mandarin oder Englisch. Wenn Sie Interesse an einer Mitarbeit haben, lesen Sie bitte die [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) für weitere Informationen und hinterlassen Sie einen Kommentar im `global-users`-Kanal unseres [Discord Community Servers](https://discord.gg/8Tpq4AcN9c). ## Gemeinschaft & Kontakt -* [GitHub Discussion](https://github.com/langgenius/dify/discussions). Am besten geeignet für: den Austausch von Feedback und das Stellen von Fragen. -* [GitHub Issues](https://github.com/langgenius/dify/issues). Am besten für: Fehler, auf die Sie bei der Verwendung von Dify.AI stoßen, und Funktionsvorschläge. Siehe unseren [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). -* [Discord](https://discord.gg/FngNHpbcY7). Am besten geeignet für: den Austausch von Bewerbungen und den Austausch mit der Community. -* [X(Twitter)](https://twitter.com/dify_ai). Am besten geeignet für: den Austausch von Bewerbungen und den Austausch mit der Community. +- [GitHub Discussion](https://github.com/langgenius/dify/discussions). Am besten geeignet für: den Austausch von Feedback und das Stellen von Fragen. +- [GitHub Issues](https://github.com/langgenius/dify/issues). Am besten für: Fehler, auf die Sie bei der Verwendung von Dify.AI stoßen, und Funktionsvorschläge. Siehe unseren [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). +- [Discord](https://discord.gg/FngNHpbcY7). Am besten geeignet für: den Austausch von Bewerbungen und den Austausch mit der Community. +- [X(Twitter)](https://twitter.com/dify_ai). Am besten geeignet für: den Austausch von Bewerbungen und den Austausch mit der Community. **Mitwirkende** @@ -259,7 +262,6 @@ Falls Sie Code beitragen möchten, lesen Sie bitte unseren [Contribution Guide]( [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date) - ## Offenlegung der Sicherheit Um Ihre Privatsphäre zu schützen, vermeiden Sie es bitte, Sicherheitsprobleme auf GitHub zu posten. Schicken Sie Ihre Fragen stattdessen an security@dify.ai und wir werden Ihnen eine ausführlichere Antwort geben. @@ -267,4 +269,3 @@ Um Ihre Privatsphäre zu schützen, vermeiden Sie es bitte, Sicherheitsprobleme ## Lizenz Dieses Repository steht unter der [Dify Open Source License](LICENSE), die im Wesentlichen Apache 2.0 mit einigen zusätzlichen Einschränkungen ist. - diff --git a/README_ES.md b/README_ES.md index 4fa59dc18f..bc3b25f2d1 100644 --- a/README_ES.md +++ b/README_ES.md @@ -48,7 +48,7 @@ README in বাংলা

-# +#

langgenius%2Fdify | Trendshift @@ -56,32 +56,31 @@ Dify es una plataforma de desarrollo de aplicaciones de LLM de código abierto. Su interfaz intuitiva combina flujo de trabajo de IA, pipeline RAG, capacidades de agente, gestión de modelos, características de observabilidad y más, lo que le permite pasar rápidamente de un prototipo a producción. Aquí hay una lista de las características principales:

-**1. Flujo de trabajo**: - Construye y prueba potentes flujos de trabajo de IA en un lienzo visual, aprovechando todas las siguientes características y más. +**1. Flujo de trabajo**: +Construye y prueba potentes flujos de trabajo de IA en un lienzo visual, aprovechando todas las siguientes características y más. -**2. Soporte de modelos completo**: - Integración perfecta con cientos de LLMs propietarios / de código abierto de docenas de proveedores de inferencia y soluciones auto-alojadas, que cubren GPT, Mistral, Llama3 y cualquier modelo compatible con la API de OpenAI. Se puede encontrar una lista completa de proveedores de modelos admitidos [aquí](https://docs.dify.ai/getting-started/readme/model-providers). +**2. Soporte de modelos completo**: +Integración perfecta con cientos de LLMs propietarios / de código abierto de docenas de proveedores de inferencia y soluciones auto-alojadas, que cubren GPT, Mistral, Llama3 y cualquier modelo compatible con la API de OpenAI. Se puede encontrar una lista completa de proveedores de modelos admitidos [aquí](https://docs.dify.ai/getting-started/readme/model-providers). ![proveedores-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3) +**3. IDE de prompt**: +Interfaz intuitiva para crear prompts, comparar el rendimiento del modelo y agregar características adicionales como texto a voz a una aplicación basada en chat. -**3. IDE de prompt**: - Interfaz intuitiva para crear prompts, comparar el rendimiento del modelo y agregar características adicionales como texto a voz a una aplicación basada en chat. +**4. Pipeline RAG**: +Amplias capacidades de RAG que cubren todo, desde la ingestión de documentos hasta la recuperación, con soporte listo para usar para la extracción de texto de PDF, PPT y otros formatos de documento comunes. -**4. Pipeline RAG**: - Amplias capacidades de RAG que cubren todo, desde la ingestión de documentos hasta la recuperación, con soporte listo para usar para la extracción de texto de PDF, PPT y otros formatos de documento comunes. +**5. Capacidades de agente**: +Puedes definir agentes basados en LLM Function Calling o ReAct, y agregar herramientas preconstruidas o personalizadas para el agente. Dify proporciona más de 50 herramientas integradas para agentes de IA, como Búsqueda de Google, DALL·E, Difusión Estable y WolframAlpha. -**5. Capacidades de agente**: - Puedes definir agentes basados en LLM Function Calling o ReAct, y agregar herramientas preconstruidas o personalizadas para el agente. Dify proporciona más de 50 herramientas integradas para agentes de IA, como Búsqueda de Google, DALL·E, Difusión Estable y WolframAlpha. - -**6. LLMOps**: - Supervisa y analiza registros de aplicaciones y rendimiento a lo largo del tiempo. Podrías mejorar continuamente prompts, conjuntos de datos y modelos basados en datos de producción y anotaciones. - -**7. Backend como servicio**: - Todas las ofertas de Dify vienen con APIs correspondientes, por lo que podrías integrar Dify sin esfuerzo en tu propia lógica empresarial. +**6. LLMOps**: +Supervisa y analiza registros de aplicaciones y rendimiento a lo largo del tiempo. Podrías mejorar continuamente prompts, conjuntos de datos y modelos basados en datos de producción y anotaciones. +**7. Backend como servicio**: +Todas las ofertas de Dify vienen con APIs correspondientes, por lo que podrías integrar Dify sin esfuerzo en tu propia lógica empresarial. ## Comparación de características +

Feature
@@ -151,16 +150,16 @@ Dify es una plataforma de desarrollo de aplicaciones de LLM de código abierto. ## Usando Dify - **Nube
** -Hospedamos un servicio [Dify Cloud](https://dify.ai) para que cualquiera lo pruebe sin configuración. Proporciona todas las capacidades de la versión autoimplementada e incluye 200 llamadas gratuitas a GPT-4 en el plan sandbox. + Hospedamos un servicio [Dify Cloud](https://dify.ai) para que cualquiera lo pruebe sin configuración. Proporciona todas las capacidades de la versión autoimplementada e incluye 200 llamadas gratuitas a GPT-4 en el plan sandbox. - **Auto-alojamiento de Dify Community Edition
** -Pon rápidamente Dify en funcionamiento en tu entorno con esta [guía de inicio rápido](#quick-start). -Usa nuestra [documentación](https://docs.dify.ai) para más referencias e instrucciones más detalladas. + Pon rápidamente Dify en funcionamiento en tu entorno con esta [guía de inicio rápido](#quick-start). + Usa nuestra [documentación](https://docs.dify.ai) para más referencias e instrucciones más detalladas. - **Dify para Empresas / Organizaciones
** -Proporcionamos características adicionales centradas en la empresa. [Envíanos un correo electrónico](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) para discutir las necesidades empresariales.
- > Para startups y pequeñas empresas que utilizan AWS, echa un vistazo a [Dify Premium en AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) e impleméntalo en tu propio VPC de AWS con un clic. Es una AMI asequible que ofrece la opción de crear aplicaciones con logotipo y marca personalizados. + Proporcionamos características adicionales centradas en la empresa. [Envíanos un correo electrónico](mailto:business@dify.ai?subject=%5BGitHub%5DBusiness%20License%20Inquiry) para discutir las necesidades empresariales.
+ > Para startups y pequeñas empresas que utilizan AWS, echa un vistazo a [Dify Premium en AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) e impleméntalo en tu propio VPC de AWS con un clic. Es una AMI asequible que ofrece la opción de crear aplicaciones con logotipo y marca personalizados. ## Manteniéndote al tanto @@ -168,13 +167,12 @@ Dale estrella a Dify en GitHub y serás notificado instantáneamente de las nuev ![danos estrella](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4) - - ## Inicio Rápido + > Antes de instalar Dify, asegúrate de que tu máquina cumpla con los siguientes requisitos mínimos del sistema: -> ->- CPU >= 2 núcleos ->- RAM >= 4GB +> +> - CPU >= 2 núcleos +> - RAM >= 4GB
@@ -210,17 +208,21 @@ Si desea configurar una configuración de alta disponibilidad, la comunidad prop Despliega Dify en una plataforma en la nube con un solo clic utilizando [terraform](https://www.terraform.io/) ##### Azure Global + - [Azure Terraform por @nikawang](https://github.com/nikawang/dify-azure-terraform) ##### Google Cloud + - [Google Cloud Terraform por @sotazum](https://github.com/DeNA/dify-google-cloud-terraform) #### Usando AWS CDK para el Despliegue Despliegue Dify en AWS usando [CDK](https://aws.amazon.com/cdk/) -##### AWS -- [AWS CDK por @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +##### AWS + +- [AWS CDK por @KevinZhao (EKS based)](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +- [AWS CDK por @tmokmss (ECS based)](https://github.com/aws-samples/dify-self-hosted-on-aws) #### Alibaba Cloud @@ -234,13 +236,11 @@ Despliega Dify en Alibaba Cloud con un solo clic con [Alibaba Cloud Data Managem Implementa Dify en AKS con un clic usando [Azure Devops Pipeline Helm Chart by @LeoZhang](https://github.com/Ruiruiz30/Dify-helm-chart-AKS) - ## Contribuir -Para aquellos que deseen contribuir con código, consulten nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). +Para aquellos que deseen contribuir con código, consulten nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). Al mismo tiempo, considera apoyar a Dify compartiéndolo en redes sociales y en eventos y conferencias. - > Estamos buscando colaboradores para ayudar con la traducción de Dify a idiomas que no sean el mandarín o el inglés. Si estás interesado en ayudar, consulta el [README de i18n](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) para obtener más información y déjanos un comentario en el canal `global-users` de nuestro [Servidor de Comunidad en Discord](https://discord.gg/8Tpq4AcN9c). **Contribuidores** @@ -251,15 +251,22 @@ Al mismo tiempo, considera apoyar a Dify compartiéndolo en redes sociales y en ## Comunidad y Contacto -* [Discusión en GitHub](https://github.com/langgenius/dify/discussions). Lo mejor para: compartir comentarios y hacer preguntas. -* [Reporte de problemas en GitHub](https://github.com/langgenius/dify/issues). Lo mejor para: errores que encuentres usando Dify.AI y propuestas de características. Consulta nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). -* [Discord](https://discord.gg/FngNHpbcY7). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad. -* [X(Twitter)](https://twitter.com/dify_ai). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad. +- [Discusión en GitHub](https://github.com/langgenius/dify/discussions). Lo mejor para: compartir comentarios y hacer preguntas. +- [Reporte de problemas en GitHub](https://github.com/langgenius/dify/issues). Lo mejor para: errores que encuentres usando Dify.AI y propuestas de características. Consulta nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). +- [Discord](https://discord.gg/FngNHpbcY7). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad. +- [X(Twitter)](https://twitter.com/dify_ai). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad. ## Historial de Estrellas [![Gráfico de Historial de Estrellas](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date) +## Divulgación de Seguridad + +Para proteger tu privacidad, evita publicar problemas de seguridad en GitHub. En su lugar, envía tus preguntas a security@dify.ai y te proporcionaremos una respuesta más detallada. + +## Licencia + +Este repositorio está disponible bajo la [Licencia de Código Abierto de Dify](LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales. ## Divulgación de Seguridad @@ -268,10 +275,3 @@ Para proteger tu privacidad, evita publicar problemas de seguridad en GitHub. En ## Licencia Este repositorio está disponible bajo la [Licencia de Código Abierto de Dify](LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales. -## Divulgación de Seguridad - -Para proteger tu privacidad, evita publicar problemas de seguridad en GitHub. En su lugar, envía tus preguntas a security@dify.ai y te proporcionaremos una respuesta más detallada. - -## Licencia - -Este repositorio está disponible bajo la [Licencia de Código Abierto de Dify](LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales. diff --git a/README_FR.md b/README_FR.md index dcbc869620..7521753100 100644 --- a/README_FR.md +++ b/README_FR.md @@ -48,7 +48,7 @@ README in বাংলা

-# +#

langgenius%2Fdify | Trendshift @@ -56,32 +56,31 @@ Dify est une plateforme de développement d'applications LLM open source. Son interface intuitive combine un flux de travail d'IA, un pipeline RAG, des capacités d'agent, une gestion de modèles, des fonctionnalités d'observabilité, et plus encore, vous permettant de passer rapidement du prototype à la production. Voici une liste des fonctionnalités principales:

-**1. Flux de travail** : - Construisez et testez des flux de travail d'IA puissants sur un canevas visuel, en utilisant toutes les fonctionnalités suivantes et plus encore. +**1. Flux de travail** : +Construisez et testez des flux de travail d'IA puissants sur un canevas visuel, en utilisant toutes les fonctionnalités suivantes et plus encore. -**2. Prise en charge complète des modèles** : - Intégration transparente avec des centaines de LLM propriétaires / open source provenant de dizaines de fournisseurs d'inférence et de solutions auto-hébergées, couvrant GPT, Mistral, Llama3, et tous les modèles compatibles avec l'API OpenAI. Une liste complète des fournisseurs de modèles pris en charge se trouve [ici](https://docs.dify.ai/getting-started/readme/model-providers). +**2. Prise en charge complète des modèles** : +Intégration transparente avec des centaines de LLM propriétaires / open source provenant de dizaines de fournisseurs d'inférence et de solutions auto-hébergées, couvrant GPT, Mistral, Llama3, et tous les modèles compatibles avec l'API OpenAI. Une liste complète des fournisseurs de modèles pris en charge se trouve [ici](https://docs.dify.ai/getting-started/readme/model-providers). ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3) +**3. IDE de prompt** : +Interface intuitive pour créer des prompts, comparer les performances des modèles et ajouter des fonctionnalités supplémentaires telles que la synthèse vocale à une application basée sur des chats. -**3. IDE de prompt** : - Interface intuitive pour créer des prompts, comparer les performances des modèles et ajouter des fonctionnalités supplémentaires telles que la synthèse vocale à une application basée sur des chats. +**4. Pipeline RAG** : +Des capacités RAG étendues qui couvrent tout, de l'ingestion de documents à la récupération, avec un support prêt à l'emploi pour l'extraction de texte à partir de PDF, PPT et autres formats de document courants. -**4. Pipeline RAG** : - Des capacités RAG étendues qui couvrent tout, de l'ingestion de documents à la récupération, avec un support prêt à l'emploi pour l'extraction de texte à partir de PDF, PPT et autres formats de document courants. +**5. Capacités d'agent** : +Vous pouvez définir des agents basés sur l'appel de fonction LLM ou ReAct, et ajouter des outils pré-construits ou personnalisés pour l'agent. Dify fournit plus de 50 outils intégrés pour les agents d'IA, tels que la recherche Google, DALL·E, Stable Diffusion et WolframAlpha. -**5. Capacités d'agent** : - Vous pouvez définir des agents basés sur l'appel de fonction LLM ou ReAct, et ajouter des outils pré-construits ou personnalisés pour l'agent. Dify fournit plus de 50 outils intégrés pour les agents d'IA, tels que la recherche Google, DALL·E, Stable Diffusion et WolframAlpha. - -**6. LLMOps** : - Surveillez et analysez les journaux d'application et les performances au fil du temps. Vous pouvez continuellement améliorer les prompts, les ensembles de données et les modèles en fonction des données de production et des annotations. - -**7. Backend-as-a-Service** : - Toutes les offres de Dify sont accompagnées d'API correspondantes, vous permettant d'intégrer facilement Dify dans votre propre logique métier. +**6. LLMOps** : +Surveillez et analysez les journaux d'application et les performances au fil du temps. Vous pouvez continuellement améliorer les prompts, les ensembles de données et les modèles en fonction des données de production et des annotations. +**7. Backend-as-a-Service** : +Toutes les offres de Dify sont accompagnées d'API correspondantes, vous permettant d'intégrer facilement Dify dans votre propre logique métier. ## Comparaison des fonctionnalités +

Característica
@@ -151,16 +150,16 @@ Dify est une plateforme de développement d'applications LLM open source. Son in ## Utiliser Dify - **Cloud
** -Nous hébergeons un service [Dify Cloud](https://dify.ai) pour que tout le monde puisse l'essayer sans aucune configuration. Il fournit toutes les capacités de la version auto-hébergée et comprend 200 appels GPT-4 gratuits dans le plan bac à sable. + Nous hébergeons un service [Dify Cloud](https://dify.ai) pour que tout le monde puisse l'essayer sans aucune configuration. Il fournit toutes les capacités de la version auto-hébergée et comprend 200 appels GPT-4 gratuits dans le plan bac à sable. - **Auto-hébergement Dify Community Edition
** -Lancez rapidement Dify dans votre environnement avec ce [guide de démarrage](#quick-start). -Utilisez notre [documentation](https://docs.dify.ai) pour plus de références et des instructions plus détaillées. + Lancez rapidement Dify dans votre environnement avec ce [guide de démarrage](#quick-start). + Utilisez notre [documentation](https://docs.dify.ai) pour plus de références et des instructions plus détaillées. - **Dify pour les entreprises / organisations
** -Nous proposons des fonctionnalités supplémentaires adaptées aux entreprises. [Envoyez-nous un e-mail](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) pour discuter des besoins de l'entreprise.
- > Pour les startups et les petites entreprises utilisant AWS, consultez [Dify Premium sur AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) et déployez-le dans votre propre VPC AWS en un clic. C'est une offre AMI abordable avec la possibilité de créer des applications avec un logo et une marque personnalisés. + Nous proposons des fonctionnalités supplémentaires adaptées aux entreprises. [Envoyez-nous un e-mail](mailto:business@dify.ai?subject=%5BGitHub%5DBusiness%20License%20Inquiry) pour discuter des besoins de l'entreprise.
+ > Pour les startups et les petites entreprises utilisant AWS, consultez [Dify Premium sur AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) et déployez-le dans votre propre VPC AWS en un clic. C'est une offre AMI abordable avec la possibilité de créer des applications avec un logo et une marque personnalisés. ## Rester en avance @@ -168,13 +167,12 @@ Mettez une étoile à Dify sur GitHub et soyez instantanément informé des nouv ![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4) - - ## Démarrage rapide + > Avant d'installer Dify, assurez-vous que votre machine répond aux exigences système minimales suivantes: -> ->- CPU >= 2 cœurs ->- RAM >= 4 Go +> +> - CPU >= 2 cœurs +> - RAM >= 4 Go
@@ -208,17 +206,21 @@ Si vous souhaitez configurer une configuration haute disponibilité, la communau Déployez Dify sur une plateforme cloud en un clic en utilisant [terraform](https://www.terraform.io/) ##### Azure Global + - [Azure Terraform par @nikawang](https://github.com/nikawang/dify-azure-terraform) ##### Google Cloud + - [Google Cloud Terraform par @sotazum](https://github.com/DeNA/dify-google-cloud-terraform) #### Utilisation d'AWS CDK pour le déploiement Déployez Dify sur AWS en utilisant [CDK](https://aws.amazon.com/cdk/) -##### AWS -- [AWS CDK par @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +##### AWS + +- [AWS CDK par @KevinZhao (EKS based)](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +- [AWS CDK par @tmokmss (ECS based)](https://github.com/aws-samples/dify-self-hosted-on-aws) #### Alibaba Cloud @@ -232,13 +234,11 @@ Déployez Dify en un clic sur Alibaba Cloud avec [Alibaba Cloud Data Management] Déployez Dify sur AKS en un clic en utilisant [Azure Devops Pipeline Helm Chart by @LeoZhang](https://github.com/Ruiruiz30/Dify-helm-chart-AKS) - ## Contribuer -Pour ceux qui souhaitent contribuer du code, consultez notre [Guide de contribution](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). +Pour ceux qui souhaitent contribuer du code, consultez notre [Guide de contribution](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). Dans le même temps, veuillez envisager de soutenir Dify en le partageant sur les réseaux sociaux et lors d'événements et de conférences. - > Nous recherchons des contributeurs pour aider à traduire Dify dans des langues autres que le mandarin ou l'anglais. Si vous êtes intéressé à aider, veuillez consulter le [README i18n](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) pour plus d'informations, et laissez-nous un commentaire dans le canal `global-users` de notre [Serveur communautaire Discord](https://discord.gg/8Tpq4AcN9c). **Contributeurs** @@ -249,15 +249,22 @@ Dans le même temps, veuillez envisager de soutenir Dify en le partageant sur le ## Communauté & Contact -* [Discussion GitHub](https://github.com/langgenius/dify/discussions). Meilleur pour: partager des commentaires et poser des questions. -* [Problèmes GitHub](https://github.com/langgenius/dify/issues). Meilleur pour: les bogues que vous rencontrez en utilisant Dify.AI et les propositions de fonctionnalités. Consultez notre [Guide de contribution](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). -* [Discord](https://discord.gg/FngNHpbcY7). Meilleur pour: partager vos applications et passer du temps avec la communauté. -* [X(Twitter)](https://twitter.com/dify_ai). Meilleur pour: partager vos applications et passer du temps avec la communauté. +- [Discussion GitHub](https://github.com/langgenius/dify/discussions). Meilleur pour: partager des commentaires et poser des questions. +- [Problèmes GitHub](https://github.com/langgenius/dify/issues). Meilleur pour: les bogues que vous rencontrez en utilisant Dify.AI et les propositions de fonctionnalités. Consultez notre [Guide de contribution](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). +- [Discord](https://discord.gg/FngNHpbcY7). Meilleur pour: partager vos applications et passer du temps avec la communauté. +- [X(Twitter)](https://twitter.com/dify_ai). Meilleur pour: partager vos applications et passer du temps avec la communauté. ## Historique des étoiles [![Graphique de l'historique des étoiles](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date) +## Divulgation de sécurité + +Pour protéger votre vie privée, veuillez éviter de publier des problèmes de sécurité sur GitHub. Au lieu de cela, envoyez vos questions à security@dify.ai et nous vous fournirons une réponse plus détaillée. + +## Licence + +Ce référentiel est disponible sous la [Licence open source Dify](LICENSE), qui est essentiellement l'Apache 2.0 avec quelques restrictions supplémentaires. ## Divulgation de sécurité @@ -266,10 +273,3 @@ Pour protéger votre vie privée, veuillez éviter de publier des problèmes de ## Licence Ce référentiel est disponible sous la [Licence open source Dify](LICENSE), qui est essentiellement l'Apache 2.0 avec quelques restrictions supplémentaires. -## Divulgation de sécurité - -Pour protéger votre vie privée, veuillez éviter de publier des problèmes de sécurité sur GitHub. Au lieu de cela, envoyez vos questions à security@dify.ai et nous vous fournirons une réponse plus détaillée. - -## Licence - -Ce référentiel est disponible sous la [Licence open source Dify](LICENSE), qui est essentiellement l'Apache 2.0 avec quelques restrictions supplémentaires. diff --git a/README_JA.md b/README_JA.md index d840fd6419..3427a86b79 100644 --- a/README_JA.md +++ b/README_JA.md @@ -48,7 +48,7 @@ README in বাংলা

-# +#

langgenius%2Fdify | Trendshift @@ -58,31 +58,30 @@ DifyはオープンソースのLLMアプリケーション開発プラットフ

**1. ワークフロー**: - 強力なAIワークフローをビジュアルキャンバス上で構築し、テストできます。すべての機能、および以下の機能を使用できます。 +強力なAIワークフローをビジュアルキャンバス上で構築し、テストできます。すべての機能、および以下の機能を使用できます。 **2. 総合的なモデルサポート**: - 数百ものプロプライエタリ/オープンソースのLLMと、数十もの推論プロバイダーおよびセルフホスティングソリューションとのシームレスな統合を提供します。GPT、Mistral、Llama3、OpenAI APIと互換性のあるすべてのモデルを統合されています。サポートされているモデルプロバイダーの完全なリストは[こちら](https://docs.dify.ai/getting-started/readme/model-providers)をご覧ください。 +数百ものプロプライエタリ/オープンソースのLLMと、数十もの推論プロバイダーおよびセルフホスティングソリューションとのシームレスな統合を提供します。GPT、Mistral、Llama3、OpenAI APIと互換性のあるすべてのモデルを統合されています。サポートされているモデルプロバイダーの完全なリストは[こちら](https://docs.dify.ai/getting-started/readme/model-providers)をご覧ください。 ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3) - **3. プロンプトIDE**: - プロンプトの作成、モデルパフォーマンスの比較が行え、チャットベースのアプリに音声合成などの機能も追加できます。 +プロンプトの作成、モデルパフォーマンスの比較が行え、チャットベースのアプリに音声合成などの機能も追加できます。 **4. RAGパイプライン**: - ドキュメントの取り込みから検索までをカバーする広範なRAG機能ができます。ほかにもPDF、PPT、その他の一般的なドキュメントフォーマットからのテキスト抽出のサポートも提供します。 +ドキュメントの取り込みから検索までをカバーする広範なRAG機能ができます。ほかにもPDF、PPT、その他の一般的なドキュメントフォーマットからのテキスト抽出のサポートも提供します。 **5. エージェント機能**: - LLM Function CallingやReActに基づくエージェントの定義が可能で、AIエージェント用のプリビルトまたはカスタムツールを追加できます。Difyには、Google検索、DALL·E、Stable Diffusion、WolframAlphaなどのAIエージェント用の50以上の組み込みツールが提供します。 +LLM Function CallingやReActに基づくエージェントの定義が可能で、AIエージェント用のプリビルトまたはカスタムツールを追加できます。Difyには、Google検索、DALL·E、Stable Diffusion、WolframAlphaなどのAIエージェント用の50以上の組み込みツールが提供します。 **6. LLMOps**: - アプリケーションのログやパフォーマンスを監視と分析し、生産のデータと注釈に基づいて、プロンプト、データセット、モデルを継続的に改善できます。 +アプリケーションのログやパフォーマンスを監視と分析し、生産のデータと注釈に基づいて、プロンプト、データセット、モデルを継続的に改善できます。 **7. Backend-as-a-Service**: - すべての機能はAPIを提供されており、Difyを自分のビジネスロジックに簡単に統合できます。 - +すべての機能はAPIを提供されており、Difyを自分のビジネスロジックに簡単に統合できます。 ## 機能比較 +

Fonctionnalité
@@ -152,16 +151,16 @@ DifyはオープンソースのLLMアプリケーション開発プラットフ ## Difyの使用方法 - **クラウド
** -[こちら](https://dify.ai)のDify Cloudサービスを利用して、セットアップ不要で試すことができます。サンドボックスプランには、200回のGPT-4呼び出しが無料で含まれています。 + [こちら](https://dify.ai)のDify Cloudサービスを利用して、セットアップ不要で試すことができます。サンドボックスプランには、200回のGPT-4呼び出しが無料で含まれています。 - **Dify Community Editionのセルフホスティング
** -この[スタートガイド](#クイックスタート)を使用して、ローカル環境でDifyを簡単に実行できます。 -詳しくは[ドキュメント](https://docs.dify.ai)をご覧ください。 + この[スタートガイド](#%E3%82%AF%E3%82%A4%E3%83%83%E3%82%AF%E3%82%B9%E3%82%BF%E3%83%BC%E3%83%88)を使用して、ローカル環境でDifyを簡単に実行できます。 + 詳しくは[ドキュメント](https://docs.dify.ai)をご覧ください。 - **企業/組織向けのDify
** -企業中心の機能を提供しています。[メールを送信](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)して企業のニーズについて相談してください。
- > AWSを使用しているスタートアップ企業や中小企業の場合は、[AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6)のDify Premiumをチェックして、ワンクリックで自分のAWS VPCにデプロイできます。さらに、手頃な価格のAMIオファリングとして、ロゴやブランディングをカスタマイズしてアプリケーションを作成するオプションがあります。 + 企業中心の機能を提供しています。[メールを送信](mailto:business@dify.ai?subject=%5BGitHub%5DBusiness%20License%20Inquiry)して企業のニーズについて相談してください。
+ > AWSを使用しているスタートアップ企業や中小企業の場合は、[AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6)のDify Premiumをチェックして、ワンクリックで自分のAWS VPCにデプロイできます。さらに、手頃な価格のAMIオファリングとして、ロゴやブランディングをカスタマイズしてアプリケーションを作成するオプションがあります。 ## 最新の情報を入手 @@ -169,13 +168,12 @@ GitHub上でDifyにスターを付けることで、Difyに関する新しいニ ![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4) - - ## クイックスタート + > Difyをインストールする前に、お使いのマシンが以下の最小システム要件を満たしていることを確認してください： > ->- CPU >= 2コア ->- RAM >= 4GB +> - CPU >= 2コア +> - RAM >= 4GB
@@ -209,9 +207,11 @@ docker compose up -d [terraform](https://www.terraform.io/) を使用して、ワンクリックでDifyをクラウドプラットフォームにデプロイします ##### Azure Global + - [@nikawangによるAzure Terraform](https://github.com/nikawang/dify-azure-terraform) ##### Google Cloud + - [@sotazumによるGoogle Cloud Terraform](https://github.com/DeNA/dify-google-cloud-terraform) #### AWS CDK を使用したデプロイ @@ -219,25 +219,27 @@ docker compose up -d [CDK](https://aws.amazon.com/cdk/) を使用して、DifyをAWSにデプロイします ##### AWS -- [@KevinZhaoによるAWS CDK](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) + +- [@KevinZhaoによるAWS CDK (EKS based)](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +- [@tmokmssによるAWS CDK (ECS based)](https://github.com/aws-samples/dify-self-hosted-on-aws) #### Alibaba Cloud + [Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88) #### Alibaba Cloud Data Management + [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/) を利用して、DifyをAlibaba Cloudへワンクリックでデプロイできます #### AKSへのデプロイにAzure Devops Pipelineを使用 [Azure Devops Pipeline Helm Chart by @LeoZhang](https://github.com/Ruiruiz30/Dify-helm-chart-AKS)を使用してDifyをAKSにワンクリックでデプロイ - ## 貢献 コードに貢献したい方は、[Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)を参照してください。 同時に、DifyをSNSやイベント、カンファレンスで共有してサポートしていただけると幸いです。 - > Difyを英語または中国語以外の言語に翻訳してくれる貢献者を募集しています。興味がある場合は、詳細については[i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md)を参照してください。また、[Discordコミュニティサーバー](https://discord.gg/8Tpq4AcN9c)の`global-users`チャンネルにコメントを残してください。 **貢献者** @@ -248,12 +250,10 @@ docker compose up -d ## コミュニティ & お問い合わせ -* [GitHub Discussion](https://github.com/langgenius/dify/discussions). 主に: フィードバックの共有や質問。 -* [GitHub Issues](https://github.com/langgenius/dify/issues). 主に: Dify.AIを使用する際に発生するエラーや問題については、[貢献ガイド](CONTRIBUTING_JA.md)を参照してください -* [Discord](https://discord.gg/FngNHpbcY7). 主に: アプリケーションの共有やコミュニティとの交流。 -* [X(Twitter)](https://twitter.com/dify_ai). 主に: アプリケーションの共有やコミュニティとの交流。 - - +- [GitHub Discussion](https://github.com/langgenius/dify/discussions). 主に: フィードバックの共有や質問。 +- [GitHub Issues](https://github.com/langgenius/dify/issues). 主に: Dify.AIを使用する際に発生するエラーや問題については、[貢献ガイド](CONTRIBUTING_JA.md)を参照してください +- [Discord](https://discord.gg/FngNHpbcY7). 主に: アプリケーションの共有やコミュニティとの交流。 +- [X(Twitter)](https://twitter.com/dify_ai). 主に: アプリケーションの共有やコミュニティとの交流。 ## ライセンス diff --git a/README_KL.md b/README_KL.md index 41c7969e1c..252a2b6db5 100644 --- a/README_KL.md +++ b/README_KL.md @@ -48,7 +48,7 @@ README in বাংলা

-# +#

langgenius%2Fdify | Trendshift @@ -56,32 +56,31 @@ Dify is an open-source LLM app development platform. Its intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production. Here's a list of the core features:

-**1. Workflow**: - Build and test powerful AI workflows on a visual canvas, leveraging all the following features and beyond. +**1. Workflow**: +Build and test powerful AI workflows on a visual canvas, leveraging all the following features and beyond. -**2. Comprehensive model support**: - Seamless integration with hundreds of proprietary / open-source LLMs from dozens of inference providers and self-hosted solutions, covering GPT, Mistral, Llama3, and any OpenAI API-compatible models. A full list of supported model providers can be found [here](https://docs.dify.ai/getting-started/readme/model-providers). +**2. Comprehensive model support**: +Seamless integration with hundreds of proprietary / open-source LLMs from dozens of inference providers and self-hosted solutions, covering GPT, Mistral, Llama3, and any OpenAI API-compatible models. A full list of supported model providers can be found [here](https://docs.dify.ai/getting-started/readme/model-providers). ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3) +**3. Prompt IDE**: +Intuitive interface for crafting prompts, comparing model performance, and adding additional features such as text-to-speech to a chat-based app. -**3. Prompt IDE**: - Intuitive interface for crafting prompts, comparing model performance, and adding additional features such as text-to-speech to a chat-based app. +**4. RAG Pipeline**: +Extensive RAG capabilities that cover everything from document ingestion to retrieval, with out-of-box support for text extraction from PDFs, PPTs, and other common document formats. -**4. RAG Pipeline**: - Extensive RAG capabilities that cover everything from document ingestion to retrieval, with out-of-box support for text extraction from PDFs, PPTs, and other common document formats. +**5. Agent capabilities**: +You can define agents based on LLM Function Calling or ReAct, and add pre-built or custom tools for the agent. Dify provides 50+ built-in tools for AI agents, such as Google Search, DALL·E, Stable Diffusion and WolframAlpha. -**5. Agent capabilities**: - You can define agents based on LLM Function Calling or ReAct, and add pre-built or custom tools for the agent. Dify provides 50+ built-in tools for AI agents, such as Google Search, DALL·E, Stable Diffusion and WolframAlpha. - -**6. LLMOps**: - Monitor and analyze application logs and performance over time. You could continuously improve prompts, datasets, and models based on production data and annotations. - -**7. Backend-as-a-Service**: - All of Dify's offerings come with corresponding APIs, so you could effortlessly integrate Dify into your own business logic. +**6. LLMOps**: +Monitor and analyze application logs and performance over time. You could continuously improve prompts, datasets, and models based on production data and annotations. +**7. Backend-as-a-Service**: +All of Dify's offerings come with corresponding APIs, so you could effortlessly integrate Dify into your own business logic. ## Feature Comparison +

機能
@@ -151,16 +150,16 @@ Dify is an open-source LLM app development platform. Its intuitive interface com ## Using Dify - **Cloud
** -We host a [Dify Cloud](https://dify.ai) service for anyone to try with zero setup. It provides all the capabilities of the self-deployed version, and includes 200 free GPT-4 calls in the sandbox plan. + We host a [Dify Cloud](https://dify.ai) service for anyone to try with zero setup. It provides all the capabilities of the self-deployed version, and includes 200 free GPT-4 calls in the sandbox plan. - **Self-hosting Dify Community Edition
** -Quickly get Dify running in your environment with this [starter guide](#quick-start). -Use our [documentation](https://docs.dify.ai) for further references and more in-depth instructions. + Quickly get Dify running in your environment with this [starter guide](#quick-start). + Use our [documentation](https://docs.dify.ai) for further references and more in-depth instructions. - **Dify for Enterprise / Organizations
** -We provide additional enterprise-centric features. [Send us an email](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) to discuss enterprise needs.
- > For startups and small businesses using AWS, check out [Dify Premium on AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) and deploy it to your own AWS VPC with one-click. It's an affordable AMI offering with the option to create apps with custom logo and branding. + We provide additional enterprise-centric features. [Send us an email](mailto:business@dify.ai?subject=%5BGitHub%5DBusiness%20License%20Inquiry) to discuss enterprise needs.
+ > For startups and small businesses using AWS, check out [Dify Premium on AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) and deploy it to your own AWS VPC with one-click. It's an affordable AMI offering with the option to create apps with custom logo and branding. ## Staying ahead @@ -168,13 +167,12 @@ Star Dify on GitHub and be instantly notified of new releases. ![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4) - - ## Quick Start + > Before installing Dify, make sure your machine meets the following minimum system requirements: -> ->- CPU >= 2 Core ->- RAM >= 4GB +> +> - CPU >= 2 Core +> - RAM >= 4GB
@@ -208,17 +206,21 @@ If you'd like to configure a highly-available setup, there are community-contrib wa'logh nIqHom neH ghun deployment toy'wI' [terraform](https://www.terraform.io/) lo'laH. ##### Azure Global + - [Azure Terraform mung @nikawang](https://github.com/nikawang/dify-azure-terraform) ##### Google Cloud + - [Google Cloud Terraform qachlot @sotazum](https://github.com/DeNA/dify-google-cloud-terraform) #### AWS CDK atorlugh pilersitsineq wa'logh nIqHom neH ghun deployment toy'wI' [CDK](https://aws.amazon.com/cdk/) lo'laH. -##### AWS -- [AWS CDK qachlot @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +##### AWS + +- [AWS CDK qachlot @KevinZhao (EKS based)](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +- [AWS CDK qachlot @tmokmss (ECS based)](https://github.com/aws-samples/dify-self-hosted-on-aws) #### Alibaba Cloud @@ -232,13 +234,11 @@ wa'logh nIqHom neH ghun deployment toy'wI' [CDK](https://aws.amazon.com/cdk/) lo [Azure Devops Pipeline Helm Chart by @LeoZhang](https://github.com/Ruiruiz30/Dify-helm-chart-AKS) lo'laH Dify AKS 'e' wa'DIch click 'e' Deploy - ## Contributing -For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). +For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). At the same time, please consider supporting Dify by sharing it on social media and at events and conferences. - > We are looking for contributors to help with translating Dify to languages other than Mandarin or English. If you are interested in helping, please see the [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) for more information, and leave us a comment in the `global-users` channel of our [Discord Community Server](https://discord.gg/8Tpq4AcN9c). **Contributors** @@ -249,18 +249,18 @@ At the same time, please consider supporting Dify by sharing it on social media ## Community & Contact -* [GitHub Discussion](https://github.com/langgenius/dify/discussions +- \[GitHub Discussion\](https://github.com/langgenius/dify/discussions ). Best for: sharing feedback and asking questions. -* [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). -* [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community. -* [X(Twitter)](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community. + +- [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). +- [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community. +- [X(Twitter)](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community. ## Star History [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date) - ## Security Disclosure To protect your privacy, please avoid posting security issues on GitHub. Instead, send your questions to security@dify.ai and we will provide you with a more detailed answer. diff --git a/README_KR.md b/README_KR.md index d4b31a8928..278e3f6c33 100644 --- a/README_KR.md +++ b/README_KR.md @@ -48,34 +48,33 @@ README in বাংলা

- - Dify는 오픈 소스 LLM 앱 개발 플랫폼입니다. 직관적인 인터페이스를 통해 AI 워크플로우, RAG 파이프라인, 에이전트 기능, 모델 관리, 관찰 기능 등을 결합하여 프로토타입에서 프로덕션까지 빠르게 전환할 수 있습니다. 주요 기능 목록은 다음과 같습니다:

+Dify는 오픈 소스 LLM 앱 개발 플랫폼입니다. 직관적인 인터페이스를 통해 AI 워크플로우, RAG 파이프라인, 에이전트 기능, 모델 관리, 관찰 기능 등을 결합하여 프로토타입에서 프로덕션까지 빠르게 전환할 수 있습니다. 주요 기능 목록은 다음과 같습니다:

**1. 워크플로우**: - 다음 기능들을 비롯한 다양한 기능을 활용하여 시각적 캔버스에서 강력한 AI 워크플로우를 구축하고 테스트하세요. +다음 기능들을 비롯한 다양한 기능을 활용하여 시각적 캔버스에서 강력한 AI 워크플로우를 구축하고 테스트하세요. -**2. 포괄적인 모델 지원:**: +**2. 포괄적인 모델 지원:**: 수십 개의 추론 제공업체와 자체 호스팅 솔루션에서 제공하는 수백 개의 독점 및 오픈 소스 LLM과 원활하게 통합되며, GPT, Mistral, Llama3 및 모든 OpenAI API 호환 모델을 포함합니다. 지원되는 모델 제공업체의 전체 목록은 [여기](https://docs.dify.ai/getting-started/readme/model-providers)에서 확인할 수 있습니다. ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3) - **3. 통합 개발환경**: - 프롬프트를 작성하고, 모델 성능을 비교하며, 텍스트-음성 변환과 같은 추가 기능을 채팅 기반 앱에 추가할 수 있는 직관적인 인터페이스를 제공합니다. +프롬프트를 작성하고, 모델 성능을 비교하며, 텍스트-음성 변환과 같은 추가 기능을 채팅 기반 앱에 추가할 수 있는 직관적인 인터페이스를 제공합니다. -**4. RAG 파이프라인**: - 문서 수집부터 검색까지 모든 것을 다루며, PDF, PPT 및 기타 일반적인 문서 형식에서 텍스트 추출을 위한 기본 지원이 포함되어 있는 광범위한 RAG 기능을 제공합니다. +**4. RAG 파이프라인**: +문서 수집부터 검색까지 모든 것을 다루며, PDF, PPT 및 기타 일반적인 문서 형식에서 텍스트 추출을 위한 기본 지원이 포함되어 있는 광범위한 RAG 기능을 제공합니다. **5. 에이전트 기능**: - LLM 함수 호출 또는 ReAct를 기반으로 에이전트를 정의하고 에이전트에 대해 사전 구축된 도구나 사용자 정의 도구를 추가할 수 있습니다. Dify는 Google Search, DALL·E, Stable Diffusion, WolframAlpha 등 AI 에이전트를 위한 50개 이상의 내장 도구를 제공합니다. +LLM 함수 호출 또는 ReAct를 기반으로 에이전트를 정의하고 에이전트에 대해 사전 구축된 도구나 사용자 정의 도구를 추가할 수 있습니다. Dify는 Google Search, DALL·E, Stable Diffusion, WolframAlpha 등 AI 에이전트를 위한 50개 이상의 내장 도구를 제공합니다. **6. LLMOps**: - 시간 경과에 따른 애플리케이션 로그와 성능을 모니터링하고 분석합니다. 생산 데이터와 주석을 기반으로 프롬프트, 데이터세트, 모델을 지속적으로 개선할 수 있습니다. +시간 경과에 따른 애플리케이션 로그와 성능을 모니터링하고 분석합니다. 생산 데이터와 주석을 기반으로 프롬프트, 데이터세트, 모델을 지속적으로 개선할 수 있습니다. **7. Backend-as-a-Service**: - Dify의 모든 제품에는 해당 API가 함께 제공되므로 Dify를 자신의 비즈니스 로직에 쉽게 통합할 수 있습니다. +Dify의 모든 제품에는 해당 API가 함께 제공되므로 Dify를 자신의 비즈니스 로직에 쉽게 통합할 수 있습니다. ## 기능 비교 +
Feature
@@ -148,27 +147,26 @@ 우리는 누구나 설정이 필요 없이 사용해 볼 수 있도록 [Dify 클라우드](https://dify.ai) 서비스를 호스팅합니다. 이는 자체 배포 버전의 모든 기능을 제공하며, 샌드박스 플랜에서 무료로 200회의 GPT-4 호출을 포함합니다. - **셀프-호스팅 Dify 커뮤니티 에디션
** - 환경에서 Dify를 빠르게 실행하려면 이 [스타터 가이드를](#quick-start) 참조하세요. + 환경에서 Dify를 빠르게 실행하려면 이 [스타터 가이드를](#quick-start) 참조하세요. 추가 참조 및 더 심층적인 지침은 [문서](https://docs.dify.ai)를 사용하세요. - **기업 / 조직을 위한 Dify
** - 우리는 추가적인 기업 중심 기능을 제공합니다. 잡거나 [이메일 보내기](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)를 통해 기업 요구 사항을 논의하십시오.
+ 우리는 추가적인 기업 중심 기능을 제공합니다. 잡거나 [이메일 보내기](mailto:business@dify.ai?subject=%5BGitHub%5DBusiness%20License%20Inquiry)를 통해 기업 요구 사항을 논의하십시오.
+ > AWS를 사용하는 스타트업 및 중소기업의 경우 [AWS Marketplace에서 Dify Premium](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6)을 확인하고 한 번의 클릭으로 자체 AWS VPC에 배포하십시오. 맞춤형 로고와 브랜딩이 포함된 앱을 생성할 수 있는 옵션이 포함된 저렴한 AMI 제품입니다. - - ## 앞서가기 GitHub에서 Dify에 별표를 찍어 새로운 릴리스를 즉시 알림 받으세요. ![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4) - - ## 빠른 시작 ->Dify를 설치하기 전에 컴퓨터가 다음과 같은 최소 시스템 요구 사항을 충족하는지 확인하세요 : ->- CPU >= 2 Core ->- RAM >= 4GB + +> Dify를 설치하기 전에 컴퓨터가 다음과 같은 최소 시스템 요구 사항을 충족하는지 확인하세요 : +> +> - CPU >= 2 Core +> - RAM >= 4GB
@@ -202,17 +200,21 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했 [terraform](https://www.terraform.io/)을 사용하여 단 한 번의 클릭으로 Dify를 클라우드 플랫폼에 배포하십시오 ##### Azure Global + - [nikawang의 Azure Terraform](https://github.com/nikawang/dify-azure-terraform) ##### Google Cloud + - [sotazum의 Google Cloud Terraform](https://github.com/DeNA/dify-google-cloud-terraform) #### AWS CDK를 사용한 배포 [CDK](https://aws.amazon.com/cdk/)를 사용하여 AWS에 Dify 배포 -##### AWS -- [KevinZhao의 AWS CDK](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +##### AWS + +- [KevinZhao의 AWS CDK (EKS based)](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +- [tmokmss의 AWS CDK (ECS based)](https://github.com/aws-samples/dify-self-hosted-on-aws) #### Alibaba Cloud @@ -226,14 +228,12 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했 [Azure Devops Pipeline Helm Chart by @LeoZhang](https://github.com/Ruiruiz30/Dify-helm-chart-AKS)을 사용하여 Dify를 AKS에 원클릭으로 배포 - ## 기여 코드에 기여하고 싶은 분들은 [기여 가이드](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)를 참조하세요. 동시에 Dify를 소셜 미디어와 행사 및 컨퍼런스에 공유하여 지원하는 것을 고려해 주시기 바랍니다. - -> 우리는 Dify를 중국어나 영어 이외의 언어로 번역하는 데 도움을 줄 수 있는 기여자를 찾고 있습니다. 도움을 주고 싶으시다면 [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md)에서 더 많은 정보를 확인하시고 [Discord 커뮤니티 서버](https://discord.gg/8Tpq4AcN9c)의 `global-users` 채널에 댓글을 남겨주세요. +> 우리는 Dify를 중국어나 영어 이외의 언어로 번역하는 데 도움을 줄 수 있는 기여자를 찾고 있습니다. 도움을 주고 싶으시다면 [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md)에서 더 많은 정보를 확인하시고 [Discord 커뮤니티 서버](https://discord.gg/8Tpq4AcN9c)의 `global-users` 채널에 댓글을 남겨주세요. **기여자** @@ -243,17 +243,15 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했 ## 커뮤니티 & 연락처 -* [GitHub 토론](https://github.com/langgenius/dify/discussions). 피드백 공유 및 질문하기에 적합합니다. -* [GitHub 이슈](https://github.com/langgenius/dify/issues). Dify.AI 사용 중 발견한 버그와 기능 제안에 적합합니다. [기여 가이드](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)를 참조하세요. -* [디스코드](https://discord.gg/FngNHpbcY7). 애플리케이션 공유 및 커뮤니티와 소통하기에 적합합니다. -* [트위터](https://twitter.com/dify_ai). 애플리케이션 공유 및 커뮤니티와 소통하기에 적합합니다. - +- [GitHub 토론](https://github.com/langgenius/dify/discussions). 피드백 공유 및 질문하기에 적합합니다. +- [GitHub 이슈](https://github.com/langgenius/dify/issues). Dify.AI 사용 중 발견한 버그와 기능 제안에 적합합니다. [기여 가이드](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)를 참조하세요. +- [디스코드](https://discord.gg/FngNHpbcY7). 애플리케이션 공유 및 커뮤니티와 소통하기에 적합합니다. +- [트위터](https://twitter.com/dify_ai). 애플리케이션 공유 및 커뮤니티와 소통하기에 적합합니다. ## Star 히스토리 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date) - ## 보안 공개 개인정보 보호를 위해 보안 문제를 GitHub에 게시하지 마십시오. 대신 security@dify.ai로 질문을 보내주시면 더 자세한 답변을 드리겠습니다. diff --git a/README_PT.md b/README_PT.md index 94452cb233..8bff880728 100644 --- a/README_PT.md +++ b/README_PT.md @@ -1,4 +1,5 @@ ![cover-v5-optimized](./images/GitHub_README_if.png) +

📌 Introduzindo o Dify Workflow com Upload de Arquivo: Recrie o Podcast Google NotebookLM

@@ -55,32 +56,31 @@ Dify é uma plataforma de desenvolvimento de aplicativos LLM de código aberto. Sua interface intuitiva combina workflow de IA, pipeline RAG, capacidades de agente, gerenciamento de modelos, recursos de observabilidade e muito mais, permitindo que você vá rapidamente do protótipo à produção. Aqui está uma lista das principais funcionalidades:

-**1. Workflow**: - Construa e teste workflows poderosos de IA em uma interface visual, aproveitando todos os recursos a seguir e muito mais. +**1. Workflow**: +Construa e teste workflows poderosos de IA em uma interface visual, aproveitando todos os recursos a seguir e muito mais. -**2. Suporte abrangente a modelos**: - Integração perfeita com centenas de LLMs proprietários e de código aberto de diversas provedoras e soluções auto-hospedadas, abrangendo GPT, Mistral, Llama3 e qualquer modelo compatível com a API da OpenAI. A lista completa de provedores suportados pode ser encontrada [aqui](https://docs.dify.ai/getting-started/readme/model-providers). +**2. Suporte abrangente a modelos**: +Integração perfeita com centenas de LLMs proprietários e de código aberto de diversas provedoras e soluções auto-hospedadas, abrangendo GPT, Mistral, Llama3 e qualquer modelo compatível com a API da OpenAI. A lista completa de provedores suportados pode ser encontrada [aqui](https://docs.dify.ai/getting-started/readme/model-providers). ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3) +**3. IDE de Prompt**: +Interface intuitiva para criação de prompts, comparação de desempenho de modelos e adição de recursos como conversão de texto para fala em um aplicativo baseado em chat. -**3. IDE de Prompt**: - Interface intuitiva para criação de prompts, comparação de desempenho de modelos e adição de recursos como conversão de texto para fala em um aplicativo baseado em chat. +**4. Pipeline RAG**: +Extensas capacidades de RAG que cobrem desde a ingestão de documentos até a recuperação, com suporte nativo para extração de texto de PDFs, PPTs e outros formatos de documentos comuns. -**4. Pipeline RAG**: - Extensas capacidades de RAG que cobrem desde a ingestão de documentos até a recuperação, com suporte nativo para extração de texto de PDFs, PPTs e outros formatos de documentos comuns. +**5. Capacidades de agente**: +Você pode definir agentes com base em LLM Function Calling ou ReAct e adicionar ferramentas pré-construídas ou personalizadas para o agente. O Dify oferece mais de 50 ferramentas integradas para agentes de IA, como Google Search, DALL·E, Stable Diffusion e WolframAlpha. -**5. Capacidades de agente**: - Você pode definir agentes com base em LLM Function Calling ou ReAct e adicionar ferramentas pré-construídas ou personalizadas para o agente. O Dify oferece mais de 50 ferramentas integradas para agentes de IA, como Google Search, DALL·E, Stable Diffusion e WolframAlpha. - -**6. LLMOps**: - Monitore e analise os registros e o desempenho do aplicativo ao longo do tempo. É possível melhorar continuamente prompts, conjuntos de dados e modelos com base nos dados de produção e anotações. - -**7. Backend como Serviço**: - Todas os recursos do Dify vêm com APIs correspondentes, permitindo que você integre o Dify sem esforço na lógica de negócios da sua empresa. +**6. LLMOps**: +Monitore e analise os registros e o desempenho do aplicativo ao longo do tempo. É possível melhorar continuamente prompts, conjuntos de dados e modelos com base nos dados de produção e anotações. +**7. Backend como Serviço**: +Todas os recursos do Dify vêm com APIs correspondentes, permitindo que você integre o Dify sem esforço na lógica de negócios da sua empresa. ## Comparação de recursos +
기능
@@ -150,16 +150,16 @@ Dify é uma plataforma de desenvolvimento de aplicativos LLM de código aberto. ## Usando o Dify - **Nuvem
** -Oferecemos o serviço [Dify Cloud](https://dify.ai) para qualquer pessoa experimentar sem nenhuma configuração. Ele fornece todas as funcionalidades da versão auto-hospedada, incluindo 200 chamadas GPT-4 gratuitas no plano sandbox. + Oferecemos o serviço [Dify Cloud](https://dify.ai) para qualquer pessoa experimentar sem nenhuma configuração. Ele fornece todas as funcionalidades da versão auto-hospedada, incluindo 200 chamadas GPT-4 gratuitas no plano sandbox. - **Auto-hospedagem do Dify Community Edition
** -Configure rapidamente o Dify no seu ambiente com este [guia inicial](#quick-start). -Use nossa [documentação](https://docs.dify.ai) para referências adicionais e instruções mais detalhadas. + Configure rapidamente o Dify no seu ambiente com este [guia inicial](#quick-start). + Use nossa [documentação](https://docs.dify.ai) para referências adicionais e instruções mais detalhadas. - **Dify para empresas/organizações
** -Oferecemos recursos adicionais voltados para empresas. [Envie suas perguntas através deste chatbot](https://udify.app/chat/22L1zSxg6yW1cWQg) ou [envie-nos um e-mail](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) para discutir necessidades empresariais.
- > Para startups e pequenas empresas que utilizam AWS, confira o [Dify Premium no AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) e implemente no seu próprio AWS VPC com um clique. É uma oferta AMI acessível com a opção de criar aplicativos com logotipo e marca personalizados. + Oferecemos recursos adicionais voltados para empresas. [Envie suas perguntas através deste chatbot](https://udify.app/chat/22L1zSxg6yW1cWQg) ou [envie-nos um e-mail](mailto:business@dify.ai?subject=%5BGitHub%5DBusiness%20License%20Inquiry) para discutir necessidades empresariais.
+ > Para startups e pequenas empresas que utilizam AWS, confira o [Dify Premium no AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) e implemente no seu próprio AWS VPC com um clique. É uma oferta AMI acessível com a opção de criar aplicativos com logotipo e marca personalizados. ## Mantendo-se atualizado @@ -167,13 +167,12 @@ Dê uma estrela no Dify no GitHub e seja notificado imediatamente sobre novos la ![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4) - - ## Início rápido + > Antes de instalar o Dify, certifique-se de que sua máquina atenda aos seguintes requisitos mínimos de sistema: -> ->- CPU >= 2 Núcleos ->- RAM >= 4 GiB +> +> - CPU >= 2 Núcleos +> - RAM >= 4 GiB
@@ -207,17 +206,21 @@ Se deseja configurar uma instalação de alta disponibilidade, há [Helm Charts] Implante o Dify na Plataforma Cloud com um único clique usando [terraform](https://www.terraform.io/) ##### Azure Global + - [Azure Terraform por @nikawang](https://github.com/nikawang/dify-azure-terraform) ##### Google Cloud + - [Google Cloud Terraform por @sotazum](https://github.com/DeNA/dify-google-cloud-terraform) #### Usando AWS CDK para Implantação Implante o Dify na AWS usando [CDK](https://aws.amazon.com/cdk/) -##### AWS -- [AWS CDK por @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +##### AWS + +- [AWS CDK por @KevinZhao (EKS based)](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +- [AWS CDK por @tmokmss (ECS based)](https://github.com/aws-samples/dify-self-hosted-on-aws) #### Alibaba Cloud @@ -231,10 +234,9 @@ Implante o Dify na Alibaba Cloud com um clique usando o [Alibaba Cloud Data Mana Implante o Dify no AKS com um clique usando [Azure Devops Pipeline Helm Chart by @LeoZhang](https://github.com/Ruiruiz30/Dify-helm-chart-AKS) - ## Contribuindo -Para aqueles que desejam contribuir com código, veja nosso [Guia de Contribuição](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). +Para aqueles que desejam contribuir com código, veja nosso [Guia de Contribuição](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). Ao mesmo tempo, considere apoiar o Dify compartilhando-o nas redes sociais e em eventos e conferências. > Estamos buscando contribuidores para ajudar na tradução do Dify para idiomas além de Mandarim e Inglês. Se você tiver interesse em ajudar, consulte o [README i18n](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) para mais informações e deixe-nos um comentário no canal `global-users` em nosso [Servidor da Comunidade no Discord](https://discord.gg/8Tpq4AcN9c). @@ -247,10 +249,10 @@ Ao mesmo tempo, considere apoiar o Dify compartilhando-o nas redes sociais e em ## Comunidade e contato -* [Discussões no GitHub](https://github.com/langgenius/dify/discussions). Melhor para: compartilhar feedback e fazer perguntas. -* [Problemas no GitHub](https://github.com/langgenius/dify/issues). Melhor para: relatar bugs encontrados no Dify.AI e propor novos recursos. Veja nosso [Guia de Contribuição](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). -* [Discord](https://discord.gg/FngNHpbcY7). Melhor para: compartilhar suas aplicações e interagir com a comunidade. -* [X(Twitter)](https://twitter.com/dify_ai). Melhor para: compartilhar suas aplicações e interagir com a comunidade. +- [Discussões no GitHub](https://github.com/langgenius/dify/discussions). Melhor para: compartilhar feedback e fazer perguntas. +- [Problemas no GitHub](https://github.com/langgenius/dify/issues). Melhor para: relatar bugs encontrados no Dify.AI e propor novos recursos. Veja nosso [Guia de Contribuição](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). +- [Discord](https://discord.gg/FngNHpbcY7). Melhor para: compartilhar suas aplicações e interagir com a comunidade. +- [X(Twitter)](https://twitter.com/dify_ai). Melhor para: compartilhar suas aplicações e interagir com a comunidade. ## Histórico de estrelas diff --git a/README_SI.md b/README_SI.md index d840e9155f..be8c6320fb 100644 --- a/README_SI.md +++ b/README_SI.md @@ -50,14 +50,14 @@ README in বাংলা

- -Dify je odprtokodna platforma za razvoj aplikacij LLM. Njegov intuitivni vmesnik združuje agentski potek dela z umetno inteligenco, cevovod RAG, zmogljivosti agentov, upravljanje modelov, funkcije opazovanja in več, kar vam omogoča hiter prehod od prototipa do proizvodnje. +Dify je odprtokodna platforma za razvoj aplikacij LLM. Njegov intuitivni vmesnik združuje agentski potek dela z umetno inteligenco, cevovod RAG, zmogljivosti agentov, upravljanje modelov, funkcije opazovanja in več, kar vam omogoča hiter prehod od prototipa do proizvodnje. ## Hitri začetek + > Preden namestite Dify, se prepričajte, da vaša naprava izpolnjuje naslednje minimalne sistemske zahteve: -> ->- CPU >= 2 Core ->- RAM >= 4 GiB +> +> - CPU >= 2 Core +> - RAM >= 4 GiB
@@ -73,34 +73,35 @@ docker compose up -d Po zagonu lahko dostopate do nadzorne plošče Dify v brskalniku na [http://localhost/install](http://localhost/install) in začnete postopek inicializacije. #### Iskanje pomoči + Prosimo, glejte naša pogosta vprašanja [FAQ](https://docs.dify.ai/getting-started/install-self-hosted/faqs) če naletite na težave pri nastavitvi Dify. Če imate še vedno težave, se obrnite na [skupnost ali nas](#community--contact). > Če želite prispevati k Difyju ali narediti dodaten razvoj, glejte naš vodnik za [uvajanje iz izvorne kode](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code) ## Ključne značilnosti -**1. Potek dela**: - Zgradite in preizkusite zmogljive poteke dela AI na vizualnem platnu, pri čemer izkoristite vse naslednje funkcije in več. -**2. Celovita podpora za modele**: - Brezhibna integracija s stotinami lastniških/odprtokodnih LLM-jev ducatov ponudnikov sklepanja in samostojnih rešitev, ki pokrivajo GPT, Mistral, Llama3 in vse modele, združljive z API-jem OpenAI. Celoten seznam podprtih ponudnikov modelov najdete [tukaj](https://docs.dify.ai/getting-started/readme/model-providers). +**1. Potek dela**: +Zgradite in preizkusite zmogljive poteke dela AI na vizualnem platnu, pri čemer izkoristite vse naslednje funkcije in več. + +**2. Celovita podpora za modele**: +Brezhibna integracija s stotinami lastniških/odprtokodnih LLM-jev ducatov ponudnikov sklepanja in samostojnih rešitev, ki pokrivajo GPT, Mistral, Llama3 in vse modele, združljive z API-jem OpenAI. Celoten seznam podprtih ponudnikov modelov najdete [tukaj](https://docs.dify.ai/getting-started/readme/model-providers). ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3) +**3. Prompt IDE**: +intuitivni vmesnik za ustvarjanje pozivov, primerjavo zmogljivosti modela in dodajanje dodatnih funkcij, kot je pretvorba besedila v govor, aplikaciji, ki temelji na klepetu. -**3. Prompt IDE**: - intuitivni vmesnik za ustvarjanje pozivov, primerjavo zmogljivosti modela in dodajanje dodatnih funkcij, kot je pretvorba besedila v govor, aplikaciji, ki temelji na klepetu. +**4. RAG Pipeline**: +E Obsežne zmogljivosti RAG, ki pokrivajo vse od vnosa dokumenta do priklica, s podporo za ekstrakcijo besedila iz datotek PDF, PPT in drugih običajnih formatov dokumentov. -**4. RAG Pipeline**: - E Obsežne zmogljivosti RAG, ki pokrivajo vse od vnosa dokumenta do priklica, s podporo za ekstrakcijo besedila iz datotek PDF, PPT in drugih običajnih formatov dokumentov. +**5. Agent capabilities**: +definirate lahko agente, ki temeljijo na klicanju funkcij LLM ali ReAct, in dodate vnaprej izdelana orodja ali orodja po meri za agenta. Dify ponuja več kot 50 vgrajenih orodij za agente AI, kot so Google Search, DALL·E, Stable Diffusion in WolframAlpha. -**5. Agent capabilities**: - definirate lahko agente, ki temeljijo na klicanju funkcij LLM ali ReAct, in dodate vnaprej izdelana orodja ali orodja po meri za agenta. Dify ponuja več kot 50 vgrajenih orodij za agente AI, kot so Google Search, DALL·E, Stable Diffusion in WolframAlpha. +**6. LLMOps**: +Spremljajte in analizirajte dnevnike aplikacij in učinkovitost skozi čas. Pozive, nabore podatkov in modele lahko nenehno izboljšujete na podlagi proizvodnih podatkov in opomb. -**6. LLMOps**: - Spremljajte in analizirajte dnevnike aplikacij in učinkovitost skozi čas. Pozive, nabore podatkov in modele lahko nenehno izboljšujete na podlagi proizvodnih podatkov in opomb. - -**7. Backend-as-a-Service**: - AVse ponudbe Difyja so opremljene z ustreznimi API-ji, tako da lahko Dify brez težav integrirate v svojo poslovno logiko. +**7. Backend-as-a-Service**: +AVse ponudbe Difyja so opremljene z ustreznimi API-ji, tako da lahko Dify brez težav integrirate v svojo poslovno logiko. ## Primerjava Funkcij @@ -173,16 +174,15 @@ Prosimo, glejte naša pogosta vprašanja [FAQ](https://docs.dify.ai/getting-star ## Uporaba Dify - **Cloud
** -Gostimo storitev Dify Cloud za vsakogar, ki jo lahko preizkusite brez nastavitev. Zagotavlja vse zmožnosti različice za samostojno namestitev in vključuje 200 brezplačnih klicev GPT-4 v načrtu peskovnika. + Gostimo storitev Dify Cloud za vsakogar, ki jo lahko preizkusite brez nastavitev. Zagotavlja vse zmožnosti različice za samostojno namestitev in vključuje 200 brezplačnih klicev GPT-4 v načrtu peskovnika. - **Self-hosting Dify Community Edition
** -Hitro zaženite Dify v svojem okolju s tem [začetnim vodnikom](#quick-start) . Za dodatne reference in podrobnejša navodila uporabite našo [dokumentacijo](https://docs.dify.ai) . - + Hitro zaženite Dify v svojem okolju s tem [začetnim vodnikom](#quick-start) . Za dodatne reference in podrobnejša navodila uporabite našo [dokumentacijo](https://docs.dify.ai) . - **Dify za podjetja/organizacije
** -Ponujamo dodatne funkcije, osredotočene na podjetja. Zabeležite svoja vprašanja prek tega klepetalnega robota ali nam pošljite e-pošto, da se pogovorimo o potrebah podjetja.
- > Za novoustanovljena podjetja in mala podjetja, ki uporabljajo AWS, si oglejte Dify Premium na AWS Marketplace in ga z enim klikom uvedite v svoj AWS VPC. To je cenovno ugodna ponudba AMI z možnostjo ustvarjanja aplikacij z logotipom in blagovno znamko po meri. + Ponujamo dodatne funkcije, osredotočene na podjetja. Zabeležite svoja vprašanja prek tega klepetalnega robota ali nam pošljite e-pošto, da se pogovorimo o potrebah podjetja.
+ > Za novoustanovljena podjetja in mala podjetja, ki uporabljajo AWS, si oglejte Dify Premium na AWS Marketplace in ga z enim klikom uvedite v svoj AWS VPC. To je cenovno ugodna ponudba AMI z možnostjo ustvarjanja aplikacij z logotipom in blagovno znamko po meri. ## Staying ahead @@ -190,7 +190,6 @@ Star Dify on GitHub and be instantly notified of new releases. ![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4) - ## Napredne nastavitve Če morate prilagoditi konfiguracijo, si oglejte komentarje v naši datoteki .env.example in posodobite ustrezne vrednosti v svoji .env datoteki. Poleg tega boste morda morali prilagoditi docker-compose.yamlsamo datoteko, na primer spremeniti različice slike, preslikave vrat ali namestitve nosilca, glede na vaše specifično okolje in zahteve za uvajanje. Po kakršnih koli spremembah ponovno zaženite docker-compose up -d. Celoten seznam razpoložljivih spremenljivk okolja najdete tukaj . @@ -208,17 +207,21 @@ Star Dify on GitHub and be instantly notified of new releases. namestite Dify v Cloud Platform z enim klikom z uporabo [terraform](https://www.terraform.io/) ##### Azure Global + - [Azure Terraform by @nikawang](https://github.com/nikawang/dify-azure-terraform) ##### Google Cloud + - [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform) #### Uporaba AWS CDK za uvajanje Uvedite Dify v AWS z uporabo [CDK](https://aws.amazon.com/cdk/) -##### AWS -- [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +##### AWS + +- [AWS CDK by @KevinZhao (EKS based)](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +- [AWS CDK by @tmokmss (ECS based)](https://github.com/aws-samples/dify-self-hosted-on-aws) #### Alibaba Cloud @@ -232,21 +235,18 @@ Z enim klikom namestite Dify na Alibaba Cloud z [Alibaba Cloud Data Management]( Z enim klikom namestite Dify v AKS z uporabo [Azure Devops Pipeline Helm Chart by @LeoZhang](https://github.com/Ruiruiz30/Dify-helm-chart-AKS) - ## Prispevam -Za tiste, ki bi radi prispevali kodo, si oglejte naš vodnik za prispevke . Hkrati vas prosimo, da podprete Dify tako, da ga delite na družbenih medijih ter na dogodkih in konferencah. - - +Za tiste, ki bi radi prispevali kodo, si oglejte naš vodnik za prispevke . Hkrati vas prosimo, da podprete Dify tako, da ga delite na družbenih medijih ter na dogodkih in konferencah. > Iščemo sodelavce za pomoč pri prevajanju Difyja v jezike, ki niso mandarinščina ali angleščina. Če želite pomagati, si oglejte i18n README za več informacij in nam pustite komentar v global-userskanalu našega strežnika skupnosti Discord . ## Skupnost in stik -* [GitHub Discussion](https://github.com/langgenius/dify/discussions). Najboljše za: izmenjavo povratnih informacij in postavljanje vprašanj. -* [GitHub Issues](https://github.com/langgenius/dify/issues). Najboljše za: hrošče, na katere naletite pri uporabi Dify.AI, in predloge funkcij. Oglejte si naš [vodnik za prispevke](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). -* [Discord](https://discord.gg/FngNHpbcY7). Najboljše za: deljenje vaših aplikacij in druženje s skupnostjo. -* [X(Twitter)](https://twitter.com/dify_ai). Najboljše za: deljenje vaših aplikacij in druženje s skupnostjo. +- [GitHub Discussion](https://github.com/langgenius/dify/discussions). Najboljše za: izmenjavo povratnih informacij in postavljanje vprašanj. +- [GitHub Issues](https://github.com/langgenius/dify/issues). Najboljše za: hrošče, na katere naletite pri uporabi Dify.AI, in predloge funkcij. Oglejte si naš [vodnik za prispevke](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). +- [Discord](https://discord.gg/FngNHpbcY7). Najboljše za: deljenje vaših aplikacij in druženje s skupnostjo. +- [X(Twitter)](https://twitter.com/dify_ai). Najboljše za: deljenje vaših aplikacij in druženje s skupnostjo. **Contributors** @@ -258,7 +258,6 @@ Za tiste, ki bi radi prispevali kodo, si oglejte naš vodnik za prispevke . Hkra [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date) - ## Varnostno razkritje Zaradi zaščite vaše zasebnosti se izogibajte objavljanju varnostnih vprašanj na GitHub. Namesto tega pošljite vprašanja na security@dify.ai in zagotovili vam bomo podrobnejši odgovor. diff --git a/README_TR.md b/README_TR.md index 470a7570e0..e54b1f4589 100644 --- a/README_TR.md +++ b/README_TR.md @@ -48,11 +48,10 @@ README in বাংলা

- Dify, açık kaynaklı bir LLM uygulama geliştirme platformudur. Sezgisel arayüzü, AI iş akışı, RAG pipeline'ı, ajan yetenekleri, model yönetimi, gözlemlenebilirlik özellikleri ve daha fazlasını birleştirerek, prototipten üretime hızlıca geçmenizi sağlar. İşte temel özelliklerin bir listesi:

-**1. Workflow**: +**1. Workflow**: Görsel bir arayüz üzerinde güçlü AI iş akışları oluşturun ve test edin, aşağıdaki tüm özellikleri ve daha fazlasını kullanarak. **2. Kapsamlı model desteği**: @@ -60,24 +59,23 @@ Görsel bir arayüz üzerinde güçlü AI iş akışları oluşturun ve test edi ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3) +**3. Prompt IDE**: +Komut istemlerini oluşturmak, model performansını karşılaştırmak ve sohbet tabanlı uygulamalara metin-konuşma gibi ek özellikler eklemek için kullanıcı dostu bir arayüz. -**3. Prompt IDE**: - Komut istemlerini oluşturmak, model performansını karşılaştırmak ve sohbet tabanlı uygulamalara metin-konuşma gibi ek özellikler eklemek için kullanıcı dostu bir arayüz. +**4. RAG Pipeline**: +Belge alımından bilgi çekmeye kadar geniş kapsamlı RAG yetenekleri. PDF'ler, PPT'ler ve diğer yaygın belge formatlarından metin çıkarma için hazır destek sunar. -**4. RAG Pipeline**: - Belge alımından bilgi çekmeye kadar geniş kapsamlı RAG yetenekleri. PDF'ler, PPT'ler ve diğer yaygın belge formatlarından metin çıkarma için hazır destek sunar. +**5. Ajan yetenekleri**: +LLM Fonksiyon Çağırma veya ReAct'a dayalı ajanlar tanımlayabilir ve bu ajanlara önceden hazırlanmış veya özel araçlar ekleyebilirsiniz. Dify, AI ajanları için Google Arama, DALL·E, Stable Diffusion ve WolframAlpha gibi 50'den fazla yerleşik araç sağlar. -**5. Ajan yetenekleri**: - LLM Fonksiyon Çağırma veya ReAct'a dayalı ajanlar tanımlayabilir ve bu ajanlara önceden hazırlanmış veya özel araçlar ekleyebilirsiniz. Dify, AI ajanları için Google Arama, DALL·E, Stable Diffusion ve WolframAlpha gibi 50'den fazla yerleşik araç sağlar. - -**6. LLMOps**: - Uygulama loglarını ve performans metriklerini zaman içinde izleme ve analiz etme imkanı. Üretim ortamından elde edilen verilere ve kullanıcı geri bildirimlerine dayanarak, prompt'ları, veri setlerini ve modelleri sürekli olarak optimize edebilirsiniz. Bu sayede, AI uygulamanızın performansını ve doğruluğunu sürekli olarak artırabilirsiniz. - -**7. Hizmet Olarak Backend**: - Dify'ın tüm özellikleri ilgili API'lerle birlikte gelir, böylece Dify'ı kendi iş mantığınıza kolayca entegre edebilirsiniz. +**6. LLMOps**: +Uygulama loglarını ve performans metriklerini zaman içinde izleme ve analiz etme imkanı. Üretim ortamından elde edilen verilere ve kullanıcı geri bildirimlerine dayanarak, prompt'ları, veri setlerini ve modelleri sürekli olarak optimize edebilirsiniz. Bu sayede, AI uygulamanızın performansını ve doğruluğunu sürekli olarak artırabilirsiniz. +**7. Hizmet Olarak Backend**: +Dify'ın tüm özellikleri ilgili API'lerle birlikte gelir, böylece Dify'ı kendi iş mantığınıza kolayca entegre edebilirsiniz. ## Özellik karşılaştırması +
Recurso
@@ -147,14 +145,15 @@ Görsel bir arayüz üzerinde güçlü AI iş akışları oluşturun ve test edi ## Dify'ı Kullanma - **Cloud
** -Herkesin sıfır kurulumla denemesi için bir [Dify Cloud](https://dify.ai) hizmeti sunuyoruz. Bu hizmet, kendi kendine dağıtılan versiyonun tüm yeteneklerini sağlar ve sandbox planında 200 ücretsiz GPT-4 çağrısı içerir. + Herkesin sıfır kurulumla denemesi için bir [Dify Cloud](https://dify.ai) hizmeti sunuyoruz. Bu hizmet, kendi kendine dağıtılan versiyonun tüm yeteneklerini sağlar ve sandbox planında 200 ücretsiz GPT-4 çağrısı içerir. - **Dify Topluluk Sürümünü Kendi Sunucunuzda Barındırma
** -Bu [başlangıç kılavuzu](#quick-start) ile Dify'ı kendi ortamınızda hızlıca çalıştırın. -Daha fazla referans ve detaylı talimatlar için [dokümantasyonumuzu](https://docs.dify.ai) kullanın. + Bu [başlangıç kılavuzu](#quick-start) ile Dify'ı kendi ortamınızda hızlıca çalıştırın. + Daha fazla referans ve detaylı talimatlar için [dokümantasyonumuzu](https://docs.dify.ai) kullanın. - **Kurumlar / organizasyonlar için Dify
** -Ek kurumsal odaklı özellikler sunuyoruz. Kurumsal ihtiyaçları görüşmek için [bize bir e-posta gönderin](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry).
+ Ek kurumsal odaklı özellikler sunuyoruz. Kurumsal ihtiyaçları görüşmek için [bize bir e-posta gönderin](mailto:business@dify.ai?subject=%5BGitHub%5DBusiness%20License%20Inquiry).
+ > AWS kullanan startuplar ve küçük işletmeler için, [AWS Marketplace'deki Dify Premium'a](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) göz atın ve tek tıklamayla kendi AWS VPC'nize dağıtın. Bu, özel logo ve marka ile uygulamalar oluşturma seçeneğine sahip uygun fiyatlı bir AMI teklifdir. ## Güncel Kalma @@ -163,13 +162,12 @@ GitHub'da Dify'a yıldız verin ve yeni sürümlerden anında haberdar olun. ![bizi-yıldızlayın](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4) - - ## Hızlı başlangıç + > Dify'ı kurmadan önce, makinenizin aşağıdaki minimum sistem gereksinimlerini karşıladığından emin olun: -> ->- CPU >= 2 Çekirdek ->- RAM >= 4GB +> +> - CPU >= 2 Çekirdek +> - RAM >= 4GB
Dify sunucusunu başlatmanın en kolay yolu, [docker-compose.yml](docker/docker-compose.yaml) dosyamızı çalıştırmaktır. Kurulum komutunu çalıştırmadan önce, makinenizde [Docker](https://docs.docker.com/get-docker/) ve [Docker Compose](https://docs.docker.com/compose/install/)'un kurulu olduğundan emin olun: @@ -201,17 +199,21 @@ Yüksek kullanılabilirliğe sahip bir kurulum yapılandırmak isterseniz, Dify' Dify'ı bulut platformuna tek tıklamayla dağıtın [terraform](https://www.terraform.io/) kullanarak ##### Azure Global + - [Azure Terraform tarafından @nikawang](https://github.com/nikawang/dify-azure-terraform) ##### Google Cloud + - [Google Cloud Terraform tarafından @sotazum](https://github.com/DeNA/dify-google-cloud-terraform) #### AWS CDK ile Dağıtım [CDK](https://aws.amazon.com/cdk/) kullanarak Dify'ı AWS'ye dağıtın -##### AWS -- [AWS CDK tarafından @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +##### AWS + +- [AWS CDK tarafından @KevinZhao (EKS based)](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +- [AWS CDK tarafından @tmokmss (ECS based)](https://github.com/aws-samples/dify-self-hosted-on-aws) #### Alibaba Cloud @@ -225,7 +227,6 @@ Dify'ı bulut platformuna tek tıklamayla dağıtın [terraform](https://www.ter [Azure Devops Pipeline Helm Chart by @LeoZhang](https://github.com/Ruiruiz30/Dify-helm-chart-AKS) kullanarak Dify'ı tek tıkla AKS'ye dağıtın - ## Katkıda Bulunma Kod katkısında bulunmak isteyenler için [Katkı Kılavuzumuza](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) bakabilirsiniz. @@ -241,10 +242,10 @@ Aynı zamanda, lütfen Dify'ı sosyal medyada, etkinliklerde ve konferanslarda p ## Topluluk & iletişim -* [GitHub Tartışmaları](https://github.com/langgenius/dify/discussions). En uygun: geri bildirim paylaşmak ve soru sormak için. -* [GitHub Sorunları](https://github.com/langgenius/dify/issues). En uygun: Dify.AI kullanırken karşılaştığınız hatalar ve özellik önerileri için. [Katkı Kılavuzumuza](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) bakın. -* [Discord](https://discord.gg/FngNHpbcY7). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için. -* [X(Twitter)](https://twitter.com/dify_ai). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için. +- [GitHub Tartışmaları](https://github.com/langgenius/dify/discussions). En uygun: geri bildirim paylaşmak ve soru sormak için. +- [GitHub Sorunları](https://github.com/langgenius/dify/issues). En uygun: Dify.AI kullanırken karşılaştığınız hatalar ve özellik önerileri için. [Katkı Kılavuzumuza](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) bakın. +- [Discord](https://discord.gg/FngNHpbcY7). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için. +- [X(Twitter)](https://twitter.com/dify_ai). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için. ## Star history diff --git a/README_TW.md b/README_TW.md index 18f1d2754a..c41434771c 100644 --- a/README_TW.md +++ b/README_TW.md @@ -180,11 +180,12 @@ Dify 的所有功能都提供相應的 API，因此您可以輕鬆地將 Dify 我們提供 [Dify Cloud](https://dify.ai) 服務，任何人都可以零配置嘗試。它提供與自部署版本相同的所有功能，並在沙盒計劃中包含 200 次免費 GPT-4 調用。 - **自託管 Dify 社區版
** - 使用這份[快速指南](#快速開始)在您的環境中快速運行 Dify。 + 使用這份[快速指南](#%E5%BF%AB%E9%80%9F%E9%96%8B%E5%A7%8B)在您的環境中快速運行 Dify。 使用我們的[文檔](https://docs.dify.ai)獲取更多參考和深入指導。 - **企業/組織版 Dify
** - 我們提供額外的企業中心功能。[通過這個聊天機器人記錄您的問題](https://udify.app/chat/22L1zSxg6yW1cWQg)或[發送電子郵件給我們](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)討論企業需求。
+ 我們提供額外的企業中心功能。[通過這個聊天機器人記錄您的問題](https://udify.app/chat/22L1zSxg6yW1cWQg)或[發送電子郵件給我們](mailto:business@dify.ai?subject=%5BGitHub%5DBusiness%20License%20Inquiry)討論企業需求。
+ > 對於使用 AWS 的初創企業和小型企業，請查看 [AWS Marketplace 上的 Dify Premium](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6)，並一鍵部署到您自己的 AWS VPC。這是一個經濟實惠的 AMI 產品，可選擇使用自定義徽標和品牌創建應用。 ## 保持領先 @@ -223,7 +224,8 @@ Dify 的所有功能都提供相應的 API，因此您可以輕鬆地將 Dify ### AWS -- [由 @KevinZhao 提供的 AWS CDK](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +- [由 @KevinZhao 提供的 AWS CDK (EKS based)](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +- [由 @tmokmss 提供的 AWS CDK (ECS based)](https://github.com/aws-samples/dify-self-hosted-on-aws) #### 使用 阿里云计算巢進行部署 @@ -237,7 +239,6 @@ Dify 的所有功能都提供相應的 API，因此您可以輕鬆地將 Dify 使用[Azure Devops Pipeline Helm Chart by @LeoZhang](https://github.com/Ruiruiz30/Dify-helm-chart-AKS) 將 Dify 一鍵部署到 AKS - ## 貢獻 對於想要貢獻程式碼的開發者，請參閱我們的[貢獻指南](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)。 diff --git a/README_VI.md b/README_VI.md index 2ab6da80fc..8c5c333e8f 100644 --- a/README_VI.md +++ b/README_VI.md @@ -48,36 +48,34 @@ README in বাংলা

- Dify là một nền tảng phát triển ứng dụng LLM mã nguồn mở. Giao diện trực quan kết hợp quy trình làm việc AI, mô hình RAG, khả năng tác nhân, quản lý mô hình, tính năng quan sát và hơn thế nữa, cho phép bạn nhanh chóng chuyển từ nguyên mẫu sang sản phẩm. Đây là danh sách các tính năng cốt lõi:

-**1. Quy trình làm việc**: - Xây dựng và kiểm tra các quy trình làm việc AI mạnh mẽ trên một canvas trực quan, tận dụng tất cả các tính năng sau đây và hơn thế nữa. +**1. Quy trình làm việc**: +Xây dựng và kiểm tra các quy trình làm việc AI mạnh mẽ trên một canvas trực quan, tận dụng tất cả các tính năng sau đây và hơn thế nữa. -**2. Hỗ trợ mô hình toàn diện**: - Tích hợp liền mạch với hàng trăm mô hình LLM độc quyền / mã nguồn mở từ hàng chục nhà cung cấp suy luận và giải pháp tự lưu trữ, bao gồm GPT, Mistral, Llama3, và bất kỳ mô hình tương thích API OpenAI nào. Danh sách đầy đủ các nhà cung cấp mô hình được hỗ trợ có thể được tìm thấy [tại đây](https://docs.dify.ai/getting-started/readme/model-providers). +**2. Hỗ trợ mô hình toàn diện**: +Tích hợp liền mạch với hàng trăm mô hình LLM độc quyền / mã nguồn mở từ hàng chục nhà cung cấp suy luận và giải pháp tự lưu trữ, bao gồm GPT, Mistral, Llama3, và bất kỳ mô hình tương thích API OpenAI nào. Danh sách đầy đủ các nhà cung cấp mô hình được hỗ trợ có thể được tìm thấy [tại đây](https://docs.dify.ai/getting-started/readme/model-providers). ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3) +**3. IDE Prompt**: +Giao diện trực quan để tạo prompt, so sánh hiệu suất mô hình và thêm các tính năng bổ sung như chuyển văn bản thành giọng nói cho một ứng dụng dựa trên trò chuyện. -**3. IDE Prompt**: - Giao diện trực quan để tạo prompt, so sánh hiệu suất mô hình và thêm các tính năng bổ sung như chuyển văn bản thành giọng nói cho một ứng dụng dựa trên trò chuyện. +**4. Mô hình RAG**: +Khả năng RAG mở rộng bao gồm mọi thứ từ nhập tài liệu đến truy xuất, với hỗ trợ sẵn có cho việc trích xuất văn bản từ PDF, PPT và các định dạng tài liệu phổ biến khác. -**4. Mô hình RAG**: - Khả năng RAG mở rộng bao gồm mọi thứ từ nhập tài liệu đến truy xuất, với hỗ trợ sẵn có cho việc trích xuất văn bản từ PDF, PPT và các định dạng tài liệu phổ biến khác. +**5. Khả năng tác nhân**: +Bạn có thể định nghĩa các tác nhân dựa trên LLM Function Calling hoặc ReAct, và thêm các công cụ được xây dựng sẵn hoặc tùy chỉnh cho tác nhân. Dify cung cấp hơn 50 công cụ tích hợp sẵn cho các tác nhân AI, như Google Search, DALL·E, Stable Diffusion và WolframAlpha. -**5. Khả năng tác nhân**: - Bạn có thể định nghĩa các tác nhân dựa trên LLM Function Calling hoặc ReAct, và thêm các công cụ được xây dựng sẵn hoặc tùy chỉnh cho tác nhân. Dify cung cấp hơn 50 công cụ tích hợp sẵn cho các tác nhân AI, như Google Search, DALL·E, Stable Diffusion và WolframAlpha. - -**6. LLMOps**: - Giám sát và phân tích nhật ký và hiệu suất ứng dụng theo thời gian. Bạn có thể liên tục cải thiện prompt, bộ dữ liệu và mô hình dựa trên dữ liệu sản xuất và chú thích. - -**7. Backend-as-a-Service**: - Tất cả các dịch vụ của Dify đều đi kèm với các API tương ứng, vì vậy bạn có thể dễ dàng tích hợp Dify vào logic kinh doanh của riêng mình. +**6. LLMOps**: +Giám sát và phân tích nhật ký và hiệu suất ứng dụng theo thời gian. Bạn có thể liên tục cải thiện prompt, bộ dữ liệu và mô hình dựa trên dữ liệu sản xuất và chú thích. +**7. Backend-as-a-Service**: +Tất cả các dịch vụ của Dify đều đi kèm với các API tương ứng, vì vậy bạn có thể dễ dàng tích hợp Dify vào logic kinh doanh của riêng mình. ## So sánh tính năng +
Özellik
@@ -147,16 +145,16 @@ Dify là một nền tảng phát triển ứng dụng LLM mã nguồn mở. Gia ## Sử dụng Dify - **Cloud
** -Chúng tôi lưu trữ dịch vụ [Dify Cloud](https://dify.ai) cho bất kỳ ai muốn thử mà không cần cài đặt. Nó cung cấp tất cả các khả năng của phiên bản tự triển khai và bao gồm 200 lượt gọi GPT-4 miễn phí trong gói sandbox. + Chúng tôi lưu trữ dịch vụ [Dify Cloud](https://dify.ai) cho bất kỳ ai muốn thử mà không cần cài đặt. Nó cung cấp tất cả các khả năng của phiên bản tự triển khai và bao gồm 200 lượt gọi GPT-4 miễn phí trong gói sandbox. - **Tự triển khai Dify Community Edition
** -Nhanh chóng chạy Dify trong môi trường của bạn với [hướng dẫn bắt đầu](#quick-start) này. -Sử dụng [tài liệu](https://docs.dify.ai) của chúng tôi để tham khảo thêm và nhận hướng dẫn chi tiết hơn. + Nhanh chóng chạy Dify trong môi trường của bạn với [hướng dẫn bắt đầu](#quick-start) này. + Sử dụng [tài liệu](https://docs.dify.ai) của chúng tôi để tham khảo thêm và nhận hướng dẫn chi tiết hơn. - **Dify cho doanh nghiệp / tổ chức
** -Chúng tôi cung cấp các tính năng bổ sung tập trung vào doanh nghiệp. [Ghi lại câu hỏi của bạn cho chúng tôi thông qua chatbot này](https://udify.app/chat/22L1zSxg6yW1cWQg) hoặc [gửi email cho chúng tôi](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) để thảo luận về nhu cầu doanh nghiệp.
- > Đối với các công ty khởi nghiệp và doanh nghiệp nhỏ sử dụng AWS, hãy xem [Dify Premium trên AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) và triển khai nó vào AWS VPC của riêng bạn chỉ với một cú nhấp chuột. Đây là một AMI giá cả phải chăng với tùy chọn tạo ứng dụng với logo và thương hiệu tùy chỉnh. + Chúng tôi cung cấp các tính năng bổ sung tập trung vào doanh nghiệp. [Ghi lại câu hỏi của bạn cho chúng tôi thông qua chatbot này](https://udify.app/chat/22L1zSxg6yW1cWQg) hoặc [gửi email cho chúng tôi](mailto:business@dify.ai?subject=%5BGitHub%5DBusiness%20License%20Inquiry) để thảo luận về nhu cầu doanh nghiệp.
+ > Đối với các công ty khởi nghiệp và doanh nghiệp nhỏ sử dụng AWS, hãy xem [Dify Premium trên AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) và triển khai nó vào AWS VPC của riêng bạn chỉ với một cú nhấp chuột. Đây là một AMI giá cả phải chăng với tùy chọn tạo ứng dụng với logo và thương hiệu tùy chỉnh. ## Luôn cập nhật @@ -164,13 +162,12 @@ Yêu thích Dify trên GitHub và được thông báo ngay lập tức về cá ![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4) - - ## Bắt đầu nhanh + > Trước khi cài đặt Dify, hãy đảm bảo máy của bạn đáp ứng các yêu cầu hệ thống tối thiểu sau: -> ->- CPU >= 2 Core ->- RAM >= 4GB +> +> - CPU >= 2 Core +> - RAM >= 4GB
@@ -203,18 +200,21 @@ Nếu bạn muốn cấu hình một cài đặt có độ sẵn sàng cao, có Triển khai Dify lên nền tảng đám mây với một cú nhấp chuột bằng cách sử dụng [terraform](https://www.terraform.io/) ##### Azure Global + - [Azure Terraform bởi @nikawang](https://github.com/nikawang/dify-azure-terraform) ##### Google Cloud + - [Google Cloud Terraform bởi @sotazum](https://github.com/DeNA/dify-google-cloud-terraform) #### Sử dụng AWS CDK để Triển khai Triển khai Dify trên AWS bằng [CDK](https://aws.amazon.com/cdk/) -##### AWS -- [AWS CDK bởi @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +##### AWS +- [AWS CDK bởi @KevinZhao (EKS based)](https://github.com/aws-samples/solution-for-deploying-dify-on-aws) +- [AWS CDK bởi @tmokmss (ECS based)](https://github.com/aws-samples/dify-self-hosted-on-aws) #### Alibaba Cloud @@ -228,13 +228,11 @@ Triển khai Dify lên Alibaba Cloud chỉ với một cú nhấp chuột bằng Triển khai Dify lên AKS chỉ với một cú nhấp chuột bằng [Azure Devops Pipeline Helm Chart bởi @LeoZhang](https://github.com/Ruiruiz30/Dify-helm-chart-AKS) - ## Đóng góp -Đối với những người muốn đóng góp mã, xem [Hướng dẫn Đóng góp](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) của chúng tôi. +Đối với những người muốn đóng góp mã, xem [Hướng dẫn Đóng góp](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) của chúng tôi. Đồng thời, vui lòng xem xét hỗ trợ Dify bằng cách chia sẻ nó trên mạng xã hội và tại các sự kiện và hội nghị. - > Chúng tôi đang tìm kiếm người đóng góp để giúp dịch Dify sang các ngôn ngữ khác ngoài tiếng Trung hoặc tiếng Anh. Nếu bạn quan tâm đến việc giúp đỡ, vui lòng xem [README i18n](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) để biết thêm thông tin và để lại bình luận cho chúng tôi trong kênh `global-users` của [Máy chủ Cộng đồng Discord](https://discord.gg/8Tpq4AcN9c) của chúng tôi. **Người đóng góp** @@ -245,10 +243,10 @@ Triển khai Dify lên AKS chỉ với một cú nhấp chuột bằng [Azure De ## Cộng đồng & liên hệ -* [Thảo luận GitHub](https://github.com/langgenius/dify/discussions). Tốt nhất cho: chia sẻ phản hồi và đặt câu hỏi. -* [Vấn đề GitHub](https://github.com/langgenius/dify/issues). Tốt nhất cho: lỗi bạn gặp phải khi sử dụng Dify.AI và đề xuất tính năng. Xem [Hướng dẫn Đóng góp](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) của chúng tôi. -* [Discord](https://discord.gg/FngNHpbcY7). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng. -* [X(Twitter)](https://twitter.com/dify_ai). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng. +- [Thảo luận GitHub](https://github.com/langgenius/dify/discussions). Tốt nhất cho: chia sẻ phản hồi và đặt câu hỏi. +- [Vấn đề GitHub](https://github.com/langgenius/dify/issues). Tốt nhất cho: lỗi bạn gặp phải khi sử dụng Dify.AI và đề xuất tính năng. Xem [Hướng dẫn Đóng góp](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) của chúng tôi. +- [Discord](https://discord.gg/FngNHpbcY7). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng. +- [X(Twitter)](https://twitter.com/dify_ai). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng. ## Lịch sử Yêu thích diff --git a/api/.env.example b/api/.env.example index 4beabfecea..3052dbfe2b 100644 --- a/api/.env.example +++ b/api/.env.example @@ -42,6 +42,15 @@ REDIS_PORT=6379 REDIS_USERNAME= REDIS_PASSWORD=difyai123456 REDIS_USE_SSL=false +# SSL configuration for Redis (when REDIS_USE_SSL=true) +REDIS_SSL_CERT_REQS=CERT_NONE +# Options: CERT_NONE, CERT_OPTIONAL, CERT_REQUIRED +REDIS_SSL_CA_CERTS= +# Path to CA certificate file for SSL verification +REDIS_SSL_CERTFILE= +# Path to client certificate file for SSL authentication +REDIS_SSL_KEYFILE= +# Path to client private key file for SSL authentication REDIS_DB=0 # redis Sentinel configuration. @@ -469,6 +478,13 @@ API_WORKFLOW_NODE_EXECUTION_REPOSITORY=repositories.sqlalchemy_api_workflow_node # API workflow run repository implementation API_WORKFLOW_RUN_REPOSITORY=repositories.sqlalchemy_api_workflow_run_repository.DifyAPISQLAlchemyWorkflowRunRepository +# Workflow log cleanup configuration +# Enable automatic cleanup of workflow run logs to manage database size +WORKFLOW_LOG_CLEANUP_ENABLED=true +# Number of days to retain workflow run logs (default: 30 days) +WORKFLOW_LOG_RETENTION_DAYS=30 +# Batch size for workflow log cleanup operations (default: 100) +WORKFLOW_LOG_CLEANUP_BATCH_SIZE=100 # App configuration APP_MAX_EXECUTION_TIME=1200 diff --git a/api/README.md b/api/README.md index b5298edf92..5571fdd0fd 100644 --- a/api/README.md +++ b/api/README.md @@ -3,7 +3,7 @@ ## Usage > [!IMPORTANT] -> +> > In the v1.3.0 release, `poetry` has been replaced with > [`uv`](https://docs.astral.sh/uv/) as the package manager > for Dify API backend service. @@ -20,25 +20,29 @@ cd ../api ``` -2. Copy `.env.example` to `.env` +1. Copy `.env.example` to `.env` ```cli - cp .env.example .env + cp .env.example .env ``` -3. Generate a `SECRET_KEY` in the `.env` file. + +1. Generate a `SECRET_KEY` in the `.env` file. bash for Linux + ```bash for Linux sed -i "/^SECRET_KEY=/c\SECRET_KEY=$(openssl rand -base64 42)" .env ``` + bash for Mac + ```bash for Mac secret_key=$(openssl rand -base64 42) sed -i '' "/^SECRET_KEY=/c\\ SECRET_KEY=${secret_key}" .env ``` -4. Create environment. +1. Create environment. Dify API service uses [UV](https://docs.astral.sh/uv/) to manage dependencies. First, you need to add the uv package manager, if you don't have it already. @@ -49,13 +53,13 @@ brew install uv ``` -5. Install dependencies +1. Install dependencies ```bash uv sync --dev ``` -6. Run migrate +1. Run migrate Before the first launch, migrate the database to the latest version. @@ -63,24 +67,27 @@ uv run flask db upgrade ``` -7. Start backend +1. Start backend ```bash uv run flask run --host 0.0.0.0 --port=5001 --debug ``` -8. Start Dify [web](../web) service. -9. Setup your application by visiting `http://localhost:3000`. -10. If you need to handle and debug the async tasks (e.g. dataset importing and documents indexing), please start the worker service. +1. Start Dify [web](../web) service. - ```bash - uv run celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail,ops_trace,app_deletion,plugin,workflow_storage - ``` +1. Setup your application by visiting `http://localhost:3000`. - Addition, if you want to debug the celery scheduled tasks, you can use the following command in another terminal: - ```bash - uv run celery -A app.celery beat - ``` +1. If you need to handle and debug the async tasks (e.g. dataset importing and documents indexing), please start the worker service. + +```bash +uv run celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail,ops_trace,app_deletion,plugin,workflow_storage +``` + +Addition, if you want to debug the celery scheduled tasks, you can use the following command in another terminal: + +```bash +uv run celery -A app.celery beat +``` ## Testing @@ -90,9 +97,8 @@ uv sync --dev ``` -2. Run the tests locally with mocked system environment variables in `tool.pytest_env` section in `pyproject.toml` +1. Run the tests locally with mocked system environment variables in `tool.pytest_env` section in `pyproject.toml` ```bash uv run -P api bash dev/pytest/pytest_all_tests.sh ``` - diff --git a/api/app_factory.py b/api/app_factory.py index 81155cbacd..032d6b17fc 100644 --- a/api/app_factory.py +++ b/api/app_factory.py @@ -51,6 +51,7 @@ def initialize_extensions(app: DifyApp): ext_login, ext_mail, ext_migrate, + ext_orjson, ext_otel, ext_proxy_fix, ext_redis, @@ -67,6 +68,7 @@ def initialize_extensions(app: DifyApp): ext_logging, ext_warnings, ext_import_modules, + ext_orjson, ext_set_secretkey, ext_compress, ext_code_based_extension, diff --git a/api/configs/feature/__init__.py b/api/configs/feature/__init__.py index 0b2f99aece..2bccc4b7a0 100644 --- a/api/configs/feature/__init__.py +++ b/api/configs/feature/__init__.py @@ -968,6 +968,14 @@ class AccountConfig(BaseSettings): ) +class WorkflowLogConfig(BaseSettings): + WORKFLOW_LOG_CLEANUP_ENABLED: bool = Field(default=True, description="Enable workflow run log cleanup") + WORKFLOW_LOG_RETENTION_DAYS: int = Field(default=30, description="Retention days for workflow run logs") + WORKFLOW_LOG_CLEANUP_BATCH_SIZE: int = Field( + default=100, description="Batch size for workflow run log cleanup operations" + ) + + class FeatureConfig( # place the configs in alphabet order AppExecutionConfig, @@ -1003,5 +1011,6 @@ class FeatureConfig( HostedServiceConfig, CeleryBeatConfig, CeleryScheduleTasksConfig, + WorkflowLogConfig, ): pass diff --git a/api/configs/middleware/cache/redis_config.py b/api/configs/middleware/cache/redis_config.py index 916f52e165..16dca98cfa 100644 --- a/api/configs/middleware/cache/redis_config.py +++ b/api/configs/middleware/cache/redis_config.py @@ -39,6 +39,26 @@ class RedisConfig(BaseSettings): default=False, ) + REDIS_SSL_CERT_REQS: str = Field( + description="SSL certificate requirements (CERT_NONE, CERT_OPTIONAL, CERT_REQUIRED)", + default="CERT_NONE", + ) + + REDIS_SSL_CA_CERTS: Optional[str] = Field( + description="Path to the CA certificate file for SSL verification", + default=None, + ) + + REDIS_SSL_CERTFILE: Optional[str] = Field( + description="Path to the client certificate file for SSL authentication", + default=None, + ) + + REDIS_SSL_KEYFILE: Optional[str] = Field( + description="Path to the client private key file for SSL authentication", + default=None, + ) + REDIS_USE_SENTINEL: Optional[bool] = Field( description="Enable Redis Sentinel mode for high availability", default=False, diff --git a/api/controllers/common/helpers.py b/api/controllers/common/helpers.py index 008f1f0f7a..6a5197635e 100644 --- a/api/controllers/common/helpers.py +++ b/api/controllers/common/helpers.py @@ -1,3 +1,4 @@ +import contextlib import mimetypes import os import platform @@ -65,10 +66,8 @@ def guess_file_info_from_response(response: httpx.Response): # Use python-magic to guess MIME type if still unknown or generic if mimetype == "application/octet-stream" and magic is not None: - try: + with contextlib.suppress(magic.MagicException): mimetype = magic.from_buffer(response.content[:1024], mime=True) - except magic.MagicException: - pass extension = os.path.splitext(filename)[1] diff --git a/api/controllers/console/app/annotation.py b/api/controllers/console/app/annotation.py index 493a9a52e2..2caa908d4a 100644 --- a/api/controllers/console/app/annotation.py +++ b/api/controllers/console/app/annotation.py @@ -1,3 +1,5 @@ +from typing import Literal + from flask import request from flask_login import current_user from flask_restful import Resource, marshal, marshal_with, reqparse @@ -24,7 +26,7 @@ class AnnotationReplyActionApi(Resource): @login_required @account_initialization_required @cloud_edition_billing_resource_check("annotation") - def post(self, app_id, action): + def post(self, app_id, action: Literal["enable", "disable"]): if not current_user.is_editor: raise Forbidden() @@ -38,8 +40,6 @@ class AnnotationReplyActionApi(Resource): result = AppAnnotationService.enable_app_annotation(args, app_id) elif action == "disable": result = AppAnnotationService.disable_app_annotation(app_id) - else: - raise ValueError("Unsupported annotation reply action") return result, 200 diff --git a/api/controllers/console/app/completion.py b/api/controllers/console/app/completion.py index 732f5b799a..ad94112f05 100644 --- a/api/controllers/console/app/completion.py +++ b/api/controllers/console/app/completion.py @@ -1,6 +1,7 @@ import logging import flask_login +from flask import request from flask_restful import Resource, reqparse from werkzeug.exceptions import InternalServerError, NotFound @@ -24,6 +25,7 @@ from core.errors.error import ( ProviderTokenNotInitError, QuotaExceededError, ) +from core.helper.trace_id_helper import get_external_trace_id from core.model_runtime.errors.invoke import InvokeError from libs import helper from libs.helper import uuid_value @@ -115,6 +117,10 @@ class ChatMessageApi(Resource): streaming = args["response_mode"] != "blocking" args["auto_generate_name"] = False + external_trace_id = get_external_trace_id(request) + if external_trace_id: + args["external_trace_id"] = external_trace_id + account = flask_login.current_user try: diff --git a/api/controllers/console/app/generator.py b/api/controllers/console/app/generator.py index 4847a2cab8..57dc1267d5 100644 --- a/api/controllers/console/app/generator.py +++ b/api/controllers/console/app/generator.py @@ -1,3 +1,5 @@ +from collections.abc import Sequence + from flask_login import current_user from flask_restful import Resource, reqparse @@ -10,6 +12,8 @@ from controllers.console.app.error import ( ) from controllers.console.wraps import account_initialization_required, setup_required from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError +from core.helper.code_executor.javascript.javascript_code_provider import JavascriptCodeProvider +from core.helper.code_executor.python3.python3_code_provider import Python3CodeProvider from core.llm_generator.llm_generator import LLMGenerator from core.model_runtime.errors.invoke import InvokeError from libs.login import login_required @@ -107,6 +111,121 @@ class RuleStructuredOutputGenerateApi(Resource): return structured_output +class InstructionGenerateApi(Resource): + @setup_required + @login_required + @account_initialization_required + def post(self): + parser = reqparse.RequestParser() + parser.add_argument("flow_id", type=str, required=True, default="", location="json") + parser.add_argument("node_id", type=str, required=False, default="", location="json") + parser.add_argument("current", type=str, required=False, default="", location="json") + parser.add_argument("language", type=str, required=False, default="javascript", location="json") + parser.add_argument("instruction", type=str, required=True, nullable=False, location="json") + parser.add_argument("model_config", type=dict, required=True, nullable=False, location="json") + parser.add_argument("ideal_output", type=str, required=False, default="", location="json") + args = parser.parse_args() + code_template = ( + Python3CodeProvider.get_default_code() + if args["language"] == "python" + else (JavascriptCodeProvider.get_default_code()) + if args["language"] == "javascript" + else "" + ) + try: + # Generate from nothing for a workflow node + if (args["current"] == code_template or args["current"] == "") and args["node_id"] != "": + from models import App, db + from services.workflow_service import WorkflowService + + app = db.session.query(App).where(App.id == args["flow_id"]).first() + if not app: + return {"error": f"app {args['flow_id']} not found"}, 400 + workflow = WorkflowService().get_draft_workflow(app_model=app) + if not workflow: + return {"error": f"workflow {args['flow_id']} not found"}, 400 + nodes: Sequence = workflow.graph_dict["nodes"] + node = [node for node in nodes if node["id"] == args["node_id"]] + if len(node) == 0: + return {"error": f"node {args['node_id']} not found"}, 400 + node_type = node[0]["data"]["type"] + match node_type: + case "llm": + return LLMGenerator.generate_rule_config( + current_user.current_tenant_id, + instruction=args["instruction"], + model_config=args["model_config"], + no_variable=True, + ) + case "agent": + return LLMGenerator.generate_rule_config( + current_user.current_tenant_id, + instruction=args["instruction"], + model_config=args["model_config"], + no_variable=True, + ) + case "code": + return LLMGenerator.generate_code( + tenant_id=current_user.current_tenant_id, + instruction=args["instruction"], + model_config=args["model_config"], + code_language=args["language"], + ) + case _: + return {"error": f"invalid node type: {node_type}"} + if args["node_id"] == "" and args["current"] != "": # For legacy app without a workflow + return LLMGenerator.instruction_modify_legacy( + tenant_id=current_user.current_tenant_id, + flow_id=args["flow_id"], + current=args["current"], + instruction=args["instruction"], + model_config=args["model_config"], + ideal_output=args["ideal_output"], + ) + if args["node_id"] != "" and args["current"] != "": # For workflow node + return LLMGenerator.instruction_modify_workflow( + tenant_id=current_user.current_tenant_id, + flow_id=args["flow_id"], + node_id=args["node_id"], + current=args["current"], + instruction=args["instruction"], + model_config=args["model_config"], + ideal_output=args["ideal_output"], + ) + return {"error": "incompatible parameters"}, 400 + except ProviderTokenNotInitError as ex: + raise ProviderNotInitializeError(ex.description) + except QuotaExceededError: + raise ProviderQuotaExceededError() + except ModelCurrentlyNotSupportError: + raise ProviderModelCurrentlyNotSupportError() + except InvokeError as e: + raise CompletionRequestError(e.description) + + +class InstructionGenerationTemplateApi(Resource): + @setup_required + @login_required + @account_initialization_required + def post(self) -> dict: + parser = reqparse.RequestParser() + parser.add_argument("type", type=str, required=True, default=False, location="json") + args = parser.parse_args() + match args["type"]: + case "prompt": + from core.llm_generator.prompts import INSTRUCTION_GENERATE_TEMPLATE_PROMPT + + return {"data": INSTRUCTION_GENERATE_TEMPLATE_PROMPT} + case "code": + from core.llm_generator.prompts import INSTRUCTION_GENERATE_TEMPLATE_CODE + + return {"data": INSTRUCTION_GENERATE_TEMPLATE_CODE} + case _: + raise ValueError(f"Invalid type: {args['type']}") + + api.add_resource(RuleGenerateApi, "/rule-generate") api.add_resource(RuleCodeGenerateApi, "/rule-code-generate") api.add_resource(RuleStructuredOutputGenerateApi, "/rule-structured-output-generate") +api.add_resource(InstructionGenerateApi, "/instruction-generate") +api.add_resource(InstructionGenerationTemplateApi, "/instruction-generate/template") diff --git a/api/controllers/console/app/workflow.py b/api/controllers/console/app/workflow.py index a9f088a276..c58301b300 100644 --- a/api/controllers/console/app/workflow.py +++ b/api/controllers/console/app/workflow.py @@ -23,6 +23,7 @@ from core.app.app_config.features.file_upload.manager import FileUploadConfigMan from core.app.apps.base_app_queue_manager import AppQueueManager from core.app.entities.app_invoke_entities import InvokeFrom from core.file.models import File +from core.helper.trace_id_helper import get_external_trace_id from extensions.ext_database import db from factories import file_factory, variable_factory from fields.workflow_fields import workflow_fields, workflow_pagination_fields @@ -185,6 +186,10 @@ class AdvancedChatDraftWorkflowRunApi(Resource): args = parser.parse_args() + external_trace_id = get_external_trace_id(request) + if external_trace_id: + args["external_trace_id"] = external_trace_id + try: response = AppGenerateService.generate( app_model=app_model, user=current_user, args=args, invoke_from=InvokeFrom.DEBUGGER, streaming=True @@ -373,6 +378,10 @@ class DraftWorkflowRunApi(Resource): parser.add_argument("files", type=list, required=False, location="json") args = parser.parse_args() + external_trace_id = get_external_trace_id(request) + if external_trace_id: + args["external_trace_id"] = external_trace_id + try: response = AppGenerateService.generate( app_model=app_model, diff --git a/api/controllers/console/app/workflow_draft_variable.py b/api/controllers/console/app/workflow_draft_variable.py index ba93f82756..414c07ef50 100644 --- a/api/controllers/console/app/workflow_draft_variable.py +++ b/api/controllers/console/app/workflow_draft_variable.py @@ -163,11 +163,11 @@ class WorkflowVariableCollectionApi(Resource): draft_var_srv = WorkflowDraftVariableService( session=session, ) - workflow_vars = draft_var_srv.list_variables_without_values( - app_id=app_model.id, - page=args.page, - limit=args.limit, - ) + workflow_vars = draft_var_srv.list_variables_without_values( + app_id=app_model.id, + page=args.page, + limit=args.limit, + ) return workflow_vars diff --git a/api/controllers/console/datasets/datasets_document.py b/api/controllers/console/datasets/datasets_document.py index 4e0955bd43..413b018baa 100644 --- a/api/controllers/console/datasets/datasets_document.py +++ b/api/controllers/console/datasets/datasets_document.py @@ -1,6 +1,6 @@ import logging from argparse import ArgumentTypeError -from typing import cast +from typing import Literal, cast from flask import request from flask_login import current_user @@ -758,7 +758,7 @@ class DocumentProcessingApi(DocumentResource): @login_required @account_initialization_required @cloud_edition_billing_rate_limit_check("knowledge") - def patch(self, dataset_id, document_id, action): + def patch(self, dataset_id, document_id, action: Literal["pause", "resume"]): dataset_id = str(dataset_id) document_id = str(document_id) document = self.get_document(dataset_id, document_id) @@ -784,8 +784,6 @@ class DocumentProcessingApi(DocumentResource): document.paused_at = None document.is_paused = False db.session.commit() - else: - raise InvalidActionError() return {"result": "success"}, 200 @@ -840,7 +838,7 @@ class DocumentStatusApi(DocumentResource): @account_initialization_required @cloud_edition_billing_resource_check("vector_space") @cloud_edition_billing_rate_limit_check("knowledge") - def patch(self, dataset_id, action): + def patch(self, dataset_id, action: Literal["enable", "disable", "archive", "un_archive"]): dataset_id = str(dataset_id) dataset = DatasetService.get_dataset(dataset_id) if dataset is None: diff --git a/api/controllers/console/datasets/metadata.py b/api/controllers/console/datasets/metadata.py index 65f76fb402..1b5570285d 100644 --- a/api/controllers/console/datasets/metadata.py +++ b/api/controllers/console/datasets/metadata.py @@ -1,3 +1,5 @@ +from typing import Literal + from flask_login import current_user from flask_restful import Resource, marshal_with, reqparse from werkzeug.exceptions import NotFound @@ -100,7 +102,7 @@ class DatasetMetadataBuiltInFieldActionApi(Resource): @login_required @account_initialization_required @enterprise_license_required - def post(self, dataset_id, action): + def post(self, dataset_id, action: Literal["enable", "disable"]): dataset_id_str = str(dataset_id) dataset = DatasetService.get_dataset(dataset_id_str) if dataset is None: diff --git a/api/controllers/console/datasets/upload_file.py b/api/controllers/console/datasets/upload_file.py index 9b456c771d..2afdaf7f2b 100644 --- a/api/controllers/console/datasets/upload_file.py +++ b/api/controllers/console/datasets/upload_file.py @@ -39,7 +39,7 @@ class UploadFileApi(Resource): data_source_info = document.data_source_info_dict if data_source_info and "upload_file_id" in data_source_info: file_id = data_source_info["upload_file_id"] - upload_file = db.session.query(UploadFile).filter(UploadFile.id == file_id).first() + upload_file = db.session.query(UploadFile).where(UploadFile.id == file_id).first() if not upload_file: raise NotFound("UploadFile not found.") else: diff --git a/api/controllers/console/version.py b/api/controllers/console/version.py index 8237ea3cdc..894785abc8 100644 --- a/api/controllers/console/version.py +++ b/api/controllers/console/version.py @@ -32,7 +32,7 @@ class VersionApi(Resource): return result try: - response = requests.get(check_update_url, {"current_version": args.get("current_version")}) + response = requests.get(check_update_url, {"current_version": args.get("current_version")}, timeout=(3, 10)) except Exception as error: logging.warning("Check update version error: %s.", str(error)) result["version"] = args.get("current_version") diff --git a/api/controllers/console/workspace/account.py b/api/controllers/console/workspace/account.py index 4d5357cd18..3f6d6bf54f 100644 --- a/api/controllers/console/workspace/account.py +++ b/api/controllers/console/workspace/account.py @@ -1,3 +1,5 @@ +from datetime import datetime + import pytz from flask import request from flask_login import current_user @@ -327,6 +329,9 @@ class EducationVerifyApi(Resource): class EducationApi(Resource): status_fields = { "result": fields.Boolean, + "is_student": fields.Boolean, + "expire_at": TimestampField, + "allow_refresh": fields.Boolean, } @setup_required @@ -354,7 +359,11 @@ class EducationApi(Resource): def get(self): account = current_user - return BillingService.EducationIdentity.is_active(account.id) + res = BillingService.EducationIdentity.status(account.id) + # convert expire_at to UTC timestamp from isoformat + if res and "expire_at" in res: + res["expire_at"] = datetime.fromisoformat(res["expire_at"]).astimezone(pytz.utc) + return res class EducationAutoCompleteApi(Resource): diff --git a/api/controllers/inner_api/mail.py b/api/controllers/inner_api/mail.py index ce3373d65c..7b96f88f51 100644 --- a/api/controllers/inner_api/mail.py +++ b/api/controllers/inner_api/mail.py @@ -1,27 +1,38 @@ -from flask_restful import ( - Resource, # type: ignore - reqparse, -) +from flask_restful import Resource, reqparse from controllers.console.wraps import setup_required from controllers.inner_api import api -from controllers.inner_api.wraps import enterprise_inner_api_only -from services.enterprise.mail_service import DifyMail, EnterpriseMailService +from controllers.inner_api.wraps import billing_inner_api_only, enterprise_inner_api_only +from tasks.mail_inner_task import send_inner_email_task + +_mail_parser = reqparse.RequestParser() +_mail_parser.add_argument("to", type=str, action="append", required=True) +_mail_parser.add_argument("subject", type=str, required=True) +_mail_parser.add_argument("body", type=str, required=True) +_mail_parser.add_argument("substitutions", type=dict, required=False) -class EnterpriseMail(Resource): - @setup_required - @enterprise_inner_api_only +class BaseMail(Resource): + """Shared logic for sending an inner email.""" + def post(self): - parser = reqparse.RequestParser() - parser.add_argument("to", type=str, action="append", required=True) - parser.add_argument("subject", type=str, required=True) - parser.add_argument("body", type=str, required=True) - parser.add_argument("substitutions", type=dict, required=False) - args = parser.parse_args() - - EnterpriseMailService.send_mail(DifyMail(**args)) + args = _mail_parser.parse_args() + send_inner_email_task.delay( + to=args["to"], + subject=args["subject"], + body=args["body"], + substitutions=args["substitutions"], + ) return {"message": "success"}, 200 +class EnterpriseMail(BaseMail): + method_decorators = [setup_required, enterprise_inner_api_only] + + +class BillingMail(BaseMail): + method_decorators = [setup_required, billing_inner_api_only] + + api.add_resource(EnterpriseMail, "/enterprise/mail") +api.add_resource(BillingMail, "/billing/mail") diff --git a/api/controllers/inner_api/wraps.py b/api/controllers/inner_api/wraps.py index 9e7b3d4f29..c5aa318f58 100644 --- a/api/controllers/inner_api/wraps.py +++ b/api/controllers/inner_api/wraps.py @@ -10,6 +10,22 @@ from extensions.ext_database import db from models.model import EndUser +def billing_inner_api_only(view): + @wraps(view) + def decorated(*args, **kwargs): + if not dify_config.INNER_API: + abort(404) + + # get header 'X-Inner-Api-Key' + inner_api_key = request.headers.get("X-Inner-Api-Key") + if not inner_api_key or inner_api_key != dify_config.INNER_API_KEY: + abort(401) + + return view(*args, **kwargs) + + return decorated + + def enterprise_inner_api_only(view): @wraps(view) def decorated(*args, **kwargs): diff --git a/api/controllers/service_api/app/annotation.py b/api/controllers/service_api/app/annotation.py index 9b22c535f4..23446bb702 100644 --- a/api/controllers/service_api/app/annotation.py +++ b/api/controllers/service_api/app/annotation.py @@ -1,3 +1,5 @@ +from typing import Literal + from flask import request from flask_restful import Resource, marshal, marshal_with, reqparse from werkzeug.exceptions import Forbidden @@ -15,7 +17,7 @@ from services.annotation_service import AppAnnotationService class AnnotationReplyActionApi(Resource): @validate_app_token - def post(self, app_model: App, action): + def post(self, app_model: App, action: Literal["enable", "disable"]): parser = reqparse.RequestParser() parser.add_argument("score_threshold", required=True, type=float, location="json") parser.add_argument("embedding_provider_name", required=True, type=str, location="json") @@ -25,8 +27,6 @@ class AnnotationReplyActionApi(Resource): result = AppAnnotationService.enable_app_annotation(args, app_model.id) elif action == "disable": result = AppAnnotationService.disable_app_annotation(app_model.id) - else: - raise ValueError("Unsupported annotation reply action") return result, 200 diff --git a/api/controllers/service_api/app/conversation.py b/api/controllers/service_api/app/conversation.py index 79c860e6b8..073307ac4a 100644 --- a/api/controllers/service_api/app/conversation.py +++ b/api/controllers/service_api/app/conversation.py @@ -1,5 +1,3 @@ -import json - from flask_restful import Resource, marshal_with, reqparse from flask_restful.inputs import int_range from sqlalchemy.orm import Session @@ -136,12 +134,15 @@ class ConversationVariableDetailApi(Resource): variable_id = str(variable_id) parser = reqparse.RequestParser() - parser.add_argument("value", required=True, location="json") + # using lambda is for passing the already-typed value without modification + # if no lambda, it will be converted to string + # the string cannot be converted using json.loads + parser.add_argument("value", required=True, location="json", type=lambda x: x) args = parser.parse_args() try: return ConversationService.update_conversation_variable( - app_model, conversation_id, variable_id, end_user, json.loads(args["value"]) + app_model, conversation_id, variable_id, end_user, args["value"] ) except services.errors.conversation.ConversationNotExistsError: raise NotFound("Conversation Not Exists.") diff --git a/api/controllers/service_api/dataset/dataset.py b/api/controllers/service_api/dataset/dataset.py index 29eef41253..35b1efeff6 100644 --- a/api/controllers/service_api/dataset/dataset.py +++ b/api/controllers/service_api/dataset/dataset.py @@ -1,3 +1,5 @@ +from typing import Literal + from flask import request from flask_restful import marshal, marshal_with, reqparse from werkzeug.exceptions import Forbidden, NotFound @@ -358,14 +360,14 @@ class DatasetApi(DatasetApiResource): class DocumentStatusApi(DatasetApiResource): """Resource for batch document status operations.""" - def patch(self, tenant_id, dataset_id, action): + def patch(self, tenant_id, dataset_id, action: Literal["enable", "disable", "archive", "un_archive"]): """ Batch update document status. Args: tenant_id: tenant id dataset_id: dataset id - action: action to perform (enable, disable, archive, un_archive) + action: action to perform (Literal["enable", "disable", "archive", "un_archive"]) Returns: dict: A dictionary with a key 'result' and a value 'success' diff --git a/api/controllers/service_api/dataset/metadata.py b/api/controllers/service_api/dataset/metadata.py index 6ba818c5fc..75a0b18285 100644 --- a/api/controllers/service_api/dataset/metadata.py +++ b/api/controllers/service_api/dataset/metadata.py @@ -1,3 +1,5 @@ +from typing import Literal + from flask_login import current_user # type: ignore from flask_restful import marshal, reqparse from werkzeug.exceptions import NotFound @@ -77,7 +79,7 @@ class DatasetMetadataBuiltInFieldServiceApi(DatasetApiResource): class DatasetMetadataBuiltInFieldActionServiceApi(DatasetApiResource): @cloud_edition_billing_rate_limit_check("knowledge", "dataset") - def post(self, tenant_id, dataset_id, action): + def post(self, tenant_id, dataset_id, action: Literal["enable", "disable"]): dataset_id_str = str(dataset_id) dataset = DatasetService.get_dataset(dataset_id_str) if dataset is None: diff --git a/api/core/app/apps/chat/app_generator.py b/api/core/app/apps/chat/app_generator.py index 0c76cc39ae..c273776eb1 100644 --- a/api/core/app/apps/chat/app_generator.py +++ b/api/core/app/apps/chat/app_generator.py @@ -140,7 +140,9 @@ class ChatAppGenerator(MessageBasedAppGenerator): ) # get tracing instance - trace_manager = TraceQueueManager(app_id=app_model.id) + trace_manager = TraceQueueManager( + app_id=app_model.id, user_id=user.id if isinstance(user, Account) else user.session_id + ) # init application generate entity application_generate_entity = ChatAppGenerateEntity( diff --git a/api/core/app/apps/completion/app_generator.py b/api/core/app/apps/completion/app_generator.py index 9356bd1cea..64dade2968 100644 --- a/api/core/app/apps/completion/app_generator.py +++ b/api/core/app/apps/completion/app_generator.py @@ -124,7 +124,9 @@ class CompletionAppGenerator(MessageBasedAppGenerator): ) # get tracing instance - trace_manager = TraceQueueManager(app_model.id) + trace_manager = TraceQueueManager( + app_id=app_model.id, user_id=user.id if isinstance(user, Account) else user.session_id + ) # init application generate entity application_generate_entity = CompletionAppGenerateEntity( diff --git a/api/core/app/apps/message_based_app_queue_manager.py b/api/core/app/apps/message_based_app_queue_manager.py index 8507f23f17..4100a0d5a9 100644 --- a/api/core/app/apps/message_based_app_queue_manager.py +++ b/api/core/app/apps/message_based_app_queue_manager.py @@ -6,7 +6,6 @@ from core.app.entities.queue_entities import ( MessageQueueMessage, QueueAdvancedChatMessageEndEvent, QueueErrorEvent, - QueueMessage, QueueMessageEndEvent, QueueStopEvent, ) @@ -22,15 +21,6 @@ class MessageBasedAppQueueManager(AppQueueManager): self._app_mode = app_mode self._message_id = str(message_id) - def construct_queue_message(self, event: AppQueueEvent) -> QueueMessage: - return MessageQueueMessage( - task_id=self._task_id, - message_id=self._message_id, - conversation_id=self._conversation_id, - app_mode=self._app_mode, - event=event, - ) - def _publish(self, event: AppQueueEvent, pub_from: PublishFrom) -> None: """ Publish event to queue diff --git a/api/core/app/task_pipeline/message_cycle_manager.py b/api/core/app/task_pipeline/message_cycle_manager.py index f3b9dbf758..0d786ba051 100644 --- a/api/core/app/task_pipeline/message_cycle_manager.py +++ b/api/core/app/task_pipeline/message_cycle_manager.py @@ -181,7 +181,7 @@ class MessageCycleManager: :param message_id: message id :return: """ - message_file = db.session.query(MessageFile).filter(MessageFile.id == message_id).first() + message_file = db.session.query(MessageFile).where(MessageFile.id == message_id).first() event_type = StreamEvent.MESSAGE_FILE if message_file else StreamEvent.MESSAGE return MessageStreamResponse( diff --git a/api/core/helper/code_executor/template_transformer.py b/api/core/helper/code_executor/template_transformer.py index b416e48ce4..3965f8cb31 100644 --- a/api/core/helper/code_executor/template_transformer.py +++ b/api/core/helper/code_executor/template_transformer.py @@ -5,7 +5,7 @@ from base64 import b64encode from collections.abc import Mapping from typing import Any -from core.variables.utils import SegmentJSONEncoder +from core.variables.utils import dumps_with_segments class TemplateTransformer(ABC): @@ -93,7 +93,7 @@ class TemplateTransformer(ABC): @classmethod def serialize_inputs(cls, inputs: Mapping[str, Any]) -> str: - inputs_json_str = json.dumps(inputs, ensure_ascii=False, cls=SegmentJSONEncoder).encode() + inputs_json_str = dumps_with_segments(inputs, ensure_ascii=False).encode() input_base64_encoded = b64encode(inputs_json_str).decode("utf-8") return input_base64_encoded diff --git a/api/core/helper/trace_id_helper.py b/api/core/helper/trace_id_helper.py index e90c3194f2..df42837796 100644 --- a/api/core/helper/trace_id_helper.py +++ b/api/core/helper/trace_id_helper.py @@ -16,15 +16,33 @@ def get_external_trace_id(request: Any) -> Optional[str]: """ Retrieve the trace_id from the request. - Priority: header ('X-Trace-Id'), then parameters, then JSON body. Returns None if not provided or invalid. + Priority: + 1. header ('X-Trace-Id') + 2. parameters + 3. JSON body + 4. Current OpenTelemetry context (if enabled) + 5. OpenTelemetry traceparent header (if present and valid) + + Returns None if no valid trace_id is provided. """ trace_id = request.headers.get("X-Trace-Id") + if not trace_id: trace_id = request.args.get("trace_id") + if not trace_id and getattr(request, "is_json", False): json_data = getattr(request, "json", None) if json_data: trace_id = json_data.get("trace_id") + + if not trace_id: + trace_id = get_trace_id_from_otel_context() + + if not trace_id: + traceparent = request.headers.get("traceparent") + if traceparent: + trace_id = parse_traceparent_header(traceparent) + if isinstance(trace_id, str) and is_valid_trace_id(trace_id): return trace_id return None @@ -40,3 +58,49 @@ def extract_external_trace_id_from_args(args: Mapping[str, Any]) -> dict: if trace_id: return {"external_trace_id": trace_id} return {} + + +def get_trace_id_from_otel_context() -> Optional[str]: + """ + Retrieve the current trace ID from the active OpenTelemetry trace context. + Returns None if: + 1. OpenTelemetry SDK is not installed or enabled. + 2. There is no active span or trace context. + """ + try: + from opentelemetry.trace import SpanContext, get_current_span + from opentelemetry.trace.span import INVALID_TRACE_ID + + span = get_current_span() + if not span: + return None + + span_context: SpanContext = span.get_span_context() + + if not span_context or span_context.trace_id == INVALID_TRACE_ID: + return None + + trace_id_hex = f"{span_context.trace_id:032x}" + return trace_id_hex + + except Exception: + return None + + +def parse_traceparent_header(traceparent: str) -> Optional[str]: + """ + Parse the `traceparent` header to extract the trace_id. + + Expected format: + 'version-trace_id-span_id-flags' + + Reference: + W3C Trace Context Specification: https://www.w3.org/TR/trace-context/ + """ + try: + parts = traceparent.split("-") + if len(parts) == 4 and len(parts[1]) == 32: + return parts[1] + except Exception: + pass + return None diff --git a/api/core/indexing_runner.py b/api/core/indexing_runner.py index 2387658bb6..b40278c76b 100644 --- a/api/core/indexing_runner.py +++ b/api/core/indexing_runner.py @@ -30,7 +30,7 @@ from core.rag.splitter.fixed_text_splitter import ( FixedRecursiveCharacterTextSplitter, ) from core.rag.splitter.text_splitter import TextSplitter -from core.tools.utils.rag_web_reader import get_image_upload_file_ids +from core.tools.utils.web_reader_tool import get_image_upload_file_ids from extensions.ext_database import db from extensions.ext_redis import redis_client from extensions.ext_storage import storage diff --git a/api/core/llm_generator/llm_generator.py b/api/core/llm_generator/llm_generator.py index 47e5a79160..8c1d171688 100644 --- a/api/core/llm_generator/llm_generator.py +++ b/api/core/llm_generator/llm_generator.py @@ -1,6 +1,7 @@ import json import logging import re +from collections.abc import Sequence from typing import Optional, cast import json_repair @@ -11,6 +12,8 @@ from core.llm_generator.prompts import ( CONVERSATION_TITLE_PROMPT, GENERATOR_QA_PROMPT, JAVASCRIPT_CODE_GENERATOR_PROMPT_TEMPLATE, + LLM_MODIFY_CODE_SYSTEM, + LLM_MODIFY_PROMPT_SYSTEM, PYTHON_CODE_GENERATOR_PROMPT_TEMPLATE, SYSTEM_STRUCTURED_OUTPUT_GENERATE, WORKFLOW_RULE_CONFIG_PROMPT_GENERATE_TEMPLATE, @@ -24,6 +27,9 @@ from core.ops.entities.trace_entity import TraceTaskName from core.ops.ops_trace_manager import TraceQueueManager, TraceTask from core.ops.utils import measure_time from core.prompt.utils.prompt_template_parser import PromptTemplateParser +from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionMetadataKey +from core.workflow.graph_engine.entities.event import AgentLogEvent +from models import App, Message, WorkflowNodeExecutionModel, db class LLMGenerator: @@ -388,3 +394,181 @@ class LLMGenerator: except Exception as e: logging.exception("Failed to invoke LLM model, model: %s", model_config.get("name")) return {"output": "", "error": f"An unexpected error occurred: {str(e)}"} + + @staticmethod + def instruction_modify_legacy( + tenant_id: str, flow_id: str, current: str, instruction: str, model_config: dict, ideal_output: str | None + ) -> dict: + app: App | None = db.session.query(App).where(App.id == flow_id).first() + last_run: Message | None = ( + db.session.query(Message).where(Message.app_id == flow_id).order_by(Message.created_at.desc()).first() + ) + if not last_run: + return LLMGenerator.__instruction_modify_common( + tenant_id=tenant_id, + model_config=model_config, + last_run=None, + current=current, + error_message="", + instruction=instruction, + node_type="llm", + ideal_output=ideal_output, + ) + last_run_dict = { + "query": last_run.query, + "answer": last_run.answer, + "error": last_run.error, + } + return LLMGenerator.__instruction_modify_common( + tenant_id=tenant_id, + model_config=model_config, + last_run=last_run_dict, + current=current, + error_message=str(last_run.error), + instruction=instruction, + node_type="llm", + ideal_output=ideal_output, + ) + + @staticmethod + def instruction_modify_workflow( + tenant_id: str, + flow_id: str, + node_id: str, + current: str, + instruction: str, + model_config: dict, + ideal_output: str | None, + ) -> dict: + from services.workflow_service import WorkflowService + + app: App | None = db.session.query(App).where(App.id == flow_id).first() + if not app: + raise ValueError("App not found.") + workflow = WorkflowService().get_draft_workflow(app_model=app) + if not workflow: + raise ValueError("Workflow not found for the given app model.") + last_run = WorkflowService().get_node_last_run(app_model=app, workflow=workflow, node_id=node_id) + try: + node_type = cast(WorkflowNodeExecutionModel, last_run).node_type + except Exception: + try: + node_type = [it for it in workflow.graph_dict["graph"]["nodes"] if it["id"] == node_id][0]["data"][ + "type" + ] + except Exception: + node_type = "llm" + + if not last_run: # Node is not executed yet + return LLMGenerator.__instruction_modify_common( + tenant_id=tenant_id, + model_config=model_config, + last_run=None, + current=current, + error_message="", + instruction=instruction, + node_type=node_type, + ideal_output=ideal_output, + ) + + def agent_log_of(node_execution: WorkflowNodeExecutionModel) -> Sequence: + raw_agent_log = node_execution.execution_metadata_dict.get(WorkflowNodeExecutionMetadataKey.AGENT_LOG) + if not raw_agent_log: + return [] + parsed: Sequence[AgentLogEvent] = json.loads(raw_agent_log) + + def dict_of_event(event: AgentLogEvent) -> dict: + return { + "status": event.status, + "error": event.error, + "data": event.data, + } + + return [dict_of_event(event) for event in parsed] + + last_run_dict = { + "inputs": last_run.inputs_dict, + "status": last_run.status, + "error": last_run.error, + "agent_log": agent_log_of(last_run), + } + + return LLMGenerator.__instruction_modify_common( + tenant_id=tenant_id, + model_config=model_config, + last_run=last_run_dict, + current=current, + error_message=last_run.error, + instruction=instruction, + node_type=last_run.node_type, + ideal_output=ideal_output, + ) + + @staticmethod + def __instruction_modify_common( + tenant_id: str, + model_config: dict, + last_run: dict | None, + current: str | None, + error_message: str | None, + instruction: str, + node_type: str, + ideal_output: str | None, + ) -> dict: + LAST_RUN = "{{#last_run#}}" + CURRENT = "{{#current#}}" + ERROR_MESSAGE = "{{#error_message#}}" + injected_instruction = instruction + if LAST_RUN in injected_instruction: + injected_instruction = injected_instruction.replace(LAST_RUN, json.dumps(last_run)) + if CURRENT in injected_instruction: + injected_instruction = injected_instruction.replace(CURRENT, current or "null") + if ERROR_MESSAGE in injected_instruction: + injected_instruction = injected_instruction.replace(ERROR_MESSAGE, error_message or "null") + model_instance = ModelManager().get_model_instance( + tenant_id=tenant_id, + model_type=ModelType.LLM, + provider=model_config.get("provider", ""), + model=model_config.get("name", ""), + ) + match node_type: + case "llm" | "agent": + system_prompt = LLM_MODIFY_PROMPT_SYSTEM + case "code": + system_prompt = LLM_MODIFY_CODE_SYSTEM + case _: + system_prompt = LLM_MODIFY_PROMPT_SYSTEM + prompt_messages = [ + SystemPromptMessage(content=system_prompt), + UserPromptMessage( + content=json.dumps( + { + "current": current, + "last_run": last_run, + "instruction": injected_instruction, + "ideal_output": ideal_output, + } + ) + ), + ] + model_parameters = {"temperature": 0.4} + + try: + response = cast( + LLMResult, + model_instance.invoke_llm( + prompt_messages=list(prompt_messages), model_parameters=model_parameters, stream=False + ), + ) + + generated_raw = cast(str, response.message.content) + first_brace = generated_raw.find("{") + last_brace = generated_raw.rfind("}") + return {**json.loads(generated_raw[first_brace : last_brace + 1])} + + except InvokeError as e: + error = str(e) + return {"error": f"Failed to generate code. Error: {error}"} + except Exception as e: + logging.exception("Failed to invoke LLM model, model: " + json.dumps(model_config.get("name")), exc_info=e) + return {"error": f"An unexpected error occurred: {str(e)}"} diff --git a/api/core/llm_generator/prompts.py b/api/core/llm_generator/prompts.py index ef81e38dc5..9268347526 100644 --- a/api/core/llm_generator/prompts.py +++ b/api/core/llm_generator/prompts.py @@ -309,3 +309,116 @@ eg: Here is the JSON schema: {{schema}} """ # noqa: E501 + +LLM_MODIFY_PROMPT_SYSTEM = """ +Both your input and output should be in JSON format. + +! Below is the schema for input content ! +{ + "type": "object", + "description": "The user is trying to process some content with a prompt, but the output is not as expected. They hope to achieve their goal by modifying the prompt.", + "properties": { + "current": { + "type": "string", + "description": "The prompt before modification, where placeholders {{}} will be replaced with actual values for the large language model. The content in the placeholders should not be changed." + }, + "last_run": { + "type": "object", + "description": "The output result from the large language model after receiving the prompt.", + }, + "instruction": { + "type": "string", + "description": "User's instruction to edit the current prompt" + }, + "ideal_output": { + "type": "string", + "description": "The ideal output that the user expects from the large language model after modifying the prompt. You should compare the last output with the ideal output and make changes to the prompt to achieve the goal." + } + } +} +! Above is the schema for input content ! + +! Below is the schema for output content ! +{ + "type": "object", + "description": "Your feedback to the user after they provide modification suggestions.", + "properties": { + "modified": { + "type": "string", + "description": "Your modified prompt. You should change the original prompt as little as possible to achieve the goal. Keep the language of prompt if not asked to change" + }, + "message": { + "type": "string", + "description": "Your feedback to the user, in the user's language, explaining what you did and your thought process in text, providing sufficient emotional value to the user." + } + }, + "required": [ + "modified", + "message" + ] +} +! Above is the schema for output content ! + +Your output must strictly follow the schema format, do not output any content outside of the JSON body. +""" # noqa: E501 + +LLM_MODIFY_CODE_SYSTEM = """ +Both your input and output should be in JSON format. + +! Below is the schema for input content ! +{ + "type": "object", + "description": "The user is trying to process some data with a code snippet, but the result is not as expected. They hope to achieve their goal by modifying the code.", + "properties": { + "current": { + "type": "string", + "description": "The code before modification." + }, + "last_run": { + "type": "object", + "description": "The result of the code.", + }, + "message": { + "type": "string", + "description": "User's instruction to edit the current code" + } + } +} +! Above is the schema for input content ! + +! Below is the schema for output content ! +{ + "type": "object", + "description": "Your feedback to the user after they provide modification suggestions.", + "properties": { + "modified": { + "type": "string", + "description": "Your modified code. You should change the original code as little as possible to achieve the goal. Keep the programming language of code if not asked to change" + }, + "message": { + "type": "string", + "description": "Your feedback to the user, in the user's language, explaining what you did and your thought process in text, providing sufficient emotional value to the user." + } + }, + "required": [ + "modified", + "message" + ] +} +! Above is the schema for output content ! + +When you are modifying the code, you should remember: +- Do not use print, this not work in dify sandbox. +- Do not try dangerous call like deleting files. It's PROHIBITED. +- Do not use any library that is not built-in in with Python. +- Get inputs from the parameters of the function and have explicit type annotations. +- Write proper imports at the top of the code. +- Use return statement to return the result. +- You should return a `dict`. If you need to return a `result: str`, you should `return {"result": result}`. +Your output must strictly follow the schema format, do not output any content outside of the JSON body. +""" # noqa: E501 + +INSTRUCTION_GENERATE_TEMPLATE_PROMPT = """The output of this prompt is not as expected: {{#last_run#}}. +You should edit the prompt according to the IDEAL OUTPUT.""" + +INSTRUCTION_GENERATE_TEMPLATE_CODE = """Please fix the errors in the {{#error_message#}}.""" diff --git a/api/core/mcp/auth/auth_flow.py b/api/core/mcp/auth/auth_flow.py index bcb31a816f..eb783297c3 100644 --- a/api/core/mcp/auth/auth_flow.py +++ b/api/core/mcp/auth/auth_flow.py @@ -5,9 +5,9 @@ import os import secrets import urllib.parse from typing import Optional -from urllib.parse import urljoin +from urllib.parse import urljoin, urlparse -import requests +import httpx from pydantic import BaseModel, ValidationError from core.mcp.auth.auth_provider import OAuthClientProvider @@ -99,24 +99,52 @@ def handle_callback(state_key: str, authorization_code: str) -> OAuthCallbackSta return full_state_data +def check_support_resource_discovery(server_url: str) -> tuple[bool, str]: + """Check if the server supports OAuth 2.0 Resource Discovery.""" + b_scheme, b_netloc, b_path, b_params, b_query, b_fragment = urlparse(server_url, "", True) + url_for_resource_discovery = f"{b_scheme}://{b_netloc}/.well-known/oauth-protected-resource{b_path}" + if b_query: + url_for_resource_discovery += f"?{b_query}" + if b_fragment: + url_for_resource_discovery += f"#{b_fragment}" + try: + headers = {"MCP-Protocol-Version": LATEST_PROTOCOL_VERSION, "User-Agent": "Dify"} + response = httpx.get(url_for_resource_discovery, headers=headers) + if 200 <= response.status_code < 300: + body = response.json() + if "authorization_server_url" in body: + return True, body["authorization_server_url"][0] + else: + return False, "" + return False, "" + except httpx.RequestError as e: + # Not support resource discovery, fall back to well-known OAuth metadata + return False, "" + + def discover_oauth_metadata(server_url: str, protocol_version: Optional[str] = None) -> Optional[OAuthMetadata]: """Looks up RFC 8414 OAuth 2.0 Authorization Server Metadata.""" - url = urljoin(server_url, "/.well-known/oauth-authorization-server") + # First check if the server supports OAuth 2.0 Resource Discovery + support_resource_discovery, oauth_discovery_url = check_support_resource_discovery(server_url) + if support_resource_discovery: + url = oauth_discovery_url + else: + url = urljoin(server_url, "/.well-known/oauth-authorization-server") try: headers = {"MCP-Protocol-Version": protocol_version or LATEST_PROTOCOL_VERSION} - response = requests.get(url, headers=headers) + response = httpx.get(url, headers=headers) if response.status_code == 404: return None - if not response.ok: + if not response.is_success: raise ValueError(f"HTTP {response.status_code} trying to load well-known OAuth metadata") return OAuthMetadata.model_validate(response.json()) - except requests.RequestException as e: - if isinstance(e, requests.ConnectionError): - response = requests.get(url) + except httpx.RequestError as e: + if isinstance(e, httpx.ConnectError): + response = httpx.get(url) if response.status_code == 404: return None - if not response.ok: + if not response.is_success: raise ValueError(f"HTTP {response.status_code} trying to load well-known OAuth metadata") return OAuthMetadata.model_validate(response.json()) raise @@ -206,8 +234,8 @@ def exchange_authorization( if client_information.client_secret: params["client_secret"] = client_information.client_secret - response = requests.post(token_url, data=params) - if not response.ok: + response = httpx.post(token_url, data=params) + if not response.is_success: raise ValueError(f"Token exchange failed: HTTP {response.status_code}") return OAuthTokens.model_validate(response.json()) @@ -237,8 +265,8 @@ def refresh_authorization( if client_information.client_secret: params["client_secret"] = client_information.client_secret - response = requests.post(token_url, data=params) - if not response.ok: + response = httpx.post(token_url, data=params) + if not response.is_success: raise ValueError(f"Token refresh failed: HTTP {response.status_code}") return OAuthTokens.model_validate(response.json()) @@ -256,12 +284,12 @@ def register_client( else: registration_url = urljoin(server_url, "/register") - response = requests.post( + response = httpx.post( registration_url, json=client_metadata.model_dump(), headers={"Content-Type": "application/json"}, ) - if not response.ok: + if not response.is_success: response.raise_for_status() return OAuthClientInformationFull.model_validate(response.json()) @@ -283,7 +311,7 @@ def auth( raise ValueError("Existing OAuth client information is required when exchanging an authorization code") try: full_information = register_client(server_url, metadata, provider.client_metadata) - except requests.RequestException as e: + except httpx.RequestError as e: raise ValueError(f"Could not register OAuth client: {e}") provider.save_client_information(full_information) client_information = full_information diff --git a/api/core/mcp/auth/auth_provider.py b/api/core/mcp/auth/auth_provider.py index 00d5a25956..bad99fc092 100644 --- a/api/core/mcp/auth/auth_provider.py +++ b/api/core/mcp/auth/auth_provider.py @@ -10,8 +10,6 @@ from core.mcp.types import ( from models.tools import MCPToolProvider from services.tools.mcp_tools_manage_service import MCPToolManageService -LATEST_PROTOCOL_VERSION = "1.0" - class OAuthClientProvider: mcp_provider: MCPToolProvider diff --git a/api/core/mcp/client/sse_client.py b/api/core/mcp/client/sse_client.py index 2d3a3f5344..cc38954eca 100644 --- a/api/core/mcp/client/sse_client.py +++ b/api/core/mcp/client/sse_client.py @@ -7,6 +7,7 @@ from typing import Any, TypeAlias, final from urllib.parse import urljoin, urlparse import httpx +from httpx_sse import EventSource, ServerSentEvent from sseclient import SSEClient from core.mcp import types @@ -37,11 +38,6 @@ WriteQueue: TypeAlias = queue.Queue[SessionMessage | Exception | None] StatusQueue: TypeAlias = queue.Queue[_StatusReady | _StatusError] -def remove_request_params(url: str) -> str: - """Remove request parameters from URL, keeping only the path.""" - return urljoin(url, urlparse(url).path) - - class SSETransport: """SSE client transport implementation.""" @@ -114,7 +110,7 @@ class SSETransport: logger.exception("Error parsing server message") read_queue.put(exc) - def _handle_sse_event(self, sse, read_queue: ReadQueue, status_queue: StatusQueue) -> None: + def _handle_sse_event(self, sse: ServerSentEvent, read_queue: ReadQueue, status_queue: StatusQueue) -> None: """Handle a single SSE event. Args: @@ -130,7 +126,7 @@ class SSETransport: case _: logger.warning("Unknown SSE event: %s", sse.event) - def sse_reader(self, event_source, read_queue: ReadQueue, status_queue: StatusQueue) -> None: + def sse_reader(self, event_source: EventSource, read_queue: ReadQueue, status_queue: StatusQueue) -> None: """Read and process SSE events. Args: @@ -225,7 +221,7 @@ class SSETransport: self, executor: ThreadPoolExecutor, client: httpx.Client, - event_source, + event_source: EventSource, ) -> tuple[ReadQueue, WriteQueue]: """Establish connection and start worker threads. diff --git a/api/core/mcp/server/streamable_http.py b/api/core/mcp/server/streamable_http.py index 496b5432a0..efe91bbff4 100644 --- a/api/core/mcp/server/streamable_http.py +++ b/api/core/mcp/server/streamable_http.py @@ -16,13 +16,14 @@ from extensions.ext_database import db from models.model import App, AppMCPServer, AppMode, EndUser from services.app_generate_service import AppGenerateService -""" -Apply to MCP HTTP streamable server with stateless http -""" logger = logging.getLogger(__name__) class MCPServerStreamableHTTPRequestHandler: + """ + Apply to MCP HTTP streamable server with stateless http + """ + def __init__( self, app: App, request: types.ClientRequest | types.ClientNotification, user_input_form: list[VariableEntity] ): diff --git a/api/core/mcp/utils.py b/api/core/mcp/utils.py index a54badcd4c..80912bc4c1 100644 --- a/api/core/mcp/utils.py +++ b/api/core/mcp/utils.py @@ -1,6 +1,10 @@ import json +from collections.abc import Generator +from contextlib import AbstractContextManager import httpx +import httpx_sse +from httpx_sse import connect_sse from configs import dify_config from core.mcp.types import ErrorData, JSONRPCError @@ -55,20 +59,42 @@ def create_ssrf_proxy_mcp_http_client( ) -def ssrf_proxy_sse_connect(url, **kwargs): +def ssrf_proxy_sse_connect(url: str, **kwargs) -> AbstractContextManager[httpx_sse.EventSource]: """Connect to SSE endpoint with SSRF proxy protection. This function creates an SSE connection using the configured proxy settings - to prevent SSRF attacks when connecting to external endpoints. + to prevent SSRF attacks when connecting to external endpoints. It returns + a context manager that yields an EventSource object for SSE streaming. + + The function handles HTTP client creation and cleanup automatically, but + also accepts a pre-configured client via kwargs. Args: - url: The SSE endpoint URL - **kwargs: Additional arguments passed to the SSE connection + url (str): The SSE endpoint URL to connect to + **kwargs: Additional arguments passed to the SSE connection, including: + - client (httpx.Client, optional): Pre-configured HTTP client. + If not provided, one will be created with SSRF protection. + - method (str, optional): HTTP method to use, defaults to "GET" + - headers (dict, optional): HTTP headers to include in the request + - timeout (httpx.Timeout, optional): Timeout configuration for the connection Returns: - EventSource object for SSE streaming + AbstractContextManager[httpx_sse.EventSource]: A context manager that yields an EventSource + object for SSE streaming. The EventSource provides access to server-sent events. + + Example: + ```python + with ssrf_proxy_sse_connect(url, headers=headers) as event_source: + for sse in event_source.iter_sse(): + print(sse.event, sse.data) + ``` + + Note: + If a client is not provided in kwargs, one will be automatically created + with SSRF protection based on the application's configuration. If an + exception occurs during connection, any automatically created client + will be cleaned up automatically. """ - from httpx_sse import connect_sse # Extract client if provided, otherwise create one client = kwargs.pop("client", None) @@ -101,7 +127,9 @@ def ssrf_proxy_sse_connect(url, **kwargs): raise -def create_mcp_error_response(request_id: int | str | None, code: int, message: str, data=None): +def create_mcp_error_response( + request_id: int | str | None, code: int, message: str, data=None +) -> Generator[bytes, None, None]: """Create MCP error response""" error_data = ErrorData(code=code, message=message, data=data) json_response = JSONRPCError( diff --git a/api/core/model_runtime/README.md b/api/core/model_runtime/README.md index b5de7ad412..3abb3f63ac 100644 --- a/api/core/model_runtime/README.md +++ b/api/core/model_runtime/README.md @@ -30,7 +30,7 @@ This module provides the interface for invoking and authenticating various model In addition, this list also returns configurable parameter information and rules for LLM, as shown below: - ![image-20231210144814617](./docs/en_US/images/index/image-20231210144814617.png) + ![image-20231210144814617](./docs/en_US/images/index/image-20231210144814617.png) These parameters are all defined in the backend, allowing different settings for various parameters supported by different models, as detailed in: [Schema](./docs/en_US/schema.md#ParameterRule). @@ -60,8 +60,6 @@ Model Runtime is divided into three layers: It offers direct invocation of various model types, predefined model configuration information, getting predefined/remote model lists, model credential authentication methods. Different models provide additional special methods, like LLM's pre-computed tokens method, cost information obtaining method, etc., **allowing horizontal expansion** for different models under the same provider (within supported model types). - - ## Next Steps - Add new provider configuration: [Link](./docs/en_US/provider_scale_out.md) diff --git a/api/core/model_runtime/README_CN.md b/api/core/model_runtime/README_CN.md index 2fc2a60461..19846481e0 100644 --- a/api/core/model_runtime/README_CN.md +++ b/api/core/model_runtime/README_CN.md @@ -20,19 +20,19 @@ ![image-20231210143654461](./docs/zh_Hans/images/index/image-20231210143654461.png) -​ 展示所有已支持的供应商列表，除了返回供应商名称、图标之外，还提供了支持的模型类型列表，预定义模型列表、配置方式以及配置凭据的表单规则等等，规则设计详见：[Schema](./docs/zh_Hans/schema.md)。 +​ 展示所有已支持的供应商列表，除了返回供应商名称、图标之外，还提供了支持的模型类型列表，预定义模型列表、配置方式以及配置凭据的表单规则等等，规则设计详见：[Schema](./docs/zh_Hans/schema.md)。 - 可选择的模型列表展示 ![image-20231210144229650](./docs/zh_Hans/images/index/image-20231210144229650.png) -​ 配置供应商/模型凭据后，可在此下拉（应用编排界面/默认模型）查看可用的 LLM 列表，其中灰色的为未配置凭据供应商的预定义模型列表，方便用户查看已支持的模型。 +​ 配置供应商/模型凭据后，可在此下拉（应用编排界面/默认模型）查看可用的 LLM 列表，其中灰色的为未配置凭据供应商的预定义模型列表，方便用户查看已支持的模型。 -​ 除此之外，该列表还返回了 LLM 可配置的参数信息和规则，如下图： +​ 除此之外，该列表还返回了 LLM 可配置的参数信息和规则，如下图： -​ ![image-20231210144814617](./docs/zh_Hans/images/index/image-20231210144814617.png) +​ ![image-20231210144814617](./docs/zh_Hans/images/index/image-20231210144814617.png) -​ 这里的参数均为后端定义，相比之前只有 5 种固定参数，这里可为不同模型设置所支持的各种参数，详见：[Schema](./docs/zh_Hans/schema.md#ParameterRule)。 +​ 这里的参数均为后端定义，相比之前只有 5 种固定参数，这里可为不同模型设置所支持的各种参数，详见：[Schema](./docs/zh_Hans/schema.md#ParameterRule)。 - 供应商/模型凭据鉴权 @@ -40,7 +40,7 @@ ![image-20231210151628992](./docs/zh_Hans/images/index/image-20231210151628992.png) -​ 供应商列表返回了凭据表单的配置信息，可通过 Runtime 提供的接口对凭据进行鉴权，上图 1 为供应商凭据 DEMO，上图 2 为模型凭据 DEMO。 +​ 供应商列表返回了凭据表单的配置信息，可通过 Runtime 提供的接口对凭据进行鉴权，上图 1 为供应商凭据 DEMO，上图 2 为模型凭据 DEMO。 ## 结构 @@ -57,9 +57,10 @@ Model Runtime 分三层： 提供获取当前供应商模型列表、获取模型实例、供应商凭据鉴权、供应商配置规则信息，**可横向扩展**以支持不同的供应商。 对于供应商/模型凭据，有两种情况 + - 如 OpenAI 这类中心化供应商，需要定义如**api_key**这类的鉴权凭据 - 如[**Xinference**](https://github.com/xorbitsai/inference)这类本地部署的供应商，需要定义如**server_url**这类的地址凭据，有时候还需要定义**model_uid**之类的模型类型凭据，就像下面这样，当在供应商层定义了这些凭据后，就可以在前端页面上直接展示，无需修改前端逻辑。 - ![Alt text](docs/zh_Hans/images/index/image.png) + ![Alt text](docs/zh_Hans/images/index/image.png) 当配置好凭据后，就可以通过 DifyRuntime 的外部接口直接获取到对应供应商所需要的**Schema**（凭据表单规则），从而在可以在不修改前端逻辑的情况下，提供新的供应商/模型的支持。 @@ -76,14 +77,17 @@ Model Runtime 分三层： ## 下一步 ### [增加新的供应商配置 👈🏻](./docs/zh_Hans/provider_scale_out.md) + 当添加后，这里将会出现一个新的供应商 ![Alt text](docs/zh_Hans/images/index/image-1.png) -### [为已存在的供应商新增模型 👈🏻](./docs/zh_Hans/provider_scale_out.md#增加模型) +### [为已存在的供应商新增模型 👈🏻](./docs/zh_Hans/provider_scale_out.md#%E5%A2%9E%E5%8A%A0%E6%A8%A1%E5%9E%8B) + 当添加后，对应供应商的模型列表中将会出现一个新的预定义模型供用户选择，如 GPT-3.5 GPT-4 ChatGLM3-6b 等，而对于支持自定义模型的供应商，则不需要新增模型。 ![Alt text](docs/zh_Hans/images/index/image-2.png) ### [接口的具体实现 👈🏻](./docs/zh_Hans/interfaces.md) + 你可以在这里找到你想要查看的接口的具体实现，以及接口的参数和返回值的具体含义。 diff --git a/api/core/model_runtime/docs/en_US/customizable_model_scale_out.md b/api/core/model_runtime/docs/en_US/customizable_model_scale_out.md index d845c4bd09..245aa4699c 100644 --- a/api/core/model_runtime/docs/en_US/customizable_model_scale_out.md +++ b/api/core/model_runtime/docs/en_US/customizable_model_scale_out.md @@ -56,7 +56,6 @@ provider_credential_schema: credential_form_schemas: ``` - Then, we need to determine what credentials are required to define a model in Xinference. - Since it supports three different types of models, we need to specify the model_type to denote the model type. Here is how we can define it: @@ -191,7 +190,6 @@ def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[Pr """ ``` - Sometimes, you might not want to return 0 directly. In such cases, you can use `self._get_num_tokens_by_gpt2(text: str)` to get pre-computed tokens and ensure environment variable `PLUGIN_BASED_TOKEN_COUNTING_ENABLED` is set to `true`, This method is provided by the `AIModel` base class, and it uses GPT2's Tokenizer for calculation. However, it should be noted that this is only a substitute and may not be fully accurate. - Model Credentials Validation diff --git a/api/core/model_runtime/docs/en_US/interfaces.md b/api/core/model_runtime/docs/en_US/interfaces.md index 158d4b306b..9a8c2ec942 100644 --- a/api/core/model_runtime/docs/en_US/interfaces.md +++ b/api/core/model_runtime/docs/en_US/interfaces.md @@ -35,12 +35,11 @@ All models need to uniformly implement the following 2 methods: Similar to provider credential verification, this step involves verification for an individual model. - ```python def validate_credentials(self, model: str, credentials: dict) -> None: """ Validate model credentials - + :param model: model name :param credentials: model credentials :return: @@ -77,12 +76,12 @@ All models need to uniformly implement the following 2 methods: The key is the error type thrown to the caller The value is the error type thrown by the model, which needs to be converted into a unified error type for the caller. - + :return: Invoke error mapping """ ``` -​ You can refer to OpenAI's `_invoke_error_mapping` for an example. +​ You can refer to OpenAI's `_invoke_error_mapping` for an example. ### LLM @@ -92,7 +91,6 @@ Inherit the `__base.large_language_model.LargeLanguageModel` base class and impl Implement the core method for LLM invocation, which can support both streaming and synchronous returns. - ```python def _invoke(self, model: str, credentials: dict, prompt_messages: list[PromptMessage], model_parameters: dict, @@ -101,7 +99,7 @@ Inherit the `__base.large_language_model.LargeLanguageModel` base class and impl -> Union[LLMResult, Generator]: """ Invoke large language model - + :param model: model name :param credentials: model credentials :param prompt_messages: prompt messages @@ -122,7 +120,7 @@ Inherit the `__base.large_language_model.LargeLanguageModel` base class and impl The parameters of credential information are defined by either the `provider_credential_schema` or `model_credential_schema` in the provider's YAML configuration file. Inputs such as `api_key` are included. - - `prompt_messages` (array[[PromptMessage](#PromptMessage)]) List of prompts + - `prompt_messages` (array\[[PromptMessage](#PromptMessage)\]) List of prompts If the model is of the `Completion` type, the list only needs to include one [UserPromptMessage](#UserPromptMessage) element; @@ -132,7 +130,7 @@ Inherit the `__base.large_language_model.LargeLanguageModel` base class and impl The model parameters are defined by the `parameter_rules` in the model's YAML configuration. - - `tools` (array[[PromptMessageTool](#PromptMessageTool)]) [optional] List of tools, equivalent to the `function` in `function calling`. + - `tools` (array\[[PromptMessageTool](#PromptMessageTool)\]) [optional] List of tools, equivalent to the `function` in `function calling`. That is, the tool list for tool calling. @@ -142,7 +140,7 @@ Inherit the `__base.large_language_model.LargeLanguageModel` base class and impl - `stream` (bool) Whether to output in a streaming manner, default is True - Streaming output returns Generator[[LLMResultChunk](#LLMResultChunk)], non-streaming output returns [LLMResult](#LLMResult). + Streaming output returns Generator\[[LLMResultChunk](#LLMResultChunk)\], non-streaming output returns [LLMResult](#LLMResult). - `user` (string) [optional] Unique identifier of the user @@ -150,7 +148,7 @@ Inherit the `__base.large_language_model.LargeLanguageModel` base class and impl - Returns - Streaming output returns Generator[[LLMResultChunk](#LLMResultChunk)], non-streaming output returns [LLMResult](#LLMResult). + Streaming output returns Generator\[[LLMResultChunk](#LLMResultChunk)\], non-streaming output returns [LLMResult](#LLMResult). - Pre-calculating Input Tokens @@ -187,7 +185,6 @@ Inherit the `__base.large_language_model.LargeLanguageModel` base class and impl When the provider supports adding custom LLMs, this method can be implemented to allow custom models to fetch model schema. The default return null. - ### TextEmbedding Inherit the `__base.text_embedding_model.TextEmbeddingModel` base class and implement the following interfaces: @@ -200,7 +197,7 @@ Inherit the `__base.text_embedding_model.TextEmbeddingModel` base class and impl -> TextEmbeddingResult: """ Invoke large language model - + :param model: model name :param credentials: model credentials :param texts: texts to embed @@ -256,7 +253,7 @@ Inherit the `__base.rerank_model.RerankModel` base class and implement the follo -> RerankResult: """ Invoke rerank model - + :param model: model name :param credentials: model credentials :param query: search query @@ -302,7 +299,7 @@ Inherit the `__base.speech2text_model.Speech2TextModel` base class and implement def _invoke(self, model: str, credentials: dict, file: IO[bytes], user: Optional[str] = None) -> str: """ Invoke large language model - + :param model: model name :param credentials: model credentials :param file: audio file @@ -339,7 +336,7 @@ Inherit the `__base.text2speech_model.Text2SpeechModel` base class and implement def _invoke(self, model: str, credentials: dict, content_text: str, streaming: bool, user: Optional[str] = None): """ Invoke large language model - + :param model: model name :param credentials: model credentials :param content_text: text content to be translated @@ -381,7 +378,7 @@ Inherit the `__base.moderation_model.ModerationModel` base class and implement t -> bool: """ Invoke large language model - + :param model: model name :param credentials: model credentials :param text: text to moderate @@ -408,11 +405,9 @@ Inherit the `__base.moderation_model.ModerationModel` base class and implement t False indicates that the input text is safe, True indicates otherwise. - - ## Entities -### PromptMessageRole +### PromptMessageRole Message role @@ -583,7 +578,7 @@ class PromptMessageTool(BaseModel): parameters: dict ``` ---- +______________________________________________________________________ ### LLMResult @@ -650,7 +645,7 @@ class LLMUsage(ModelUsage): latency: float # Request latency (s) ``` ---- +______________________________________________________________________ ### TextEmbeddingResult @@ -680,7 +675,7 @@ class EmbeddingUsage(ModelUsage): latency: float # Request latency (s) ``` ---- +______________________________________________________________________ ### RerankResult diff --git a/api/core/model_runtime/docs/en_US/predefined_model_scale_out.md b/api/core/model_runtime/docs/en_US/predefined_model_scale_out.md index a770ed157b..97968e9988 100644 --- a/api/core/model_runtime/docs/en_US/predefined_model_scale_out.md +++ b/api/core/model_runtime/docs/en_US/predefined_model_scale_out.md @@ -153,8 +153,11 @@ Runtime Errors: - `InvokeConnectionError` Connection error - `InvokeServerUnavailableError` Service provider unavailable + - `InvokeRateLimitError` Rate limit reached + - `InvokeAuthorizationError` Authorization failed + - `InvokeBadRequestError` Parameter error ```python diff --git a/api/core/model_runtime/docs/en_US/provider_scale_out.md b/api/core/model_runtime/docs/en_US/provider_scale_out.md index 07be5811d3..c38c7c0f0c 100644 --- a/api/core/model_runtime/docs/en_US/provider_scale_out.md +++ b/api/core/model_runtime/docs/en_US/provider_scale_out.md @@ -63,6 +63,7 @@ You can also refer to the YAML configuration information under other provider di ### Implementing Provider Code Providers need to inherit the `__base.model_provider.ModelProvider` base class and implement the `validate_provider_credentials` method for unified provider credential verification. For reference, see [AnthropicProvider](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/anthropic.py). + > If the provider is the type of `customizable-model`, there is no need to implement the `validate_provider_credentials` method. ```python @@ -80,7 +81,7 @@ def validate_provider_credentials(self, credentials: dict) -> None: Of course, you can also preliminarily reserve the implementation of `validate_provider_credentials` and directly reuse it after the model credential verification method is implemented. ---- +______________________________________________________________________ ### Adding Models @@ -166,7 +167,7 @@ In `llm.py`, create an Anthropic LLM class, which we name `AnthropicLargeLanguag -> Union[LLMResult, Generator]: """ Invoke large language model - + :param model: model name :param credentials: model credentials :param prompt_messages: prompt messages @@ -205,7 +206,7 @@ In `llm.py`, create an Anthropic LLM class, which we name `AnthropicLargeLanguag def validate_credentials(self, model: str, credentials: dict) -> None: """ Validate model credentials - + :param model: model name :param credentials: model credentials :return: @@ -232,7 +233,7 @@ In `llm.py`, create an Anthropic LLM class, which we name `AnthropicLargeLanguag The key is the error type thrown to the caller The value is the error type thrown by the model, which needs to be converted into a unified error type for the caller. - + :return: Invoke error mapping """ ``` diff --git a/api/core/model_runtime/docs/en_US/schema.md b/api/core/model_runtime/docs/en_US/schema.md index f819a4dbdc..1cea4127f4 100644 --- a/api/core/model_runtime/docs/en_US/schema.md +++ b/api/core/model_runtime/docs/en_US/schema.md @@ -28,8 +28,8 @@ - `url` (object) help link, i18n - `zh_Hans` (string) [optional] Chinese link - `en_US` (string) English link -- `supported_model_types` (array[[ModelType](#ModelType)]) Supported model types -- `configurate_methods` (array[[ConfigurateMethod](#ConfigurateMethod)]) Configuration methods +- `supported_model_types` (array\[[ModelType](#ModelType)\]) Supported model types +- `configurate_methods` (array\[[ConfigurateMethod](#ConfigurateMethod)\]) Configuration methods - `provider_credential_schema` ([ProviderCredentialSchema](#ProviderCredentialSchema)) Provider credential specification - `model_credential_schema` ([ModelCredentialSchema](#ModelCredentialSchema)) Model credential specification @@ -40,23 +40,23 @@ - `zh_Hans` (string) [optional] Chinese label name - `en_US` (string) English label name - `model_type` ([ModelType](#ModelType)) Model type -- `features` (array[[ModelFeature](#ModelFeature)]) [optional] Supported feature list +- `features` (array\[[ModelFeature](#ModelFeature)\]) [optional] Supported feature list - `model_properties` (object) Model properties - `mode` ([LLMMode](#LLMMode)) Mode (available for model type `llm`) - `context_size` (int) Context size (available for model types `llm`, `text-embedding`) - `max_chunks` (int) Maximum number of chunks (available for model types `text-embedding`, `moderation`) - `file_upload_limit` (int) Maximum file upload limit, in MB (available for model type `speech2text`) - `supported_file_extensions` (string) Supported file extension formats, e.g., mp3, mp4 (available for model type `speech2text`) - - `default_voice` (string) default voice, e.g.：alloy,echo,fable,onyx,nova,shimmer（available for model type `tts`） - - `voices` (list) List of available voice.（available for model type `tts`） - - `mode` (string) voice model.（available for model type `tts`） - - `name` (string) voice model display name.（available for model type `tts`） - - `language` (string) the voice model supports languages.（available for model type `tts`） - - `word_limit` (int) Single conversion word limit, paragraph-wise by default（available for model type `tts`） - - `audio_type` (string) Support audio file extension format, e.g.：mp3,wav（available for model type `tts`） - - `max_workers` (int) Number of concurrent workers supporting text and audio conversion（available for model type`tts`） + - `default_voice` (string) default voice, e.g.：alloy,echo,fable,onyx,nova,shimmer（available for model type `tts`） + - `voices` (list) List of available voice.（available for model type `tts`） + - `mode` (string) voice model.（available for model type `tts`） + - `name` (string) voice model display name.（available for model type `tts`） + - `language` (string) the voice model supports languages.（available for model type `tts`） + - `word_limit` (int) Single conversion word limit, paragraph-wise by default（available for model type `tts`） + - `audio_type` (string) Support audio file extension format, e.g.：mp3,wav（available for model type `tts`） + - `max_workers` (int) Number of concurrent workers supporting text and audio conversion（available for model type`tts`） - `max_characters_per_chunk` (int) Maximum characters per chunk (available for model type `moderation`) -- `parameter_rules` (array[[ParameterRule](#ParameterRule)]) [optional] Model invocation parameter rules +- `parameter_rules` (array\[[ParameterRule](#ParameterRule)\]) [optional] Model invocation parameter rules - `pricing` ([PriceConfig](#PriceConfig)) [optional] Pricing information - `deprecated` (bool) Whether deprecated. If deprecated, the model will no longer be displayed in the list, but those already configured can continue to be used. Default False. @@ -74,6 +74,7 @@ - `predefined-model` Predefined model Indicates that users can use the predefined models under the provider by configuring the unified provider credentials. + - `customizable-model` Customizable model Users need to add credential configuration for each model. @@ -103,6 +104,7 @@ ### ParameterRule - `name` (string) Actual model invocation parameter name + - `use_template` (string) [optional] Using template By default, 5 variable content configuration templates are preset: @@ -112,7 +114,7 @@ - `frequency_penalty` - `presence_penalty` - `max_tokens` - + In use_template, you can directly set the template variable name, which will use the default configuration in entities.defaults.PARAMETER_RULE_TEMPLATE No need to set any parameters other than `name` and `use_template`. If additional configuration parameters are set, they will override the default configuration. Refer to `openai/llm/gpt-3.5-turbo.yaml`. @@ -155,7 +157,7 @@ ### ProviderCredentialSchema -- `credential_form_schemas` (array[[CredentialFormSchema](#CredentialFormSchema)]) Credential form standard +- `credential_form_schemas` (array\[[CredentialFormSchema](#CredentialFormSchema)\]) Credential form standard ### ModelCredentialSchema @@ -166,7 +168,7 @@ - `placeholder` (object) Model prompt content - `en_US`(string) English - `zh_Hans`(string) [optional] Chinese -- `credential_form_schemas` (array[[CredentialFormSchema](#CredentialFormSchema)]) Credential form standard +- `credential_form_schemas` (array\[[CredentialFormSchema](#CredentialFormSchema)\]) Credential form standard ### CredentialFormSchema @@ -177,12 +179,12 @@ - `type` ([FormType](#FormType)) Form item type - `required` (bool) Whether required - `default`(string) Default value -- `options` (array[[FormOption](#FormOption)]) Specific property of form items of type `select` or `radio`, defining dropdown content +- `options` (array\[[FormOption](#FormOption)\]) Specific property of form items of type `select` or `radio`, defining dropdown content - `placeholder`(object) Specific property of form items of type `text-input`, placeholder content - `en_US`(string) English - `zh_Hans` (string) [optional] Chinese - `max_length` (int) Specific property of form items of type `text-input`, defining maximum input length, 0 for no limit. -- `show_on` (array[[FormShowOnObject](#FormShowOnObject)]) Displayed when other form item values meet certain conditions, displayed always if empty. +- `show_on` (array\[[FormShowOnObject](#FormShowOnObject)\]) Displayed when other form item values meet certain conditions, displayed always if empty. ### FormType @@ -198,7 +200,7 @@ - `en_US`(string) English - `zh_Hans`(string) [optional] Chinese - `value` (string) Dropdown option value -- `show_on` (array[[FormShowOnObject](#FormShowOnObject)]) Displayed when other form item values meet certain conditions, displayed always if empty. +- `show_on` (array\[[FormShowOnObject](#FormShowOnObject)\]) Displayed when other form item values meet certain conditions, displayed always if empty. ### FormShowOnObject diff --git a/api/core/model_runtime/docs/zh_Hans/customizable_model_scale_out.md b/api/core/model_runtime/docs/zh_Hans/customizable_model_scale_out.md index 7d30655469..825f9349d7 100644 --- a/api/core/model_runtime/docs/zh_Hans/customizable_model_scale_out.md +++ b/api/core/model_runtime/docs/zh_Hans/customizable_model_scale_out.md @@ -10,7 +10,6 @@ ![Alt text](images/index/image-3.png) - 在前文中，我们已经知道了供应商无需实现`validate_provider_credential`，Runtime 会自行根据用户在此选择的模型类型和模型名称调用对应的模型层的`validate_credentials`来进行验证。 ### 编写供应商 yaml @@ -55,6 +54,7 @@ provider_credential_schema: 随后，我们需要思考在 Xinference 中定义一个模型需要哪些凭据 - 它支持三种不同的模型，因此，我们需要有`model_type`来指定这个模型的类型，它有三种类型，所以我们这么编写 + ```yaml provider_credential_schema: credential_form_schemas: @@ -76,7 +76,9 @@ provider_credential_schema: label: en_US: Rerank ``` + - 每一个模型都有自己的名称`model_name`，因此需要在这里定义 + ```yaml - variable: model_name type: text-input @@ -88,7 +90,9 @@ provider_credential_schema: zh_Hans: 填写模型名称 en_US: Input model name ``` + - 填写 Xinference 本地部署的地址 + ```yaml - variable: server_url label: @@ -100,7 +104,9 @@ provider_credential_schema: zh_Hans: 在此输入 Xinference 的服务器地址，如 https://example.com/xxx en_US: Enter the url of your Xinference, for example https://example.com/xxx ``` + - 每个模型都有唯一的 model_uid，因此需要在这里定义 + ```yaml - variable: model_uid label: @@ -112,6 +118,7 @@ provider_credential_schema: zh_Hans: 在此输入您的 Model UID en_US: Enter the model uid ``` + 现在，我们就完成了供应商的基础定义。 ### 编写模型代码 @@ -132,7 +139,7 @@ provider_credential_schema: -> Union[LLMResult, Generator]: """ Invoke large language model - + :param model: model name :param credentials: model credentials :param prompt_messages: prompt messages @@ -189,7 +196,7 @@ provider_credential_schema: def validate_credentials(self, model: str, credentials: dict) -> None: """ Validate model credentials - + :param model: model name :param credentials: model credentials :return: @@ -197,78 +204,78 @@ provider_credential_schema: ``` - 模型参数 Schema - + 与自定义类型不同，由于没有在 yaml 文件中定义一个模型支持哪些参数，因此，我们需要动态时间模型参数的 Schema。 - + 如 Xinference 支持`max_tokens` `temperature` `top_p` 这三个模型参数。 - + 但是有的供应商根据不同的模型支持不同的参数，如供应商`OpenLLM`支持`top_k`，但是并不是这个供应商提供的所有模型都支持`top_k`，我们这里举例 A 模型支持`top_k`，B 模型不支持`top_k`，那么我们需要在这里动态生成模型参数的 Schema，如下所示： - - ```python - def get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]: - """ - used to define customizable model schema - """ - rules = [ - ParameterRule( - name='temperature', type=ParameterType.FLOAT, - use_template='temperature', - label=I18nObject( - zh_Hans='温度', en_US='Temperature' - ) - ), - ParameterRule( - name='top_p', type=ParameterType.FLOAT, - use_template='top_p', - label=I18nObject( - zh_Hans='Top P', en_US='Top P' - ) - ), - ParameterRule( - name='max_tokens', type=ParameterType.INT, - use_template='max_tokens', - min=1, - default=512, - label=I18nObject( - zh_Hans='最大生成长度', en_US='Max Tokens' - ) - ) - ] - # if model is A, add top_k to rules - if model == 'A': - rules.append( - ParameterRule( - name='top_k', type=ParameterType.INT, - use_template='top_k', - min=1, - default=50, - label=I18nObject( - zh_Hans='Top K', en_US='Top K' - ) - ) - ) + ```python + def get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]: + """ + used to define customizable model schema + """ + rules = [ + ParameterRule( + name='temperature', type=ParameterType.FLOAT, + use_template='temperature', + label=I18nObject( + zh_Hans='温度', en_US='Temperature' + ) + ), + ParameterRule( + name='top_p', type=ParameterType.FLOAT, + use_template='top_p', + label=I18nObject( + zh_Hans='Top P', en_US='Top P' + ) + ), + ParameterRule( + name='max_tokens', type=ParameterType.INT, + use_template='max_tokens', + min=1, + default=512, + label=I18nObject( + zh_Hans='最大生成长度', en_US='Max Tokens' + ) + ) + ] - """ - some NOT IMPORTANT code here - """ + # if model is A, add top_k to rules + if model == 'A': + rules.append( + ParameterRule( + name='top_k', type=ParameterType.INT, + use_template='top_k', + min=1, + default=50, + label=I18nObject( + zh_Hans='Top K', en_US='Top K' + ) + ) + ) - entity = AIModelEntity( - model=model, - label=I18nObject( - en_US=model - ), - fetch_from=FetchFrom.CUSTOMIZABLE_MODEL, - model_type=model_type, - model_properties={ - ModelPropertyKey.MODE: ModelType.LLM, - }, - parameter_rules=rules - ) + """ + some NOT IMPORTANT code here + """ + + entity = AIModelEntity( + model=model, + label=I18nObject( + en_US=model + ), + fetch_from=FetchFrom.CUSTOMIZABLE_MODEL, + model_type=model_type, + model_properties={ + ModelPropertyKey.MODE: ModelType.LLM, + }, + parameter_rules=rules + ) + + return entity + ``` - return entity - ``` - - 调用异常错误映射表 当模型调用异常时需要映射到 Runtime 指定的 `InvokeError` 类型，方便 Dify 针对不同错误做不同后续处理。 @@ -278,7 +285,7 @@ provider_credential_schema: - `InvokeConnectionError` 调用连接错误 - `InvokeServerUnavailableError ` 调用服务方不可用 - `InvokeRateLimitError ` 调用达到限额 - - `InvokeAuthorizationError` 调用鉴权失败 + - `InvokeAuthorizationError` 调用鉴权失败 - `InvokeBadRequestError ` 调用传参有误 ```python @@ -289,7 +296,7 @@ provider_credential_schema: The key is the error type thrown to the caller The value is the error type thrown by the model, which needs to be converted into a unified error type for the caller. - + :return: Invoke error mapping """ ``` diff --git a/api/core/model_runtime/docs/zh_Hans/interfaces.md b/api/core/model_runtime/docs/zh_Hans/interfaces.md index 93a48cafb8..8eeeee9ff9 100644 --- a/api/core/model_runtime/docs/zh_Hans/interfaces.md +++ b/api/core/model_runtime/docs/zh_Hans/interfaces.md @@ -49,7 +49,7 @@ class XinferenceProvider(Provider): def validate_credentials(self, model: str, credentials: dict) -> None: """ Validate model credentials - + :param model: model name :param credentials: model credentials :return: @@ -75,7 +75,7 @@ class XinferenceProvider(Provider): - `InvokeConnectionError` 调用连接错误 - `InvokeServerUnavailableError ` 调用服务方不可用 - `InvokeRateLimitError ` 调用达到限额 - - `InvokeAuthorizationError` 调用鉴权失败 + - `InvokeAuthorizationError` 调用鉴权失败 - `InvokeBadRequestError ` 调用传参有误 ```python @@ -86,36 +86,36 @@ class XinferenceProvider(Provider): The key is the error type thrown to the caller The value is the error type thrown by the model, which needs to be converted into a unified error type for the caller. - + :return: Invoke error mapping """ ``` 也可以直接抛出对应 Errors，并做如下定义，这样在之后的调用中可以直接抛出`InvokeConnectionError`等异常。 - - ```python - @property - def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]: - return { - InvokeConnectionError: [ - InvokeConnectionError - ], - InvokeServerUnavailableError: [ - InvokeServerUnavailableError - ], - InvokeRateLimitError: [ - InvokeRateLimitError - ], - InvokeAuthorizationError: [ - InvokeAuthorizationError - ], - InvokeBadRequestError: [ - InvokeBadRequestError - ], - } - ``` -​ 可参考 OpenAI `_invoke_error_mapping`。 + ```python + @property + def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]: + return { + InvokeConnectionError: [ + InvokeConnectionError + ], + InvokeServerUnavailableError: [ + InvokeServerUnavailableError + ], + InvokeRateLimitError: [ + InvokeRateLimitError + ], + InvokeAuthorizationError: [ + InvokeAuthorizationError + ], + InvokeBadRequestError: [ + InvokeBadRequestError + ], + } + ``` + +​ 可参考 OpenAI `_invoke_error_mapping`。 ### LLM @@ -133,7 +133,7 @@ class XinferenceProvider(Provider): -> Union[LLMResult, Generator]: """ Invoke large language model - + :param model: model name :param credentials: model credentials :param prompt_messages: prompt messages @@ -151,38 +151,38 @@ class XinferenceProvider(Provider): - `model` (string) 模型名称 - `credentials` (object) 凭据信息 - + 凭据信息的参数由供应商 YAML 配置文件的 `provider_credential_schema` 或 `model_credential_schema` 定义，传入如：`api_key` 等。 - - `prompt_messages` (array[[PromptMessage](#PromptMessage)]) Prompt 列表 - + - `prompt_messages` (array\[[PromptMessage](#PromptMessage)\]) Prompt 列表 + 若模型为 `Completion` 类型，则列表只需要传入一个 [UserPromptMessage](#UserPromptMessage) 元素即可； - + 若模型为 `Chat` 类型，需要根据消息不同传入 [SystemPromptMessage](#SystemPromptMessage), [UserPromptMessage](#UserPromptMessage), [AssistantPromptMessage](#AssistantPromptMessage), [ToolPromptMessage](#ToolPromptMessage) 元素列表 - `model_parameters` (object) 模型参数 - + 模型参数由模型 YAML 配置的 `parameter_rules` 定义。 - - `tools` (array[[PromptMessageTool](#PromptMessageTool)]) [optional] 工具列表，等同于 `function calling` 中的 `function`。 - + - `tools` (array\[[PromptMessageTool](#PromptMessageTool)\]) [optional] 工具列表，等同于 `function calling` 中的 `function`。 + 即传入 tool calling 的工具列表。 - `stop` (array[string]) [optional] 停止序列 - + 模型返回将在停止序列定义的字符串之前停止输出。 - `stream` (bool) 是否流式输出，默认 True - - 流式输出返回 Generator[[LLMResultChunk](#LLMResultChunk)]，非流式输出返回 [LLMResult](#LLMResult)。 + + 流式输出返回 Generator\[[LLMResultChunk](#LLMResultChunk)\]，非流式输出返回 [LLMResult](#LLMResult)。 - `user` (string) [optional] 用户的唯一标识符 - + 可以帮助供应商监控和检测滥用行为。 - 返回 - 流式输出返回 Generator[[LLMResultChunk](#LLMResultChunk)]，非流式输出返回 [LLMResult](#LLMResult)。 + 流式输出返回 Generator\[[LLMResultChunk](#LLMResultChunk)\]，非流式输出返回 [LLMResult](#LLMResult)。 - 预计算输入 tokens @@ -236,7 +236,7 @@ class XinferenceProvider(Provider): -> TextEmbeddingResult: """ Invoke large language model - + :param model: model name :param credentials: model credentials :param texts: texts to embed @@ -294,7 +294,7 @@ class XinferenceProvider(Provider): -> RerankResult: """ Invoke rerank model - + :param model: model name :param credentials: model credentials :param query: search query @@ -342,7 +342,7 @@ class XinferenceProvider(Provider): -> str: """ Invoke large language model - + :param model: model name :param credentials: model credentials :param file: audio file @@ -379,7 +379,7 @@ class XinferenceProvider(Provider): def _invoke(self, model: str, credentials: dict, content_text: str, streaming: bool, user: Optional[str] = None): """ Invoke large language model - + :param model: model name :param credentials: model credentials :param content_text: text content to be translated @@ -421,7 +421,7 @@ class XinferenceProvider(Provider): -> bool: """ Invoke large language model - + :param model: model name :param credentials: model credentials :param text: text to moderate @@ -448,11 +448,9 @@ class XinferenceProvider(Provider): False 代表传入的文本安全，True 则反之。 - - ## 实体 -### PromptMessageRole +### PromptMessageRole 消息角色 @@ -623,7 +621,7 @@ class PromptMessageTool(BaseModel): parameters: dict # 工具参数 dict ``` ---- +______________________________________________________________________ ### LLMResult @@ -690,7 +688,7 @@ class LLMUsage(ModelUsage): latency: float # 请求耗时 (s) ``` ---- +______________________________________________________________________ ### TextEmbeddingResult @@ -720,7 +718,7 @@ class EmbeddingUsage(ModelUsage): latency: float # 请求耗时 (s) ``` ---- +______________________________________________________________________ ### RerankResult diff --git a/api/core/model_runtime/docs/zh_Hans/predefined_model_scale_out.md b/api/core/model_runtime/docs/zh_Hans/predefined_model_scale_out.md index 80e7982e9f..cd4de51ef7 100644 --- a/api/core/model_runtime/docs/zh_Hans/predefined_model_scale_out.md +++ b/api/core/model_runtime/docs/zh_Hans/predefined_model_scale_out.md @@ -62,7 +62,7 @@ pricing: # 价格信息 建议将所有模型配置都准备完毕后再开始模型代码的实现。 -同样，也可以参考 `model_providers` 目录下其他供应商对应模型类型目录下的 YAML 配置信息，完整的 YAML 规则见：[Schema](schema.md#aimodelentity)。 +同样，也可以参考 `model_providers` 目录下其他供应商对应模型类型目录下的 YAML 配置信息，完整的 YAML 规则见：[Schema](schema.md#aimodelentity)。 ### 实现模型调用代码 @@ -82,7 +82,7 @@ pricing: # 价格信息 -> Union[LLMResult, Generator]: """ Invoke large language model - + :param model: model name :param credentials: model credentials :param prompt_messages: prompt messages @@ -137,7 +137,7 @@ pricing: # 价格信息 def validate_credentials(self, model: str, credentials: dict) -> None: """ Validate model credentials - + :param model: model name :param credentials: model credentials :return: @@ -153,7 +153,7 @@ pricing: # 价格信息 - `InvokeConnectionError` 调用连接错误 - `InvokeServerUnavailableError ` 调用服务方不可用 - `InvokeRateLimitError ` 调用达到限额 - - `InvokeAuthorizationError` 调用鉴权失败 + - `InvokeAuthorizationError` 调用鉴权失败 - `InvokeBadRequestError ` 调用传参有误 ```python @@ -164,7 +164,7 @@ pricing: # 价格信息 The key is the error type thrown to the caller The value is the error type thrown by the model, which needs to be converted into a unified error type for the caller. - + :return: Invoke error mapping """ ``` diff --git a/api/core/model_runtime/docs/zh_Hans/provider_scale_out.md b/api/core/model_runtime/docs/zh_Hans/provider_scale_out.md index 2048b506ac..de48b0d11a 100644 --- a/api/core/model_runtime/docs/zh_Hans/provider_scale_out.md +++ b/api/core/model_runtime/docs/zh_Hans/provider_scale_out.md @@ -5,7 +5,7 @@ - `predefined-model ` 预定义模型 表示用户只需要配置统一的供应商凭据即可使用供应商下的预定义模型。 - + - `customizable-model` 自定义模型 用户需要新增每个模型的凭据配置，如 Xinference，它同时支持 LLM 和 Text Embedding，但是每个模型都有唯一的**model_uid**，如果想要将两者同时接入，就需要为每个模型配置一个**model_uid**。 @@ -23,9 +23,11 @@ ### 介绍 #### 名词解释 - - `module`: 一个`module`即为一个 Python Package，或者通俗一点，称为一个文件夹，里面包含了一个`__init__.py`文件，以及其他的`.py`文件。 + +- `module`: 一个`module`即为一个 Python Package，或者通俗一点，称为一个文件夹，里面包含了一个`__init__.py`文件，以及其他的`.py`文件。 #### 步骤 + 新增一个供应商主要分为几步，这里简单列出，帮助大家有一个大概的认识，具体的步骤会在下面详细介绍。 - 创建供应商 yaml 文件，根据[ProviderSchema](./schema.md#provider)编写 @@ -117,7 +119,7 @@ model_credential_schema: en_US: Enter your API Base ``` -也可以参考 `model_providers` 目录下其他供应商目录下的 YAML 配置信息，完整的 YAML 规则见：[Schema](schema.md#provider)。 +也可以参考 `model_providers` 目录下其他供应商目录下的 YAML 配置信息，完整的 YAML 规则见：[Schema](schema.md#provider)。 #### 实现供应商代码 @@ -155,12 +157,14 @@ def validate_provider_credentials(self, credentials: dict) -> None: #### 增加模型 #### [增加预定义模型 👈🏻](./predefined_model_scale_out.md) + 对于预定义模型，我们可以通过简单定义一个 yaml，并通过实现调用代码来接入。 #### [增加自定义模型 👈🏻](./customizable_model_scale_out.md) + 对于自定义模型，我们只需要实现调用代码即可接入，但是它需要处理的参数可能会更加复杂。 ---- +______________________________________________________________________ ### 测试 diff --git a/api/core/model_runtime/docs/zh_Hans/schema.md b/api/core/model_runtime/docs/zh_Hans/schema.md index 681f49c435..e68cb500e1 100644 --- a/api/core/model_runtime/docs/zh_Hans/schema.md +++ b/api/core/model_runtime/docs/zh_Hans/schema.md @@ -16,9 +16,9 @@ - `zh_Hans` (string) [optional] 中文描述 - `en_US` (string) 英文描述 - `icon_small` (string) [optional] 供应商小 ICON，存储在对应供应商实现目录下的 `_assets` 目录，中英文策略同 `label` - - `zh_Hans` (string) [optional] 中文 ICON + - `zh_Hans` (string) [optional] 中文 ICON - `en_US` (string) 英文 ICON -- `icon_large` (string) [optional] 供应商大 ICON，存储在对应供应商实现目录下的 _assets 目录，中英文策略同 label +- `icon_large` (string) [optional] 供应商大 ICON，存储在对应供应商实现目录下的 \_assets 目录，中英文策略同 label - `zh_Hans `(string) [optional] 中文 ICON - `en_US` (string) 英文 ICON - `background` (string) [optional] 背景颜色色值，例：#FFFFFF，为空则展示前端默认色值。 @@ -29,8 +29,8 @@ - `url` (object) 帮助链接，i18n - `zh_Hans` (string) [optional] 中文链接 - `en_US` (string) 英文链接 -- `supported_model_types` (array[[ModelType](#ModelType)]) 支持的模型类型 -- `configurate_methods` (array[[ConfigurateMethod](#ConfigurateMethod)]) 配置方式 +- `supported_model_types` (array\[[ModelType](#ModelType)\]) 支持的模型类型 +- `configurate_methods` (array\[[ConfigurateMethod](#ConfigurateMethod)\]) 配置方式 - `provider_credential_schema` ([ProviderCredentialSchema](#ProviderCredentialSchema)) 供应商凭据规格 - `model_credential_schema` ([ModelCredentialSchema](#ModelCredentialSchema)) 模型凭据规格 @@ -41,23 +41,23 @@ - `zh_Hans `(string) [optional] 中文标签名 - `en_US` (string) 英文标签名 - `model_type` ([ModelType](#ModelType)) 模型类型 -- `features` (array[[ModelFeature](#ModelFeature)]) [optional] 支持功能列表 +- `features` (array\[[ModelFeature](#ModelFeature)\]) [optional] 支持功能列表 - `model_properties` (object) 模型属性 - `mode` ([LLMMode](#LLMMode)) 模式 (模型类型 `llm` 可用) - `context_size` (int) 上下文大小 (模型类型 `llm` `text-embedding` 可用) - `max_chunks` (int) 最大分块数量 (模型类型 `text-embedding ` `moderation` 可用) - `file_upload_limit` (int) 文件最大上传限制，单位：MB。（模型类型 `speech2text` 可用） - - `supported_file_extensions` (string) 支持文件扩展格式，如：mp3,mp4（模型类型 `speech2text` 可用） - - `default_voice` (string) 缺省音色，必选：alloy,echo,fable,onyx,nova,shimmer（模型类型 `tts` 可用） - - `voices` (list) 可选音色列表。 - - `mode` (string) 音色模型。（模型类型 `tts` 可用） - - `name` (string) 音色模型显示名称。（模型类型 `tts` 可用） - - `language` (string) 音色模型支持语言。（模型类型 `tts` 可用） - - `word_limit` (int) 单次转换字数限制，默认按段落分段（模型类型 `tts` 可用） - - `audio_type` (string) 支持音频文件扩展格式，如：mp3,wav（模型类型 `tts` 可用） - - `max_workers` (int) 支持文字音频转换并发任务数（模型类型 `tts` 可用） - - `max_characters_per_chunk` (int) 每块最大字符数 (模型类型 `moderation` 可用) -- `parameter_rules` (array[[ParameterRule](#ParameterRule)]) [optional] 模型调用参数规则 + - `supported_file_extensions` (string) 支持文件扩展格式，如：mp3,mp4（模型类型 `speech2text` 可用） + - `default_voice` (string) 缺省音色，必选：alloy,echo,fable,onyx,nova,shimmer（模型类型 `tts` 可用） + - `voices` (list) 可选音色列表。 + - `mode` (string) 音色模型。（模型类型 `tts` 可用） + - `name` (string) 音色模型显示名称。（模型类型 `tts` 可用） + - `language` (string) 音色模型支持语言。（模型类型 `tts` 可用） + - `word_limit` (int) 单次转换字数限制，默认按段落分段（模型类型 `tts` 可用） + - `audio_type` (string) 支持音频文件扩展格式，如：mp3,wav（模型类型 `tts` 可用） + - `max_workers` (int) 支持文字音频转换并发任务数（模型类型 `tts` 可用） + - `max_characters_per_chunk` (int) 每块最大字符数 (模型类型 `moderation` 可用) +- `parameter_rules` (array\[[ParameterRule](#ParameterRule)\]) [optional] 模型调用参数规则 - `pricing` ([PriceConfig](#PriceConfig)) [optional] 价格信息 - `deprecated` (bool) 是否废弃。若废弃，模型列表将不再展示，但已经配置的可以继续使用，默认 False。 @@ -75,6 +75,7 @@ - `predefined-model ` 预定义模型 表示用户只需要配置统一的供应商凭据即可使用供应商下的预定义模型。 + - `customizable-model` 自定义模型 用户需要新增每个模型的凭据配置。 @@ -106,7 +107,7 @@ - `name` (string) 调用模型实际参数名 - `use_template` (string) [optional] 使用模板 - + 默认预置了 5 种变量内容配置模板： - `temperature` @@ -114,7 +115,7 @@ - `frequency_penalty` - `presence_penalty` - `max_tokens` - + 可在 use_template 中直接设置模板变量名，将会使用 entities.defaults.PARAMETER_RULE_TEMPLATE 中的默认配置 不用设置除 `name` 和 `use_template` 之外的所有参数，若设置了额外的配置参数，将覆盖默认配置。 可参考 `openai/llm/gpt-3.5-turbo.yaml`。 @@ -157,7 +158,7 @@ ### ProviderCredentialSchema -- `credential_form_schemas` (array[[CredentialFormSchema](#CredentialFormSchema)]) 凭据表单规范 +- `credential_form_schemas` (array\[[CredentialFormSchema](#CredentialFormSchema)\]) 凭据表单规范 ### ModelCredentialSchema @@ -168,7 +169,7 @@ - `placeholder` (object) 模型提示内容 - `en_US`(string) 英文 - `zh_Hans`(string) [optional] 中文 -- `credential_form_schemas` (array[[CredentialFormSchema](#CredentialFormSchema)]) 凭据表单规范 +- `credential_form_schemas` (array\[[CredentialFormSchema](#CredentialFormSchema)\]) 凭据表单规范 ### CredentialFormSchema @@ -179,12 +180,12 @@ - `type` ([FormType](#FormType)) 表单项类型 - `required` (bool) 是否必填 - `default`(string) 默认值 -- `options` (array[[FormOption](#FormOption)]) 表单项为 `select` 或 `radio` 专有属性，定义下拉内容 +- `options` (array\[[FormOption](#FormOption)\]) 表单项为 `select` 或 `radio` 专有属性，定义下拉内容 - `placeholder`(object) 表单项为 `text-input `专有属性，表单项 PlaceHolder - `en_US`(string) 英文 - `zh_Hans` (string) [optional] 中文 - `max_length` (int) 表单项为`text-input`专有属性，定义输入最大长度，0 为不限制。 -- `show_on` (array[[FormShowOnObject](#FormShowOnObject)]) 当其他表单项值符合条件时显示，为空则始终显示。 +- `show_on` (array\[[FormShowOnObject](#FormShowOnObject)\]) 当其他表单项值符合条件时显示，为空则始终显示。 ### FormType @@ -200,7 +201,7 @@ - `en_US`(string) 英文 - `zh_Hans`(string) [optional] 中文 - `value` (string) 下拉选项值 -- `show_on` (array[[FormShowOnObject](#FormShowOnObject)]) 当其他表单项值符合条件时显示，为空则始终显示。 +- `show_on` (array\[[FormShowOnObject](#FormShowOnObject)\]) 当其他表单项值符合条件时显示，为空则始终显示。 ### FormShowOnObject diff --git a/api/core/model_runtime/utils/encoders.py b/api/core/model_runtime/utils/encoders.py index a5c11aeeba..f65339fbfc 100644 --- a/api/core/model_runtime/utils/encoders.py +++ b/api/core/model_runtime/utils/encoders.py @@ -151,12 +151,9 @@ def jsonable_encoder( return format(obj, "f") if isinstance(obj, dict): encoded_dict = {} - allowed_keys = set(obj.keys()) for key, value in obj.items(): - if ( - (not sqlalchemy_safe or (not isinstance(key, str)) or (not key.startswith("_sa"))) - and (value is not None or not exclude_none) - and key in allowed_keys + if (not sqlalchemy_safe or (not isinstance(key, str)) or (not key.startswith("_sa"))) and ( + value is not None or not exclude_none ): encoded_key = jsonable_encoder( key, diff --git a/api/core/ops/aliyun_trace/aliyun_trace.py b/api/core/ops/aliyun_trace/aliyun_trace.py index 06050619e9..82f54582ed 100644 --- a/api/core/ops/aliyun_trace/aliyun_trace.py +++ b/api/core/ops/aliyun_trace/aliyun_trace.py @@ -4,15 +4,15 @@ from collections.abc import Sequence from typing import Optional from urllib.parse import urljoin -from opentelemetry.trace import Status, StatusCode +from opentelemetry.trace import Link, Status, StatusCode from sqlalchemy.orm import Session, sessionmaker from core.ops.aliyun_trace.data_exporter.traceclient import ( TraceClient, convert_datetime_to_nanoseconds, - convert_string_to_id, convert_to_span_id, convert_to_trace_id, + create_link, generate_span_id, ) from core.ops.aliyun_trace.entities.aliyun_trace_entity import SpanData @@ -103,10 +103,11 @@ class AliyunDataTrace(BaseTraceInstance): def workflow_trace(self, trace_info: WorkflowTraceInfo): trace_id = convert_to_trace_id(trace_info.workflow_run_id) + links = [] if trace_info.trace_id: - trace_id = convert_string_to_id(trace_info.trace_id) + links.append(create_link(trace_id_str=trace_info.trace_id)) workflow_span_id = convert_to_span_id(trace_info.workflow_run_id, "workflow") - self.add_workflow_span(trace_id, workflow_span_id, trace_info) + self.add_workflow_span(trace_id, workflow_span_id, trace_info, links) workflow_node_executions = self.get_workflow_node_executions(trace_info) for node_execution in workflow_node_executions: @@ -132,8 +133,9 @@ class AliyunDataTrace(BaseTraceInstance): status = Status(StatusCode.ERROR, trace_info.error) trace_id = convert_to_trace_id(message_id) + links = [] if trace_info.trace_id: - trace_id = convert_string_to_id(trace_info.trace_id) + links.append(create_link(trace_id_str=trace_info.trace_id)) message_span_id = convert_to_span_id(message_id, "message") message_span = SpanData( @@ -152,6 +154,7 @@ class AliyunDataTrace(BaseTraceInstance): OUTPUT_VALUE: str(trace_info.outputs), }, status=status, + links=links, ) self.trace_client.add_span(message_span) @@ -192,8 +195,9 @@ class AliyunDataTrace(BaseTraceInstance): message_id = trace_info.message_id trace_id = convert_to_trace_id(message_id) + links = [] if trace_info.trace_id: - trace_id = convert_string_to_id(trace_info.trace_id) + links.append(create_link(trace_id_str=trace_info.trace_id)) documents_data = extract_retrieval_documents(trace_info.documents) dataset_retrieval_span = SpanData( @@ -211,6 +215,7 @@ class AliyunDataTrace(BaseTraceInstance): INPUT_VALUE: str(trace_info.inputs), OUTPUT_VALUE: json.dumps(documents_data, ensure_ascii=False), }, + links=links, ) self.trace_client.add_span(dataset_retrieval_span) @@ -224,8 +229,9 @@ class AliyunDataTrace(BaseTraceInstance): status = Status(StatusCode.ERROR, trace_info.error) trace_id = convert_to_trace_id(message_id) + links = [] if trace_info.trace_id: - trace_id = convert_string_to_id(trace_info.trace_id) + links.append(create_link(trace_id_str=trace_info.trace_id)) tool_span = SpanData( trace_id=trace_id, @@ -244,6 +250,7 @@ class AliyunDataTrace(BaseTraceInstance): OUTPUT_VALUE: str(trace_info.tool_outputs), }, status=status, + links=links, ) self.trace_client.add_span(tool_span) @@ -413,7 +420,9 @@ class AliyunDataTrace(BaseTraceInstance): status=self.get_workflow_node_status(node_execution), ) - def add_workflow_span(self, trace_id: int, workflow_span_id: int, trace_info: WorkflowTraceInfo): + def add_workflow_span( + self, trace_id: int, workflow_span_id: int, trace_info: WorkflowTraceInfo, links: Sequence[Link] + ): message_span_id = None if trace_info.message_id: message_span_id = convert_to_span_id(trace_info.message_id, "message") @@ -438,6 +447,7 @@ class AliyunDataTrace(BaseTraceInstance): OUTPUT_VALUE: json.dumps(trace_info.workflow_run_outputs, ensure_ascii=False), }, status=status, + links=links, ) self.trace_client.add_span(message_span) @@ -456,6 +466,7 @@ class AliyunDataTrace(BaseTraceInstance): OUTPUT_VALUE: json.dumps(trace_info.workflow_run_outputs, ensure_ascii=False), }, status=status, + links=links, ) self.trace_client.add_span(workflow_span) @@ -466,8 +477,9 @@ class AliyunDataTrace(BaseTraceInstance): status = Status(StatusCode.ERROR, trace_info.error) trace_id = convert_to_trace_id(message_id) + links = [] if trace_info.trace_id: - trace_id = convert_string_to_id(trace_info.trace_id) + links.append(create_link(trace_id_str=trace_info.trace_id)) suggested_question_span = SpanData( trace_id=trace_id, @@ -487,6 +499,7 @@ class AliyunDataTrace(BaseTraceInstance): OUTPUT_VALUE: json.dumps(trace_info.suggested_question, ensure_ascii=False), }, status=status, + links=links, ) self.trace_client.add_span(suggested_question_span) diff --git a/api/core/ops/aliyun_trace/data_exporter/traceclient.py b/api/core/ops/aliyun_trace/data_exporter/traceclient.py index bd19c8a503..3eb7c30d55 100644 --- a/api/core/ops/aliyun_trace/data_exporter/traceclient.py +++ b/api/core/ops/aliyun_trace/data_exporter/traceclient.py @@ -16,6 +16,7 @@ from opentelemetry.sdk.resources import Resource from opentelemetry.sdk.trace import ReadableSpan from opentelemetry.sdk.util.instrumentation import InstrumentationScope from opentelemetry.semconv.resource import ResourceAttributes +from opentelemetry.trace import Link, SpanContext, TraceFlags from configs import dify_config from core.ops.aliyun_trace.entities.aliyun_trace_entity import SpanData @@ -166,6 +167,16 @@ class SpanBuilder: return span +def create_link(trace_id_str: str) -> Link: + placeholder_span_id = 0x0000000000000000 + trace_id = int(trace_id_str, 16) + span_context = SpanContext( + trace_id=trace_id, span_id=placeholder_span_id, is_remote=False, trace_flags=TraceFlags(TraceFlags.SAMPLED) + ) + + return Link(span_context) + + def generate_span_id() -> int: span_id = random.getrandbits(64) while span_id == INVALID_SPAN_ID: diff --git a/api/core/provider_manager.py b/api/core/provider_manager.py index 6de4f3a303..9250497d29 100644 --- a/api/core/provider_manager.py +++ b/api/core/provider_manager.py @@ -523,7 +523,7 @@ class ProviderManager: # Init trial provider records if not exists if ProviderQuotaType.TRIAL not in provider_quota_to_provider_record_dict: try: - # FIXME ignore the type errork, onyl TrialHostingQuota has limit need to change the logic + # FIXME ignore the type error, only TrialHostingQuota has limit need to change the logic new_provider_record = Provider( tenant_id=tenant_id, # TODO: Use provider name with prefix after the data migration. diff --git a/api/core/rag/datasource/keyword/jieba/jieba.py b/api/core/rag/datasource/keyword/jieba/jieba.py index 7c5f47006f..c98306ea4b 100644 --- a/api/core/rag/datasource/keyword/jieba/jieba.py +++ b/api/core/rag/datasource/keyword/jieba/jieba.py @@ -1,7 +1,7 @@ -import json from collections import defaultdict from typing import Any, Optional +import orjson from pydantic import BaseModel from configs import dify_config @@ -134,13 +134,13 @@ class Jieba(BaseKeyword): dataset_keyword_table = self.dataset.dataset_keyword_table keyword_data_source_type = dataset_keyword_table.data_source_type if keyword_data_source_type == "database": - dataset_keyword_table.keyword_table = json.dumps(keyword_table_dict, cls=SetEncoder) + dataset_keyword_table.keyword_table = dumps_with_sets(keyword_table_dict) db.session.commit() else: file_key = "keyword_files/" + self.dataset.tenant_id + "/" + self.dataset.id + ".txt" if storage.exists(file_key): storage.delete(file_key) - storage.save(file_key, json.dumps(keyword_table_dict, cls=SetEncoder).encode("utf-8")) + storage.save(file_key, dumps_with_sets(keyword_table_dict).encode("utf-8")) def _get_dataset_keyword_table(self) -> Optional[dict]: dataset_keyword_table = self.dataset.dataset_keyword_table @@ -156,12 +156,11 @@ class Jieba(BaseKeyword): data_source_type=keyword_data_source_type, ) if keyword_data_source_type == "database": - dataset_keyword_table.keyword_table = json.dumps( + dataset_keyword_table.keyword_table = dumps_with_sets( { "__type__": "keyword_table", "__data__": {"index_id": self.dataset.id, "summary": None, "table": {}}, - }, - cls=SetEncoder, + } ) db.session.add(dataset_keyword_table) db.session.commit() @@ -252,8 +251,13 @@ class Jieba(BaseKeyword): self._save_dataset_keyword_table(keyword_table) -class SetEncoder(json.JSONEncoder): - def default(self, obj): - if isinstance(obj, set): - return list(obj) - return super().default(obj) +def set_orjson_default(obj: Any) -> Any: + """Default function for orjson serialization of set types""" + if isinstance(obj, set): + return list(obj) + raise TypeError(f"Object of type {type(obj).__name__} is not JSON serializable") + + +def dumps_with_sets(obj: Any) -> str: + """JSON dumps with set support using orjson""" + return orjson.dumps(obj, default=set_orjson_default).decode("utf-8") diff --git a/api/core/rag/datasource/vdb/analyticdb/analyticdb_vector_sql.py b/api/core/rag/datasource/vdb/analyticdb/analyticdb_vector_sql.py index 14481b1f10..2df17181a4 100644 --- a/api/core/rag/datasource/vdb/analyticdb/analyticdb_vector_sql.py +++ b/api/core/rag/datasource/vdb/analyticdb/analyticdb_vector_sql.py @@ -98,14 +98,19 @@ class AnalyticdbVectorBySql: try: cur.execute(f"CREATE DATABASE {self.databaseName}") except Exception as e: - if "already exists" in str(e): - return - raise e + if "already exists" not in str(e): + raise e finally: cur.close() conn.close() self.pool = self._create_connection_pool() with self._get_cursor() as cur: + try: + cur.execute("CREATE EXTENSION IF NOT EXISTS zhparser;") + except Exception as e: + raise RuntimeError( + "Failed to create zhparser extension. Please ensure it is available in your AnalyticDB." + ) from e try: cur.execute("CREATE TEXT SEARCH CONFIGURATION zh_cn (PARSER = zhparser)") cur.execute("ALTER TEXT SEARCH CONFIGURATION zh_cn ADD MAPPING FOR n,v,a,i,e,l,x WITH simple") diff --git a/api/core/rag/datasource/vdb/clickzetta/README.md b/api/core/rag/datasource/vdb/clickzetta/README.md index 2ee3e657d3..969d4e40a0 100644 --- a/api/core/rag/datasource/vdb/clickzetta/README.md +++ b/api/core/rag/datasource/vdb/clickzetta/README.md @@ -92,17 +92,21 @@ Clickzetta supports advanced full-text search with multiple analyzers: ### Analyzer Types 1. **keyword**: No tokenization, treats the entire string as a single token + - Best for: Exact matching, IDs, codes -2. **english**: Designed for English text +1. **english**: Designed for English text + - Features: Recognizes ASCII letters and numbers, converts to lowercase - Best for: English content -3. **chinese**: Chinese text tokenizer +1. **chinese**: Chinese text tokenizer + - Features: Recognizes Chinese and English characters, removes punctuation - Best for: Chinese or mixed Chinese-English content -4. **unicode**: Multi-language tokenizer based on Unicode +1. **unicode**: Multi-language tokenizer based on Unicode + - Features: Recognizes text boundaries in multiple languages - Best for: Multi-language content @@ -124,21 +128,25 @@ Clickzetta supports advanced full-text search with multiple analyzers: ### Vector Search 1. **Adjust exploration factor** for accuracy vs speed trade-off: + ```sql SET cz.vector.index.search.ef=64; ``` -2. **Use appropriate distance functions**: +1. **Use appropriate distance functions**: + - `cosine_distance`: Best for normalized embeddings (e.g., from language models) - `l2_distance`: Best for raw feature vectors ### Full-Text Search 1. **Choose the right analyzer**: + - Use `keyword` for exact matching - Use language-specific analyzers for better tokenization -2. **Combine with vector search**: +1. **Combine with vector search**: + - Pre-filter with full-text search for better performance - Use hybrid search for improved relevance @@ -147,27 +155,30 @@ Clickzetta supports advanced full-text search with multiple analyzers: ### Connection Issues 1. Verify all 7 required configuration parameters are set -2. Check network connectivity to Clickzetta service -3. Ensure the user has proper permissions on the schema +1. Check network connectivity to Clickzetta service +1. Ensure the user has proper permissions on the schema ### Search Performance 1. Verify vector index exists: + ```sql SHOW INDEX FROM .; ``` -2. Check if vector index is being used: +1. Check if vector index is being used: + ```sql EXPLAIN SELECT ... WHERE l2_distance(...) < threshold; ``` + Look for `vector_index_search_type` in the execution plan. ### Full-Text Search Not Working 1. Verify inverted index is created -2. Check analyzer configuration matches your content language -3. Use `TOKENIZE()` function to test tokenization: +1. Check analyzer configuration matches your content language +1. Use `TOKENIZE()` function to test tokenization: ```sql SELECT TOKENIZE('your text', map('analyzer', 'chinese', 'mode', 'smart')); ``` @@ -175,13 +186,13 @@ Clickzetta supports advanced full-text search with multiple analyzers: ## Limitations 1. Vector operations don't support `ORDER BY` or `GROUP BY` directly on vector columns -2. Full-text search relevance scores are not provided by Clickzetta -3. Inverted index creation may fail for very large existing tables (continue without error) -4. Index naming constraints: +1. Full-text search relevance scores are not provided by Clickzetta +1. Inverted index creation may fail for very large existing tables (continue without error) +1. Index naming constraints: - Index names must be unique within a schema - Only one vector index can be created per column - The implementation uses timestamps to ensure unique index names -5. A column can only have one vector index at a time +1. A column can only have one vector index at a time ## References diff --git a/api/core/rag/datasource/vdb/oceanbase/oceanbase_vector.py b/api/core/rag/datasource/vdb/oceanbase/oceanbase_vector.py index d6dfe967d7..8efe105bbf 100644 --- a/api/core/rag/datasource/vdb/oceanbase/oceanbase_vector.py +++ b/api/core/rag/datasource/vdb/oceanbase/oceanbase_vector.py @@ -4,8 +4,8 @@ import math from typing import Any from pydantic import BaseModel, model_validator -from pyobvector import VECTOR, ObVecClient # type: ignore -from sqlalchemy import JSON, Column, String, func +from pyobvector import VECTOR, FtsIndexParam, FtsParser, ObVecClient, l2_distance # type: ignore +from sqlalchemy import JSON, Column, String from sqlalchemy.dialects.mysql import LONGTEXT from configs import dify_config @@ -119,14 +119,21 @@ class OceanBaseVector(BaseVector): ) try: if self._hybrid_search_enabled: - self._client.perform_raw_text_sql(f"""ALTER TABLE {self._collection_name} - ADD FULLTEXT INDEX fulltext_index_for_col_text (text) WITH PARSER ik""") + self._client.create_fts_idx_with_fts_index_param( + table_name=self._collection_name, + fts_idx_param=FtsIndexParam( + index_name="fulltext_index_for_col_text", + field_names=["text"], + parser_type=FtsParser.IK, + ), + ) except Exception as e: raise Exception( "Failed to add fulltext index to the target table, your OceanBase version must be 4.3.5.1 or above " + "to support fulltext index and vector index in the same table", e, ) + self._client.refresh_metadata([self._collection_name]) redis_client.set(collection_exist_cache_key, 1, ex=3600) def _check_hybrid_search_support(self) -> bool: @@ -252,7 +259,7 @@ class OceanBaseVector(BaseVector): vec_column_name="vector", vec_data=query_vector, topk=topk, - distance_func=func.l2_distance, + distance_func=l2_distance, output_column_names=["text", "metadata"], with_dist=True, where_clause=_where_clause, diff --git a/api/core/rag/datasource/vdb/qdrant/qdrant_vector.py b/api/core/rag/datasource/vdb/qdrant/qdrant_vector.py index 9741dd8b1d..fcf3a6d126 100644 --- a/api/core/rag/datasource/vdb/qdrant/qdrant_vector.py +++ b/api/core/rag/datasource/vdb/qdrant/qdrant_vector.py @@ -331,6 +331,12 @@ class QdrantVector(BaseVector): def search_by_vector(self, query_vector: list[float], **kwargs: Any) -> list[Document]: from qdrant_client.http import models + score_threshold = float(kwargs.get("score_threshold") or 0.0) + if score_threshold >= 1: + # return empty list because some versions of qdrant may response with 400 bad request， + # and at the same time, the score_threshold with value 1 may be valid for other vector stores + return [] + filter = models.Filter( must=[ models.FieldCondition( @@ -355,7 +361,7 @@ class QdrantVector(BaseVector): limit=kwargs.get("top_k", 4), with_payload=True, with_vectors=True, - score_threshold=float(kwargs.get("score_threshold") or 0.0), + score_threshold=score_threshold, ) docs = [] for result in results: @@ -363,7 +369,6 @@ class QdrantVector(BaseVector): continue metadata = result.payload.get(Field.METADATA_KEY.value) or {} # duplicate check score threshold - score_threshold = float(kwargs.get("score_threshold") or 0.0) if result.score > score_threshold: metadata["score"] = result.score doc = Document( diff --git a/api/core/tools/custom_tool/tool.py b/api/core/tools/custom_tool/tool.py index e112de9578..3c0bfa5240 100644 --- a/api/core/tools/custom_tool/tool.py +++ b/api/core/tools/custom_tool/tool.py @@ -81,14 +81,11 @@ class ApiTool(Tool): return ToolProviderType.API def assembling_request(self, parameters: dict[str, Any]) -> dict[str, Any]: + headers = {} if self.runtime is None: raise ToolProviderCredentialValidationError("runtime not initialized") - headers = {} - if self.runtime is None: - raise ValueError("runtime is required") credentials = self.runtime.credentials or {} - if "auth_type" not in credentials: raise ToolProviderCredentialValidationError("Missing auth_type") diff --git a/api/core/tools/entities/agent_entities.py b/api/core/tools/entities/agent_entities.py deleted file mode 100644 index e69de29bb2..0000000000 diff --git a/api/core/tools/entities/api_entities.py b/api/core/tools/entities/api_entities.py index 27ce96b90e..48015c04ee 100644 --- a/api/core/tools/entities/api_entities.py +++ b/api/core/tools/entities/api_entities.py @@ -62,7 +62,7 @@ class ToolProviderApiEntity(BaseModel): parameter.pop("input_schema", None) # ------------- optional_fields = self.optional_field("server_url", self.server_url) - if self.type == ToolProviderType.MCP.value: + if self.type == ToolProviderType.MCP: optional_fields.update(self.optional_field("updated_at", self.updated_at)) optional_fields.update(self.optional_field("server_identifier", self.server_identifier)) return { diff --git a/api/core/tools/entities/file_entities.py b/api/core/tools/entities/file_entities.py deleted file mode 100644 index 8b13789179..0000000000 --- a/api/core/tools/entities/file_entities.py +++ /dev/null @@ -1 +0,0 @@ - diff --git a/api/core/tools/entities/tool_entities.py b/api/core/tools/entities/tool_entities.py index 5377cbbb69..5ffba07b44 100644 --- a/api/core/tools/entities/tool_entities.py +++ b/api/core/tools/entities/tool_entities.py @@ -108,10 +108,18 @@ class ApiProviderAuthType(Enum): :param value: mode value :return: mode """ + # 'api_key' deprecated in PR #21656 + # normalize & tiny alias for backward compatibility + v = (value or "").strip().lower() + if v == "api_key": + v = cls.API_KEY_HEADER.value + for mode in cls: - if mode.value == value: + if mode.value == v: return mode - raise ValueError(f"invalid mode value {value}") + + valid = ", ".join(m.value for m in cls) + raise ValueError(f"invalid mode value '{value}', expected one of: {valid}") class ToolInvokeMessage(BaseModel): diff --git a/api/core/tools/tool_manager.py b/api/core/tools/tool_manager.py index 7472f4f605..2089313b08 100644 --- a/api/core/tools/tool_manager.py +++ b/api/core/tools/tool_manager.py @@ -959,7 +959,7 @@ class ToolManager: elif provider_type == ToolProviderType.WORKFLOW: return cls.generate_workflow_tool_icon_url(tenant_id, provider_id) elif provider_type == ToolProviderType.PLUGIN: - provider = ToolManager.get_builtin_provider(provider_id, tenant_id) + provider = ToolManager.get_plugin_provider(provider_id, tenant_id) if isinstance(provider, PluginToolProviderController): try: return cls.generate_plugin_tool_icon_url(tenant_id, provider.entity.identity.icon) diff --git a/api/core/tools/utils/rag_web_reader.py b/api/core/tools/utils/rag_web_reader.py deleted file mode 100644 index 22c47fa814..0000000000 --- a/api/core/tools/utils/rag_web_reader.py +++ /dev/null @@ -1,17 +0,0 @@ -import re - - -def get_image_upload_file_ids(content): - pattern = r"!\[image\]\((http?://.*?(file-preview|image-preview))\)" - matches = re.findall(pattern, content) - image_upload_file_ids = [] - for match in matches: - if match[1] == "file-preview": - content_pattern = r"files/([^/]+)/file-preview" - else: - content_pattern = r"files/([^/]+)/image-preview" - content_match = re.search(content_pattern, match[0]) - if content_match: - image_upload_file_id = content_match.group(1) - image_upload_file_ids.append(image_upload_file_id) - return image_upload_file_ids diff --git a/api/core/tools/utils/web_reader_tool.py b/api/core/tools/utils/web_reader_tool.py index df052c16db..770c0ef7bd 100644 --- a/api/core/tools/utils/web_reader_tool.py +++ b/api/core/tools/utils/web_reader_tool.py @@ -80,14 +80,14 @@ def get_url(url: str, user_agent: Optional[str] = None) -> str: else: content = response.text - article = extract_using_readabilipy(content) + article = extract_using_readability(content) if not article.text: return "" res = FULL_TEMPLATE.format( title=article.title, - author=article.auther, + author=article.author, text=article.text, ) @@ -97,15 +97,15 @@ def get_url(url: str, user_agent: Optional[str] = None) -> str: @dataclass class Article: title: str - auther: str + author: str text: Sequence[dict] -def extract_using_readabilipy(html: str): +def extract_using_readability(html: str): json_article: dict[str, Any] = simple_json_from_html_string(html, use_readability=True) article = Article( title=json_article.get("title") or "", - auther=json_article.get("byline") or "", + author=json_article.get("byline") or "", text=json_article.get("plain_text") or [], ) @@ -113,7 +113,7 @@ def extract_using_readabilipy(html: str): def get_image_upload_file_ids(content): - pattern = r"!\[image\]\((http?://.*?(file-preview|image-preview))\)" + pattern = r"!\[image\]\((https?://.*?(file-preview|image-preview))\)" matches = re.findall(pattern, content) image_upload_file_ids = [] for match in matches: diff --git a/api/core/tools/workflow_as_tool/provider.py b/api/core/tools/workflow_as_tool/provider.py index 83f5f558d5..18e6993b38 100644 --- a/api/core/tools/workflow_as_tool/provider.py +++ b/api/core/tools/workflow_as_tool/provider.py @@ -203,9 +203,6 @@ class WorkflowToolProviderController(ToolProviderController): raise ValueError("app not found") app = db_providers.app - if not app: - raise ValueError("can not read app of workflow") - self.tools = [self._get_db_provider_tool(db_providers, app)] return self.tools diff --git a/api/core/variables/utils.py b/api/core/variables/utils.py index 692db3502e..7ebd29f865 100644 --- a/api/core/variables/utils.py +++ b/api/core/variables/utils.py @@ -1,5 +1,7 @@ -import json from collections.abc import Iterable, Sequence +from typing import Any + +import orjson from .segment_group import SegmentGroup from .segments import ArrayFileSegment, FileSegment, Segment @@ -12,15 +14,20 @@ def to_selector(node_id: str, name: str, paths: Iterable[str] = ()) -> Sequence[ return selectors -class SegmentJSONEncoder(json.JSONEncoder): - def default(self, o): - if isinstance(o, ArrayFileSegment): - return [v.model_dump() for v in o.value] - elif isinstance(o, FileSegment): - return o.value.model_dump() - elif isinstance(o, SegmentGroup): - return [self.default(seg) for seg in o.value] - elif isinstance(o, Segment): - return o.value - else: - super().default(o) +def segment_orjson_default(o: Any) -> Any: + """Default function for orjson serialization of Segment types""" + if isinstance(o, ArrayFileSegment): + return [v.model_dump() for v in o.value] + elif isinstance(o, FileSegment): + return o.value.model_dump() + elif isinstance(o, SegmentGroup): + return [segment_orjson_default(seg) for seg in o.value] + elif isinstance(o, Segment): + return o.value + raise TypeError(f"Object of type {type(o).__name__} is not JSON serializable") + + +def dumps_with_segments(obj: Any, ensure_ascii: bool = False) -> str: + """JSON dumps with segment support using orjson""" + option = orjson.OPT_NON_STR_KEYS + return orjson.dumps(obj, default=segment_orjson_default, option=option).decode("utf-8") diff --git a/api/core/workflow/nodes/llm/node.py b/api/core/workflow/nodes/llm/node.py index c0c0cb405c..dfc2a0000b 100644 --- a/api/core/workflow/nodes/llm/node.py +++ b/api/core/workflow/nodes/llm/node.py @@ -5,7 +5,7 @@ import logging from collections.abc import Generator, Mapping, Sequence from typing import TYPE_CHECKING, Any, Optional -from core.app.entities.app_invoke_entities import InvokeFrom, ModelConfigWithCredentialsEntity +from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEntity from core.file import FileType, file_manager from core.helper.code_executor import CodeExecutor, CodeLanguage from core.llm_generator.output_parser.errors import OutputParserError @@ -194,17 +194,6 @@ class LLMNode(BaseNode): else [] ) - # single step run fetch file from sys files - if not files and self.invoke_from == InvokeFrom.DEBUGGER and not self.previous_node_id: - files = ( - llm_utils.fetch_files( - variable_pool=variable_pool, - selector=["sys", "files"], - ) - if self._node_data.vision.enabled - else [] - ) - if files: node_inputs["#files#"] = [file.to_dict() for file in files] diff --git a/api/core/workflow/nodes/loop/loop_node.py b/api/core/workflow/nodes/loop/loop_node.py index 655de9362f..9a288c6133 100644 --- a/api/core/workflow/nodes/loop/loop_node.py +++ b/api/core/workflow/nodes/loop/loop_node.py @@ -313,30 +313,31 @@ class LoopNode(BaseNode): and event.node_type == NodeType.LOOP_END and not isinstance(event, NodeRunStreamChunkEvent) ): - check_break_result = True + # Check if variables in break conditions exist and process conditions + # Allow loop internal variables to be used in break conditions + available_conditions = [] + for condition in break_conditions: + variable = self.graph_runtime_state.variable_pool.get(condition.variable_selector) + if variable: + available_conditions.append(condition) + + # Process conditions if at least one variable is available + if available_conditions: + input_conditions, group_result, check_break_result = condition_processor.process_conditions( + variable_pool=self.graph_runtime_state.variable_pool, + conditions=available_conditions, + operator=logical_operator, + ) + if check_break_result: + break + else: + check_break_result = True yield self._handle_event_metadata(event=event, iter_run_index=current_index) break if isinstance(event, NodeRunSucceededEvent): yield self._handle_event_metadata(event=event, iter_run_index=current_index) - # Check if all variables in break conditions exist - exists_variable = False - for condition in break_conditions: - if not self.graph_runtime_state.variable_pool.get(condition.variable_selector): - exists_variable = False - break - else: - exists_variable = True - if exists_variable: - input_conditions, group_result, check_break_result = condition_processor.process_conditions( - variable_pool=self.graph_runtime_state.variable_pool, - conditions=break_conditions, - operator=logical_operator, - ) - if check_break_result: - break - elif isinstance(event, BaseGraphEvent): if isinstance(event, GraphRunFailedEvent): # Loop run failed diff --git a/api/core/workflow/nodes/tool/tool_node.py b/api/core/workflow/nodes/tool/tool_node.py index df89b2476d..4c8e13de70 100644 --- a/api/core/workflow/nodes/tool/tool_node.py +++ b/api/core/workflow/nodes/tool/tool_node.py @@ -318,33 +318,6 @@ class ToolNode(BaseNode): json.append(message.message.json_object) elif message.type == ToolInvokeMessage.MessageType.LINK: assert isinstance(message.message, ToolInvokeMessage.TextMessage) - - if message.meta: - transfer_method = message.meta.get("transfer_method", FileTransferMethod.TOOL_FILE) - else: - transfer_method = FileTransferMethod.TOOL_FILE - - tool_file_id = message.message.text.split("/")[-1].split(".")[0] - - with Session(db.engine) as session: - stmt = select(ToolFile).where(ToolFile.id == tool_file_id) - tool_file = session.scalar(stmt) - if tool_file is None: - raise ToolFileError(f"Tool file {tool_file_id} does not exist") - - mapping = { - "tool_file_id": tool_file_id, - "type": file_factory.get_file_type_by_mime_type(tool_file.mimetype), - "transfer_method": transfer_method, - "url": message.message.text, - } - - file = file_factory.build_from_mapping( - mapping=mapping, - tenant_id=self.tenant_id, - ) - files.append(file) - stream_text = f"Link: {message.message.text}\n" text += stream_text yield RunStreamChunkEvent(chunk_content=stream_text, from_variable_selector=[node_id, "text"]) diff --git a/api/core/workflow/workflow_engine_manager.py b/api/core/workflow/workflow_engine_manager.py deleted file mode 100644 index e69de29bb2..0000000000 diff --git a/api/events/event_handlers/document_index_event.py b/api/events/document_index_event.py similarity index 100% rename from api/events/event_handlers/document_index_event.py rename to api/events/document_index_event.py diff --git a/api/events/event_handlers/create_document_index.py b/api/events/event_handlers/create_document_index.py index bdb69945f0..c607161e2a 100644 --- a/api/events/event_handlers/create_document_index.py +++ b/api/events/event_handlers/create_document_index.py @@ -5,7 +5,7 @@ import click from werkzeug.exceptions import NotFound from core.indexing_runner import DocumentIsPausedError, IndexingRunner -from events.event_handlers.document_index_event import document_index_created +from events.document_index_event import document_index_created from extensions.ext_database import db from libs.datetime_utils import naive_utc_now from models.dataset import Document diff --git a/api/extensions/ext_celery.py b/api/extensions/ext_celery.py index bd72c93404..00e0bd9a16 100644 --- a/api/extensions/ext_celery.py +++ b/api/extensions/ext_celery.py @@ -1,4 +1,6 @@ +import ssl from datetime import timedelta +from typing import Any, Optional import pytz from celery import Celery, Task # type: ignore @@ -8,6 +10,40 @@ from configs import dify_config from dify_app import DifyApp +def _get_celery_ssl_options() -> Optional[dict[str, Any]]: + """Get SSL configuration for Celery broker/backend connections.""" + # Use REDIS_USE_SSL for consistency with the main Redis client + # Only apply SSL if we're using Redis as broker/backend + if not dify_config.REDIS_USE_SSL: + return None + + # Check if Celery is actually using Redis + broker_is_redis = dify_config.CELERY_BROKER_URL and ( + dify_config.CELERY_BROKER_URL.startswith("redis://") or dify_config.CELERY_BROKER_URL.startswith("rediss://") + ) + + if not broker_is_redis: + return None + + # Map certificate requirement strings to SSL constants + cert_reqs_map = { + "CERT_NONE": ssl.CERT_NONE, + "CERT_OPTIONAL": ssl.CERT_OPTIONAL, + "CERT_REQUIRED": ssl.CERT_REQUIRED, + } + + ssl_cert_reqs = cert_reqs_map.get(dify_config.REDIS_SSL_CERT_REQS, ssl.CERT_NONE) + + ssl_options = { + "ssl_cert_reqs": ssl_cert_reqs, + "ssl_ca_certs": dify_config.REDIS_SSL_CA_CERTS, + "ssl_certfile": dify_config.REDIS_SSL_CERTFILE, + "ssl_keyfile": dify_config.REDIS_SSL_KEYFILE, + } + + return ssl_options + + def init_app(app: DifyApp) -> Celery: class FlaskTask(Task): def __call__(self, *args: object, **kwargs: object) -> object: @@ -33,14 +69,6 @@ def init_app(app: DifyApp) -> Celery: task_ignore_result=True, ) - # Add SSL options to the Celery configuration - ssl_options = { - "ssl_cert_reqs": None, - "ssl_ca_certs": None, - "ssl_certfile": None, - "ssl_keyfile": None, - } - celery_app.conf.update( result_backend=dify_config.CELERY_RESULT_BACKEND, broker_transport_options=broker_transport_options, @@ -51,9 +79,13 @@ def init_app(app: DifyApp) -> Celery: timezone=pytz.timezone(dify_config.LOG_TZ or "UTC"), ) - if dify_config.BROKER_USE_SSL: + # Apply SSL configuration if enabled + ssl_options = _get_celery_ssl_options() + if ssl_options: celery_app.conf.update( - broker_use_ssl=ssl_options, # Add the SSL options to the broker configuration + broker_use_ssl=ssl_options, + # Also apply SSL to the backend if it's Redis + redis_backend_use_ssl=ssl_options if dify_config.CELERY_BACKEND == "redis" else None, ) if dify_config.LOG_FILE: @@ -113,13 +145,19 @@ def init_app(app: DifyApp) -> Celery: minutes=dify_config.QUEUE_MONITOR_INTERVAL if dify_config.QUEUE_MONITOR_INTERVAL else 30 ), } - if dify_config.ENABLE_CHECK_UPGRADABLE_PLUGIN_TASK: + if dify_config.ENABLE_CHECK_UPGRADABLE_PLUGIN_TASK and dify_config.MARKETPLACE_ENABLED: imports.append("schedule.check_upgradable_plugin_task") beat_schedule["check_upgradable_plugin_task"] = { "task": "schedule.check_upgradable_plugin_task.check_upgradable_plugin_task", "schedule": crontab(minute="*/15"), } - + if dify_config.WORKFLOW_LOG_CLEANUP_ENABLED: + # 2:00 AM every day + imports.append("schedule.clean_workflow_runlogs_precise") + beat_schedule["clean_workflow_runlogs_precise"] = { + "task": "schedule.clean_workflow_runlogs_precise.clean_workflow_runlogs_precise", + "schedule": crontab(minute="0", hour="2"), + } celery_app.conf.update(beat_schedule=beat_schedule, imports=imports) return celery_app diff --git a/api/extensions/ext_orjson.py b/api/extensions/ext_orjson.py new file mode 100644 index 0000000000..659784a585 --- /dev/null +++ b/api/extensions/ext_orjson.py @@ -0,0 +1,8 @@ +from flask_orjson import OrjsonProvider + +from dify_app import DifyApp + + +def init_app(app: DifyApp) -> None: + """Initialize Flask-Orjson extension for faster JSON serialization""" + app.json = OrjsonProvider(app) diff --git a/api/extensions/ext_redis.py b/api/extensions/ext_redis.py index 914d6219cf..f5f544679f 100644 --- a/api/extensions/ext_redis.py +++ b/api/extensions/ext_redis.py @@ -1,5 +1,6 @@ import functools import logging +import ssl from collections.abc import Callable from datetime import timedelta from typing import TYPE_CHECKING, Any, Union @@ -116,76 +117,132 @@ class RedisClientWrapper: redis_client: RedisClientWrapper = RedisClientWrapper() -def init_app(app: DifyApp): - global redis_client - connection_class: type[Union[Connection, SSLConnection]] = Connection - if dify_config.REDIS_USE_SSL: - connection_class = SSLConnection - resp_protocol = dify_config.REDIS_SERIALIZATION_PROTOCOL - if dify_config.REDIS_ENABLE_CLIENT_SIDE_CACHE: - if resp_protocol >= 3: - clientside_cache_config = CacheConfig() - else: - raise ValueError("Client side cache is only supported in RESP3") - else: - clientside_cache_config = None +def _get_ssl_configuration() -> tuple[type[Union[Connection, SSLConnection]], dict[str, Any]]: + """Get SSL configuration for Redis connection.""" + if not dify_config.REDIS_USE_SSL: + return Connection, {} - redis_params: dict[str, Any] = { + cert_reqs_map = { + "CERT_NONE": ssl.CERT_NONE, + "CERT_OPTIONAL": ssl.CERT_OPTIONAL, + "CERT_REQUIRED": ssl.CERT_REQUIRED, + } + ssl_cert_reqs = cert_reqs_map.get(dify_config.REDIS_SSL_CERT_REQS, ssl.CERT_NONE) + + ssl_kwargs = { + "ssl_cert_reqs": ssl_cert_reqs, + "ssl_ca_certs": dify_config.REDIS_SSL_CA_CERTS, + "ssl_certfile": dify_config.REDIS_SSL_CERTFILE, + "ssl_keyfile": dify_config.REDIS_SSL_KEYFILE, + } + + return SSLConnection, ssl_kwargs + + +def _get_cache_configuration() -> CacheConfig | None: + """Get client-side cache configuration if enabled.""" + if not dify_config.REDIS_ENABLE_CLIENT_SIDE_CACHE: + return None + + resp_protocol = dify_config.REDIS_SERIALIZATION_PROTOCOL + if resp_protocol < 3: + raise ValueError("Client side cache is only supported in RESP3") + + return CacheConfig() + + +def _get_base_redis_params() -> dict[str, Any]: + """Get base Redis connection parameters.""" + return { "username": dify_config.REDIS_USERNAME, - "password": dify_config.REDIS_PASSWORD or None, # Temporary fix for empty password + "password": dify_config.REDIS_PASSWORD or None, "db": dify_config.REDIS_DB, "encoding": "utf-8", "encoding_errors": "strict", "decode_responses": False, - "protocol": resp_protocol, - "cache_config": clientside_cache_config, + "protocol": dify_config.REDIS_SERIALIZATION_PROTOCOL, + "cache_config": _get_cache_configuration(), } - if dify_config.REDIS_USE_SENTINEL: - assert dify_config.REDIS_SENTINELS is not None, "REDIS_SENTINELS must be set when REDIS_USE_SENTINEL is True" - assert dify_config.REDIS_SENTINEL_SERVICE_NAME is not None, ( - "REDIS_SENTINEL_SERVICE_NAME must be set when REDIS_USE_SENTINEL is True" - ) - sentinel_hosts = [ - (node.split(":")[0], int(node.split(":")[1])) for node in dify_config.REDIS_SENTINELS.split(",") - ] - sentinel = Sentinel( - sentinel_hosts, - sentinel_kwargs={ - "socket_timeout": dify_config.REDIS_SENTINEL_SOCKET_TIMEOUT, - "username": dify_config.REDIS_SENTINEL_USERNAME, - "password": dify_config.REDIS_SENTINEL_PASSWORD, - }, - ) - master = sentinel.master_for(dify_config.REDIS_SENTINEL_SERVICE_NAME, **redis_params) - redis_client.initialize(master) - elif dify_config.REDIS_USE_CLUSTERS: - assert dify_config.REDIS_CLUSTERS is not None, "REDIS_CLUSTERS must be set when REDIS_USE_CLUSTERS is True" - nodes = [ - ClusterNode(host=node.split(":")[0], port=int(node.split(":")[1])) - for node in dify_config.REDIS_CLUSTERS.split(",") - ] - redis_client.initialize( - RedisCluster( - startup_nodes=nodes, - password=dify_config.REDIS_CLUSTERS_PASSWORD, - protocol=resp_protocol, - cache_config=clientside_cache_config, - ) - ) - else: - redis_params.update( - { - "host": dify_config.REDIS_HOST, - "port": dify_config.REDIS_PORT, - "connection_class": connection_class, - "protocol": resp_protocol, - "cache_config": clientside_cache_config, - } - ) - pool = redis.ConnectionPool(**redis_params) - redis_client.initialize(redis.Redis(connection_pool=pool)) +def _create_sentinel_client(redis_params: dict[str, Any]) -> Union[redis.Redis, RedisCluster]: + """Create Redis client using Sentinel configuration.""" + if not dify_config.REDIS_SENTINELS: + raise ValueError("REDIS_SENTINELS must be set when REDIS_USE_SENTINEL is True") + + if not dify_config.REDIS_SENTINEL_SERVICE_NAME: + raise ValueError("REDIS_SENTINEL_SERVICE_NAME must be set when REDIS_USE_SENTINEL is True") + + sentinel_hosts = [(node.split(":")[0], int(node.split(":")[1])) for node in dify_config.REDIS_SENTINELS.split(",")] + + sentinel = Sentinel( + sentinel_hosts, + sentinel_kwargs={ + "socket_timeout": dify_config.REDIS_SENTINEL_SOCKET_TIMEOUT, + "username": dify_config.REDIS_SENTINEL_USERNAME, + "password": dify_config.REDIS_SENTINEL_PASSWORD, + }, + ) + + master: redis.Redis = sentinel.master_for(dify_config.REDIS_SENTINEL_SERVICE_NAME, **redis_params) + return master + + +def _create_cluster_client() -> Union[redis.Redis, RedisCluster]: + """Create Redis cluster client.""" + if not dify_config.REDIS_CLUSTERS: + raise ValueError("REDIS_CLUSTERS must be set when REDIS_USE_CLUSTERS is True") + + nodes = [ + ClusterNode(host=node.split(":")[0], port=int(node.split(":")[1])) + for node in dify_config.REDIS_CLUSTERS.split(",") + ] + + cluster: RedisCluster = RedisCluster( + startup_nodes=nodes, + password=dify_config.REDIS_CLUSTERS_PASSWORD, + protocol=dify_config.REDIS_SERIALIZATION_PROTOCOL, + cache_config=_get_cache_configuration(), + ) + return cluster + + +def _create_standalone_client(redis_params: dict[str, Any]) -> Union[redis.Redis, RedisCluster]: + """Create standalone Redis client.""" + connection_class, ssl_kwargs = _get_ssl_configuration() + + redis_params.update( + { + "host": dify_config.REDIS_HOST, + "port": dify_config.REDIS_PORT, + "connection_class": connection_class, + } + ) + + if ssl_kwargs: + redis_params.update(ssl_kwargs) + + pool = redis.ConnectionPool(**redis_params) + client: redis.Redis = redis.Redis(connection_pool=pool) + return client + + +def init_app(app: DifyApp): + """Initialize Redis client and attach it to the app.""" + global redis_client + + # Determine Redis mode and create appropriate client + if dify_config.REDIS_USE_SENTINEL: + redis_params = _get_base_redis_params() + client = _create_sentinel_client(redis_params) + elif dify_config.REDIS_USE_CLUSTERS: + client = _create_cluster_client() + else: + redis_params = _get_base_redis_params() + client = _create_standalone_client(redis_params) + + # Initialize the wrapper and attach to app + redis_client.initialize(client) app.extensions["redis"] = redis_client diff --git a/api/models/workflow.py b/api/models/workflow.py index 453a650f84..7ff463e08f 100644 --- a/api/models/workflow.py +++ b/api/models/workflow.py @@ -1153,7 +1153,7 @@ class WorkflowDraftVariable(Base): value: The Segment object to store as the variable's value. """ self.__value = value - self.value = json.dumps(value, cls=variable_utils.SegmentJSONEncoder) + self.value = variable_utils.dumps_with_segments(value) self.value_type = value.value_type def get_node_id(self) -> str | None: diff --git a/api/mypy.ini b/api/mypy.ini index 6836b2602b..3a6a54afe1 100644 --- a/api/mypy.ini +++ b/api/mypy.ini @@ -5,8 +5,7 @@ check_untyped_defs = True cache_fine_grained = True sqlite_cache = True exclude = (?x)( - core/model_runtime/model_providers/ - | tests/ + tests/ | migrations/ ) diff --git a/api/pyproject.toml b/api/pyproject.toml index de472c870a..ce642aa9c8 100644 --- a/api/pyproject.toml +++ b/api/pyproject.toml @@ -18,6 +18,7 @@ dependencies = [ "flask-cors~=6.0.0", "flask-login~=0.6.3", "flask-migrate~=4.0.7", + "flask-orjson~=2.0.0", "flask-restful~=0.3.10", "flask-sqlalchemy~=3.1.1", "gevent~=24.11.1", @@ -204,7 +205,7 @@ vdb = [ "pgvector==0.2.5", "pymilvus~=2.5.0", "pymochow==1.3.1", - "pyobvector~=0.1.6", + "pyobvector~=0.2.15", "qdrant-client==1.9.0", "tablestore==6.2.0", "tcvectordb~=1.6.4", diff --git a/api/schedule/clean_workflow_runlogs_precise.py b/api/schedule/clean_workflow_runlogs_precise.py new file mode 100644 index 0000000000..8c21be01dc --- /dev/null +++ b/api/schedule/clean_workflow_runlogs_precise.py @@ -0,0 +1,155 @@ +import datetime +import logging +import time + +import click + +import app +from configs import dify_config +from extensions.ext_database import db +from models.model import ( + AppAnnotationHitHistory, + Conversation, + Message, + MessageAgentThought, + MessageAnnotation, + MessageChain, + MessageFeedback, + MessageFile, +) +from models.workflow import ConversationVariable, WorkflowAppLog, WorkflowNodeExecutionModel, WorkflowRun + +_logger = logging.getLogger(__name__) + + +MAX_RETRIES = 3 +BATCH_SIZE = dify_config.WORKFLOW_LOG_CLEANUP_BATCH_SIZE + + +@app.celery.task(queue="dataset") +def clean_workflow_runlogs_precise(): + """Clean expired workflow run logs with retry mechanism and complete message cascade""" + + click.echo(click.style("Start clean workflow run logs (precise mode with complete cascade).", fg="green")) + start_at = time.perf_counter() + + retention_days = dify_config.WORKFLOW_LOG_RETENTION_DAYS + cutoff_date = datetime.datetime.now() - datetime.timedelta(days=retention_days) + + try: + total_workflow_runs = db.session.query(WorkflowRun).where(WorkflowRun.created_at < cutoff_date).count() + if total_workflow_runs == 0: + _logger.info("No expired workflow run logs found") + return + _logger.info("Found %s expired workflow run logs to clean", total_workflow_runs) + + total_deleted = 0 + failed_batches = 0 + batch_count = 0 + + while True: + workflow_runs = ( + db.session.query(WorkflowRun.id).where(WorkflowRun.created_at < cutoff_date).limit(BATCH_SIZE).all() + ) + + if not workflow_runs: + break + + workflow_run_ids = [run.id for run in workflow_runs] + batch_count += 1 + + success = _delete_batch_with_retry(workflow_run_ids, failed_batches) + + if success: + total_deleted += len(workflow_run_ids) + failed_batches = 0 + else: + failed_batches += 1 + if failed_batches >= MAX_RETRIES: + _logger.error("Failed to delete batch after %s retries, aborting cleanup for today", MAX_RETRIES) + break + else: + # Calculate incremental delay times: 5, 10, 15 minutes + retry_delay_minutes = failed_batches * 5 + _logger.warning("Batch deletion failed, retrying in %s minutes...", retry_delay_minutes) + time.sleep(retry_delay_minutes * 60) + continue + + _logger.info("Cleanup completed: %s expired workflow run logs deleted", total_deleted) + + except Exception as e: + db.session.rollback() + _logger.exception("Unexpected error in workflow log cleanup") + raise + + end_at = time.perf_counter() + execution_time = end_at - start_at + click.echo(click.style(f"Cleaned workflow run logs from db success latency: {execution_time:.2f}s", fg="green")) + + +def _delete_batch_with_retry(workflow_run_ids: list[str], attempt_count: int) -> bool: + """Delete a single batch with a retry mechanism and complete cascading deletion""" + try: + with db.session.begin_nested(): + message_data = ( + db.session.query(Message.id, Message.conversation_id) + .filter(Message.workflow_run_id.in_(workflow_run_ids)) + .all() + ) + message_id_list = [msg.id for msg in message_data] + conversation_id_list = list({msg.conversation_id for msg in message_data if msg.conversation_id}) + if message_id_list: + db.session.query(AppAnnotationHitHistory).where( + AppAnnotationHitHistory.message_id.in_(message_id_list) + ).delete(synchronize_session=False) + + db.session.query(MessageAgentThought).where(MessageAgentThought.message_id.in_(message_id_list)).delete( + synchronize_session=False + ) + + db.session.query(MessageChain).where(MessageChain.message_id.in_(message_id_list)).delete( + synchronize_session=False + ) + + db.session.query(MessageFile).where(MessageFile.message_id.in_(message_id_list)).delete( + synchronize_session=False + ) + + db.session.query(MessageAnnotation).where(MessageAnnotation.message_id.in_(message_id_list)).delete( + synchronize_session=False + ) + + db.session.query(MessageFeedback).where(MessageFeedback.message_id.in_(message_id_list)).delete( + synchronize_session=False + ) + + db.session.query(Message).where(Message.workflow_run_id.in_(workflow_run_ids)).delete( + synchronize_session=False + ) + + db.session.query(WorkflowAppLog).where(WorkflowAppLog.workflow_run_id.in_(workflow_run_ids)).delete( + synchronize_session=False + ) + + db.session.query(WorkflowNodeExecutionModel).where( + WorkflowNodeExecutionModel.workflow_run_id.in_(workflow_run_ids) + ).delete(synchronize_session=False) + + if conversation_id_list: + db.session.query(ConversationVariable).where( + ConversationVariable.conversation_id.in_(conversation_id_list) + ).delete(synchronize_session=False) + + db.session.query(Conversation).where(Conversation.id.in_(conversation_id_list)).delete( + synchronize_session=False + ) + + db.session.query(WorkflowRun).where(WorkflowRun.id.in_(workflow_run_ids)).delete(synchronize_session=False) + + db.session.commit() + return True + + except Exception as e: + db.session.rollback() + _logger.exception("Batch deletion failed (attempt %s)", attempt_count + 1) + return False diff --git a/api/services/annotation_service.py b/api/services/annotation_service.py index b7a047914e..1a0fdfa420 100644 --- a/api/services/annotation_service.py +++ b/api/services/annotation_service.py @@ -293,7 +293,7 @@ class AppAnnotationService: annotation_ids_to_delete = [annotation.id for annotation, _ in annotations_to_delete] # Step 2: Bulk delete hit histories in a single query - db.session.query(AppAnnotationHitHistory).filter( + db.session.query(AppAnnotationHitHistory).where( AppAnnotationHitHistory.annotation_id.in_(annotation_ids_to_delete) ).delete(synchronize_session=False) @@ -307,7 +307,7 @@ class AppAnnotationService: # Step 4: Bulk delete annotations in a single query deleted_count = ( db.session.query(MessageAnnotation) - .filter(MessageAnnotation.id.in_(annotation_ids_to_delete)) + .where(MessageAnnotation.id.in_(annotation_ids_to_delete)) .delete(synchronize_session=False) ) @@ -505,9 +505,9 @@ class AppAnnotationService: db.session.query(AppAnnotationSetting).where(AppAnnotationSetting.app_id == app_id).first() ) - annotations_query = db.session.query(MessageAnnotation).filter(MessageAnnotation.app_id == app_id) + annotations_query = db.session.query(MessageAnnotation).where(MessageAnnotation.app_id == app_id) for annotation in annotations_query.yield_per(100): - annotation_hit_histories_query = db.session.query(AppAnnotationHitHistory).filter( + annotation_hit_histories_query = db.session.query(AppAnnotationHitHistory).where( AppAnnotationHitHistory.annotation_id == annotation.id ) for annotation_hit_history in annotation_hit_histories_query.yield_per(100): diff --git a/api/services/billing_service.py b/api/services/billing_service.py index 476fce0057..40d45af376 100644 --- a/api/services/billing_service.py +++ b/api/services/billing_service.py @@ -123,7 +123,7 @@ class BillingService: return BillingService._send_request("GET", "/education/verify", params=params) @classmethod - def is_active(cls, account_id: str): + def status(cls, account_id: str): params = {"account_id": account_id} return BillingService._send_request("GET", "/education/status", params=params) diff --git a/api/services/conversation_service.py b/api/services/conversation_service.py index 713c4c6782..4f3dd3c762 100644 --- a/api/services/conversation_service.py +++ b/api/services/conversation_service.py @@ -103,10 +103,10 @@ class ConversationService: @classmethod def _build_filter_condition(cls, sort_field: str, sort_direction: Callable, reference_conversation: Conversation): field_value = getattr(reference_conversation, sort_field) - if sort_direction == desc: + if sort_direction is desc: return getattr(Conversation, sort_field) < field_value - else: - return getattr(Conversation, sort_field) > field_value + + return getattr(Conversation, sort_field) > field_value @classmethod def rename( @@ -147,7 +147,7 @@ class ConversationService: app_model.tenant_id, message.query, conversation.id, app_model.id ) conversation.name = name - except: + except Exception: pass db.session.commit() @@ -277,6 +277,11 @@ class ConversationService: # Validate that the new value type matches the expected variable type expected_type = SegmentType(current_variable.value_type) + + # There is showing number in web ui but int in db + if expected_type == SegmentType.INTEGER: + expected_type = SegmentType.NUMBER + if not expected_type.is_valid(new_value): inferred_type = SegmentType.infer_segment_type(new_value) raise ConversationVariableTypeMismatchError( diff --git a/api/services/dataset_service.py b/api/services/dataset_service.py index 8934608da1..9fb048fac4 100644 --- a/api/services/dataset_service.py +++ b/api/services/dataset_service.py @@ -6,7 +6,7 @@ import secrets import time import uuid from collections import Counter -from typing import Any, Optional +from typing import Any, Literal, Optional from flask_login import current_user from sqlalchemy import func, select @@ -51,7 +51,7 @@ from services.entities.knowledge_entities.knowledge_entities import ( RetrievalModel, SegmentUpdateArgs, ) -from services.errors.account import InvalidActionError, NoPermissionError +from services.errors.account import NoPermissionError from services.errors.chunk import ChildChunkDeleteIndexError, ChildChunkIndexingError from services.errors.dataset import DatasetNameDuplicateError from services.errors.document import DocumentIndexingError @@ -250,6 +250,11 @@ class DatasetService: dataset: Optional[Dataset] = db.session.query(Dataset).filter_by(id=dataset_id).first() return dataset + @staticmethod + def check_doc_form(dataset: Dataset, doc_form: str): + if dataset.doc_form and doc_form != dataset.doc_form: + raise ValueError("doc_form is different from the dataset doc_form.") + @staticmethod def check_dataset_model_setting(dataset): if dataset.indexing_technique == "high_quality": @@ -1085,6 +1090,8 @@ class DocumentService: dataset_process_rule: Optional[DatasetProcessRule] = None, created_from: str = "web", ): + # check doc_form + DatasetService.check_doc_form(dataset, knowledge_config.doc_form) # check document limit features = FeatureService.get_features(current_user.current_tenant_id) @@ -1800,14 +1807,16 @@ class DocumentService: raise ValueError("Process rule segmentation max_tokens is invalid") @staticmethod - def batch_update_document_status(dataset: Dataset, document_ids: list[str], action: str, user): + def batch_update_document_status( + dataset: Dataset, document_ids: list[str], action: Literal["enable", "disable", "archive", "un_archive"], user + ): """ Batch update document status. Args: dataset (Dataset): The dataset object document_ids (list[str]): List of document IDs to update - action (str): Action to perform (enable, disable, archive, un_archive) + action (Literal["enable", "disable", "archive", "un_archive"]): Action to perform user: Current user performing the action Raises: @@ -1890,9 +1899,10 @@ class DocumentService: raise propagation_error @staticmethod - def _prepare_document_status_update(document, action: str, user): - """ - Prepare document status update information. + def _prepare_document_status_update( + document: Document, action: Literal["enable", "disable", "archive", "un_archive"], user + ): + """Prepare document status update information. Args: document: Document object to update @@ -2355,7 +2365,9 @@ class SegmentService: db.session.commit() @classmethod - def update_segments_status(cls, segment_ids: list, action: str, dataset: Dataset, document: Document): + def update_segments_status( + cls, segment_ids: list, action: Literal["enable", "disable"], dataset: Dataset, document: Document + ): # Check if segment_ids is not empty to avoid WHERE false condition if not segment_ids or len(segment_ids) == 0: return @@ -2413,8 +2425,6 @@ class SegmentService: db.session.commit() disable_segments_from_index_task.delay(real_deal_segment_ids, dataset.id, document.id) - else: - raise InvalidActionError() @classmethod def create_child_chunk( diff --git a/api/services/enterprise/mail_service.py b/api/services/enterprise/mail_service.py deleted file mode 100644 index 630e7679ac..0000000000 --- a/api/services/enterprise/mail_service.py +++ /dev/null @@ -1,18 +0,0 @@ -from pydantic import BaseModel - -from tasks.mail_enterprise_task import send_enterprise_email_task - - -class DifyMail(BaseModel): - to: list[str] - subject: str - body: str - substitutions: dict[str, str] = {} - - -class EnterpriseMailService: - @classmethod - def send_mail(cls, mail: DifyMail): - send_enterprise_email_task.delay( - to=mail.to, subject=mail.subject, body=mail.body, substitutions=mail.substitutions - ) diff --git a/api/services/plugin/oauth_service.py b/api/services/plugin/oauth_service.py index b84dd0afc5..055fbb8138 100644 --- a/api/services/plugin/oauth_service.py +++ b/api/services/plugin/oauth_service.py @@ -47,7 +47,9 @@ class OAuthProxyService(BasePluginClient): if not context_id: raise ValueError("context_id is required") # get data from redis - data = redis_client.getdel(f"{OAuthProxyService.__KEY_PREFIX__}{context_id}") + key = f"{OAuthProxyService.__KEY_PREFIX__}{context_id}" + data = redis_client.get(key) if not data: raise ValueError("context_id is invalid") + redis_client.delete(key) return json.loads(data) diff --git a/api/tasks/clean_dataset_task.py b/api/tasks/clean_dataset_task.py index 9a45115b05..7b940847c9 100644 --- a/api/tasks/clean_dataset_task.py +++ b/api/tasks/clean_dataset_task.py @@ -5,7 +5,7 @@ import click from celery import shared_task # type: ignore from core.rag.index_processor.index_processor_factory import IndexProcessorFactory -from core.tools.utils.rag_web_reader import get_image_upload_file_ids +from core.tools.utils.web_reader_tool import get_image_upload_file_ids from extensions.ext_database import db from extensions.ext_storage import storage from models.dataset import ( diff --git a/api/tasks/clean_document_task.py b/api/tasks/clean_document_task.py index d690106d17..5479ba8e8f 100644 --- a/api/tasks/clean_document_task.py +++ b/api/tasks/clean_document_task.py @@ -6,7 +6,7 @@ import click from celery import shared_task # type: ignore from core.rag.index_processor.index_processor_factory import IndexProcessorFactory -from core.tools.utils.rag_web_reader import get_image_upload_file_ids +from core.tools.utils.web_reader_tool import get_image_upload_file_ids from extensions.ext_database import db from extensions.ext_storage import storage from models.dataset import Dataset, DatasetMetadataBinding, DocumentSegment diff --git a/api/tasks/deal_dataset_vector_index_task.py b/api/tasks/deal_dataset_vector_index_task.py index 8c4c1876ad..5ab377c232 100644 --- a/api/tasks/deal_dataset_vector_index_task.py +++ b/api/tasks/deal_dataset_vector_index_task.py @@ -1,5 +1,6 @@ import logging import time +from typing import Literal import click from celery import shared_task # type: ignore @@ -13,7 +14,7 @@ from models.dataset import Document as DatasetDocument @shared_task(queue="dataset") -def deal_dataset_vector_index_task(dataset_id: str, action: str): +def deal_dataset_vector_index_task(dataset_id: str, action: Literal["remove", "add", "update"]): """ Async deal dataset from index :param dataset_id: dataset_id diff --git a/api/tasks/mail_enterprise_task.py b/api/tasks/mail_inner_task.py similarity index 89% rename from api/tasks/mail_enterprise_task.py rename to api/tasks/mail_inner_task.py index 9c80da06e5..101f7ebaa4 100644 --- a/api/tasks/mail_enterprise_task.py +++ b/api/tasks/mail_inner_task.py @@ -11,7 +11,7 @@ from libs.email_i18n import get_email_i18n_service @shared_task(queue="mail") -def send_enterprise_email_task(to: list[str], subject: str, body: str, substitutions: Mapping[str, str]): +def send_inner_email_task(to: list[str], subject: str, body: str, substitutions: Mapping[str, str]): if not mail.is_inited(): return diff --git a/api/tests/integration_tests/vdb/qdrant/test_qdrant.py b/api/tests/integration_tests/vdb/qdrant/test_qdrant.py index 61d9a9e712..fe0e03f7b8 100644 --- a/api/tests/integration_tests/vdb/qdrant/test_qdrant.py +++ b/api/tests/integration_tests/vdb/qdrant/test_qdrant.py @@ -1,4 +1,5 @@ from core.rag.datasource.vdb.qdrant.qdrant_vector import QdrantConfig, QdrantVector +from core.rag.models.document import Document from tests.integration_tests.vdb.test_vector_store import ( AbstractVectorTest, setup_mock_redis, @@ -18,6 +19,14 @@ class QdrantVectorTest(AbstractVectorTest): ), ) + def search_by_vector(self): + super().search_by_vector() + # only test for qdrant, may not work on other vector stores + hits_by_vector: list[Document] = self.vector.search_by_vector( + query_vector=self.example_embedding, score_threshold=1 + ) + assert len(hits_by_vector) == 0 + def test_qdrant_vector(setup_mock_redis): QdrantVectorTest().run_all_tests() diff --git a/api/tests/test_containers_integration_tests/services/test_annotation_service.py b/api/tests/test_containers_integration_tests/services/test_annotation_service.py index 0ab5f398e3..8816698af8 100644 --- a/api/tests/test_containers_integration_tests/services/test_annotation_service.py +++ b/api/tests/test_containers_integration_tests/services/test_annotation_service.py @@ -471,7 +471,7 @@ class TestAnnotationService: # Verify annotation was deleted from extensions.ext_database import db - deleted_annotation = db.session.query(MessageAnnotation).filter(MessageAnnotation.id == annotation_id).first() + deleted_annotation = db.session.query(MessageAnnotation).where(MessageAnnotation.id == annotation_id).first() assert deleted_annotation is None # Verify delete_annotation_index_task was called (when annotation setting exists) @@ -1175,7 +1175,7 @@ class TestAnnotationService: AppAnnotationService.delete_app_annotation(app.id, annotation_id) # Verify annotation was deleted - deleted_annotation = db.session.query(MessageAnnotation).filter(MessageAnnotation.id == annotation_id).first() + deleted_annotation = db.session.query(MessageAnnotation).where(MessageAnnotation.id == annotation_id).first() assert deleted_annotation is None # Verify delete_annotation_index_task was called diff --git a/api/tests/test_containers_integration_tests/services/test_api_based_extension_service.py b/api/tests/test_containers_integration_tests/services/test_api_based_extension_service.py index 38f532fd64..6cd8337ff9 100644 --- a/api/tests/test_containers_integration_tests/services/test_api_based_extension_service.py +++ b/api/tests/test_containers_integration_tests/services/test_api_based_extension_service.py @@ -234,7 +234,7 @@ class TestAPIBasedExtensionService: # Verify extension was deleted from extensions.ext_database import db - deleted_extension = db.session.query(APIBasedExtension).filter(APIBasedExtension.id == extension_id).first() + deleted_extension = db.session.query(APIBasedExtension).where(APIBasedExtension.id == extension_id).first() assert deleted_extension is None def test_save_extension_duplicate_name(self, db_session_with_containers, mock_external_service_dependencies): diff --git a/api/tests/test_containers_integration_tests/services/test_feature_service.py b/api/tests/test_containers_integration_tests/services/test_feature_service.py new file mode 100644 index 0000000000..8bd5440411 --- /dev/null +++ b/api/tests/test_containers_integration_tests/services/test_feature_service.py @@ -0,0 +1,1785 @@ +from unittest.mock import patch + +import pytest +from faker import Faker + +from services.feature_service import FeatureModel, FeatureService, KnowledgeRateLimitModel, SystemFeatureModel + + +class TestFeatureService: + """Integration tests for FeatureService using testcontainers.""" + + @pytest.fixture + def mock_external_service_dependencies(self): + """Mock setup for external service dependencies.""" + with ( + patch("services.feature_service.BillingService") as mock_billing_service, + patch("services.feature_service.EnterpriseService") as mock_enterprise_service, + ): + # Setup default mock returns for BillingService + mock_billing_service.get_info.return_value = { + "enabled": True, + "subscription": {"plan": "pro", "interval": "monthly", "education": True}, + "members": {"size": 5, "limit": 10}, + "apps": {"size": 3, "limit": 20}, + "vector_space": {"size": 2, "limit": 10}, + "documents_upload_quota": {"size": 15, "limit": 100}, + "annotation_quota_limit": {"size": 8, "limit": 50}, + "docs_processing": "enhanced", + "can_replace_logo": True, + "model_load_balancing_enabled": True, + "knowledge_rate_limit": {"limit": 100}, + } + + mock_billing_service.get_knowledge_rate_limit.return_value = {"limit": 100, "subscription_plan": "pro"} + + # Setup default mock returns for EnterpriseService + mock_enterprise_service.get_workspace_info.return_value = { + "WorkspaceMembers": {"used": 5, "limit": 10, "enabled": True} + } + + mock_enterprise_service.get_info.return_value = { + "SSOEnforcedForSignin": True, + "SSOEnforcedForSigninProtocol": "saml", + "EnableEmailCodeLogin": True, + "EnableEmailPasswordLogin": False, + "IsAllowRegister": False, + "IsAllowCreateWorkspace": False, + "Branding": { + "applicationTitle": "Test Enterprise", + "loginPageLogo": "https://example.com/logo.png", + "workspaceLogo": "https://example.com/workspace.png", + "favicon": "https://example.com/favicon.ico", + }, + "WebAppAuth": {"allowSso": True, "allowEmailCodeLogin": True, "allowEmailPasswordLogin": False}, + "SSOEnforcedForWebProtocol": "oidc", + "License": { + "status": "active", + "expiredAt": "2025-12-31", + "workspaces": {"enabled": True, "limit": 5, "used": 2}, + }, + "PluginInstallationPermission": { + "pluginInstallationScope": "official_only", + "restrictToMarketplaceOnly": True, + }, + } + + yield { + "billing_service": mock_billing_service, + "enterprise_service": mock_enterprise_service, + } + + def _create_test_tenant_id(self): + """Helper method to create a test tenant ID.""" + fake = Faker() + return fake.uuid4() + + def test_get_features_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful feature retrieval with billing and enterprise enabled. + + This test verifies: + - Proper feature model creation with all required fields + - Correct integration with billing service + - Proper enterprise workspace information handling + - Return value correctness and structure + """ + # Arrange: Setup test data with proper config mocking + tenant_id = self._create_test_tenant_id() + + with patch("services.feature_service.dify_config") as mock_config: + mock_config.BILLING_ENABLED = True + mock_config.ENTERPRISE_ENABLED = True + mock_config.CAN_REPLACE_LOGO = True + mock_config.MODEL_LB_ENABLED = True + mock_config.DATASET_OPERATOR_ENABLED = True + mock_config.EDUCATION_ENABLED = True + + # Act: Execute the method under test + result = FeatureService.get_features(tenant_id) + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, FeatureModel) + + # Verify billing features + assert result.billing.enabled is True + assert result.billing.subscription.plan == "pro" + assert result.billing.subscription.interval == "monthly" + assert result.education.activated is True + + # Verify member limitations + assert result.members.size == 5 + assert result.members.limit == 10 + + # Verify app limitations + assert result.apps.size == 3 + assert result.apps.limit == 20 + + # Verify vector space limitations + assert result.vector_space.size == 2 + assert result.vector_space.limit == 10 + + # Verify document upload quota + assert result.documents_upload_quota.size == 15 + assert result.documents_upload_quota.limit == 100 + + # Verify annotation quota + assert result.annotation_quota_limit.size == 8 + assert result.annotation_quota_limit.limit == 50 + + # Verify other features + assert result.docs_processing == "enhanced" + assert result.can_replace_logo is True + assert result.model_load_balancing_enabled is True + assert result.knowledge_rate_limit == 100 + + # Verify enterprise features + assert result.workspace_members.enabled is True + assert result.workspace_members.size == 5 + assert result.workspace_members.limit == 10 + + # Verify webapp copyright is enabled for non-sandbox plans + assert result.webapp_copyright_enabled is True + assert result.is_allow_transfer_workspace is True + + # Verify mock interactions + mock_external_service_dependencies["billing_service"].get_info.assert_called_once_with(tenant_id) + mock_external_service_dependencies["enterprise_service"].get_workspace_info.assert_called_once_with( + tenant_id + ) + + def test_get_features_sandbox_plan(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test feature retrieval for sandbox plan with specific limitations. + + This test verifies: + - Proper handling of sandbox plan limitations + - Correct webapp copyright settings for sandbox + - Transfer workspace restrictions for sandbox plans + - Proper billing service integration + """ + # Arrange: Setup sandbox plan mock with proper config + tenant_id = self._create_test_tenant_id() + + with patch("services.feature_service.dify_config") as mock_config: + mock_config.BILLING_ENABLED = True + mock_config.ENTERPRISE_ENABLED = False + mock_config.CAN_REPLACE_LOGO = False + mock_config.MODEL_LB_ENABLED = False + mock_config.DATASET_OPERATOR_ENABLED = False + mock_config.EDUCATION_ENABLED = False + + # Set mock return value inside the patch context + mock_external_service_dependencies["billing_service"].get_info.return_value = { + "enabled": True, + "subscription": {"plan": "sandbox", "interval": "monthly", "education": False}, + "members": {"size": 1, "limit": 3}, + "apps": {"size": 1, "limit": 5}, + "vector_space": {"size": 1, "limit": 2}, + "documents_upload_quota": {"size": 5, "limit": 20}, + "annotation_quota_limit": {"size": 2, "limit": 10}, + "docs_processing": "standard", + "can_replace_logo": False, + "model_load_balancing_enabled": False, + "knowledge_rate_limit": {"limit": 10}, + } + + # Act: Execute the method under test + result = FeatureService.get_features(tenant_id) + + # Assert: Verify sandbox-specific limitations + assert result.billing.subscription.plan == "sandbox" + assert result.education.activated is False + + # Verify sandbox limitations + assert result.members.size == 1 + assert result.members.limit == 3 + assert result.apps.size == 1 + assert result.apps.limit == 5 + assert result.vector_space.size == 1 + assert result.vector_space.limit == 2 + assert result.documents_upload_quota.size == 5 + assert result.documents_upload_quota.limit == 20 + assert result.annotation_quota_limit.size == 2 + assert result.annotation_quota_limit.limit == 10 + + # Verify sandbox-specific restrictions + assert result.webapp_copyright_enabled is False + assert result.is_allow_transfer_workspace is False + assert result.can_replace_logo is False + assert result.model_load_balancing_enabled is False + assert result.docs_processing == "standard" + assert result.knowledge_rate_limit == 10 + + # Verify mock interactions + mock_external_service_dependencies["billing_service"].get_info.assert_called_once_with(tenant_id) + + def test_get_knowledge_rate_limit_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful knowledge rate limit retrieval with billing enabled. + + This test verifies: + - Proper knowledge rate limit model creation + - Correct integration with billing service + - Proper rate limit configuration + - Return value correctness and structure + """ + # Arrange: Setup test data with proper config + tenant_id = self._create_test_tenant_id() + + with patch("services.feature_service.dify_config") as mock_config: + mock_config.BILLING_ENABLED = True + + # Act: Execute the method under test + result = FeatureService.get_knowledge_rate_limit(tenant_id) + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, KnowledgeRateLimitModel) + + # Verify rate limit configuration + assert result.enabled is True + assert result.limit == 100 + assert result.subscription_plan == "pro" + + # Verify mock interactions + mock_external_service_dependencies["billing_service"].get_knowledge_rate_limit.assert_called_once_with( + tenant_id + ) + + def test_get_system_features_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful system features retrieval with enterprise and marketplace enabled. + + This test verifies: + - Proper system feature model creation + - Correct integration with enterprise service + - Proper marketplace configuration + - Return value correctness and structure + """ + # Arrange: Setup test data with proper config + tenant_id = self._create_test_tenant_id() + + with patch("services.feature_service.dify_config") as mock_config: + mock_config.ENTERPRISE_ENABLED = True + mock_config.MARKETPLACE_ENABLED = True + mock_config.ENABLE_EMAIL_CODE_LOGIN = True + mock_config.ENABLE_EMAIL_PASSWORD_LOGIN = True + mock_config.ENABLE_SOCIAL_OAUTH_LOGIN = False + mock_config.ALLOW_REGISTER = False + mock_config.ALLOW_CREATE_WORKSPACE = False + mock_config.MAIL_TYPE = "smtp" + mock_config.PLUGIN_MAX_PACKAGE_SIZE = 100 + + # Act: Execute the method under test + result = FeatureService.get_system_features() + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, SystemFeatureModel) + + # Verify enterprise features + assert result.branding.enabled is True + assert result.webapp_auth.enabled is True + assert result.enable_change_email is False + + # Verify SSO configuration + assert result.sso_enforced_for_signin is True + assert result.sso_enforced_for_signin_protocol == "saml" + + # Verify authentication settings + assert result.enable_email_code_login is True + assert result.enable_email_password_login is False + assert result.is_allow_register is False + assert result.is_allow_create_workspace is False + + # Verify branding configuration + assert result.branding.application_title == "Test Enterprise" + assert result.branding.login_page_logo == "https://example.com/logo.png" + assert result.branding.workspace_logo == "https://example.com/workspace.png" + assert result.branding.favicon == "https://example.com/favicon.ico" + + # Verify webapp auth configuration + assert result.webapp_auth.allow_sso is True + assert result.webapp_auth.allow_email_code_login is True + assert result.webapp_auth.allow_email_password_login is False + assert result.webapp_auth.sso_config.protocol == "oidc" + + # Verify license configuration + assert result.license.status.value == "active" + assert result.license.expired_at == "2025-12-31" + assert result.license.workspaces.enabled is True + assert result.license.workspaces.limit == 5 + assert result.license.workspaces.size == 2 + + # Verify plugin installation permission + assert result.plugin_installation_permission.plugin_installation_scope == "official_only" + assert result.plugin_installation_permission.restrict_to_marketplace_only is True + + # Verify marketplace configuration + assert result.enable_marketplace is True + + # Verify mock interactions + mock_external_service_dependencies["enterprise_service"].get_info.assert_called_once() + + def test_get_system_features_basic_config(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test system features retrieval with basic configuration (no enterprise). + + This test verifies: + - Proper system feature model creation without enterprise + - Correct environment variable handling + - Default configuration values + - Return value correctness and structure + """ + # Arrange: Setup basic config mock (no enterprise) + with patch("services.feature_service.dify_config") as mock_config: + mock_config.ENTERPRISE_ENABLED = False + mock_config.MARKETPLACE_ENABLED = False + mock_config.ENABLE_EMAIL_CODE_LOGIN = True + mock_config.ENABLE_EMAIL_PASSWORD_LOGIN = True + mock_config.ENABLE_SOCIAL_OAUTH_LOGIN = False + mock_config.ALLOW_REGISTER = True + mock_config.ALLOW_CREATE_WORKSPACE = True + mock_config.MAIL_TYPE = "smtp" + mock_config.PLUGIN_MAX_PACKAGE_SIZE = 100 + + # Act: Execute the method under test + result = FeatureService.get_system_features() + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, SystemFeatureModel) + + # Verify basic configuration + assert result.branding.enabled is False + assert result.webapp_auth.enabled is False + assert result.enable_change_email is True + + # Verify authentication settings from config + assert result.enable_email_code_login is True + assert result.enable_email_password_login is True + assert result.enable_social_oauth_login is False + assert result.is_allow_register is True + assert result.is_allow_create_workspace is True + assert result.is_email_setup is True + + # Verify marketplace configuration + assert result.enable_marketplace is False + + # Verify plugin package size (uses default value from dify_config) + assert result.max_plugin_package_size == 15728640 + + def test_get_features_billing_disabled(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test feature retrieval when billing is disabled. + + This test verifies: + - Proper feature model creation without billing + - Correct environment variable handling + - Default configuration values + - Return value correctness and structure + """ + # Arrange: Setup billing disabled mock + with patch("services.feature_service.dify_config") as mock_config: + mock_config.BILLING_ENABLED = False + mock_config.ENTERPRISE_ENABLED = False + mock_config.CAN_REPLACE_LOGO = True + mock_config.MODEL_LB_ENABLED = True + mock_config.DATASET_OPERATOR_ENABLED = True + mock_config.EDUCATION_ENABLED = True + + tenant_id = self._create_test_tenant_id() + + # Act: Execute the method under test + result = FeatureService.get_features(tenant_id) + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, FeatureModel) + + # Verify billing is disabled + assert result.billing.enabled is False + + # Verify environment-based features + assert result.can_replace_logo is True + assert result.model_load_balancing_enabled is True + assert result.dataset_operator_enabled is True + assert result.education.enabled is True + + # Verify default limitations + assert result.members.size == 0 + assert result.members.limit == 1 + assert result.apps.size == 0 + assert result.apps.limit == 10 + assert result.vector_space.size == 0 + assert result.vector_space.limit == 5 + assert result.documents_upload_quota.size == 0 + assert result.documents_upload_quota.limit == 50 + assert result.annotation_quota_limit.size == 0 + assert result.annotation_quota_limit.limit == 10 + assert result.knowledge_rate_limit == 10 + assert result.docs_processing == "standard" + + # Verify no enterprise features + assert result.workspace_members.enabled is False + assert result.webapp_copyright_enabled is False + + def test_get_knowledge_rate_limit_billing_disabled( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test knowledge rate limit retrieval when billing is disabled. + + This test verifies: + - Proper knowledge rate limit model creation without billing + - Default rate limit configuration + - Return value correctness and structure + """ + # Arrange: Setup billing disabled mock + with patch("services.feature_service.dify_config") as mock_config: + mock_config.BILLING_ENABLED = False + + tenant_id = self._create_test_tenant_id() + + # Act: Execute the method under test + result = FeatureService.get_knowledge_rate_limit(tenant_id) + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, KnowledgeRateLimitModel) + + # Verify default configuration + assert result.enabled is False + assert result.limit == 10 + assert result.subscription_plan == "" # Empty string when billing is disabled + + # Verify no billing service calls + mock_external_service_dependencies["billing_service"].get_knowledge_rate_limit.assert_not_called() + + def test_get_features_enterprise_only(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test feature retrieval with enterprise enabled but billing disabled. + + This test verifies: + - Proper feature model creation with enterprise only + - Correct enterprise service integration + - Proper workspace member handling + - Return value correctness and structure + """ + # Arrange: Setup enterprise only mock + with patch("services.feature_service.dify_config") as mock_config: + mock_config.BILLING_ENABLED = False + mock_config.ENTERPRISE_ENABLED = True + mock_config.CAN_REPLACE_LOGO = False + mock_config.MODEL_LB_ENABLED = False + mock_config.DATASET_OPERATOR_ENABLED = False + mock_config.EDUCATION_ENABLED = False + + tenant_id = self._create_test_tenant_id() + + # Act: Execute the method under test + result = FeatureService.get_features(tenant_id) + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, FeatureModel) + + # Verify billing is disabled + assert result.billing.enabled is False + + # Verify enterprise features + assert result.webapp_copyright_enabled is True + + # Verify workspace members from enterprise + assert result.workspace_members.enabled is True + assert result.workspace_members.size == 5 + assert result.workspace_members.limit == 10 + + # Verify environment-based features + assert result.can_replace_logo is False + assert result.model_load_balancing_enabled is False + assert result.dataset_operator_enabled is False + assert result.education.enabled is False + + # Verify default limitations + assert result.members.size == 0 + assert result.members.limit == 1 + assert result.apps.size == 0 + assert result.apps.limit == 10 + assert result.vector_space.size == 0 + assert result.vector_space.limit == 5 + + # Verify mock interactions + mock_external_service_dependencies["enterprise_service"].get_workspace_info.assert_called_once_with( + tenant_id + ) + mock_external_service_dependencies["billing_service"].get_info.assert_not_called() + + def test_get_system_features_enterprise_disabled( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test system features retrieval when enterprise is disabled. + + This test verifies: + - Proper system feature model creation without enterprise + - Correct environment variable handling + - Default configuration values + - Return value correctness and structure + """ + # Arrange: Setup enterprise disabled mock + with patch("services.feature_service.dify_config") as mock_config: + mock_config.ENTERPRISE_ENABLED = False + mock_config.MARKETPLACE_ENABLED = True + mock_config.ENABLE_EMAIL_CODE_LOGIN = False + mock_config.ENABLE_EMAIL_PASSWORD_LOGIN = True + mock_config.ENABLE_SOCIAL_OAUTH_LOGIN = True + mock_config.ALLOW_REGISTER = False + mock_config.ALLOW_CREATE_WORKSPACE = False + mock_config.MAIL_TYPE = None + mock_config.PLUGIN_MAX_PACKAGE_SIZE = 50 + + # Act: Execute the method under test + result = FeatureService.get_system_features() + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, SystemFeatureModel) + + # Verify enterprise features are disabled + assert result.branding.enabled is False + assert result.webapp_auth.enabled is False + assert result.enable_change_email is True + + # Verify authentication settings from config + assert result.enable_email_code_login is False + assert result.enable_email_password_login is True + assert result.enable_social_oauth_login is True + assert result.is_allow_register is False + assert result.is_allow_create_workspace is False + assert result.is_email_setup is False + + # Verify marketplace configuration + assert result.enable_marketplace is True + + # Verify plugin package size (uses default value from dify_config) + assert result.max_plugin_package_size == 15728640 + + # Verify default license status + assert result.license.status.value == "none" + assert result.license.expired_at == "" + assert result.license.workspaces.enabled is False + + # Verify no enterprise service calls + mock_external_service_dependencies["enterprise_service"].get_info.assert_not_called() + + def test_get_features_no_tenant_id(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test feature retrieval without tenant ID (billing disabled). + + This test verifies: + - Proper feature model creation without tenant ID + - Correct handling when billing is disabled + - Default configuration values + - Return value correctness and structure + """ + # Arrange: Setup no tenant ID scenario + with patch("services.feature_service.dify_config") as mock_config: + mock_config.BILLING_ENABLED = True + mock_config.ENTERPRISE_ENABLED = False + mock_config.CAN_REPLACE_LOGO = True + mock_config.MODEL_LB_ENABLED = False + mock_config.DATASET_OPERATOR_ENABLED = True + mock_config.EDUCATION_ENABLED = False + + # Act: Execute the method under test + result = FeatureService.get_features("") + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, FeatureModel) + + # Verify billing is disabled due to no tenant ID + assert result.billing.enabled is False + + # Verify environment-based features + assert result.can_replace_logo is True + assert result.model_load_balancing_enabled is False + assert result.dataset_operator_enabled is True + assert result.education.enabled is False + + # Verify default limitations + assert result.members.size == 0 + assert result.members.limit == 1 + assert result.apps.size == 0 + assert result.apps.limit == 10 + assert result.vector_space.size == 0 + assert result.vector_space.limit == 5 + + # Verify no billing service calls + mock_external_service_dependencies["billing_service"].get_info.assert_not_called() + + def test_get_features_partial_billing_info(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test feature retrieval with partial billing information. + + This test verifies: + - Proper handling of partial billing data + - Correct fallback to default values + - Proper billing service integration + - Return value correctness and structure + """ + # Arrange: Setup partial billing info mock with proper config + tenant_id = self._create_test_tenant_id() + + with patch("services.feature_service.dify_config") as mock_config: + mock_config.BILLING_ENABLED = True + mock_config.ENTERPRISE_ENABLED = False + mock_config.CAN_REPLACE_LOGO = True + mock_config.MODEL_LB_ENABLED = False + mock_config.DATASET_OPERATOR_ENABLED = True + mock_config.EDUCATION_ENABLED = False + + mock_external_service_dependencies["billing_service"].get_info.return_value = { + "enabled": True, + "subscription": {"plan": "basic", "interval": "yearly"}, + # Missing members, apps, vector_space, etc. + } + + # Act: Execute the method under test + result = FeatureService.get_features(tenant_id) + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, FeatureModel) + + # Verify billing features + assert result.billing.enabled is True + assert result.billing.subscription.plan == "basic" + assert result.billing.subscription.interval == "yearly" + + # Verify default values for missing billing info + assert result.members.size == 0 + assert result.members.limit == 1 + assert result.apps.size == 0 + assert result.apps.limit == 10 + assert result.vector_space.size == 0 + assert result.vector_space.limit == 5 + assert result.documents_upload_quota.size == 0 + assert result.documents_upload_quota.limit == 50 + assert result.annotation_quota_limit.size == 0 + assert result.annotation_quota_limit.limit == 10 + assert result.knowledge_rate_limit == 10 + assert result.docs_processing == "standard" + + # Verify basic plan restrictions (non-sandbox plans have webapp copyright enabled) + assert result.webapp_copyright_enabled is True + assert result.is_allow_transfer_workspace is True + + # Verify mock interactions + mock_external_service_dependencies["billing_service"].get_info.assert_called_once_with(tenant_id) + + def test_get_features_edge_case_vector_space(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test feature retrieval with edge case vector space configuration. + + This test verifies: + - Proper handling of vector space quota limits + - Correct integration with billing service + - Proper fallback to default values + - Return value correctness and structure + """ + # Arrange: Setup edge case vector space mock with proper config + tenant_id = self._create_test_tenant_id() + + with patch("services.feature_service.dify_config") as mock_config: + mock_config.BILLING_ENABLED = True + mock_config.ENTERPRISE_ENABLED = False + mock_config.CAN_REPLACE_LOGO = True + mock_config.MODEL_LB_ENABLED = False + mock_config.DATASET_OPERATOR_ENABLED = True + mock_config.EDUCATION_ENABLED = False + + mock_external_service_dependencies["billing_service"].get_info.return_value = { + "enabled": True, + "subscription": {"plan": "pro", "interval": "monthly"}, + "vector_space": {"size": 0, "limit": 0}, + "apps": {"size": 5, "limit": 10}, + } + + # Act: Execute the method under test + result = FeatureService.get_features(tenant_id) + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, FeatureModel) + + # Verify vector space configuration + assert result.vector_space.size == 0 + assert result.vector_space.limit == 0 + + # Verify apps configuration + assert result.apps.size == 5 + assert result.apps.limit == 10 + + # Verify pro plan features + assert result.webapp_copyright_enabled is True + assert result.is_allow_transfer_workspace is True + + # Verify default values for missing billing info + assert result.members.size == 0 + assert result.members.limit == 1 + assert result.documents_upload_quota.size == 0 + assert result.documents_upload_quota.limit == 50 + assert result.annotation_quota_limit.size == 0 + assert result.annotation_quota_limit.limit == 10 + assert result.knowledge_rate_limit == 10 + assert result.docs_processing == "standard" + + # Verify mock interactions + mock_external_service_dependencies["billing_service"].get_info.assert_called_once_with(tenant_id) + + def test_get_system_features_edge_case_webapp_auth( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test system features retrieval with edge case webapp auth configuration. + + This test verifies: + - Proper handling of webapp auth configuration + - Correct enterprise service integration + - Proper fallback to default values + - Return value correctness and structure + """ + # Arrange: Setup edge case webapp auth mock with proper config + with patch("services.feature_service.dify_config") as mock_config: + mock_config.ENTERPRISE_ENABLED = True + mock_config.MARKETPLACE_ENABLED = False + mock_config.ENABLE_EMAIL_CODE_LOGIN = False + mock_config.ENABLE_EMAIL_PASSWORD_LOGIN = True + mock_config.ENABLE_SOCIAL_OAUTH_LOGIN = False + mock_config.ALLOW_REGISTER = False + mock_config.ALLOW_CREATE_WORKSPACE = False + mock_config.MAIL_TYPE = "smtp" + mock_config.PLUGIN_MAX_PACKAGE_SIZE = 100 + + mock_external_service_dependencies["enterprise_service"].get_info.return_value = { + "WebAppAuth": {"allowSso": False, "allowEmailCodeLogin": True, "allowEmailPasswordLogin": False} + } + + # Act: Execute the method under test + result = FeatureService.get_system_features() + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, SystemFeatureModel) + + # Verify webapp auth configuration + assert result.webapp_auth.allow_sso is False + assert result.webapp_auth.allow_email_code_login is True + assert result.webapp_auth.allow_email_password_login is False + assert result.webapp_auth.sso_config.protocol == "" + + # Verify enterprise features + assert result.branding.enabled is True + assert result.webapp_auth.enabled is True + assert result.enable_change_email is False + + # Verify default values for missing enterprise info + assert result.sso_enforced_for_signin is False + assert result.sso_enforced_for_signin_protocol == "" + assert result.enable_email_code_login is False + assert result.enable_email_password_login is True + assert result.is_allow_register is False + assert result.is_allow_create_workspace is False + + # Verify mock interactions + mock_external_service_dependencies["enterprise_service"].get_info.assert_called_once() + + def test_get_features_edge_case_members_quota(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test feature retrieval with edge case members quota configuration. + + This test verifies: + - Proper handling of members quota limits + - Correct integration with billing service + - Proper fallback to default values + - Return value correctness and structure + """ + # Arrange: Setup edge case members quota mock with proper config + tenant_id = self._create_test_tenant_id() + + with patch("services.feature_service.dify_config") as mock_config: + mock_config.BILLING_ENABLED = True + mock_config.ENTERPRISE_ENABLED = False + mock_config.CAN_REPLACE_LOGO = True + mock_config.MODEL_LB_ENABLED = False + mock_config.DATASET_OPERATOR_ENABLED = True + mock_config.EDUCATION_ENABLED = False + + mock_external_service_dependencies["billing_service"].get_info.return_value = { + "enabled": True, + "subscription": {"plan": "basic", "interval": "yearly"}, + "members": {"size": 10, "limit": 10}, + "vector_space": {"size": 3, "limit": 5}, + } + + # Act: Execute the method under test + result = FeatureService.get_features(tenant_id) + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, FeatureModel) + + # Verify members configuration + assert result.members.size == 10 + assert result.members.limit == 10 + + # Verify vector space configuration + assert result.vector_space.size == 3 + assert result.vector_space.limit == 5 + + # Verify basic plan features (non-sandbox plans have webapp copyright enabled) + assert result.webapp_copyright_enabled is True + assert result.is_allow_transfer_workspace is True + + # Verify default values for missing billing info + assert result.apps.size == 0 + assert result.apps.limit == 10 + assert result.documents_upload_quota.size == 0 + assert result.documents_upload_quota.limit == 50 + assert result.annotation_quota_limit.size == 0 + assert result.annotation_quota_limit.limit == 10 + assert result.knowledge_rate_limit == 10 + assert result.docs_processing == "standard" + + # Verify mock interactions + mock_external_service_dependencies["billing_service"].get_info.assert_called_once_with(tenant_id) + + def test_plugin_installation_permission_scopes( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test system features retrieval with different plugin installation permission scopes. + + This test verifies: + - Proper handling of different plugin installation scopes + - Correct enterprise service integration + - Proper permission configuration + - Return value correctness and structure + """ + + # Test case 1: Official only scope + with patch("services.feature_service.dify_config") as mock_config: + mock_config.ENTERPRISE_ENABLED = True + mock_config.MARKETPLACE_ENABLED = False + mock_config.ENABLE_EMAIL_CODE_LOGIN = False + mock_config.ENABLE_EMAIL_PASSWORD_LOGIN = True + mock_config.ENABLE_SOCIAL_OAUTH_LOGIN = False + mock_config.ALLOW_REGISTER = False + mock_config.ALLOW_CREATE_WORKSPACE = False + mock_config.MAIL_TYPE = "smtp" + mock_config.PLUGIN_MAX_PACKAGE_SIZE = 100 + + mock_external_service_dependencies["enterprise_service"].get_info.return_value = { + "PluginInstallationPermission": { + "pluginInstallationScope": "official_only", + "restrictToMarketplaceOnly": True, + } + } + + result = FeatureService.get_system_features() + assert result.plugin_installation_permission.plugin_installation_scope == "official_only" + assert result.plugin_installation_permission.restrict_to_marketplace_only is True + + # Test case 2: All plugins scope + with patch("services.feature_service.dify_config") as mock_config: + mock_config.ENTERPRISE_ENABLED = True + mock_config.MARKETPLACE_ENABLED = False + mock_config.ENABLE_EMAIL_CODE_LOGIN = False + mock_config.ENABLE_EMAIL_PASSWORD_LOGIN = True + mock_config.ENABLE_SOCIAL_OAUTH_LOGIN = False + mock_config.ALLOW_REGISTER = False + mock_config.ALLOW_CREATE_WORKSPACE = False + mock_config.MAIL_TYPE = "smtp" + mock_config.PLUGIN_MAX_PACKAGE_SIZE = 100 + + mock_external_service_dependencies["enterprise_service"].get_info.return_value = { + "PluginInstallationPermission": {"pluginInstallationScope": "all", "restrictToMarketplaceOnly": False} + } + + result = FeatureService.get_system_features() + assert result.plugin_installation_permission.plugin_installation_scope == "all" + assert result.plugin_installation_permission.restrict_to_marketplace_only is False + + # Test case 3: Specific partners scope + with patch("services.feature_service.dify_config") as mock_config: + mock_config.ENTERPRISE_ENABLED = True + mock_config.MARKETPLACE_ENABLED = False + mock_config.ENABLE_EMAIL_CODE_LOGIN = False + mock_config.ENABLE_EMAIL_PASSWORD_LOGIN = True + mock_config.ENABLE_SOCIAL_OAUTH_LOGIN = False + mock_config.ALLOW_REGISTER = False + mock_config.ALLOW_CREATE_WORKSPACE = False + mock_config.MAIL_TYPE = "smtp" + mock_config.PLUGIN_MAX_PACKAGE_SIZE = 100 + + mock_external_service_dependencies["enterprise_service"].get_info.return_value = { + "PluginInstallationPermission": { + "pluginInstallationScope": "official_and_specific_partners", + "restrictToMarketplaceOnly": False, + } + } + + result = FeatureService.get_system_features() + assert result.plugin_installation_permission.plugin_installation_scope == "official_and_specific_partners" + assert result.plugin_installation_permission.restrict_to_marketplace_only is False + + # Test case 4: None scope + with patch("services.feature_service.dify_config") as mock_config: + mock_config.ENTERPRISE_ENABLED = True + mock_config.MARKETPLACE_ENABLED = False + mock_config.ENABLE_EMAIL_CODE_LOGIN = False + mock_config.ENABLE_EMAIL_PASSWORD_LOGIN = True + mock_config.ENABLE_SOCIAL_OAUTH_LOGIN = False + mock_config.ALLOW_REGISTER = False + mock_config.ALLOW_CREATE_WORKSPACE = False + mock_config.MAIL_TYPE = "smtp" + mock_config.PLUGIN_MAX_PACKAGE_SIZE = 100 + + mock_external_service_dependencies["enterprise_service"].get_info.return_value = { + "PluginInstallationPermission": {"pluginInstallationScope": "none", "restrictToMarketplaceOnly": True} + } + + result = FeatureService.get_system_features() + assert result.plugin_installation_permission.plugin_installation_scope == "none" + assert result.plugin_installation_permission.restrict_to_marketplace_only is True + + def test_get_features_workspace_members_missing( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test feature retrieval when workspace members info is missing from enterprise. + + This test verifies: + - Proper handling of missing workspace members data + - Correct enterprise service integration + - Proper fallback to default values + - Return value correctness and structure + """ + # Arrange: Setup missing workspace members mock + tenant_id = self._create_test_tenant_id() + mock_external_service_dependencies["enterprise_service"].get_workspace_info.return_value = { + # Missing WorkspaceMembers key + } + + with patch("services.feature_service.dify_config") as mock_config: + mock_config.BILLING_ENABLED = False + mock_config.ENTERPRISE_ENABLED = True + + # Act: Execute the method under test + result = FeatureService.get_features(tenant_id) + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, FeatureModel) + + # Verify workspace members use default values + assert result.workspace_members.enabled is False + assert result.workspace_members.size == 0 + assert result.workspace_members.limit == 0 + + # Verify enterprise features + assert result.webapp_copyright_enabled is True + + # Verify mock interactions + mock_external_service_dependencies["enterprise_service"].get_workspace_info.assert_called_once_with( + tenant_id + ) + + def test_get_system_features_license_inactive(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test system features retrieval with inactive license. + + This test verifies: + - Proper handling of inactive license status + - Correct enterprise service integration + - Proper license status handling + - Return value correctness and structure + """ + # Arrange: Setup inactive license mock with proper config + with patch("services.feature_service.dify_config") as mock_config: + mock_config.ENTERPRISE_ENABLED = True + mock_config.MARKETPLACE_ENABLED = False + mock_config.ENABLE_EMAIL_CODE_LOGIN = False + mock_config.ENABLE_EMAIL_PASSWORD_LOGIN = True + mock_config.ENABLE_SOCIAL_OAUTH_LOGIN = False + mock_config.ALLOW_REGISTER = False + mock_config.ALLOW_CREATE_WORKSPACE = False + mock_config.MAIL_TYPE = "smtp" + mock_config.PLUGIN_MAX_PACKAGE_SIZE = 100 + + mock_external_service_dependencies["enterprise_service"].get_info.return_value = { + "License": { + "status": "inactive", + "expiredAt": "", + "workspaces": {"enabled": False, "limit": 0, "used": 0}, + } + } + + # Act: Execute the method under test + result = FeatureService.get_system_features() + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, SystemFeatureModel) + + # Verify license status + assert result.license.status == "inactive" + assert result.license.expired_at == "" + assert result.license.workspaces.enabled is False + assert result.license.workspaces.size == 0 + assert result.license.workspaces.limit == 0 + + # Verify enterprise features + assert result.branding.enabled is True + assert result.webapp_auth.enabled is True + assert result.enable_change_email is False + + # Verify mock interactions + mock_external_service_dependencies["enterprise_service"].get_info.assert_called_once() + + def test_get_system_features_partial_enterprise_info( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test system features retrieval with partial enterprise information. + + This test verifies: + - Proper handling of partial enterprise data + - Correct fallback to default values + - Proper enterprise service integration + - Return value correctness and structure + """ + # Arrange: Setup partial enterprise info mock with proper config + with patch("services.feature_service.dify_config") as mock_config: + mock_config.ENTERPRISE_ENABLED = True + mock_config.MARKETPLACE_ENABLED = False + mock_config.ENABLE_EMAIL_CODE_LOGIN = False + mock_config.ENABLE_EMAIL_PASSWORD_LOGIN = True + mock_config.ENABLE_SOCIAL_OAUTH_LOGIN = False + mock_config.ALLOW_REGISTER = False + mock_config.ALLOW_CREATE_WORKSPACE = False + mock_config.MAIL_TYPE = "smtp" + mock_config.PLUGIN_MAX_PACKAGE_SIZE = 100 + + mock_external_service_dependencies["enterprise_service"].get_info.return_value = { + "SSOEnforcedForSignin": True, + "Branding": {"applicationTitle": "Partial Enterprise"}, + # Missing WebAppAuth, License, PluginInstallationPermission, etc. + } + + # Act: Execute the method under test + result = FeatureService.get_system_features() + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, SystemFeatureModel) + + # Verify enterprise features + assert result.branding.enabled is True + assert result.webapp_auth.enabled is True + assert result.enable_change_email is False + + # Verify SSO configuration + assert result.sso_enforced_for_signin is True + assert result.sso_enforced_for_signin_protocol == "" + + # Verify branding configuration (partial) + assert result.branding.application_title == "Partial Enterprise" + assert result.branding.login_page_logo == "" + assert result.branding.workspace_logo == "" + assert result.branding.favicon == "" + + # Verify default values for missing enterprise info + assert result.webapp_auth.allow_sso is False + assert result.webapp_auth.allow_email_code_login is False + assert result.webapp_auth.allow_email_password_login is False + assert result.webapp_auth.sso_config.protocol == "" + + # Verify default license status + assert result.license.status == "none" + assert result.license.expired_at == "" + assert result.license.workspaces.enabled is False + + # Verify default plugin installation permission + assert result.plugin_installation_permission.plugin_installation_scope == "all" + assert result.plugin_installation_permission.restrict_to_marketplace_only is False + + # Verify mock interactions + mock_external_service_dependencies["enterprise_service"].get_info.assert_called_once() + + def test_get_features_edge_case_limits(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test feature retrieval with edge case limit values. + + This test verifies: + - Proper handling of zero and negative limits + - Correct handling of very large limits + - Proper fallback to default values + - Return value correctness and structure + """ + # Arrange: Setup edge case limits mock with proper config + tenant_id = self._create_test_tenant_id() + + with patch("services.feature_service.dify_config") as mock_config: + mock_config.BILLING_ENABLED = True + mock_config.ENTERPRISE_ENABLED = False + mock_config.CAN_REPLACE_LOGO = True + mock_config.MODEL_LB_ENABLED = False + mock_config.DATASET_OPERATOR_ENABLED = True + mock_config.EDUCATION_ENABLED = False + + mock_external_service_dependencies["billing_service"].get_info.return_value = { + "enabled": True, + "subscription": {"plan": "enterprise", "interval": "yearly"}, + "members": {"size": 0, "limit": 0}, + "apps": {"size": 0, "limit": -1}, + "vector_space": {"size": 0, "limit": 999999}, + "documents_upload_quota": {"size": 0, "limit": 0}, + "annotation_quota_limit": {"size": 0, "limit": 1}, + } + + # Act: Execute the method under test + result = FeatureService.get_features(tenant_id) + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, FeatureModel) + + # Verify edge case limits + assert result.members.size == 0 + assert result.members.limit == 0 + assert result.apps.size == 0 + assert result.apps.limit == -1 + assert result.vector_space.size == 0 + assert result.vector_space.limit == 999999 + assert result.documents_upload_quota.size == 0 + assert result.documents_upload_quota.limit == 0 + assert result.annotation_quota_limit.size == 0 + assert result.annotation_quota_limit.limit == 1 + + # Verify enterprise plan features + assert result.webapp_copyright_enabled is True + assert result.is_allow_transfer_workspace is True + + # Verify mock interactions + mock_external_service_dependencies["billing_service"].get_info.assert_called_once_with(tenant_id) + + def test_get_system_features_edge_case_protocols( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test system features retrieval with edge case protocol values. + + This test verifies: + - Proper handling of empty protocol strings + - Correct handling of special protocol values + - Proper fallback to default values + - Return value correctness and structure + """ + # Arrange: Setup edge case protocols mock with proper config + with patch("services.feature_service.dify_config") as mock_config: + mock_config.ENTERPRISE_ENABLED = True + mock_config.MARKETPLACE_ENABLED = False + mock_config.ENABLE_EMAIL_CODE_LOGIN = False + mock_config.ENABLE_EMAIL_PASSWORD_LOGIN = True + mock_config.ENABLE_SOCIAL_OAUTH_LOGIN = False + mock_config.ALLOW_REGISTER = False + mock_config.ALLOW_CREATE_WORKSPACE = False + mock_config.MAIL_TYPE = "smtp" + mock_config.PLUGIN_MAX_PACKAGE_SIZE = 100 + + mock_external_service_dependencies["enterprise_service"].get_info.return_value = { + "SSOEnforcedForSigninProtocol": "", + "SSOEnforcedForWebProtocol": " ", + "WebAppAuth": {"allowSso": True, "allowEmailCodeLogin": False, "allowEmailPasswordLogin": True}, + } + + # Act: Execute the method under test + result = FeatureService.get_system_features() + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, SystemFeatureModel) + + # Verify edge case protocols + assert result.sso_enforced_for_signin_protocol == "" + assert result.webapp_auth.sso_config.protocol == " " + + # Verify webapp auth configuration + assert result.webapp_auth.allow_sso is True + assert result.webapp_auth.allow_email_code_login is False + assert result.webapp_auth.allow_email_password_login is True + + # Verify enterprise features + assert result.branding.enabled is True + assert result.webapp_auth.enabled is True + assert result.enable_change_email is False + + # Verify mock interactions + mock_external_service_dependencies["enterprise_service"].get_info.assert_called_once() + + def test_get_features_edge_case_education(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test feature retrieval with edge case education configuration. + + This test verifies: + - Proper handling of education feature flags + - Correct integration with billing service + - Proper fallback to default values + - Return value correctness and structure + """ + # Arrange: Setup edge case education mock + tenant_id = self._create_test_tenant_id() + mock_external_service_dependencies["billing_service"].get_info.return_value = { + "enabled": True, + "subscription": {"plan": "education", "interval": "semester", "education": True}, + "members": {"size": 100, "limit": 200}, + "apps": {"size": 50, "limit": 100}, + "vector_space": {"size": 20, "limit": 50}, + "documents_upload_quota": {"size": 500, "limit": 1000}, + "annotation_quota_limit": {"size": 200, "limit": 500}, + } + + with patch("services.feature_service.dify_config") as mock_config: + mock_config.EDUCATION_ENABLED = True + + # Act: Execute the method under test + result = FeatureService.get_features(tenant_id) + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, FeatureModel) + + # Verify education features + assert result.education.enabled is True + assert result.education.activated is True + + # Verify education plan limits + assert result.members.size == 100 + assert result.members.limit == 200 + assert result.apps.size == 50 + assert result.apps.limit == 100 + assert result.vector_space.size == 20 + assert result.vector_space.limit == 50 + assert result.documents_upload_quota.size == 500 + assert result.documents_upload_quota.limit == 1000 + assert result.annotation_quota_limit.size == 200 + assert result.annotation_quota_limit.limit == 500 + + # Verify education plan features + assert result.webapp_copyright_enabled is True + assert result.is_allow_transfer_workspace is True + + # Verify mock interactions + mock_external_service_dependencies["billing_service"].get_info.assert_called_once_with(tenant_id) + + def test_license_limitation_model_is_available( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test LicenseLimitationModel.is_available method with various scenarios. + + This test verifies: + - Proper quota availability calculation + - Correct handling of unlimited limits + - Proper handling of disabled limits + - Return value correctness for different scenarios + """ + from services.feature_service import LicenseLimitationModel + + # Test case 1: Limit disabled + disabled_limit = LicenseLimitationModel(enabled=False, size=5, limit=10) + assert disabled_limit.is_available(3) is True + assert disabled_limit.is_available(10) is True + + # Test case 2: Unlimited limit + unlimited_limit = LicenseLimitationModel(enabled=True, size=5, limit=0) + assert unlimited_limit.is_available(3) is True + assert unlimited_limit.is_available(100) is True + + # Test case 3: Available quota + available_limit = LicenseLimitationModel(enabled=True, size=5, limit=10) + assert available_limit.is_available(3) is True + assert available_limit.is_available(5) is True + assert available_limit.is_available(1) is True + + # Test case 4: Insufficient quota + insufficient_limit = LicenseLimitationModel(enabled=True, size=8, limit=10) + assert insufficient_limit.is_available(3) is False + assert insufficient_limit.is_available(2) is True + assert insufficient_limit.is_available(1) is True + + # Test case 5: Exact quota usage + exact_limit = LicenseLimitationModel(enabled=True, size=7, limit=10) + assert exact_limit.is_available(3) is True + assert exact_limit.is_available(3) is True + + def test_get_features_workspace_members_disabled( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test feature retrieval when workspace members are disabled in enterprise. + + This test verifies: + - Proper handling of disabled workspace members + - Correct enterprise service integration + - Proper fallback to default values + - Return value correctness and structure + """ + # Arrange: Setup workspace members disabled mock + tenant_id = self._create_test_tenant_id() + mock_external_service_dependencies["enterprise_service"].get_workspace_info.return_value = { + "WorkspaceMembers": {"used": 0, "limit": 0, "enabled": False} + } + + with patch("services.feature_service.dify_config") as mock_config: + mock_config.BILLING_ENABLED = False + mock_config.ENTERPRISE_ENABLED = True + + # Act: Execute the method under test + result = FeatureService.get_features(tenant_id) + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, FeatureModel) + + # Verify workspace members are disabled + assert result.workspace_members.enabled is False + assert result.workspace_members.size == 0 + assert result.workspace_members.limit == 0 + + # Verify enterprise features + assert result.webapp_copyright_enabled is True + + # Verify mock interactions + mock_external_service_dependencies["enterprise_service"].get_workspace_info.assert_called_once_with(tenant_id) + + def test_get_system_features_license_expired(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test system features retrieval with expired license. + + This test verifies: + - Proper handling of expired license status + - Correct enterprise service integration + - Proper license status handling + - Return value correctness and structure + """ + # Arrange: Setup expired license mock with proper config + with patch("services.feature_service.dify_config") as mock_config: + mock_config.ENTERPRISE_ENABLED = True + mock_config.MARKETPLACE_ENABLED = False + mock_config.ENABLE_EMAIL_CODE_LOGIN = False + mock_config.ENABLE_EMAIL_PASSWORD_LOGIN = True + mock_config.ENABLE_SOCIAL_OAUTH_LOGIN = False + mock_config.ALLOW_REGISTER = False + mock_config.ALLOW_CREATE_WORKSPACE = False + mock_config.MAIL_TYPE = "smtp" + mock_config.PLUGIN_MAX_PACKAGE_SIZE = 100 + + mock_external_service_dependencies["enterprise_service"].get_info.return_value = { + "License": { + "status": "expired", + "expiredAt": "2023-12-31", + "workspaces": {"enabled": False, "limit": 0, "used": 0}, + } + } + + # Act: Execute the method under test + result = FeatureService.get_system_features() + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, SystemFeatureModel) + + # Verify license status + assert result.license.status == "expired" + assert result.license.expired_at == "2023-12-31" + assert result.license.workspaces.enabled is False + assert result.license.workspaces.size == 0 + assert result.license.workspaces.limit == 0 + + # Verify enterprise features + assert result.branding.enabled is True + assert result.webapp_auth.enabled is True + assert result.enable_change_email is False + + # Verify mock interactions + mock_external_service_dependencies["enterprise_service"].get_info.assert_called_once() + + def test_get_features_edge_case_docs_processing( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test feature retrieval with edge case document processing configuration. + + This test verifies: + - Proper handling of different document processing modes + - Correct integration with billing service + - Proper fallback to default values + - Return value correctness and structure + """ + # Arrange: Setup edge case docs processing mock with proper config + tenant_id = self._create_test_tenant_id() + + with patch("services.feature_service.dify_config") as mock_config: + mock_config.BILLING_ENABLED = True + mock_config.ENTERPRISE_ENABLED = False + mock_config.CAN_REPLACE_LOGO = True + mock_config.MODEL_LB_ENABLED = True + mock_config.DATASET_OPERATOR_ENABLED = True + mock_config.EDUCATION_ENABLED = False + + mock_external_service_dependencies["billing_service"].get_info.return_value = { + "enabled": True, + "subscription": {"plan": "premium", "interval": "monthly"}, + "docs_processing": "advanced", + "can_replace_logo": True, + "model_load_balancing_enabled": True, + } + + # Act: Execute the method under test + result = FeatureService.get_features(tenant_id) + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, FeatureModel) + + # Verify docs processing configuration + assert result.docs_processing == "advanced" + assert result.can_replace_logo is True + assert result.model_load_balancing_enabled is True + + # Verify premium plan features + assert result.webapp_copyright_enabled is True + assert result.is_allow_transfer_workspace is True + + # Verify default limitations (no specific billing info) + assert result.members.size == 0 + assert result.members.limit == 1 + assert result.apps.size == 0 + assert result.apps.limit == 10 + assert result.vector_space.size == 0 + assert result.vector_space.limit == 5 + + # Verify mock interactions + mock_external_service_dependencies["billing_service"].get_info.assert_called_once_with(tenant_id) + + def test_get_system_features_edge_case_branding( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test system features retrieval with edge case branding configuration. + + This test verifies: + - Proper handling of partial branding information + - Correct enterprise service integration + - Proper fallback to default values + - Return value correctness and structure + """ + # Arrange: Setup edge case branding mock with proper config + with patch("services.feature_service.dify_config") as mock_config: + mock_config.ENTERPRISE_ENABLED = True + mock_config.MARKETPLACE_ENABLED = False + mock_config.ENABLE_EMAIL_CODE_LOGIN = False + mock_config.ENABLE_EMAIL_PASSWORD_LOGIN = True + mock_config.ENABLE_SOCIAL_OAUTH_LOGIN = False + mock_config.ALLOW_REGISTER = False + mock_config.ALLOW_CREATE_WORKSPACE = False + mock_config.MAIL_TYPE = "smtp" + mock_config.PLUGIN_MAX_PACKAGE_SIZE = 100 + + mock_external_service_dependencies["enterprise_service"].get_info.return_value = { + "Branding": { + "applicationTitle": "Edge Case App", + "loginPageLogo": None, + "workspaceLogo": "", + "favicon": "https://example.com/favicon.ico", + } + } + + # Act: Execute the method under test + result = FeatureService.get_system_features() + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, SystemFeatureModel) + + # Verify branding configuration (edge cases) + assert result.branding.application_title == "Edge Case App" + assert result.branding.login_page_logo is None # None value from mock + assert result.branding.workspace_logo == "" + assert result.branding.favicon == "https://example.com/favicon.ico" + + # Verify enterprise features + assert result.branding.enabled is True + assert result.webapp_auth.enabled is True + assert result.enable_change_email is False + + # Verify default values for missing enterprise info + assert result.sso_enforced_for_signin is False + assert result.sso_enforced_for_signin_protocol == "" + assert result.enable_email_code_login is False + assert result.enable_email_password_login is True + assert result.is_allow_register is False + assert result.is_allow_create_workspace is False + + # Verify mock interactions + mock_external_service_dependencies["enterprise_service"].get_info.assert_called_once() + + def test_get_features_edge_case_annotation_quota( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test feature retrieval with edge case annotation quota configuration. + + This test verifies: + - Proper handling of annotation quota limits + - Correct integration with billing service + - Proper fallback to default values + - Return value correctness and structure + """ + # Arrange: Setup edge case annotation quota mock with proper config + tenant_id = self._create_test_tenant_id() + + with patch("services.feature_service.dify_config") as mock_config: + mock_config.BILLING_ENABLED = True + mock_config.ENTERPRISE_ENABLED = False + mock_config.CAN_REPLACE_LOGO = True + mock_config.MODEL_LB_ENABLED = False + mock_config.DATASET_OPERATOR_ENABLED = True + mock_config.EDUCATION_ENABLED = False + + mock_external_service_dependencies["billing_service"].get_info.return_value = { + "enabled": True, + "subscription": {"plan": "enterprise", "interval": "yearly"}, + "annotation_quota_limit": {"size": 999, "limit": 1000}, + "knowledge_rate_limit": {"limit": 500}, + } + + # Act: Execute the method under test + result = FeatureService.get_features(tenant_id) + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, FeatureModel) + + # Verify annotation quota configuration + assert result.annotation_quota_limit.size == 999 + assert result.annotation_quota_limit.limit == 1000 + + # Verify knowledge rate limit + assert result.knowledge_rate_limit == 500 + + # Verify enterprise plan features + assert result.webapp_copyright_enabled is True + assert result.is_allow_transfer_workspace is True + + # Verify default values for missing billing info + assert result.members.size == 0 + assert result.members.limit == 1 + assert result.apps.size == 0 + assert result.apps.limit == 10 + assert result.vector_space.size == 0 + assert result.vector_space.limit == 5 + assert result.documents_upload_quota.size == 0 + assert result.documents_upload_quota.limit == 50 + assert result.docs_processing == "standard" + + # Verify mock interactions + mock_external_service_dependencies["billing_service"].get_info.assert_called_once_with(tenant_id) + + def test_get_features_edge_case_documents_upload( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test feature retrieval with edge case documents upload settings. + + This test verifies: + - Proper handling of edge case documents upload configuration + - Correct integration with billing service + - Proper fallback to default values + - Return value correctness and structure + """ + # Arrange: Setup edge case documents upload mock with proper config + tenant_id = self._create_test_tenant_id() + + with patch("services.feature_service.dify_config") as mock_config: + mock_config.BILLING_ENABLED = True + mock_config.ENTERPRISE_ENABLED = False + mock_config.CAN_REPLACE_LOGO = True + mock_config.MODEL_LB_ENABLED = False + mock_config.DATASET_OPERATOR_ENABLED = True + mock_config.EDUCATION_ENABLED = False + + mock_external_service_dependencies["billing_service"].get_info.return_value = { + "enabled": True, + "subscription": {"plan": "pro", "interval": "monthly"}, + "documents_upload_quota": { + "size": 0, # Edge case: zero current size + "limit": 0, # Edge case: zero limit + }, + "knowledge_rate_limit": {"limit": 100}, + } + + # Act: Execute the method under test + result = FeatureService.get_features(tenant_id) + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, FeatureModel) + + # Verify documents upload quota configuration (edge cases) + assert result.documents_upload_quota.size == 0 + assert result.documents_upload_quota.limit == 0 + + # Verify knowledge rate limit + assert result.knowledge_rate_limit == 100 + + # Verify pro plan features + assert result.webapp_copyright_enabled is True + assert result.is_allow_transfer_workspace is True + + # Verify default values for missing billing info + assert result.members.size == 0 + assert result.members.limit == 1 + assert result.apps.size == 0 + assert result.apps.limit == 10 + assert result.vector_space.size == 0 + assert result.vector_space.limit == 5 + assert result.annotation_quota_limit.size == 0 + assert result.annotation_quota_limit.limit == 10 # Default value when not provided + assert result.docs_processing == "standard" + + # Verify mock interactions + mock_external_service_dependencies["billing_service"].get_info.assert_called_once_with(tenant_id) + + def test_get_system_features_edge_case_license_lost( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test system features with lost license status. + + This test verifies: + - Proper handling of lost license status + - Correct enterprise service integration + - Proper fallback to default values + - Return value correctness and structure + """ + # Arrange: Setup lost license mock with proper config + with patch("services.feature_service.dify_config") as mock_config: + mock_config.ENTERPRISE_ENABLED = True + mock_config.MARKETPLACE_ENABLED = False + mock_config.ENABLE_EMAIL_CODE_LOGIN = False + mock_config.ENABLE_EMAIL_PASSWORD_LOGIN = True + mock_config.ENABLE_SOCIAL_OAUTH_LOGIN = False + mock_config.ALLOW_REGISTER = False + mock_config.ALLOW_CREATE_WORKSPACE = False + mock_config.MAIL_TYPE = "smtp" + mock_config.PLUGIN_MAX_PACKAGE_SIZE = 100 + + mock_external_service_dependencies["enterprise_service"].get_info.return_value = { + "license": {"status": "lost", "expired_at": None, "plan": None} + } + + # Act: Execute the method under test + result = FeatureService.get_system_features() + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, SystemFeatureModel) + + # Verify enterprise features + assert result.branding.enabled is True + assert result.webapp_auth.enabled is True + assert result.enable_change_email is False + + # Verify default values for missing enterprise info + assert result.sso_enforced_for_signin is False + assert result.sso_enforced_for_signin_protocol == "" + assert result.enable_email_code_login is False + assert result.enable_email_password_login is True + assert result.is_allow_register is False + assert result.is_allow_create_workspace is False + + # Verify mock interactions + mock_external_service_dependencies["enterprise_service"].get_info.assert_called_once() + + def test_get_features_edge_case_education_disabled( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test feature retrieval with education feature disabled. + + This test verifies: + - Proper handling of disabled education features + - Correct integration with billing service + - Proper fallback to default values + - Return value correctness and structure + """ + # Arrange: Setup education disabled mock with proper config + tenant_id = self._create_test_tenant_id() + + with patch("services.feature_service.dify_config") as mock_config: + mock_config.BILLING_ENABLED = True + mock_config.ENTERPRISE_ENABLED = False + mock_config.CAN_REPLACE_LOGO = True + mock_config.MODEL_LB_ENABLED = False + mock_config.DATASET_OPERATOR_ENABLED = True + mock_config.EDUCATION_ENABLED = False + + mock_external_service_dependencies["billing_service"].get_info.return_value = { + "enabled": True, + "subscription": { + "plan": "pro", + "interval": "monthly", + "education": False, # Education explicitly disabled + }, + "knowledge_rate_limit": {"limit": 100}, + } + + # Act: Execute the method under test + result = FeatureService.get_features(tenant_id) + + # Assert: Verify the expected outcomes + assert result is not None + assert isinstance(result, FeatureModel) + + # Verify education configuration + assert result.education.activated is False + + # Verify knowledge rate limit + assert result.knowledge_rate_limit == 100 + + # Verify pro plan features + assert result.webapp_copyright_enabled is True + assert result.is_allow_transfer_workspace is True + + # Verify default values for missing billing info + assert result.members.size == 0 + assert result.members.limit == 1 + assert result.apps.size == 0 + assert result.apps.limit == 10 + assert result.vector_space.size == 0 + assert result.vector_space.limit == 5 + assert result.documents_upload_quota.size == 0 + assert result.documents_upload_quota.limit == 50 + assert result.annotation_quota_limit.size == 0 + assert result.annotation_quota_limit.limit == 10 # Default value when not provided + assert result.docs_processing == "standard" + + # Verify mock interactions + mock_external_service_dependencies["billing_service"].get_info.assert_called_once_with(tenant_id) diff --git a/api/tests/test_containers_integration_tests/services/test_message_service.py b/api/tests/test_containers_integration_tests/services/test_message_service.py index 25ba0d03ef..ece6de6cdf 100644 --- a/api/tests/test_containers_integration_tests/services/test_message_service.py +++ b/api/tests/test_containers_integration_tests/services/test_message_service.py @@ -484,7 +484,7 @@ class TestMessageService: # Verify feedback was deleted from extensions.ext_database import db - deleted_feedback = db.session.query(MessageFeedback).filter(MessageFeedback.id == feedback.id).first() + deleted_feedback = db.session.query(MessageFeedback).where(MessageFeedback.id == feedback.id).first() assert deleted_feedback is None def test_create_feedback_no_rating_when_not_exists( diff --git a/api/tests/test_containers_integration_tests/services/test_metadata_service.py b/api/tests/test_containers_integration_tests/services/test_metadata_service.py new file mode 100644 index 0000000000..7fef572c14 --- /dev/null +++ b/api/tests/test_containers_integration_tests/services/test_metadata_service.py @@ -0,0 +1,1144 @@ +from unittest.mock import patch + +import pytest +from faker import Faker + +from core.rag.index_processor.constant.built_in_field import BuiltInField +from models.account import Account, Tenant, TenantAccountJoin, TenantAccountRole +from models.dataset import Dataset, DatasetMetadata, DatasetMetadataBinding, Document +from services.entities.knowledge_entities.knowledge_entities import MetadataArgs +from services.metadata_service import MetadataService + + +class TestMetadataService: + """Integration tests for MetadataService using testcontainers.""" + + @pytest.fixture + def mock_external_service_dependencies(self): + """Mock setup for external service dependencies.""" + with ( + patch("services.metadata_service.current_user") as mock_current_user, + patch("services.metadata_service.redis_client") as mock_redis_client, + patch("services.dataset_service.DocumentService") as mock_document_service, + ): + # Setup default mock returns + mock_redis_client.get.return_value = None + mock_redis_client.set.return_value = True + mock_redis_client.delete.return_value = 1 + + yield { + "current_user": mock_current_user, + "redis_client": mock_redis_client, + "document_service": mock_document_service, + } + + def _create_test_account_and_tenant(self, db_session_with_containers, mock_external_service_dependencies): + """ + Helper method to create a test account and tenant for testing. + + Args: + db_session_with_containers: Database session from testcontainers infrastructure + mock_external_service_dependencies: Mock dependencies + + Returns: + tuple: (account, tenant) - Created account and tenant instances + """ + fake = Faker() + + # Create account + account = Account( + email=fake.email(), + name=fake.name(), + interface_language="en-US", + status="active", + ) + + from extensions.ext_database import db + + db.session.add(account) + db.session.commit() + + # Create tenant for the account + tenant = Tenant( + name=fake.company(), + status="normal", + ) + db.session.add(tenant) + db.session.commit() + + # Create tenant-account join + join = TenantAccountJoin( + tenant_id=tenant.id, + account_id=account.id, + role=TenantAccountRole.OWNER.value, + current=True, + ) + db.session.add(join) + db.session.commit() + + # Set current tenant for account + account.current_tenant = tenant + + return account, tenant + + def _create_test_dataset(self, db_session_with_containers, mock_external_service_dependencies, account, tenant): + """ + Helper method to create a test dataset for testing. + + Args: + db_session_with_containers: Database session from testcontainers infrastructure + mock_external_service_dependencies: Mock dependencies + account: Account instance + tenant: Tenant instance + + Returns: + Dataset: Created dataset instance + """ + fake = Faker() + + dataset = Dataset( + tenant_id=tenant.id, + name=fake.company(), + description=fake.text(max_nb_chars=100), + data_source_type="upload_file", + created_by=account.id, + built_in_field_enabled=False, + ) + + from extensions.ext_database import db + + db.session.add(dataset) + db.session.commit() + + return dataset + + def _create_test_document(self, db_session_with_containers, mock_external_service_dependencies, dataset, account): + """ + Helper method to create a test document for testing. + + Args: + db_session_with_containers: Database session from testcontainers infrastructure + mock_external_service_dependencies: Mock dependencies + dataset: Dataset instance + account: Account instance + + Returns: + Document: Created document instance + """ + fake = Faker() + + document = Document( + tenant_id=dataset.tenant_id, + dataset_id=dataset.id, + position=1, + data_source_type="upload_file", + data_source_info="{}", + batch="test-batch", + name=fake.file_name(), + created_from="web", + created_by=account.id, + doc_form="text", + doc_language="en", + ) + + from extensions.ext_database import db + + db.session.add(document) + db.session.commit() + + return document + + def test_create_metadata_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful metadata creation with valid parameters. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + metadata_args = MetadataArgs(type="string", name="test_metadata") + + # Act: Execute the method under test + result = MetadataService.create_metadata(dataset.id, metadata_args) + + # Assert: Verify the expected outcomes + assert result is not None + assert result.name == "test_metadata" + assert result.type == "string" + assert result.dataset_id == dataset.id + assert result.tenant_id == tenant.id + assert result.created_by == account.id + + # Verify database state + from extensions.ext_database import db + + db.session.refresh(result) + assert result.id is not None + assert result.created_at is not None + + def test_create_metadata_name_too_long(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test metadata creation fails when name exceeds 255 characters. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + long_name = "a" * 256 # 256 characters, exceeding 255 limit + metadata_args = MetadataArgs(type="string", name=long_name) + + # Act & Assert: Verify proper error handling + with pytest.raises(ValueError, match="Metadata name cannot exceed 255 characters."): + MetadataService.create_metadata(dataset.id, metadata_args) + + def test_create_metadata_name_already_exists(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test metadata creation fails when name already exists in the same dataset. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Create first metadata + first_metadata_args = MetadataArgs(type="string", name="duplicate_name") + MetadataService.create_metadata(dataset.id, first_metadata_args) + + # Try to create second metadata with same name + second_metadata_args = MetadataArgs(type="number", name="duplicate_name") + + # Act & Assert: Verify proper error handling + with pytest.raises(ValueError, match="Metadata name already exists."): + MetadataService.create_metadata(dataset.id, second_metadata_args) + + def test_create_metadata_name_conflicts_with_built_in_field( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test metadata creation fails when name conflicts with built-in field names. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Try to create metadata with built-in field name + built_in_field_name = BuiltInField.document_name.value + metadata_args = MetadataArgs(type="string", name=built_in_field_name) + + # Act & Assert: Verify proper error handling + with pytest.raises(ValueError, match="Metadata name already exists in Built-in fields."): + MetadataService.create_metadata(dataset.id, metadata_args) + + def test_update_metadata_name_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful metadata name update with valid parameters. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Create metadata first + metadata_args = MetadataArgs(type="string", name="old_name") + metadata = MetadataService.create_metadata(dataset.id, metadata_args) + + # Act: Execute the method under test + new_name = "new_name" + result = MetadataService.update_metadata_name(dataset.id, metadata.id, new_name) + + # Assert: Verify the expected outcomes + assert result is not None + assert result.name == new_name + assert result.updated_by == account.id + assert result.updated_at is not None + + # Verify database state + from extensions.ext_database import db + + db.session.refresh(result) + assert result.name == new_name + + def test_update_metadata_name_too_long(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test metadata name update fails when new name exceeds 255 characters. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Create metadata first + metadata_args = MetadataArgs(type="string", name="old_name") + metadata = MetadataService.create_metadata(dataset.id, metadata_args) + + # Try to update with too long name + long_name = "a" * 256 # 256 characters, exceeding 255 limit + + # Act & Assert: Verify proper error handling + with pytest.raises(ValueError, match="Metadata name cannot exceed 255 characters."): + MetadataService.update_metadata_name(dataset.id, metadata.id, long_name) + + def test_update_metadata_name_already_exists(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test metadata name update fails when new name already exists in the same dataset. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Create two metadata entries + first_metadata_args = MetadataArgs(type="string", name="first_metadata") + first_metadata = MetadataService.create_metadata(dataset.id, first_metadata_args) + + second_metadata_args = MetadataArgs(type="number", name="second_metadata") + second_metadata = MetadataService.create_metadata(dataset.id, second_metadata_args) + + # Try to update first metadata with second metadata's name + with pytest.raises(ValueError, match="Metadata name already exists."): + MetadataService.update_metadata_name(dataset.id, first_metadata.id, "second_metadata") + + def test_update_metadata_name_conflicts_with_built_in_field( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test metadata name update fails when new name conflicts with built-in field names. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Create metadata first + metadata_args = MetadataArgs(type="string", name="old_name") + metadata = MetadataService.create_metadata(dataset.id, metadata_args) + + # Try to update with built-in field name + built_in_field_name = BuiltInField.document_name.value + + with pytest.raises(ValueError, match="Metadata name already exists in Built-in fields."): + MetadataService.update_metadata_name(dataset.id, metadata.id, built_in_field_name) + + def test_update_metadata_name_not_found(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test metadata name update fails when metadata ID does not exist. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Try to update non-existent metadata + import uuid + + fake_metadata_id = str(uuid.uuid4()) # Use valid UUID format + new_name = "new_name" + + # Act: Execute the method under test + result = MetadataService.update_metadata_name(dataset.id, fake_metadata_id, new_name) + + # Assert: Verify the method returns None when metadata is not found + assert result is None + + def test_delete_metadata_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful metadata deletion with valid parameters. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Create metadata first + metadata_args = MetadataArgs(type="string", name="to_be_deleted") + metadata = MetadataService.create_metadata(dataset.id, metadata_args) + + # Act: Execute the method under test + result = MetadataService.delete_metadata(dataset.id, metadata.id) + + # Assert: Verify the expected outcomes + assert result is not None + assert result.id == metadata.id + + # Verify metadata was deleted from database + from extensions.ext_database import db + + deleted_metadata = db.session.query(DatasetMetadata).filter_by(id=metadata.id).first() + assert deleted_metadata is None + + def test_delete_metadata_not_found(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test metadata deletion fails when metadata ID does not exist. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Try to delete non-existent metadata + import uuid + + fake_metadata_id = str(uuid.uuid4()) # Use valid UUID format + + # Act: Execute the method under test + result = MetadataService.delete_metadata(dataset.id, fake_metadata_id) + + # Assert: Verify the method returns None when metadata is not found + assert result is None + + def test_delete_metadata_with_document_bindings( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test metadata deletion successfully removes document metadata bindings. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + document = self._create_test_document( + db_session_with_containers, mock_external_service_dependencies, dataset, account + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Create metadata + metadata_args = MetadataArgs(type="string", name="test_metadata") + metadata = MetadataService.create_metadata(dataset.id, metadata_args) + + # Create metadata binding + binding = DatasetMetadataBinding( + tenant_id=tenant.id, + dataset_id=dataset.id, + metadata_id=metadata.id, + document_id=document.id, + created_by=account.id, + ) + + from extensions.ext_database import db + + db.session.add(binding) + db.session.commit() + + # Set document metadata + document.doc_metadata = {"test_metadata": "test_value"} + db.session.add(document) + db.session.commit() + + # Act: Execute the method under test + result = MetadataService.delete_metadata(dataset.id, metadata.id) + + # Assert: Verify the expected outcomes + assert result is not None + + # Verify metadata was deleted from database + deleted_metadata = db.session.query(DatasetMetadata).filter_by(id=metadata.id).first() + assert deleted_metadata is None + + # Note: The service attempts to update document metadata but may not succeed + # due to mock configuration. The main functionality (metadata deletion) is verified. + + def test_get_built_in_fields_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful retrieval of built-in metadata fields. + """ + # Act: Execute the method under test + result = MetadataService.get_built_in_fields() + + # Assert: Verify the expected outcomes + assert result is not None + assert len(result) == 5 + + # Verify all expected built-in fields are present + field_names = [field["name"] for field in result] + field_types = [field["type"] for field in result] + + assert BuiltInField.document_name.value in field_names + assert BuiltInField.uploader.value in field_names + assert BuiltInField.upload_date.value in field_names + assert BuiltInField.last_update_date.value in field_names + assert BuiltInField.source.value in field_names + + # Verify field types + assert "string" in field_types + assert "time" in field_types + + def test_enable_built_in_field_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful enabling of built-in fields for a dataset. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + document = self._create_test_document( + db_session_with_containers, mock_external_service_dependencies, dataset, account + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Mock DocumentService.get_working_documents_by_dataset_id + mock_external_service_dependencies["document_service"].get_working_documents_by_dataset_id.return_value = [ + document + ] + + # Verify dataset starts with built-in fields disabled + assert dataset.built_in_field_enabled is False + + # Act: Execute the method under test + MetadataService.enable_built_in_field(dataset) + + # Assert: Verify the expected outcomes + from extensions.ext_database import db + + db.session.refresh(dataset) + assert dataset.built_in_field_enabled is True + + # Note: Document metadata update depends on DocumentService mock working correctly + # The main functionality (enabling built-in fields) is verified + + def test_enable_built_in_field_already_enabled( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test enabling built-in fields when they are already enabled. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Enable built-in fields first + dataset.built_in_field_enabled = True + from extensions.ext_database import db + + db.session.add(dataset) + db.session.commit() + + # Mock DocumentService.get_working_documents_by_dataset_id + mock_external_service_dependencies["document_service"].get_working_documents_by_dataset_id.return_value = [] + + # Act: Execute the method under test + MetadataService.enable_built_in_field(dataset) + + # Assert: Verify the method returns early without changes + db.session.refresh(dataset) + assert dataset.built_in_field_enabled is True + + def test_enable_built_in_field_with_no_documents( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test enabling built-in fields for a dataset with no documents. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Mock DocumentService.get_working_documents_by_dataset_id to return empty list + mock_external_service_dependencies["document_service"].get_working_documents_by_dataset_id.return_value = [] + + # Act: Execute the method under test + MetadataService.enable_built_in_field(dataset) + + # Assert: Verify the expected outcomes + from extensions.ext_database import db + + db.session.refresh(dataset) + assert dataset.built_in_field_enabled is True + + def test_disable_built_in_field_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful disabling of built-in fields for a dataset. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + document = self._create_test_document( + db_session_with_containers, mock_external_service_dependencies, dataset, account + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Enable built-in fields first + dataset.built_in_field_enabled = True + from extensions.ext_database import db + + db.session.add(dataset) + db.session.commit() + + # Set document metadata with built-in fields + document.doc_metadata = { + BuiltInField.document_name.value: document.name, + BuiltInField.uploader.value: "test_uploader", + BuiltInField.upload_date.value: 1234567890.0, + BuiltInField.last_update_date.value: 1234567890.0, + BuiltInField.source.value: "test_source", + } + db.session.add(document) + db.session.commit() + + # Mock DocumentService.get_working_documents_by_dataset_id + mock_external_service_dependencies["document_service"].get_working_documents_by_dataset_id.return_value = [ + document + ] + + # Act: Execute the method under test + MetadataService.disable_built_in_field(dataset) + + # Assert: Verify the expected outcomes + db.session.refresh(dataset) + assert dataset.built_in_field_enabled is False + + # Note: Document metadata update depends on DocumentService mock working correctly + # The main functionality (disabling built-in fields) is verified + + def test_disable_built_in_field_already_disabled( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test disabling built-in fields when they are already disabled. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Verify dataset starts with built-in fields disabled + assert dataset.built_in_field_enabled is False + + # Mock DocumentService.get_working_documents_by_dataset_id + mock_external_service_dependencies["document_service"].get_working_documents_by_dataset_id.return_value = [] + + # Act: Execute the method under test + MetadataService.disable_built_in_field(dataset) + + # Assert: Verify the method returns early without changes + from extensions.ext_database import db + + db.session.refresh(dataset) + assert dataset.built_in_field_enabled is False + + def test_disable_built_in_field_with_no_documents( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test disabling built-in fields for a dataset with no documents. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Enable built-in fields first + dataset.built_in_field_enabled = True + from extensions.ext_database import db + + db.session.add(dataset) + db.session.commit() + + # Mock DocumentService.get_working_documents_by_dataset_id to return empty list + mock_external_service_dependencies["document_service"].get_working_documents_by_dataset_id.return_value = [] + + # Act: Execute the method under test + MetadataService.disable_built_in_field(dataset) + + # Assert: Verify the expected outcomes + db.session.refresh(dataset) + assert dataset.built_in_field_enabled is False + + def test_update_documents_metadata_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful update of documents metadata. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + document = self._create_test_document( + db_session_with_containers, mock_external_service_dependencies, dataset, account + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Create metadata + metadata_args = MetadataArgs(type="string", name="test_metadata") + metadata = MetadataService.create_metadata(dataset.id, metadata_args) + + # Mock DocumentService.get_document + mock_external_service_dependencies["document_service"].get_document.return_value = document + + # Create metadata operation data + from services.entities.knowledge_entities.knowledge_entities import ( + DocumentMetadataOperation, + MetadataDetail, + MetadataOperationData, + ) + + metadata_detail = MetadataDetail(id=metadata.id, name=metadata.name, value="test_value") + + operation = DocumentMetadataOperation(document_id=document.id, metadata_list=[metadata_detail]) + + operation_data = MetadataOperationData(operation_data=[operation]) + + # Act: Execute the method under test + MetadataService.update_documents_metadata(dataset, operation_data) + + # Assert: Verify the expected outcomes + from extensions.ext_database import db + + # Verify document metadata was updated + db.session.refresh(document) + assert document.doc_metadata is not None + assert "test_metadata" in document.doc_metadata + assert document.doc_metadata["test_metadata"] == "test_value" + + # Verify metadata binding was created + binding = ( + db.session.query(DatasetMetadataBinding).filter_by(metadata_id=metadata.id, document_id=document.id).first() + ) + assert binding is not None + assert binding.tenant_id == tenant.id + assert binding.dataset_id == dataset.id + + def test_update_documents_metadata_with_built_in_fields_enabled( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test update of documents metadata when built-in fields are enabled. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + document = self._create_test_document( + db_session_with_containers, mock_external_service_dependencies, dataset, account + ) + + # Enable built-in fields + dataset.built_in_field_enabled = True + from extensions.ext_database import db + + db.session.add(dataset) + db.session.commit() + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Create metadata + metadata_args = MetadataArgs(type="string", name="test_metadata") + metadata = MetadataService.create_metadata(dataset.id, metadata_args) + + # Mock DocumentService.get_document + mock_external_service_dependencies["document_service"].get_document.return_value = document + + # Create metadata operation data + from services.entities.knowledge_entities.knowledge_entities import ( + DocumentMetadataOperation, + MetadataDetail, + MetadataOperationData, + ) + + metadata_detail = MetadataDetail(id=metadata.id, name=metadata.name, value="test_value") + + operation = DocumentMetadataOperation(document_id=document.id, metadata_list=[metadata_detail]) + + operation_data = MetadataOperationData(operation_data=[operation]) + + # Act: Execute the method under test + MetadataService.update_documents_metadata(dataset, operation_data) + + # Assert: Verify the expected outcomes + # Verify document metadata was updated with both custom and built-in fields + db.session.refresh(document) + assert document.doc_metadata is not None + assert "test_metadata" in document.doc_metadata + assert document.doc_metadata["test_metadata"] == "test_value" + + # Note: Built-in fields would be added if DocumentService mock works correctly + # The main functionality (custom metadata update) is verified + + def test_update_documents_metadata_document_not_found( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test update of documents metadata when document is not found. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Create metadata + metadata_args = MetadataArgs(type="string", name="test_metadata") + metadata = MetadataService.create_metadata(dataset.id, metadata_args) + + # Mock DocumentService.get_document to return None (document not found) + mock_external_service_dependencies["document_service"].get_document.return_value = None + + # Create metadata operation data + from services.entities.knowledge_entities.knowledge_entities import ( + DocumentMetadataOperation, + MetadataDetail, + MetadataOperationData, + ) + + metadata_detail = MetadataDetail(id=metadata.id, name=metadata.name, value="test_value") + + operation = DocumentMetadataOperation(document_id="non-existent-document-id", metadata_list=[metadata_detail]) + + operation_data = MetadataOperationData(operation_data=[operation]) + + # Act: Execute the method under test + # The method should handle the error gracefully and continue + MetadataService.update_documents_metadata(dataset, operation_data) + + # Assert: Verify the method completes without raising exceptions + # The main functionality (error handling) is verified + + def test_knowledge_base_metadata_lock_check_dataset_id( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test metadata lock check for dataset operations. + """ + # Arrange: Setup mocks + mock_external_service_dependencies["redis_client"].get.return_value = None + mock_external_service_dependencies["redis_client"].set.return_value = True + + dataset_id = "test-dataset-id" + + # Act: Execute the method under test + MetadataService.knowledge_base_metadata_lock_check(dataset_id, None) + + # Assert: Verify the expected outcomes + # Verify Redis lock was set + mock_external_service_dependencies["redis_client"].set.assert_called_once() + + # Verify lock key format + call_args = mock_external_service_dependencies["redis_client"].set.call_args + assert call_args[0][0] == f"dataset_metadata_lock_{dataset_id}" + + def test_knowledge_base_metadata_lock_check_document_id( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test metadata lock check for document operations. + """ + # Arrange: Setup mocks + mock_external_service_dependencies["redis_client"].get.return_value = None + mock_external_service_dependencies["redis_client"].set.return_value = True + + document_id = "test-document-id" + + # Act: Execute the method under test + MetadataService.knowledge_base_metadata_lock_check(None, document_id) + + # Assert: Verify the expected outcomes + # Verify Redis lock was set + mock_external_service_dependencies["redis_client"].set.assert_called_once() + + # Verify lock key format + call_args = mock_external_service_dependencies["redis_client"].set.call_args + assert call_args[0][0] == f"document_metadata_lock_{document_id}" + + def test_knowledge_base_metadata_lock_check_lock_exists( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test metadata lock check when lock already exists. + """ + # Arrange: Setup mocks to simulate existing lock + mock_external_service_dependencies["redis_client"].get.return_value = "1" # Lock exists + + dataset_id = "test-dataset-id" + + # Act & Assert: Verify proper error handling + with pytest.raises( + ValueError, match="Another knowledge base metadata operation is running, please wait a moment." + ): + MetadataService.knowledge_base_metadata_lock_check(dataset_id, None) + + def test_knowledge_base_metadata_lock_check_document_lock_exists( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test metadata lock check when document lock already exists. + """ + # Arrange: Setup mocks to simulate existing lock + mock_external_service_dependencies["redis_client"].get.return_value = "1" # Lock exists + + document_id = "test-document-id" + + # Act & Assert: Verify proper error handling + with pytest.raises(ValueError, match="Another document metadata operation is running, please wait a moment."): + MetadataService.knowledge_base_metadata_lock_check(None, document_id) + + def test_get_dataset_metadatas_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful retrieval of dataset metadata information. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Create metadata + metadata_args = MetadataArgs(type="string", name="test_metadata") + metadata = MetadataService.create_metadata(dataset.id, metadata_args) + + # Create document and metadata binding + document = self._create_test_document( + db_session_with_containers, mock_external_service_dependencies, dataset, account + ) + + binding = DatasetMetadataBinding( + tenant_id=tenant.id, + dataset_id=dataset.id, + metadata_id=metadata.id, + document_id=document.id, + created_by=account.id, + ) + + from extensions.ext_database import db + + db.session.add(binding) + db.session.commit() + + # Act: Execute the method under test + result = MetadataService.get_dataset_metadatas(dataset) + + # Assert: Verify the expected outcomes + assert result is not None + assert "doc_metadata" in result + assert "built_in_field_enabled" in result + + # Verify metadata information + doc_metadata = result["doc_metadata"] + assert len(doc_metadata) == 1 + assert doc_metadata[0]["id"] == metadata.id + assert doc_metadata[0]["name"] == metadata.name + assert doc_metadata[0]["type"] == metadata.type + assert doc_metadata[0]["count"] == 1 # One document bound to this metadata + + # Verify built-in field status + assert result["built_in_field_enabled"] is False + + def test_get_dataset_metadatas_with_built_in_fields_enabled( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test retrieval of dataset metadata when built-in fields are enabled. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + + # Enable built-in fields + dataset.built_in_field_enabled = True + from extensions.ext_database import db + + db.session.add(dataset) + db.session.commit() + + # Setup mocks + mock_external_service_dependencies["current_user"].current_tenant_id = tenant.id + mock_external_service_dependencies["current_user"].id = account.id + + # Create metadata + metadata_args = MetadataArgs(type="string", name="test_metadata") + metadata = MetadataService.create_metadata(dataset.id, metadata_args) + + # Act: Execute the method under test + result = MetadataService.get_dataset_metadatas(dataset) + + # Assert: Verify the expected outcomes + assert result is not None + assert "doc_metadata" in result + assert "built_in_field_enabled" in result + + # Verify metadata information + doc_metadata = result["doc_metadata"] + assert len(doc_metadata) == 1 # Only custom metadata, built-in fields are not included in this list + + # Verify built-in field status + assert result["built_in_field_enabled"] is True + + def test_get_dataset_metadatas_no_metadata(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test retrieval of dataset metadata when no metadata exists. + """ + # Arrange: Create test data + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + dataset = self._create_test_dataset( + db_session_with_containers, mock_external_service_dependencies, account, tenant + ) + + # Act: Execute the method under test + result = MetadataService.get_dataset_metadatas(dataset) + + # Assert: Verify the expected outcomes + assert result is not None + assert "doc_metadata" in result + assert "built_in_field_enabled" in result + + # Verify metadata information + doc_metadata = result["doc_metadata"] + assert len(doc_metadata) == 0 # No metadata exists + + # Verify built-in field status + assert result["built_in_field_enabled"] is False diff --git a/api/tests/test_containers_integration_tests/services/test_model_load_balancing_service.py b/api/tests/test_containers_integration_tests/services/test_model_load_balancing_service.py new file mode 100644 index 0000000000..cb20238f0c --- /dev/null +++ b/api/tests/test_containers_integration_tests/services/test_model_load_balancing_service.py @@ -0,0 +1,474 @@ +from unittest.mock import MagicMock, patch + +import pytest +from faker import Faker + +from models.account import TenantAccountJoin, TenantAccountRole +from models.model import Account, Tenant +from models.provider import LoadBalancingModelConfig, Provider, ProviderModelSetting +from services.model_load_balancing_service import ModelLoadBalancingService + + +class TestModelLoadBalancingService: + """Integration tests for ModelLoadBalancingService using testcontainers.""" + + @pytest.fixture + def mock_external_service_dependencies(self): + """Mock setup for external service dependencies.""" + with ( + patch("services.model_load_balancing_service.ProviderManager") as mock_provider_manager, + patch("services.model_load_balancing_service.LBModelManager") as mock_lb_model_manager, + patch("services.model_load_balancing_service.ModelProviderFactory") as mock_model_provider_factory, + patch("services.model_load_balancing_service.encrypter") as mock_encrypter, + ): + # Setup default mock returns + mock_provider_manager_instance = mock_provider_manager.return_value + + # Mock provider configuration + mock_provider_config = MagicMock() + mock_provider_config.provider.provider = "openai" + mock_provider_config.custom_configuration.provider = None + + # Mock provider model setting + mock_provider_model_setting = MagicMock() + mock_provider_model_setting.load_balancing_enabled = False + + mock_provider_config.get_provider_model_setting.return_value = mock_provider_model_setting + + # Mock provider configurations dict + mock_provider_configs = {"openai": mock_provider_config} + mock_provider_manager_instance.get_configurations.return_value = mock_provider_configs + + # Mock LBModelManager + mock_lb_model_manager.get_config_in_cooldown_and_ttl.return_value = (False, 0) + + # Mock ModelProviderFactory + mock_model_provider_factory_instance = mock_model_provider_factory.return_value + + # Mock credential schemas + mock_credential_schema = MagicMock() + mock_credential_schema.credential_form_schemas = [] + + # Mock provider configuration methods + mock_provider_config.extract_secret_variables.return_value = [] + mock_provider_config.obfuscated_credentials.return_value = {} + mock_provider_config._get_credential_schema.return_value = mock_credential_schema + + yield { + "provider_manager": mock_provider_manager, + "lb_model_manager": mock_lb_model_manager, + "model_provider_factory": mock_model_provider_factory, + "encrypter": mock_encrypter, + "provider_config": mock_provider_config, + "provider_model_setting": mock_provider_model_setting, + "credential_schema": mock_credential_schema, + } + + def _create_test_account_and_tenant(self, db_session_with_containers, mock_external_service_dependencies): + """ + Helper method to create a test account and tenant for testing. + + Args: + db_session_with_containers: Database session from testcontainers infrastructure + mock_external_service_dependencies: Mock dependencies + + Returns: + tuple: (account, tenant) - Created account and tenant instances + """ + fake = Faker() + + # Create account + account = Account( + email=fake.email(), + name=fake.name(), + interface_language="en-US", + status="active", + ) + + from extensions.ext_database import db + + db.session.add(account) + db.session.commit() + + # Create tenant for the account + tenant = Tenant( + name=fake.company(), + status="normal", + ) + db.session.add(tenant) + db.session.commit() + + # Create tenant-account join + join = TenantAccountJoin( + tenant_id=tenant.id, + account_id=account.id, + role=TenantAccountRole.OWNER.value, + current=True, + ) + db.session.add(join) + db.session.commit() + + # Set current tenant for account + account.current_tenant = tenant + + return account, tenant + + def _create_test_provider_and_setting( + self, db_session_with_containers, tenant_id, mock_external_service_dependencies + ): + """ + Helper method to create a test provider and provider model setting. + + Args: + db_session_with_containers: Database session from testcontainers infrastructure + tenant_id: Tenant ID for the provider + mock_external_service_dependencies: Mock dependencies + + Returns: + tuple: (provider, provider_model_setting) - Created provider and setting instances + """ + fake = Faker() + + from extensions.ext_database import db + + # Create provider + provider = Provider( + tenant_id=tenant_id, + provider_name="openai", + provider_type="custom", + is_valid=True, + ) + db.session.add(provider) + db.session.commit() + + # Create provider model setting + provider_model_setting = ProviderModelSetting( + tenant_id=tenant_id, + provider_name="openai", + model_name="gpt-3.5-turbo", + model_type="text-generation", # Use the origin model type that matches the query + enabled=True, + load_balancing_enabled=False, + ) + db.session.add(provider_model_setting) + db.session.commit() + + return provider, provider_model_setting + + def test_enable_model_load_balancing_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful model load balancing enablement. + + This test verifies: + - Proper provider configuration retrieval + - Successful enablement of model load balancing + - Correct method calls to provider configuration + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + provider, provider_model_setting = self._create_test_provider_and_setting( + db_session_with_containers, tenant.id, mock_external_service_dependencies + ) + + # Setup mocks for enable method + mock_provider_config = mock_external_service_dependencies["provider_config"] + mock_provider_config.enable_model_load_balancing = MagicMock() + + # Act: Execute the method under test + service = ModelLoadBalancingService() + service.enable_model_load_balancing( + tenant_id=tenant.id, provider="openai", model="gpt-3.5-turbo", model_type="llm" + ) + + # Assert: Verify the expected outcomes + mock_provider_config.enable_model_load_balancing.assert_called_once() + call_args = mock_provider_config.enable_model_load_balancing.call_args + assert call_args.kwargs["model"] == "gpt-3.5-turbo" + assert call_args.kwargs["model_type"].value == "llm" # ModelType enum value + + # Verify database state + from extensions.ext_database import db + + db.session.refresh(provider) + db.session.refresh(provider_model_setting) + assert provider.id is not None + assert provider_model_setting.id is not None + + def test_disable_model_load_balancing_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful model load balancing disablement. + + This test verifies: + - Proper provider configuration retrieval + - Successful disablement of model load balancing + - Correct method calls to provider configuration + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + provider, provider_model_setting = self._create_test_provider_and_setting( + db_session_with_containers, tenant.id, mock_external_service_dependencies + ) + + # Setup mocks for disable method + mock_provider_config = mock_external_service_dependencies["provider_config"] + mock_provider_config.disable_model_load_balancing = MagicMock() + + # Act: Execute the method under test + service = ModelLoadBalancingService() + service.disable_model_load_balancing( + tenant_id=tenant.id, provider="openai", model="gpt-3.5-turbo", model_type="llm" + ) + + # Assert: Verify the expected outcomes + mock_provider_config.disable_model_load_balancing.assert_called_once() + call_args = mock_provider_config.disable_model_load_balancing.call_args + assert call_args.kwargs["model"] == "gpt-3.5-turbo" + assert call_args.kwargs["model_type"].value == "llm" # ModelType enum value + + # Verify database state + from extensions.ext_database import db + + db.session.refresh(provider) + db.session.refresh(provider_model_setting) + assert provider.id is not None + assert provider_model_setting.id is not None + + def test_enable_model_load_balancing_provider_not_found( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test error handling when provider does not exist. + + This test verifies: + - Proper error handling for non-existent provider + - Correct exception type and message + - No database state changes + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Setup mocks to return empty provider configurations + mock_provider_manager = mock_external_service_dependencies["provider_manager"] + mock_provider_manager_instance = mock_provider_manager.return_value + mock_provider_manager_instance.get_configurations.return_value = {} + + # Act & Assert: Verify proper error handling + service = ModelLoadBalancingService() + with pytest.raises(ValueError) as exc_info: + service.enable_model_load_balancing( + tenant_id=tenant.id, provider="nonexistent_provider", model="gpt-3.5-turbo", model_type="llm" + ) + + # Verify correct error message + assert "Provider nonexistent_provider does not exist." in str(exc_info.value) + + # Verify no database state changes occurred + from extensions.ext_database import db + + db.session.rollback() + + def test_get_load_balancing_configs_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful retrieval of load balancing configurations. + + This test verifies: + - Proper provider configuration retrieval + - Successful database query for load balancing configs + - Correct return format and data structure + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + provider, provider_model_setting = self._create_test_provider_and_setting( + db_session_with_containers, tenant.id, mock_external_service_dependencies + ) + + # Create load balancing config + from extensions.ext_database import db + + load_balancing_config = LoadBalancingModelConfig( + tenant_id=tenant.id, + provider_name="openai", + model_name="gpt-3.5-turbo", + model_type="text-generation", # Use the origin model type that matches the query + name="config1", + encrypted_config='{"api_key": "test_key"}', + enabled=True, + ) + db.session.add(load_balancing_config) + db.session.commit() + + # Verify the config was created + db.session.refresh(load_balancing_config) + assert load_balancing_config.id is not None + + # Setup mocks for get_load_balancing_configs method + mock_provider_config = mock_external_service_dependencies["provider_config"] + mock_provider_model_setting = mock_external_service_dependencies["provider_model_setting"] + mock_provider_model_setting.load_balancing_enabled = True + + # Mock credential schema methods + mock_credential_schema = mock_external_service_dependencies["credential_schema"] + mock_credential_schema.credential_form_schemas = [] + + # Mock encrypter + mock_encrypter = mock_external_service_dependencies["encrypter"] + mock_encrypter.get_decrypt_decoding.return_value = ("key", "cipher") + + # Mock _get_credential_schema method + mock_provider_config._get_credential_schema.return_value = mock_credential_schema + + # Mock extract_secret_variables method + mock_provider_config.extract_secret_variables.return_value = [] + + # Mock obfuscated_credentials method + mock_provider_config.obfuscated_credentials.return_value = {} + + # Mock LBModelManager.get_config_in_cooldown_and_ttl + mock_lb_model_manager = mock_external_service_dependencies["lb_model_manager"] + mock_lb_model_manager.get_config_in_cooldown_and_ttl.return_value = (False, 0) + + # Act: Execute the method under test + service = ModelLoadBalancingService() + is_enabled, configs = service.get_load_balancing_configs( + tenant_id=tenant.id, provider="openai", model="gpt-3.5-turbo", model_type="llm" + ) + + # Assert: Verify the expected outcomes + assert is_enabled is True + assert len(configs) == 1 + assert configs[0]["id"] == load_balancing_config.id + assert configs[0]["name"] == "config1" + assert configs[0]["enabled"] is True + assert configs[0]["in_cooldown"] is False + assert configs[0]["ttl"] == 0 + + # Verify database state + db.session.refresh(load_balancing_config) + assert load_balancing_config.id is not None + + def test_get_load_balancing_configs_provider_not_found( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test error handling when provider does not exist in get_load_balancing_configs. + + This test verifies: + - Proper error handling for non-existent provider + - Correct exception type and message + - No database state changes + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Setup mocks to return empty provider configurations + mock_provider_manager = mock_external_service_dependencies["provider_manager"] + mock_provider_manager_instance = mock_provider_manager.return_value + mock_provider_manager_instance.get_configurations.return_value = {} + + # Act & Assert: Verify proper error handling + service = ModelLoadBalancingService() + with pytest.raises(ValueError) as exc_info: + service.get_load_balancing_configs( + tenant_id=tenant.id, provider="nonexistent_provider", model="gpt-3.5-turbo", model_type="llm" + ) + + # Verify correct error message + assert "Provider nonexistent_provider does not exist." in str(exc_info.value) + + # Verify no database state changes occurred + from extensions.ext_database import db + + db.session.rollback() + + def test_get_load_balancing_configs_with_inherit_config( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test load balancing configs retrieval with inherit configuration. + + This test verifies: + - Proper handling of inherit configuration + - Correct ordering of configurations + - Inherit config initialization when needed + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + provider, provider_model_setting = self._create_test_provider_and_setting( + db_session_with_containers, tenant.id, mock_external_service_dependencies + ) + + # Create load balancing config + from extensions.ext_database import db + + load_balancing_config = LoadBalancingModelConfig( + tenant_id=tenant.id, + provider_name="openai", + model_name="gpt-3.5-turbo", + model_type="text-generation", # Use the origin model type that matches the query + name="config1", + encrypted_config='{"api_key": "test_key"}', + enabled=True, + ) + db.session.add(load_balancing_config) + db.session.commit() + + # Setup mocks for inherit config scenario + mock_provider_config = mock_external_service_dependencies["provider_config"] + mock_provider_config.custom_configuration.provider = MagicMock() # Enable custom config + + mock_provider_model_setting = mock_external_service_dependencies["provider_model_setting"] + mock_provider_model_setting.load_balancing_enabled = True + + # Mock credential schema methods + mock_credential_schema = mock_external_service_dependencies["credential_schema"] + mock_credential_schema.credential_form_schemas = [] + + # Mock encrypter + mock_encrypter = mock_external_service_dependencies["encrypter"] + mock_encrypter.get_decrypt_decoding.return_value = ("key", "cipher") + + # Act: Execute the method under test + service = ModelLoadBalancingService() + is_enabled, configs = service.get_load_balancing_configs( + tenant_id=tenant.id, provider="openai", model="gpt-3.5-turbo", model_type="llm" + ) + + # Assert: Verify the expected outcomes + assert is_enabled is True + assert len(configs) == 2 # inherit config + existing config + + # First config should be inherit config + assert configs[0]["name"] == "__inherit__" + assert configs[0]["enabled"] is True + + # Second config should be the existing config + assert configs[1]["id"] == load_balancing_config.id + assert configs[1]["name"] == "config1" + + # Verify database state + db.session.refresh(load_balancing_config) + assert load_balancing_config.id is not None + + # Verify inherit config was created in database + inherit_configs = ( + db.session.query(LoadBalancingModelConfig).where(LoadBalancingModelConfig.name == "__inherit__").all() + ) + assert len(inherit_configs) == 1 diff --git a/api/tests/test_containers_integration_tests/services/test_model_provider_service.py b/api/tests/test_containers_integration_tests/services/test_model_provider_service.py new file mode 100644 index 0000000000..8b7d44c1e4 --- /dev/null +++ b/api/tests/test_containers_integration_tests/services/test_model_provider_service.py @@ -0,0 +1,1172 @@ +from unittest.mock import MagicMock, patch + +import pytest +from faker import Faker + +from core.entities.model_entities import ModelStatus +from core.model_runtime.entities.model_entities import FetchFrom, ModelType +from models.account import Account, Tenant, TenantAccountJoin, TenantAccountRole +from models.provider import Provider, ProviderModel, ProviderModelSetting, ProviderType +from services.model_provider_service import ModelProviderService + + +class TestModelProviderService: + """Integration tests for ModelProviderService using testcontainers.""" + + @pytest.fixture + def mock_external_service_dependencies(self): + """Mock setup for external service dependencies.""" + with ( + patch("services.model_provider_service.ProviderManager") as mock_provider_manager, + patch("services.model_provider_service.ModelProviderFactory") as mock_model_provider_factory, + ): + # Setup default mock returns + mock_provider_manager.return_value.get_configurations.return_value = MagicMock() + mock_model_provider_factory.return_value.get_provider_icon.return_value = (None, None) + + yield { + "provider_manager": mock_provider_manager, + "model_provider_factory": mock_model_provider_factory, + } + + def _create_test_account_and_tenant(self, db_session_with_containers, mock_external_service_dependencies): + """ + Helper method to create a test account and tenant for testing. + + Args: + db_session_with_containers: Database session from testcontainers infrastructure + mock_external_service_dependencies: Mock dependencies + + Returns: + tuple: (account, tenant) - Created account and tenant instances + """ + fake = Faker() + + # Create account + account = Account( + email=fake.email(), + name=fake.name(), + interface_language="en-US", + status="active", + ) + + from extensions.ext_database import db + + db.session.add(account) + db.session.commit() + + # Create tenant for the account + tenant = Tenant( + name=fake.company(), + status="normal", + ) + db.session.add(tenant) + db.session.commit() + + # Create tenant-account join + join = TenantAccountJoin( + tenant_id=tenant.id, + account_id=account.id, + role=TenantAccountRole.OWNER.value, + current=True, + ) + db.session.add(join) + db.session.commit() + + # Set current tenant for account + account.current_tenant = tenant + + return account, tenant + + def _create_test_provider( + self, + db_session_with_containers, + mock_external_service_dependencies, + tenant_id: str, + provider_name: str = "openai", + ): + """ + Helper method to create a test provider for testing. + + Args: + db_session_with_containers: Database session from testcontainers infrastructure + mock_external_service_dependencies: Mock dependencies + tenant_id: Tenant ID for the provider + provider_name: Name of the provider + + Returns: + Provider: Created provider instance + """ + fake = Faker() + + provider = Provider( + tenant_id=tenant_id, + provider_name=provider_name, + provider_type="custom", + is_valid=True, + quota_type="free", + quota_limit=1000, + quota_used=0, + ) + + from extensions.ext_database import db + + db.session.add(provider) + db.session.commit() + + return provider + + def _create_test_provider_model( + self, + db_session_with_containers, + mock_external_service_dependencies, + tenant_id: str, + provider_name: str, + model_name: str = "gpt-3.5-turbo", + model_type: str = "llm", + ): + """ + Helper method to create a test provider model for testing. + + Args: + db_session_with_containers: Database session from testcontainers infrastructure + mock_external_service_dependencies: Mock dependencies + tenant_id: Tenant ID for the provider model + provider_name: Name of the provider + model_name: Name of the model + model_type: Type of the model + + Returns: + ProviderModel: Created provider model instance + """ + fake = Faker() + + provider_model = ProviderModel( + tenant_id=tenant_id, + provider_name=provider_name, + model_name=model_name, + model_type=model_type, + is_valid=True, + ) + + from extensions.ext_database import db + + db.session.add(provider_model) + db.session.commit() + + return provider_model + + def _create_test_provider_model_setting( + self, + db_session_with_containers, + mock_external_service_dependencies, + tenant_id: str, + provider_name: str, + model_name: str = "gpt-3.5-turbo", + model_type: str = "llm", + ): + """ + Helper method to create a test provider model setting for testing. + + Args: + db_session_with_containers: Database session from testcontainers infrastructure + mock_external_service_dependencies: Mock dependencies + tenant_id: Tenant ID for the provider model setting + provider_name: Name of the provider + model_name: Name of the model + model_type: Type of the model + + Returns: + ProviderModelSetting: Created provider model setting instance + """ + fake = Faker() + + provider_model_setting = ProviderModelSetting( + tenant_id=tenant_id, + provider_name=provider_name, + model_name=model_name, + model_type=model_type, + enabled=True, + load_balancing_enabled=False, + ) + + from extensions.ext_database import db + + db.session.add(provider_model_setting) + db.session.commit() + + return provider_model_setting + + def test_get_provider_list_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful provider list retrieval. + + This test verifies: + - Proper provider list retrieval with all required fields + - Correct filtering by model type + - Proper response structure and data mapping + - Mock interactions with ProviderManager + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Create test provider + provider = self._create_test_provider( + db_session_with_containers, mock_external_service_dependencies, tenant.id, "openai" + ) + + # Mock ProviderManager to return realistic configuration + mock_provider_manager = mock_external_service_dependencies["provider_manager"].return_value + + # Create mock provider configuration + mock_provider_entity = MagicMock() + mock_provider_entity.provider = "openai" + mock_provider_entity.label = {"en_US": "OpenAI", "zh_Hans": "OpenAI"} + mock_provider_entity.description = {"en_US": "OpenAI provider", "zh_Hans": "OpenAI 提供商"} + mock_provider_entity.icon_small = {"en_US": "icon_small.png", "zh_Hans": "icon_small.png"} + mock_provider_entity.icon_large = {"en_US": "icon_large.png", "zh_Hans": "icon_large.png"} + mock_provider_entity.background = "#FF6B6B" + mock_provider_entity.help = None + mock_provider_entity.supported_model_types = [ModelType.LLM, ModelType.TEXT_EMBEDDING] + mock_provider_entity.configurate_methods = [] + mock_provider_entity.provider_credential_schema = None + mock_provider_entity.model_credential_schema = None + + mock_provider_config = MagicMock() + mock_provider_config.provider = mock_provider_entity + mock_provider_config.preferred_provider_type = ProviderType.CUSTOM + mock_provider_config.is_custom_configuration_available.return_value = True + mock_provider_config.system_configuration.enabled = True + mock_provider_config.system_configuration.current_quota_type = "free" + mock_provider_config.system_configuration.quota_configurations = [] + + mock_configurations = MagicMock() + mock_configurations.values.return_value = [mock_provider_config] + mock_provider_manager.get_configurations.return_value = mock_configurations + + # Act: Execute the method under test + service = ModelProviderService() + result = service.get_provider_list(tenant.id) + + # Assert: Verify the expected outcomes + assert result is not None + assert len(result) == 1 + + provider_response = result[0] + assert provider_response.tenant_id == tenant.id + assert provider_response.provider == "openai" + assert provider_response.background == "#FF6B6B" + assert len(provider_response.supported_model_types) == 2 + assert ModelType.LLM in provider_response.supported_model_types + assert ModelType.TEXT_EMBEDDING in provider_response.supported_model_types + + # Verify mock interactions + mock_provider_manager.get_configurations.assert_called_once_with(tenant.id) + mock_provider_config.is_custom_configuration_available.assert_called_once() + + def test_get_provider_list_with_model_type_filter( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test provider list retrieval with model type filtering. + + This test verifies: + - Proper filtering by model type + - Only providers supporting the specified model type are returned + - Correct handling of unsupported model types + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Mock ProviderManager to return multiple provider configurations + mock_provider_manager = mock_external_service_dependencies["provider_manager"].return_value + + # Create mock provider configurations with different supported model types + mock_provider_entity_llm = MagicMock() + mock_provider_entity_llm.provider = "openai" + mock_provider_entity_llm.label = {"en_US": "OpenAI", "zh_Hans": "OpenAI"} + mock_provider_entity_llm.description = {"en_US": "OpenAI provider", "zh_Hans": "OpenAI 提供商"} + mock_provider_entity_llm.icon_small = {"en_US": "icon_small.png", "zh_Hans": "icon_small.png"} + mock_provider_entity_llm.icon_large = {"en_US": "icon_large.png", "zh_Hans": "icon_large.png"} + mock_provider_entity_llm.background = "#FF6B6B" + mock_provider_entity_llm.help = None + mock_provider_entity_llm.supported_model_types = [ModelType.LLM] + mock_provider_entity_llm.configurate_methods = [] + mock_provider_entity_llm.provider_credential_schema = None + mock_provider_entity_llm.model_credential_schema = None + + mock_provider_entity_embedding = MagicMock() + mock_provider_entity_embedding.provider = "cohere" + mock_provider_entity_embedding.label = {"en_US": "Cohere", "zh_Hans": "Cohere"} + mock_provider_entity_embedding.description = {"en_US": "Cohere provider", "zh_Hans": "Cohere 提供商"} + mock_provider_entity_embedding.icon_small = {"en_US": "icon_small.png", "zh_Hans": "icon_small.png"} + mock_provider_entity_embedding.icon_large = {"en_US": "icon_large.png", "zh_Hans": "icon_large.png"} + mock_provider_entity_embedding.background = "#4ECDC4" + mock_provider_entity_embedding.help = None + mock_provider_entity_embedding.supported_model_types = [ModelType.TEXT_EMBEDDING] + mock_provider_entity_embedding.configurate_methods = [] + mock_provider_entity_embedding.provider_credential_schema = None + mock_provider_entity_embedding.model_credential_schema = None + + mock_provider_config_llm = MagicMock() + mock_provider_config_llm.provider = mock_provider_entity_llm + mock_provider_config_llm.preferred_provider_type = ProviderType.CUSTOM + mock_provider_config_llm.is_custom_configuration_available.return_value = True + mock_provider_config_llm.system_configuration.enabled = True + mock_provider_config_llm.system_configuration.current_quota_type = "free" + mock_provider_config_llm.system_configuration.quota_configurations = [] + + mock_provider_config_embedding = MagicMock() + mock_provider_config_embedding.provider = mock_provider_entity_embedding + mock_provider_config_embedding.preferred_provider_type = ProviderType.CUSTOM + mock_provider_config_embedding.is_custom_configuration_available.return_value = True + mock_provider_config_embedding.system_configuration.enabled = True + mock_provider_config_embedding.system_configuration.current_quota_type = "free" + mock_provider_config_embedding.system_configuration.quota_configurations = [] + + mock_configurations = MagicMock() + mock_configurations.values.return_value = [mock_provider_config_llm, mock_provider_config_embedding] + mock_provider_manager.get_configurations.return_value = mock_configurations + + # Act: Execute the method under test with LLM filter + service = ModelProviderService() + result = service.get_provider_list(tenant.id, model_type="llm") + + # Assert: Verify only LLM providers are returned + assert result is not None + assert len(result) == 1 + assert result[0].provider == "openai" + assert ModelType.LLM in result[0].supported_model_types + + # Act: Execute the method under test with TEXT_EMBEDDING filter + result = service.get_provider_list(tenant.id, model_type="text-embedding") + + # Assert: Verify only TEXT_EMBEDDING providers are returned + assert result is not None + assert len(result) == 1 + assert result[0].provider == "cohere" + assert ModelType.TEXT_EMBEDDING in result[0].supported_model_types + + def test_get_models_by_provider_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful retrieval of models by provider. + + This test verifies: + - Proper model retrieval for a specific provider + - Correct response structure with tenant_id and model data + - Mock interactions with ProviderManager + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Create test provider and models + provider = self._create_test_provider( + db_session_with_containers, mock_external_service_dependencies, tenant.id, "openai" + ) + + provider_model_1 = self._create_test_provider_model( + db_session_with_containers, mock_external_service_dependencies, tenant.id, "openai", "gpt-3.5-turbo", "llm" + ) + + provider_model_2 = self._create_test_provider_model( + db_session_with_containers, mock_external_service_dependencies, tenant.id, "openai", "gpt-4", "llm" + ) + + # Mock ProviderManager to return realistic configuration + mock_provider_manager = mock_external_service_dependencies["provider_manager"].return_value + + # Create mock models + from core.entities.model_entities import ModelWithProviderEntity, SimpleModelProviderEntity + from core.model_runtime.entities.common_entities import I18nObject + from core.model_runtime.entities.provider_entities import ProviderEntity + + # Create real model objects instead of mocks + provider_entity_1 = SimpleModelProviderEntity( + ProviderEntity( + provider="openai", + label=I18nObject(en_US="OpenAI", zh_Hans="OpenAI"), + icon_small=I18nObject(en_US="icon_small.png", zh_Hans="icon_small.png"), + icon_large=I18nObject(en_US="icon_large.png", zh_Hans="icon_large.png"), + supported_model_types=[ModelType.LLM], + configurate_methods=[], + models=[], + ) + ) + + provider_entity_2 = SimpleModelProviderEntity( + ProviderEntity( + provider="openai", + label=I18nObject(en_US="OpenAI", zh_Hans="OpenAI"), + icon_small=I18nObject(en_US="icon_small.png", zh_Hans="icon_small.png"), + icon_large=I18nObject(en_US="icon_large.png", zh_Hans="icon_large.png"), + supported_model_types=[ModelType.LLM], + configurate_methods=[], + models=[], + ) + ) + + mock_model_1 = ModelWithProviderEntity( + model="gpt-3.5-turbo", + label=I18nObject(en_US="GPT-3.5 Turbo", zh_Hans="GPT-3.5 Turbo"), + model_type=ModelType.LLM, + features=[], + fetch_from=FetchFrom.PREDEFINED_MODEL, + model_properties={}, + deprecated=False, + provider=provider_entity_1, + status="active", + load_balancing_enabled=False, + ) + + mock_model_2 = ModelWithProviderEntity( + model="gpt-4", + label=I18nObject(en_US="GPT-4", zh_Hans="GPT-4"), + model_type=ModelType.LLM, + features=[], + fetch_from=FetchFrom.PREDEFINED_MODEL, + model_properties={}, + deprecated=False, + provider=provider_entity_2, + status="active", + load_balancing_enabled=False, + ) + + mock_configurations = MagicMock() + mock_configurations.get_models.return_value = [mock_model_1, mock_model_2] + mock_provider_manager.get_configurations.return_value = mock_configurations + + # Act: Execute the method under test + service = ModelProviderService() + result = service.get_models_by_provider(tenant.id, "openai") + + # Assert: Verify the expected outcomes + assert result is not None + assert len(result) == 2 + + # Verify first model + assert result[0].provider.tenant_id == tenant.id + assert result[0].model == "gpt-3.5-turbo" + assert result[0].provider.provider == "openai" + + # Verify second model + assert result[1].provider.tenant_id == tenant.id + assert result[1].model == "gpt-4" + assert result[1].provider.provider == "openai" + + # Verify mock interactions + mock_provider_manager.get_configurations.assert_called_once_with(tenant.id) + mock_configurations.get_models.assert_called_once_with(provider="openai") + + def test_get_provider_credentials_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful retrieval of provider credentials. + + This test verifies: + - Proper credential retrieval for existing provider + - Correct handling of obfuscated credentials + - Mock interactions with ProviderManager + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Create test provider + provider = self._create_test_provider( + db_session_with_containers, mock_external_service_dependencies, tenant.id, "openai" + ) + + # Mock ProviderManager to return realistic configuration + mock_provider_manager = mock_external_service_dependencies["provider_manager"].return_value + + # Create mock provider configuration with credentials + mock_provider_configuration = MagicMock() + mock_provider_configuration.get_custom_credentials.return_value = { + "api_key": "sk-***123", + "base_url": "https://api.openai.com", + } + mock_provider_manager.get_configurations.return_value = {"openai": mock_provider_configuration} + + # Act: Execute the method under test + service = ModelProviderService() + result = service.get_provider_credentials(tenant.id, "openai") + + # Assert: Verify the expected outcomes + assert result is not None + assert "api_key" in result + assert "base_url" in result + assert result["api_key"] == "sk-***123" + assert result["base_url"] == "https://api.openai.com" + + # Verify mock interactions + mock_provider_manager.get_configurations.assert_called_once_with(tenant.id) + mock_provider_configuration.get_custom_credentials.assert_called_once_with(obfuscated=True) + + def test_provider_credentials_validate_success( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test successful validation of provider credentials. + + This test verifies: + - Proper credential validation for existing provider + - Correct handling of valid credentials + - Mock interactions with ProviderManager + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Create test provider + provider = self._create_test_provider( + db_session_with_containers, mock_external_service_dependencies, tenant.id, "openai" + ) + + # Mock ProviderManager to return realistic configuration + mock_provider_manager = mock_external_service_dependencies["provider_manager"].return_value + + # Create mock provider configuration with validation method + mock_provider_configuration = MagicMock() + mock_provider_configuration.custom_credentials_validate.return_value = True + mock_provider_manager.get_configurations.return_value = {"openai": mock_provider_configuration} + + # Test credentials + test_credentials = {"api_key": "sk-test123", "base_url": "https://api.openai.com"} + + # Act: Execute the method under test + service = ModelProviderService() + # This should not raise an exception + service.provider_credentials_validate(tenant.id, "openai", test_credentials) + + # Assert: Verify mock interactions + mock_provider_manager.get_configurations.assert_called_once_with(tenant.id) + mock_provider_configuration.custom_credentials_validate.assert_called_once_with(test_credentials) + + def test_provider_credentials_validate_invalid_provider( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test validation failure for non-existent provider. + + This test verifies: + - Proper error handling for non-existent provider + - Correct exception raising + - Mock interactions with ProviderManager + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Mock ProviderManager to return empty configurations + mock_provider_manager = mock_external_service_dependencies["provider_manager"].return_value + mock_provider_manager.get_configurations.return_value = {} + + # Test credentials + test_credentials = {"api_key": "sk-test123", "base_url": "https://api.openai.com"} + + # Act & Assert: Execute the method under test and verify exception + service = ModelProviderService() + with pytest.raises(ValueError, match="Provider nonexistent does not exist."): + service.provider_credentials_validate(tenant.id, "nonexistent", test_credentials) + + # Verify mock interactions + mock_provider_manager.get_configurations.assert_called_once_with(tenant.id) + + def test_get_default_model_of_model_type_success( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test successful retrieval of default model for a specific model type. + + This test verifies: + - Proper default model retrieval for tenant and model type + - Correct response structure with tenant_id and model data + - Mock interactions with ProviderManager + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Create test provider + provider = self._create_test_provider( + db_session_with_containers, mock_external_service_dependencies, tenant.id, "openai" + ) + + # Mock ProviderManager to return realistic default model + mock_provider_manager = mock_external_service_dependencies["provider_manager"].return_value + + # Create mock default model response + from core.entities.model_entities import DefaultModelEntity, DefaultModelProviderEntity + from core.model_runtime.entities.common_entities import I18nObject + + mock_default_model = DefaultModelEntity( + model="gpt-3.5-turbo", + model_type=ModelType.LLM, + provider=DefaultModelProviderEntity( + provider="openai", + label=I18nObject(en_US="OpenAI", zh_Hans="OpenAI"), + icon_small=I18nObject(en_US="icon_small.png", zh_Hans="icon_small.png"), + icon_large=I18nObject(en_US="icon_large.png", zh_Hans="icon_large.png"), + supported_model_types=[ModelType.LLM], + ), + ) + + mock_provider_manager.get_default_model.return_value = mock_default_model + + # Act: Execute the method under test + service = ModelProviderService() + result = service.get_default_model_of_model_type(tenant.id, "llm") + + # Assert: Verify the expected outcomes + assert result is not None + assert result.model == "gpt-3.5-turbo" + assert result.model_type == ModelType.LLM + assert result.provider.tenant_id == tenant.id + assert result.provider.provider == "openai" + + # Verify mock interactions + mock_provider_manager.get_default_model.assert_called_once_with(tenant_id=tenant.id, model_type=ModelType.LLM) + + def test_update_default_model_of_model_type_success( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test successful update of default model for a specific model type. + + This test verifies: + - Proper default model update for tenant and model type + - Correct mock interactions with ProviderManager + - Database state management + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Create test provider + provider = self._create_test_provider( + db_session_with_containers, mock_external_service_dependencies, tenant.id, "openai" + ) + + # Mock ProviderManager to return realistic configuration + mock_provider_manager = mock_external_service_dependencies["provider_manager"].return_value + + # Act: Execute the method under test + service = ModelProviderService() + service.update_default_model_of_model_type(tenant.id, "llm", "openai", "gpt-4") + + # Assert: Verify mock interactions + mock_provider_manager.update_default_model_record.assert_called_once_with( + tenant_id=tenant.id, model_type=ModelType.LLM, provider="openai", model="gpt-4" + ) + + def test_get_model_provider_icon_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful retrieval of model provider icon. + + This test verifies: + - Proper icon retrieval for provider and icon type + - Correct response structure with byte data and mime type + - Mock interactions with ModelProviderFactory + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Create test provider + provider = self._create_test_provider( + db_session_with_containers, mock_external_service_dependencies, tenant.id, "openai" + ) + + # Mock ModelProviderFactory to return realistic icon data + mock_model_provider_factory = mock_external_service_dependencies["model_provider_factory"].return_value + mock_model_provider_factory.get_provider_icon.return_value = (b"fake_icon_data", "image/png") + + # Act: Execute the method under test + service = ModelProviderService() + result = service.get_model_provider_icon(tenant.id, "openai", "icon_small", "en_US") + + # Assert: Verify the expected outcomes + assert result is not None + assert len(result) == 2 + assert result[0] == b"fake_icon_data" + assert result[1] == "image/png" + + # Verify mock interactions + mock_model_provider_factory.get_provider_icon.assert_called_once_with("openai", "icon_small", "en_US") + + def test_switch_preferred_provider_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful switching of preferred provider type. + + This test verifies: + - Proper provider type switching for tenant and provider + - Correct mock interactions with ProviderManager + - Provider configuration management + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Create test provider + provider = self._create_test_provider( + db_session_with_containers, mock_external_service_dependencies, tenant.id, "openai" + ) + + # Mock ProviderManager to return realistic configuration + mock_provider_manager = mock_external_service_dependencies["provider_manager"].return_value + + # Create mock provider configuration with switch method + mock_provider_configuration = MagicMock() + mock_provider_configuration.switch_preferred_provider_type.return_value = None + mock_provider_manager.get_configurations.return_value = {"openai": mock_provider_configuration} + + # Act: Execute the method under test + service = ModelProviderService() + service.switch_preferred_provider(tenant.id, "openai", "custom") + + # Assert: Verify mock interactions + mock_provider_manager.get_configurations.assert_called_once_with(tenant.id) + mock_provider_configuration.switch_preferred_provider_type.assert_called_once() + + def test_enable_model_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful enabling of a model. + + This test verifies: + - Proper model enabling for tenant, provider, and model + - Correct mock interactions with ProviderManager + - Model configuration management + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Create test provider + provider = self._create_test_provider( + db_session_with_containers, mock_external_service_dependencies, tenant.id, "openai" + ) + + # Mock ProviderManager to return realistic configuration + mock_provider_manager = mock_external_service_dependencies["provider_manager"].return_value + + # Create mock provider configuration with enable method + mock_provider_configuration = MagicMock() + mock_provider_configuration.enable_model.return_value = None + mock_provider_manager.get_configurations.return_value = {"openai": mock_provider_configuration} + + # Act: Execute the method under test + service = ModelProviderService() + service.enable_model(tenant.id, "openai", "gpt-4", "llm") + + # Assert: Verify mock interactions + mock_provider_manager.get_configurations.assert_called_once_with(tenant.id) + mock_provider_configuration.enable_model.assert_called_once_with(model_type=ModelType.LLM, model="gpt-4") + + def test_get_model_credentials_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful retrieval of model credentials. + + This test verifies: + - Proper credential retrieval for model + - Correct response structure with obfuscated credentials + - Mock interactions with ProviderManager + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Create test provider + provider = self._create_test_provider( + db_session_with_containers, mock_external_service_dependencies, tenant.id, "openai" + ) + + # Mock ProviderManager to return realistic configuration + mock_provider_manager = mock_external_service_dependencies["provider_manager"].return_value + + # Create mock provider configuration with model credentials + mock_provider_configuration = MagicMock() + mock_provider_configuration.get_custom_model_credentials.return_value = { + "api_key": "sk-***123", + "base_url": "https://api.openai.com", + } + mock_provider_manager.get_configurations.return_value = {"openai": mock_provider_configuration} + + # Act: Execute the method under test + service = ModelProviderService() + result = service.get_model_credentials(tenant.id, "openai", "llm", "gpt-4") + + # Assert: Verify the expected outcomes + assert result is not None + assert "api_key" in result + assert "base_url" in result + assert result["api_key"] == "sk-***123" + assert result["base_url"] == "https://api.openai.com" + + # Verify mock interactions + mock_provider_manager.get_configurations.assert_called_once_with(tenant.id) + mock_provider_configuration.get_custom_model_credentials.assert_called_once_with( + model_type=ModelType.LLM, model="gpt-4", obfuscated=True + ) + + def test_model_credentials_validate_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful validation of model credentials. + + This test verifies: + - Proper credential validation for model + - Correct mock interactions with ProviderManager + - Model credential validation process + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Create test provider + provider = self._create_test_provider( + db_session_with_containers, mock_external_service_dependencies, tenant.id, "openai" + ) + + # Mock ProviderManager to return realistic configuration + mock_provider_manager = mock_external_service_dependencies["provider_manager"].return_value + + # Create mock provider configuration with validation method + mock_provider_configuration = MagicMock() + mock_provider_configuration.custom_model_credentials_validate.return_value = True + mock_provider_manager.get_configurations.return_value = {"openai": mock_provider_configuration} + + # Test credentials + test_credentials = {"api_key": "sk-test123", "base_url": "https://api.openai.com"} + + # Act: Execute the method under test + service = ModelProviderService() + # This should not raise an exception + service.model_credentials_validate(tenant.id, "openai", "llm", "gpt-4", test_credentials) + + # Assert: Verify mock interactions + mock_provider_manager.get_configurations.assert_called_once_with(tenant.id) + mock_provider_configuration.custom_model_credentials_validate.assert_called_once_with( + model_type=ModelType.LLM, model="gpt-4", credentials=test_credentials + ) + + def test_save_model_credentials_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful saving of model credentials. + + This test verifies: + - Proper credential saving for model + - Correct mock interactions with ProviderManager + - Model credential management + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Create test provider + provider = self._create_test_provider( + db_session_with_containers, mock_external_service_dependencies, tenant.id, "openai" + ) + + # Mock ProviderManager to return realistic configuration + mock_provider_manager = mock_external_service_dependencies["provider_manager"].return_value + + # Create mock provider configuration with save method + mock_provider_configuration = MagicMock() + mock_provider_configuration.add_or_update_custom_model_credentials.return_value = None + mock_provider_manager.get_configurations.return_value = {"openai": mock_provider_configuration} + + # Test credentials + test_credentials = {"api_key": "sk-test123", "base_url": "https://api.openai.com"} + + # Act: Execute the method under test + service = ModelProviderService() + service.save_model_credentials(tenant.id, "openai", "llm", "gpt-4", test_credentials) + + # Assert: Verify mock interactions + mock_provider_manager.get_configurations.assert_called_once_with(tenant.id) + mock_provider_configuration.add_or_update_custom_model_credentials.assert_called_once_with( + model_type=ModelType.LLM, model="gpt-4", credentials=test_credentials + ) + + def test_remove_model_credentials_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful removal of model credentials. + + This test verifies: + - Proper credential removal for model + - Correct mock interactions with ProviderManager + - Model credential cleanup + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Create test provider + provider = self._create_test_provider( + db_session_with_containers, mock_external_service_dependencies, tenant.id, "openai" + ) + + # Mock ProviderManager to return realistic configuration + mock_provider_manager = mock_external_service_dependencies["provider_manager"].return_value + + # Create mock provider configuration with remove method + mock_provider_configuration = MagicMock() + mock_provider_configuration.delete_custom_model_credentials.return_value = None + mock_provider_manager.get_configurations.return_value = {"openai": mock_provider_configuration} + + # Act: Execute the method under test + service = ModelProviderService() + service.remove_model_credentials(tenant.id, "openai", "llm", "gpt-4") + + # Assert: Verify mock interactions + mock_provider_manager.get_configurations.assert_called_once_with(tenant.id) + mock_provider_configuration.delete_custom_model_credentials.assert_called_once_with( + model_type=ModelType.LLM, model="gpt-4" + ) + + def test_get_models_by_model_type_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful retrieval of models by model type. + + This test verifies: + - Proper model retrieval for specific model type + - Correct response structure with provider grouping + - Mock interactions with ProviderManager + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Create test provider + provider = self._create_test_provider( + db_session_with_containers, mock_external_service_dependencies, tenant.id, "openai" + ) + + # Mock ProviderManager to return realistic configuration + mock_provider_manager = mock_external_service_dependencies["provider_manager"].return_value + + # Create mock provider configurations object with get_models method + mock_provider_configurations = MagicMock() + mock_provider_configurations.get_models.return_value = [ + MagicMock( + provider=MagicMock( + provider="openai", + label={"en_US": "OpenAI", "zh_Hans": "OpenAI"}, + icon_small={"en_US": "icon_small.png", "zh_Hans": "icon_small.png"}, + icon_large={"en_US": "icon_large.png", "zh_Hans": "icon_large.png"}, + ), + model="gpt-3.5-turbo", + model_type=ModelType.LLM, + status=ModelStatus.ACTIVE, + deprecated=False, + label={"en_US": "GPT-3.5 Turbo", "zh_Hans": "GPT-3.5 Turbo"}, + features=[], + fetch_from="predefined-model", + model_properties={}, + load_balancing_enabled=False, + ), + MagicMock( + provider=MagicMock( + provider="openai", + label={"en_US": "OpenAI", "zh_Hans": "OpenAI"}, + icon_small={"en_US": "icon_small.png", "zh_Hans": "icon_small.png"}, + icon_large={"en_US": "icon_large.png", "zh_Hans": "icon_large.png"}, + ), + model="gpt-4", + model_type=ModelType.LLM, + status=ModelStatus.ACTIVE, + deprecated=False, + label={"en_US": "GPT-4", "zh_Hans": "GPT-4"}, + features=[], + fetch_from="predefined-model", + model_properties={}, + load_balancing_enabled=False, + ), + ] + mock_provider_manager.get_configurations.return_value = mock_provider_configurations + + # Act: Execute the method under test + service = ModelProviderService() + result = service.get_models_by_model_type(tenant.id, "llm") + + # Assert: Verify the expected outcomes + assert result is not None + assert len(result) == 1 # One provider group + assert result[0].provider == "openai" + assert len(result[0].models) == 2 # Two models in the provider + + # Verify mock interactions + mock_provider_manager.get_configurations.assert_called_once_with(tenant.id) + mock_provider_configurations.get_models.assert_called_once_with(model_type=ModelType.LLM) + + def test_get_model_parameter_rules_success(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful retrieval of model parameter rules. + + This test verifies: + - Proper parameter rules retrieval for model + - Correct mock interactions with ProviderManager + - Model schema handling + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Create test provider + provider = self._create_test_provider( + db_session_with_containers, mock_external_service_dependencies, tenant.id, "openai" + ) + + # Mock ProviderManager to return realistic configuration + mock_provider_manager = mock_external_service_dependencies["provider_manager"].return_value + + # Create mock provider configuration with parameter rules + mock_provider_configuration = MagicMock() + mock_credentials = {"api_key": "sk-test123"} + mock_model_schema = MagicMock() + + # Create mock parameter rules with proper return values + mock_temperature_rule = MagicMock() + mock_temperature_rule.name = "temperature" + mock_temperature_rule.type = "float" + mock_temperature_rule.min = 0.0 + mock_temperature_rule.max = 2.0 + + mock_max_tokens_rule = MagicMock() + mock_max_tokens_rule.name = "max_tokens" + mock_max_tokens_rule.type = "integer" + mock_max_tokens_rule.min = 1 + mock_max_tokens_rule.max = 4096 + + mock_model_schema.parameter_rules = [mock_temperature_rule, mock_max_tokens_rule] + + mock_provider_configuration.get_current_credentials.return_value = mock_credentials + mock_provider_configuration.get_model_schema.return_value = mock_model_schema + mock_provider_manager.get_configurations.return_value = {"openai": mock_provider_configuration} + + # Act: Execute the method under test + service = ModelProviderService() + result = service.get_model_parameter_rules(tenant.id, "openai", "gpt-4") + + # Assert: Verify the expected outcomes + assert result is not None + assert len(result) == 2 + assert result[0].name == "temperature" + assert result[1].name == "max_tokens" + + # Verify mock interactions + mock_provider_manager.get_configurations.assert_called_once_with(tenant.id) + mock_provider_configuration.get_current_credentials.assert_called_once_with( + model_type=ModelType.LLM, model="gpt-4" + ) + mock_provider_configuration.get_model_schema.assert_called_once_with( + model_type=ModelType.LLM, model="gpt-4", credentials=mock_credentials + ) + + def test_get_model_parameter_rules_no_credentials( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test parameter rules retrieval when no credentials are available. + + This test verifies: + - Proper handling of missing credentials + - Empty result when no credentials exist + - Mock interactions with ProviderManager + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Create test provider + provider = self._create_test_provider( + db_session_with_containers, mock_external_service_dependencies, tenant.id, "openai" + ) + + # Mock ProviderManager to return realistic configuration + mock_provider_manager = mock_external_service_dependencies["provider_manager"].return_value + + # Create mock provider configuration with no credentials + mock_provider_configuration = MagicMock() + mock_provider_configuration.get_current_credentials.return_value = None + mock_provider_manager.get_configurations.return_value = {"openai": mock_provider_configuration} + + # Act: Execute the method under test + service = ModelProviderService() + result = service.get_model_parameter_rules(tenant.id, "openai", "gpt-4") + + # Assert: Verify the expected outcomes + assert result is not None + assert len(result) == 0 + + # Verify mock interactions + mock_provider_manager.get_configurations.assert_called_once_with(tenant.id) + mock_provider_configuration.get_current_credentials.assert_called_once_with( + model_type=ModelType.LLM, model="gpt-4" + ) + + def test_get_model_parameter_rules_provider_not_found( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test parameter rules retrieval when provider does not exist. + + This test verifies: + - Proper error handling for non-existent provider + - ValueError is raised with appropriate message + - Mock interactions with ProviderManager + """ + # Arrange: Create test data + fake = Faker() + account, tenant = self._create_test_account_and_tenant( + db_session_with_containers, mock_external_service_dependencies + ) + + # Mock ProviderManager to return empty configurations + mock_provider_manager = mock_external_service_dependencies["provider_manager"].return_value + mock_provider_manager.get_configurations.return_value = {} + + # Act & Assert: Execute the method under test and expect ValueError + service = ModelProviderService() + with pytest.raises(ValueError, match="Provider openai does not exist."): + service.get_model_parameter_rules(tenant.id, "openai", "gpt-4") + + # Verify mock interactions + mock_provider_manager.get_configurations.assert_called_once_with(tenant.id) diff --git a/api/tests/test_containers_integration_tests/services/test_saved_message_service.py b/api/tests/test_containers_integration_tests/services/test_saved_message_service.py new file mode 100644 index 0000000000..9e6b9837ae --- /dev/null +++ b/api/tests/test_containers_integration_tests/services/test_saved_message_service.py @@ -0,0 +1,620 @@ +from unittest.mock import patch + +import pytest +from faker import Faker + +from models.model import EndUser, Message +from models.web import SavedMessage +from services.app_service import AppService +from services.saved_message_service import SavedMessageService + + +class TestSavedMessageService: + """Integration tests for SavedMessageService using testcontainers.""" + + @pytest.fixture + def mock_external_service_dependencies(self): + """Mock setup for external service dependencies.""" + with ( + patch("services.account_service.FeatureService") as mock_account_feature_service, + patch("services.app_service.ModelManager") as mock_model_manager, + patch("services.saved_message_service.MessageService") as mock_message_service, + ): + # Setup default mock returns + mock_account_feature_service.get_system_features.return_value.is_allow_register = True + + # Mock ModelManager for app creation + mock_model_instance = mock_model_manager.return_value + mock_model_instance.get_default_model_instance.return_value = None + mock_model_instance.get_default_provider_model_name.return_value = ("openai", "gpt-3.5-turbo") + + # Mock MessageService + mock_message_service.get_message.return_value = None + mock_message_service.pagination_by_last_id.return_value = None + + yield { + "account_feature_service": mock_account_feature_service, + "model_manager": mock_model_manager, + "message_service": mock_message_service, + } + + def _create_test_app_and_account(self, db_session_with_containers, mock_external_service_dependencies): + """ + Helper method to create a test app and account for testing. + + Args: + db_session_with_containers: Database session from testcontainers infrastructure + mock_external_service_dependencies: Mock dependencies + + Returns: + tuple: (app, account) - Created app and account instances + """ + fake = Faker() + + # Setup mocks for account creation + mock_external_service_dependencies[ + "account_feature_service" + ].get_system_features.return_value.is_allow_register = True + + # Create account and tenant first + from services.account_service import AccountService, TenantService + + account = AccountService.create_account( + email=fake.email(), + name=fake.name(), + interface_language="en-US", + password=fake.password(length=12), + ) + TenantService.create_owner_tenant_if_not_exist(account, name=fake.company()) + tenant = account.current_tenant + + # Create app with realistic data + app_args = { + "name": fake.company(), + "description": fake.text(max_nb_chars=100), + "mode": "chat", + "icon_type": "emoji", + "icon": "🤖", + "icon_background": "#FF6B6B", + "api_rph": 100, + "api_rpm": 10, + } + + app_service = AppService() + app = app_service.create_app(tenant.id, app_args, account) + + return app, account + + def _create_test_end_user(self, db_session_with_containers, app): + """ + Helper method to create a test end user for testing. + + Args: + db_session_with_containers: Database session from testcontainers infrastructure + app: App instance to associate the end user with + + Returns: + EndUser: Created end user instance + """ + fake = Faker() + + end_user = EndUser( + tenant_id=app.tenant_id, + app_id=app.id, + external_user_id=fake.uuid4(), + name=fake.name(), + type="normal", + session_id=fake.uuid4(), + is_anonymous=False, + ) + + from extensions.ext_database import db + + db.session.add(end_user) + db.session.commit() + + return end_user + + def _create_test_message(self, db_session_with_containers, app, user): + """ + Helper method to create a test message for testing. + + Args: + db_session_with_containers: Database session from testcontainers infrastructure + app: App instance to associate the message with + user: User instance (Account or EndUser) to associate the message with + + Returns: + Message: Created message instance + """ + fake = Faker() + + # Create a simple conversation first + from models.model import Conversation + + conversation = Conversation( + app_id=app.id, + from_source="account" if hasattr(user, "current_tenant") else "end_user", + from_end_user_id=user.id if not hasattr(user, "current_tenant") else None, + from_account_id=user.id if hasattr(user, "current_tenant") else None, + name=fake.sentence(nb_words=3), + inputs={}, + status="normal", + mode="chat", + ) + + from extensions.ext_database import db + + db.session.add(conversation) + db.session.commit() + + # Create message + message = Message( + app_id=app.id, + conversation_id=conversation.id, + from_source="account" if hasattr(user, "current_tenant") else "end_user", + from_end_user_id=user.id if not hasattr(user, "current_tenant") else None, + from_account_id=user.id if hasattr(user, "current_tenant") else None, + inputs={}, + query=fake.sentence(nb_words=5), + message=fake.text(max_nb_chars=100), + answer=fake.text(max_nb_chars=200), + message_tokens=50, + answer_tokens=100, + message_unit_price=0.001, + answer_unit_price=0.002, + total_price=0.003, + currency="USD", + status="success", + ) + + db.session.add(message) + db.session.commit() + + return message + + def test_pagination_by_last_id_success_with_account_user( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test successful pagination by last ID with account user. + + This test verifies: + - Proper pagination with account user + - Correct filtering by app_id and user + - Proper role identification for account users + - MessageService integration + """ + # Arrange: Create test data + fake = Faker() + app, account = self._create_test_app_and_account(db_session_with_containers, mock_external_service_dependencies) + + # Create test messages + message1 = self._create_test_message(db_session_with_containers, app, account) + message2 = self._create_test_message(db_session_with_containers, app, account) + + # Create saved messages + saved_message1 = SavedMessage( + app_id=app.id, + message_id=message1.id, + created_by_role="account", + created_by=account.id, + ) + saved_message2 = SavedMessage( + app_id=app.id, + message_id=message2.id, + created_by_role="account", + created_by=account.id, + ) + + from extensions.ext_database import db + + db.session.add_all([saved_message1, saved_message2]) + db.session.commit() + + # Mock MessageService.pagination_by_last_id return value + from libs.infinite_scroll_pagination import InfiniteScrollPagination + + mock_pagination = InfiniteScrollPagination(data=[message1, message2], limit=10, has_more=False) + mock_external_service_dependencies["message_service"].pagination_by_last_id.return_value = mock_pagination + + # Act: Execute the method under test + result = SavedMessageService.pagination_by_last_id(app_model=app, user=account, last_id=None, limit=10) + + # Assert: Verify the expected outcomes + assert result is not None + assert result.data == [message1, message2] + assert result.limit == 10 + assert result.has_more is False + + # Verify MessageService was called with correct parameters + # Sort the IDs to handle database query order variations + expected_include_ids = sorted([message1.id, message2.id]) + actual_call = mock_external_service_dependencies["message_service"].pagination_by_last_id.call_args + actual_include_ids = sorted(actual_call.kwargs.get("include_ids", [])) + + assert actual_call.kwargs["app_model"] == app + assert actual_call.kwargs["user"] == account + assert actual_call.kwargs["last_id"] is None + assert actual_call.kwargs["limit"] == 10 + assert actual_include_ids == expected_include_ids + + # Verify database state + db.session.refresh(saved_message1) + db.session.refresh(saved_message2) + assert saved_message1.id is not None + assert saved_message2.id is not None + assert saved_message1.created_by_role == "account" + assert saved_message2.created_by_role == "account" + + def test_pagination_by_last_id_success_with_end_user( + self, db_session_with_containers, mock_external_service_dependencies + ): + """ + Test successful pagination by last ID with end user. + + This test verifies: + - Proper pagination with end user + - Correct filtering by app_id and user + - Proper role identification for end users + - MessageService integration + """ + # Arrange: Create test data + fake = Faker() + app, account = self._create_test_app_and_account(db_session_with_containers, mock_external_service_dependencies) + end_user = self._create_test_end_user(db_session_with_containers, app) + + # Create test messages + message1 = self._create_test_message(db_session_with_containers, app, end_user) + message2 = self._create_test_message(db_session_with_containers, app, end_user) + + # Create saved messages + saved_message1 = SavedMessage( + app_id=app.id, + message_id=message1.id, + created_by_role="end_user", + created_by=end_user.id, + ) + saved_message2 = SavedMessage( + app_id=app.id, + message_id=message2.id, + created_by_role="end_user", + created_by=end_user.id, + ) + + from extensions.ext_database import db + + db.session.add_all([saved_message1, saved_message2]) + db.session.commit() + + # Mock MessageService.pagination_by_last_id return value + from libs.infinite_scroll_pagination import InfiniteScrollPagination + + mock_pagination = InfiniteScrollPagination(data=[message1, message2], limit=5, has_more=True) + mock_external_service_dependencies["message_service"].pagination_by_last_id.return_value = mock_pagination + + # Act: Execute the method under test + result = SavedMessageService.pagination_by_last_id( + app_model=app, user=end_user, last_id="test_last_id", limit=5 + ) + + # Assert: Verify the expected outcomes + assert result is not None + assert result.data == [message1, message2] + assert result.limit == 5 + assert result.has_more is True + + # Verify MessageService was called with correct parameters + # Sort the IDs to handle database query order variations + expected_include_ids = sorted([message1.id, message2.id]) + actual_call = mock_external_service_dependencies["message_service"].pagination_by_last_id.call_args + actual_include_ids = sorted(actual_call.kwargs.get("include_ids", [])) + + assert actual_call.kwargs["app_model"] == app + assert actual_call.kwargs["user"] == end_user + assert actual_call.kwargs["last_id"] == "test_last_id" + assert actual_call.kwargs["limit"] == 5 + assert actual_include_ids == expected_include_ids + + # Verify database state + db.session.refresh(saved_message1) + db.session.refresh(saved_message2) + assert saved_message1.id is not None + assert saved_message2.id is not None + assert saved_message1.created_by_role == "end_user" + assert saved_message2.created_by_role == "end_user" + + def test_save_success_with_new_message(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful save of a new message. + + This test verifies: + - Proper creation of new saved message + - Correct database state after save + - Proper relationship establishment + - MessageService integration for message retrieval + """ + # Arrange: Create test data + fake = Faker() + app, account = self._create_test_app_and_account(db_session_with_containers, mock_external_service_dependencies) + message = self._create_test_message(db_session_with_containers, app, account) + + # Mock MessageService.get_message return value + mock_external_service_dependencies["message_service"].get_message.return_value = message + + # Act: Execute the method under test + SavedMessageService.save(app_model=app, user=account, message_id=message.id) + + # Assert: Verify the expected outcomes + # Check if saved message was created in database + from extensions.ext_database import db + + saved_message = ( + db.session.query(SavedMessage) + .where( + SavedMessage.app_id == app.id, + SavedMessage.message_id == message.id, + SavedMessage.created_by_role == "account", + SavedMessage.created_by == account.id, + ) + .first() + ) + + assert saved_message is not None + assert saved_message.app_id == app.id + assert saved_message.message_id == message.id + assert saved_message.created_by_role == "account" + assert saved_message.created_by == account.id + assert saved_message.created_at is not None + + # Verify MessageService.get_message was called + mock_external_service_dependencies["message_service"].get_message.assert_called_once_with( + app_model=app, user=account, message_id=message.id + ) + + # Verify database state + db.session.refresh(saved_message) + assert saved_message.id is not None + + def test_pagination_by_last_id_error_no_user(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test error handling when no user is provided. + + This test verifies: + - Proper error handling for missing user + - ValueError is raised when user is None + - No database operations are performed + """ + # Arrange: Create test data + fake = Faker() + app, account = self._create_test_app_and_account(db_session_with_containers, mock_external_service_dependencies) + + # Act & Assert: Verify proper error handling + with pytest.raises(ValueError) as exc_info: + SavedMessageService.pagination_by_last_id(app_model=app, user=None, last_id=None, limit=10) + + assert "User is required" in str(exc_info.value) + + # Verify no database operations were performed + from extensions.ext_database import db + + saved_messages = db.session.query(SavedMessage).all() + assert len(saved_messages) == 0 + + def test_save_error_no_user(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test error handling when saving message with no user. + + This test verifies: + - Method returns early when user is None + - No database operations are performed + - No exceptions are raised + """ + # Arrange: Create test data + fake = Faker() + app, account = self._create_test_app_and_account(db_session_with_containers, mock_external_service_dependencies) + message = self._create_test_message(db_session_with_containers, app, account) + + # Act: Execute the method under test with None user + result = SavedMessageService.save(app_model=app, user=None, message_id=message.id) + + # Assert: Verify the expected outcomes + assert result is None + + # Verify no saved message was created + from extensions.ext_database import db + + saved_message = ( + db.session.query(SavedMessage) + .where( + SavedMessage.app_id == app.id, + SavedMessage.message_id == message.id, + ) + .first() + ) + + assert saved_message is None + + def test_delete_success_existing_message(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful deletion of an existing saved message. + + This test verifies: + - Proper deletion of existing saved message + - Correct database state after deletion + - No errors during deletion process + """ + # Arrange: Create test data + fake = Faker() + app, account = self._create_test_app_and_account(db_session_with_containers, mock_external_service_dependencies) + message = self._create_test_message(db_session_with_containers, app, account) + + # Create a saved message first + saved_message = SavedMessage( + app_id=app.id, + message_id=message.id, + created_by_role="account", + created_by=account.id, + ) + + from extensions.ext_database import db + + db.session.add(saved_message) + db.session.commit() + + # Verify saved message exists + assert ( + db.session.query(SavedMessage) + .where( + SavedMessage.app_id == app.id, + SavedMessage.message_id == message.id, + SavedMessage.created_by_role == "account", + SavedMessage.created_by == account.id, + ) + .first() + is not None + ) + + # Act: Execute the method under test + SavedMessageService.delete(app_model=app, user=account, message_id=message.id) + + # Assert: Verify the expected outcomes + # Check if saved message was deleted from database + deleted_saved_message = ( + db.session.query(SavedMessage) + .where( + SavedMessage.app_id == app.id, + SavedMessage.message_id == message.id, + SavedMessage.created_by_role == "account", + SavedMessage.created_by == account.id, + ) + .first() + ) + + assert deleted_saved_message is None + + # Verify database state + db.session.commit() + # The message should still exist, only the saved_message should be deleted + assert db.session.query(Message).where(Message.id == message.id).first() is not None + + def test_pagination_by_last_id_error_no_user(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test error handling when no user is provided. + + This test verifies: + - Proper error handling for missing user + - ValueError is raised when user is None + - No database operations are performed + """ + # Arrange: Create test data + fake = Faker() + app, account = self._create_test_app_and_account(db_session_with_containers, mock_external_service_dependencies) + + # Act & Assert: Verify proper error handling + with pytest.raises(ValueError) as exc_info: + SavedMessageService.pagination_by_last_id(app_model=app, user=None, last_id=None, limit=10) + + assert "User is required" in str(exc_info.value) + + # Verify no database operations were performed for this specific test + # Note: We don't check total count as other tests may have created data + # Instead, we verify that the error was properly raised + pass + + def test_save_error_no_user(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test error handling when saving message with no user. + + This test verifies: + - Method returns early when user is None + - No database operations are performed + - No exceptions are raised + """ + # Arrange: Create test data + fake = Faker() + app, account = self._create_test_app_and_account(db_session_with_containers, mock_external_service_dependencies) + message = self._create_test_message(db_session_with_containers, app, account) + + # Act: Execute the method under test with None user + result = SavedMessageService.save(app_model=app, user=None, message_id=message.id) + + # Assert: Verify the expected outcomes + assert result is None + + # Verify no saved message was created + from extensions.ext_database import db + + saved_message = ( + db.session.query(SavedMessage) + .where( + SavedMessage.app_id == app.id, + SavedMessage.message_id == message.id, + ) + .first() + ) + + assert saved_message is None + + def test_delete_success_existing_message(self, db_session_with_containers, mock_external_service_dependencies): + """ + Test successful deletion of an existing saved message. + + This test verifies: + - Proper deletion of existing saved message + - Correct database state after deletion + - No errors during deletion process + """ + # Arrange: Create test data + fake = Faker() + app, account = self._create_test_app_and_account(db_session_with_containers, mock_external_service_dependencies) + message = self._create_test_message(db_session_with_containers, app, account) + + # Create a saved message first + saved_message = SavedMessage( + app_id=app.id, + message_id=message.id, + created_by_role="account", + created_by=account.id, + ) + + from extensions.ext_database import db + + db.session.add(saved_message) + db.session.commit() + + # Verify saved message exists + assert ( + db.session.query(SavedMessage) + .where( + SavedMessage.app_id == app.id, + SavedMessage.message_id == message.id, + SavedMessage.created_by_role == "account", + SavedMessage.created_by == account.id, + ) + .first() + is not None + ) + + # Act: Execute the method under test + SavedMessageService.delete(app_model=app, user=account, message_id=message.id) + + # Assert: Verify the expected outcomes + # Check if saved message was deleted from database + deleted_saved_message = ( + db.session.query(SavedMessage) + .where( + SavedMessage.app_id == app.id, + SavedMessage.message_id == message.id, + SavedMessage.created_by_role == "account", + SavedMessage.created_by == account.id, + ) + .first() + ) + + assert deleted_saved_message is None + + # Verify database state + db.session.commit() + # The message should still exist, only the saved_message should be deleted + assert db.session.query(Message).where(Message.id == message.id).first() is not None diff --git a/api/tests/unit_tests/core/mcp/client/test_sse.py b/api/tests/unit_tests/core/mcp/client/test_sse.py index 8122cd08eb..880a0d4940 100644 --- a/api/tests/unit_tests/core/mcp/client/test_sse.py +++ b/api/tests/unit_tests/core/mcp/client/test_sse.py @@ -262,26 +262,6 @@ def test_sse_client_queue_cleanup(): # Note: In real implementation, cleanup should put None to signal shutdown -def test_sse_client_url_processing(): - """Test SSE client URL processing functions.""" - from core.mcp.client.sse_client import remove_request_params - - # Test URL with parameters - url_with_params = "http://example.com/sse?param1=value1¶m2=value2" - cleaned_url = remove_request_params(url_with_params) - assert cleaned_url == "http://example.com/sse" - - # Test URL without parameters - url_without_params = "http://example.com/sse" - cleaned_url = remove_request_params(url_without_params) - assert cleaned_url == "http://example.com/sse" - - # Test URL with path and parameters - complex_url = "http://example.com/path/to/sse?session=123&token=abc" - cleaned_url = remove_request_params(complex_url) - assert cleaned_url == "http://example.com/path/to/sse" - - def test_sse_client_headers_propagation(): """Test that custom headers are properly propagated in SSE client.""" test_url = "http://test.example/sse" diff --git a/api/tests/unit_tests/core/tools/utils/test_tool_engine_serialization.py b/api/tests/unit_tests/core/tools/utils/test_tool_engine_serialization.py new file mode 100644 index 0000000000..4029edfb68 --- /dev/null +++ b/api/tests/unit_tests/core/tools/utils/test_tool_engine_serialization.py @@ -0,0 +1,481 @@ +import json +from datetime import date, datetime +from decimal import Decimal +from uuid import uuid4 + +import numpy as np +import pytest +import pytz + +from core.tools.entities.tool_entities import ToolInvokeMessage +from core.tools.utils.message_transformer import ToolFileMessageTransformer, safe_json_dict, safe_json_value + + +class TestSafeJsonValue: + """Test suite for safe_json_value function to ensure proper serialization of complex types""" + + def test_datetime_conversion(self): + """Test datetime conversion with timezone handling""" + # Test datetime with UTC timezone + dt = datetime(2024, 1, 1, 12, 0, 0, tzinfo=pytz.UTC) + result = safe_json_value(dt) + assert isinstance(result, str) + assert "2024-01-01T12:00:00+00:00" in result + + # Test datetime without timezone (should default to UTC) + dt_no_tz = datetime(2024, 1, 1, 12, 0, 0) + result = safe_json_value(dt_no_tz) + assert isinstance(result, str) + # The exact time will depend on the system's timezone, so we check the format + assert "T" in result # ISO format separator + # Check that it's a valid ISO format datetime string + assert len(result) >= 19 # At least YYYY-MM-DDTHH:MM:SS + + def test_date_conversion(self): + """Test date conversion to ISO format""" + test_date = date(2024, 1, 1) + result = safe_json_value(test_date) + assert result == "2024-01-01" + + def test_uuid_conversion(self): + """Test UUID conversion to string""" + test_uuid = uuid4() + result = safe_json_value(test_uuid) + assert isinstance(result, str) + assert result == str(test_uuid) + + def test_decimal_conversion(self): + """Test Decimal conversion to float""" + test_decimal = Decimal("123.456") + result = safe_json_value(test_decimal) + assert result == 123.456 + assert isinstance(result, float) + + def test_bytes_conversion(self): + """Test bytes conversion with UTF-8 decoding""" + # Test valid UTF-8 bytes + test_bytes = b"Hello, World!" + result = safe_json_value(test_bytes) + assert result == "Hello, World!" + + # Test invalid UTF-8 bytes (should fall back to hex) + invalid_bytes = b"\xff\xfe\xfd" + result = safe_json_value(invalid_bytes) + assert result == "fffefd" + + def test_memoryview_conversion(self): + """Test memoryview conversion to hex string""" + test_bytes = b"test data" + test_memoryview = memoryview(test_bytes) + result = safe_json_value(test_memoryview) + assert result == "746573742064617461" # hex of "test data" + + def test_numpy_ndarray_conversion(self): + """Test numpy ndarray conversion to list""" + # Test 1D array + test_array = np.array([1, 2, 3, 4]) + result = safe_json_value(test_array) + assert result == [1, 2, 3, 4] + + # Test 2D array + test_2d_array = np.array([[1, 2], [3, 4]]) + result = safe_json_value(test_2d_array) + assert result == [[1, 2], [3, 4]] + + # Test array with float values + test_float_array = np.array([1.5, 2.7, 3.14]) + result = safe_json_value(test_float_array) + assert result == [1.5, 2.7, 3.14] + + def test_dict_conversion(self): + """Test dictionary conversion using safe_json_dict""" + test_dict = { + "string": "value", + "number": 42, + "float": 3.14, + "boolean": True, + "list": [1, 2, 3], + "nested": {"key": "value"}, + } + result = safe_json_value(test_dict) + assert isinstance(result, dict) + assert result == test_dict + + def test_list_conversion(self): + """Test list conversion with mixed types""" + test_list = [ + "string", + 42, + 3.14, + True, + [1, 2, 3], + {"key": "value"}, + datetime(2024, 1, 1, 12, 0, 0, tzinfo=pytz.UTC), + Decimal("123.456"), + uuid4(), + ] + result = safe_json_value(test_list) + assert isinstance(result, list) + assert len(result) == len(test_list) + assert isinstance(result[6], str) # datetime should be converted to string + assert isinstance(result[7], float) # Decimal should be converted to float + assert isinstance(result[8], str) # UUID should be converted to string + + def test_tuple_conversion(self): + """Test tuple conversion to list""" + test_tuple = (1, "string", 3.14) + result = safe_json_value(test_tuple) + assert isinstance(result, list) + assert result == [1, "string", 3.14] + + def test_set_conversion(self): + """Test set conversion to list""" + test_set = {1, "string", 3.14} + result = safe_json_value(test_set) + assert isinstance(result, list) + # Note: set order is not guaranteed, so we check length and content + assert len(result) == 3 + assert 1 in result + assert "string" in result + assert 3.14 in result + + def test_basic_types_passthrough(self): + """Test that basic types are passed through unchanged""" + assert safe_json_value("string") == "string" + assert safe_json_value(42) == 42 + assert safe_json_value(3.14) == 3.14 + assert safe_json_value(True) is True + assert safe_json_value(False) is False + assert safe_json_value(None) is None + + def test_nested_complex_structure(self): + """Test complex nested structure with all types""" + complex_data = { + "dates": [date(2024, 1, 1), date(2024, 1, 2)], + "timestamps": [ + datetime(2024, 1, 1, 12, 0, 0, tzinfo=pytz.UTC), + datetime(2024, 1, 2, 12, 0, 0, tzinfo=pytz.UTC), + ], + "numbers": [Decimal("123.456"), Decimal("789.012")], + "identifiers": [uuid4(), uuid4()], + "binary_data": [b"hello", b"world"], + "arrays": [np.array([1, 2, 3]), np.array([4, 5, 6])], + } + + result = safe_json_value(complex_data) + + # Verify structure is maintained + assert isinstance(result, dict) + assert "dates" in result + assert "timestamps" in result + assert "numbers" in result + assert "identifiers" in result + assert "binary_data" in result + assert "arrays" in result + + # Verify conversions + assert all(isinstance(d, str) for d in result["dates"]) + assert all(isinstance(t, str) for t in result["timestamps"]) + assert all(isinstance(n, float) for n in result["numbers"]) + assert all(isinstance(i, str) for i in result["identifiers"]) + assert all(isinstance(b, str) for b in result["binary_data"]) + assert all(isinstance(a, list) for a in result["arrays"]) + + +class TestSafeJsonDict: + """Test suite for safe_json_dict function""" + + def test_valid_dict_conversion(self): + """Test valid dictionary conversion""" + test_dict = { + "string": "value", + "number": 42, + "datetime": datetime(2024, 1, 1, 12, 0, 0, tzinfo=pytz.UTC), + "decimal": Decimal("123.456"), + } + result = safe_json_dict(test_dict) + assert isinstance(result, dict) + assert result["string"] == "value" + assert result["number"] == 42 + assert isinstance(result["datetime"], str) + assert isinstance(result["decimal"], float) + + def test_invalid_input_type(self): + """Test that invalid input types raise TypeError""" + with pytest.raises(TypeError, match="safe_json_dict\\(\\) expects a dictionary \\(dict\\) as input"): + safe_json_dict("not a dict") + + with pytest.raises(TypeError, match="safe_json_dict\\(\\) expects a dictionary \\(dict\\) as input"): + safe_json_dict([1, 2, 3]) + + with pytest.raises(TypeError, match="safe_json_dict\\(\\) expects a dictionary \\(dict\\) as input"): + safe_json_dict(42) + + def test_empty_dict(self): + """Test empty dictionary handling""" + result = safe_json_dict({}) + assert result == {} + + def test_nested_dict_conversion(self): + """Test nested dictionary conversion""" + test_dict = { + "level1": { + "level2": {"datetime": datetime(2024, 1, 1, 12, 0, 0, tzinfo=pytz.UTC), "decimal": Decimal("123.456")} + } + } + result = safe_json_dict(test_dict) + assert isinstance(result["level1"]["level2"]["datetime"], str) + assert isinstance(result["level1"]["level2"]["decimal"], float) + + +class TestToolInvokeMessageJsonSerialization: + """Test suite for ToolInvokeMessage JSON serialization through safe_json_value""" + + def test_json_message_serialization(self): + """Test JSON message serialization with complex data""" + complex_data = { + "timestamp": datetime(2024, 1, 1, 12, 0, 0, tzinfo=pytz.UTC), + "amount": Decimal("123.45"), + "id": uuid4(), + "binary": b"test data", + "array": np.array([1, 2, 3]), + } + + # Create JSON message + json_message = ToolInvokeMessage.JsonMessage(json_object=complex_data) + message = ToolInvokeMessage(type=ToolInvokeMessage.MessageType.JSON, message=json_message) + + # Apply safe_json_value transformation + transformed_data = safe_json_value(message.message.json_object) + + # Verify transformations + assert isinstance(transformed_data["timestamp"], str) + assert isinstance(transformed_data["amount"], float) + assert isinstance(transformed_data["id"], str) + assert isinstance(transformed_data["binary"], str) + assert isinstance(transformed_data["array"], list) + + # Verify JSON serialization works + json_string = json.dumps(transformed_data, ensure_ascii=False) + assert isinstance(json_string, str) + + # Verify we can deserialize back + deserialized = json.loads(json_string) + assert deserialized["amount"] == 123.45 + assert deserialized["array"] == [1, 2, 3] + + def test_json_message_with_nested_structures(self): + """Test JSON message with deeply nested complex structures""" + nested_data = { + "level1": { + "level2": { + "level3": { + "dates": [date(2024, 1, 1), date(2024, 1, 2)], + "timestamps": [datetime(2024, 1, 1, 12, 0, 0, tzinfo=pytz.UTC)], + "numbers": [Decimal("1.1"), Decimal("2.2")], + "arrays": [np.array([1, 2]), np.array([3, 4])], + } + } + } + } + + json_message = ToolInvokeMessage.JsonMessage(json_object=nested_data) + message = ToolInvokeMessage(type=ToolInvokeMessage.MessageType.JSON, message=json_message) + + # Transform the data + transformed_data = safe_json_value(message.message.json_object) + + # Verify nested transformations + level3 = transformed_data["level1"]["level2"]["level3"] + assert all(isinstance(d, str) for d in level3["dates"]) + assert all(isinstance(t, str) for t in level3["timestamps"]) + assert all(isinstance(n, float) for n in level3["numbers"]) + assert all(isinstance(a, list) for a in level3["arrays"]) + + # Test JSON serialization + json_string = json.dumps(transformed_data, ensure_ascii=False) + assert isinstance(json_string, str) + + # Verify deserialization + deserialized = json.loads(json_string) + assert deserialized["level1"]["level2"]["level3"]["numbers"] == [1.1, 2.2] + + def test_json_message_transformer_integration(self): + """Test integration with ToolFileMessageTransformer for JSON messages""" + complex_data = { + "metadata": { + "created_at": datetime(2024, 1, 1, 12, 0, 0, tzinfo=pytz.UTC), + "version": Decimal("1.0"), + "tags": ["tag1", "tag2"], + }, + "data": {"values": np.array([1.1, 2.2, 3.3]), "binary": b"binary content"}, + } + + # Create message generator + def message_generator(): + json_message = ToolInvokeMessage.JsonMessage(json_object=complex_data) + message = ToolInvokeMessage(type=ToolInvokeMessage.MessageType.JSON, message=json_message) + yield message + + # Transform messages + transformed_messages = list( + ToolFileMessageTransformer.transform_tool_invoke_messages( + message_generator(), user_id="test_user", tenant_id="test_tenant" + ) + ) + + assert len(transformed_messages) == 1 + transformed_message = transformed_messages[0] + assert transformed_message.type == ToolInvokeMessage.MessageType.JSON + + # Verify the JSON object was transformed + json_obj = transformed_message.message.json_object + assert isinstance(json_obj["metadata"]["created_at"], str) + assert isinstance(json_obj["metadata"]["version"], float) + assert isinstance(json_obj["data"]["values"], list) + assert isinstance(json_obj["data"]["binary"], str) + + # Test final JSON serialization + final_json = json.dumps(json_obj, ensure_ascii=False) + assert isinstance(final_json, str) + + # Verify we can deserialize + deserialized = json.loads(final_json) + assert deserialized["metadata"]["version"] == 1.0 + assert deserialized["data"]["values"] == [1.1, 2.2, 3.3] + + def test_edge_cases_and_error_handling(self): + """Test edge cases and error handling in JSON serialization""" + # Test with None values + data_with_none = {"null_value": None, "empty_string": "", "zero": 0, "false_value": False} + + json_message = ToolInvokeMessage.JsonMessage(json_object=data_with_none) + message = ToolInvokeMessage(type=ToolInvokeMessage.MessageType.JSON, message=json_message) + + transformed_data = safe_json_value(message.message.json_object) + json_string = json.dumps(transformed_data, ensure_ascii=False) + + # Verify serialization works with edge cases + assert json_string is not None + deserialized = json.loads(json_string) + assert deserialized["null_value"] is None + assert deserialized["empty_string"] == "" + assert deserialized["zero"] == 0 + assert deserialized["false_value"] is False + + # Test with very large numbers + large_data = { + "large_int": 2**63 - 1, + "large_float": 1.7976931348623157e308, + "small_float": 2.2250738585072014e-308, + } + + json_message = ToolInvokeMessage.JsonMessage(json_object=large_data) + message = ToolInvokeMessage(type=ToolInvokeMessage.MessageType.JSON, message=json_message) + + transformed_data = safe_json_value(message.message.json_object) + json_string = json.dumps(transformed_data, ensure_ascii=False) + + # Verify large numbers are handled correctly + deserialized = json.loads(json_string) + assert deserialized["large_int"] == 2**63 - 1 + assert deserialized["large_float"] == 1.7976931348623157e308 + assert deserialized["small_float"] == 2.2250738585072014e-308 + + +class TestEndToEndSerialization: + """Test suite for end-to-end serialization workflow""" + + def test_complete_workflow_with_real_data(self): + """Test complete workflow from complex data to JSON string and back""" + # Simulate real-world complex data structure + real_world_data = { + "user_profile": { + "id": uuid4(), + "name": "John Doe", + "email": "john@example.com", + "created_at": datetime(2024, 1, 1, 12, 0, 0, tzinfo=pytz.UTC), + "last_login": datetime(2024, 1, 15, 14, 30, 0, tzinfo=pytz.UTC), + "preferences": {"theme": "dark", "language": "en", "timezone": "UTC"}, + }, + "analytics": { + "session_count": 42, + "total_time": Decimal("123.45"), + "metrics": np.array([1.1, 2.2, 3.3, 4.4, 5.5]), + "events": [ + { + "timestamp": datetime(2024, 1, 1, 10, 0, 0, tzinfo=pytz.UTC), + "action": "login", + "duration": Decimal("5.67"), + }, + { + "timestamp": datetime(2024, 1, 1, 11, 0, 0, tzinfo=pytz.UTC), + "action": "logout", + "duration": Decimal("3600.0"), + }, + ], + }, + "files": [ + { + "id": uuid4(), + "name": "document.pdf", + "size": 1024, + "uploaded_at": datetime(2024, 1, 1, 9, 0, 0, tzinfo=pytz.UTC), + "checksum": b"abc123def456", + } + ], + } + + # Step 1: Create ToolInvokeMessage + json_message = ToolInvokeMessage.JsonMessage(json_object=real_world_data) + message = ToolInvokeMessage(type=ToolInvokeMessage.MessageType.JSON, message=json_message) + + # Step 2: Apply safe_json_value transformation + transformed_data = safe_json_value(message.message.json_object) + + # Step 3: Serialize to JSON string + json_string = json.dumps(transformed_data, ensure_ascii=False) + + # Step 4: Verify the string is valid JSON + assert isinstance(json_string, str) + assert json_string.startswith("{") + assert json_string.endswith("}") + + # Step 5: Deserialize back to Python object + deserialized_data = json.loads(json_string) + + # Step 6: Verify data integrity + assert deserialized_data["user_profile"]["name"] == "John Doe" + assert deserialized_data["user_profile"]["email"] == "john@example.com" + assert isinstance(deserialized_data["user_profile"]["created_at"], str) + assert isinstance(deserialized_data["analytics"]["total_time"], float) + assert deserialized_data["analytics"]["total_time"] == 123.45 + assert isinstance(deserialized_data["analytics"]["metrics"], list) + assert deserialized_data["analytics"]["metrics"] == [1.1, 2.2, 3.3, 4.4, 5.5] + assert isinstance(deserialized_data["files"][0]["checksum"], str) + + # Step 7: Verify all complex types were properly converted + self._verify_all_complex_types_converted(deserialized_data) + + def _verify_all_complex_types_converted(self, data): + """Helper method to verify all complex types were properly converted""" + if isinstance(data, dict): + for key, value in data.items(): + if key in ["id", "checksum"]: + # These should be strings (UUID/bytes converted) + assert isinstance(value, str) + elif key in ["created_at", "last_login", "timestamp", "uploaded_at"]: + # These should be strings (datetime converted) + assert isinstance(value, str) + elif key in ["total_time", "duration"]: + # These should be floats (Decimal converted) + assert isinstance(value, float) + elif key == "metrics": + # This should be a list (ndarray converted) + assert isinstance(value, list) + else: + # Recursively check nested structures + self._verify_all_complex_types_converted(value) + elif isinstance(data, list): + for item in data: + self._verify_all_complex_types_converted(item) diff --git a/api/tests/unit_tests/core/tools/utils/test_web_reader_tool.py b/api/tests/unit_tests/core/tools/utils/test_web_reader_tool.py new file mode 100644 index 0000000000..c17308baad --- /dev/null +++ b/api/tests/unit_tests/core/tools/utils/test_web_reader_tool.py @@ -0,0 +1,25 @@ +from core.tools.utils.web_reader_tool import get_image_upload_file_ids + + +def test_get_image_upload_file_ids(): + # should extract id from https + file-preview + content = "![image](https://example.com/a/b/files/abc123/file-preview)" + assert get_image_upload_file_ids(content) == ["abc123"] + + # should extract id from http + image-preview + content = "![image](http://host/files/xyz789/image-preview)" + assert get_image_upload_file_ids(content) == ["xyz789"] + + # should not match invalid scheme 'htt://' + content = "![image](htt://host/files/bad/file-preview)" + assert get_image_upload_file_ids(content) == [] + + # should extract multiple ids in order + content = """ + some text + ![image](https://h/files/id1/file-preview) + middle + ![image](http://h/files/id2/image-preview) + end + """ + assert get_image_upload_file_ids(content) == ["id1", "id2"] diff --git a/api/tests/unit_tests/extensions/test_celery_ssl.py b/api/tests/unit_tests/extensions/test_celery_ssl.py new file mode 100644 index 0000000000..bc46fe8322 --- /dev/null +++ b/api/tests/unit_tests/extensions/test_celery_ssl.py @@ -0,0 +1,149 @@ +"""Tests for Celery SSL configuration.""" + +import ssl +from unittest.mock import MagicMock, patch + + +class TestCelerySSLConfiguration: + """Test suite for Celery SSL configuration.""" + + def test_get_celery_ssl_options_when_ssl_disabled(self): + """Test SSL options when REDIS_USE_SSL is False.""" + mock_config = MagicMock() + mock_config.REDIS_USE_SSL = False + + with patch("extensions.ext_celery.dify_config", mock_config): + from extensions.ext_celery import _get_celery_ssl_options + + result = _get_celery_ssl_options() + assert result is None + + def test_get_celery_ssl_options_when_broker_not_redis(self): + """Test SSL options when broker is not Redis.""" + mock_config = MagicMock() + mock_config.REDIS_USE_SSL = True + mock_config.CELERY_BROKER_URL = "amqp://localhost:5672" + + with patch("extensions.ext_celery.dify_config", mock_config): + from extensions.ext_celery import _get_celery_ssl_options + + result = _get_celery_ssl_options() + assert result is None + + def test_get_celery_ssl_options_with_cert_none(self): + """Test SSL options with CERT_NONE requirement.""" + mock_config = MagicMock() + mock_config.REDIS_USE_SSL = True + mock_config.CELERY_BROKER_URL = "redis://localhost:6379/0" + mock_config.REDIS_SSL_CERT_REQS = "CERT_NONE" + mock_config.REDIS_SSL_CA_CERTS = None + mock_config.REDIS_SSL_CERTFILE = None + mock_config.REDIS_SSL_KEYFILE = None + + with patch("extensions.ext_celery.dify_config", mock_config): + from extensions.ext_celery import _get_celery_ssl_options + + result = _get_celery_ssl_options() + assert result is not None + assert result["ssl_cert_reqs"] == ssl.CERT_NONE + assert result["ssl_ca_certs"] is None + assert result["ssl_certfile"] is None + assert result["ssl_keyfile"] is None + + def test_get_celery_ssl_options_with_cert_required(self): + """Test SSL options with CERT_REQUIRED and certificates.""" + mock_config = MagicMock() + mock_config.REDIS_USE_SSL = True + mock_config.CELERY_BROKER_URL = "rediss://localhost:6380/0" + mock_config.REDIS_SSL_CERT_REQS = "CERT_REQUIRED" + mock_config.REDIS_SSL_CA_CERTS = "/path/to/ca.crt" + mock_config.REDIS_SSL_CERTFILE = "/path/to/client.crt" + mock_config.REDIS_SSL_KEYFILE = "/path/to/client.key" + + with patch("extensions.ext_celery.dify_config", mock_config): + from extensions.ext_celery import _get_celery_ssl_options + + result = _get_celery_ssl_options() + assert result is not None + assert result["ssl_cert_reqs"] == ssl.CERT_REQUIRED + assert result["ssl_ca_certs"] == "/path/to/ca.crt" + assert result["ssl_certfile"] == "/path/to/client.crt" + assert result["ssl_keyfile"] == "/path/to/client.key" + + def test_get_celery_ssl_options_with_cert_optional(self): + """Test SSL options with CERT_OPTIONAL requirement.""" + mock_config = MagicMock() + mock_config.REDIS_USE_SSL = True + mock_config.CELERY_BROKER_URL = "redis://localhost:6379/0" + mock_config.REDIS_SSL_CERT_REQS = "CERT_OPTIONAL" + mock_config.REDIS_SSL_CA_CERTS = "/path/to/ca.crt" + mock_config.REDIS_SSL_CERTFILE = None + mock_config.REDIS_SSL_KEYFILE = None + + with patch("extensions.ext_celery.dify_config", mock_config): + from extensions.ext_celery import _get_celery_ssl_options + + result = _get_celery_ssl_options() + assert result is not None + assert result["ssl_cert_reqs"] == ssl.CERT_OPTIONAL + assert result["ssl_ca_certs"] == "/path/to/ca.crt" + + def test_get_celery_ssl_options_with_invalid_cert_reqs(self): + """Test SSL options with invalid cert requirement defaults to CERT_NONE.""" + mock_config = MagicMock() + mock_config.REDIS_USE_SSL = True + mock_config.CELERY_BROKER_URL = "redis://localhost:6379/0" + mock_config.REDIS_SSL_CERT_REQS = "INVALID_VALUE" + mock_config.REDIS_SSL_CA_CERTS = None + mock_config.REDIS_SSL_CERTFILE = None + mock_config.REDIS_SSL_KEYFILE = None + + with patch("extensions.ext_celery.dify_config", mock_config): + from extensions.ext_celery import _get_celery_ssl_options + + result = _get_celery_ssl_options() + assert result is not None + assert result["ssl_cert_reqs"] == ssl.CERT_NONE # Should default to CERT_NONE + + def test_celery_init_applies_ssl_to_broker_and_backend(self): + """Test that SSL options are applied to both broker and backend when using Redis.""" + mock_config = MagicMock() + mock_config.REDIS_USE_SSL = True + mock_config.CELERY_BROKER_URL = "redis://localhost:6379/0" + mock_config.CELERY_BACKEND = "redis" + mock_config.CELERY_RESULT_BACKEND = "redis://localhost:6379/0" + mock_config.REDIS_SSL_CERT_REQS = "CERT_NONE" + mock_config.REDIS_SSL_CA_CERTS = None + mock_config.REDIS_SSL_CERTFILE = None + mock_config.REDIS_SSL_KEYFILE = None + mock_config.CELERY_USE_SENTINEL = False + mock_config.LOG_FORMAT = "%(message)s" + mock_config.LOG_TZ = "UTC" + mock_config.LOG_FILE = None + + # Mock all the scheduler configs + mock_config.CELERY_BEAT_SCHEDULER_TIME = 1 + mock_config.ENABLE_CLEAN_EMBEDDING_CACHE_TASK = False + mock_config.ENABLE_CLEAN_UNUSED_DATASETS_TASK = False + mock_config.ENABLE_CREATE_TIDB_SERVERLESS_TASK = False + mock_config.ENABLE_UPDATE_TIDB_SERVERLESS_STATUS_TASK = False + mock_config.ENABLE_CLEAN_MESSAGES = False + mock_config.ENABLE_MAIL_CLEAN_DOCUMENT_NOTIFY_TASK = False + mock_config.ENABLE_DATASETS_QUEUE_MONITOR = False + mock_config.ENABLE_CHECK_UPGRADABLE_PLUGIN_TASK = False + + with patch("extensions.ext_celery.dify_config", mock_config): + from dify_app import DifyApp + from extensions.ext_celery import init_app + + app = DifyApp(__name__) + celery_app = init_app(app) + + # Check that SSL options were applied + assert "broker_use_ssl" in celery_app.conf + assert celery_app.conf["broker_use_ssl"] is not None + assert celery_app.conf["broker_use_ssl"]["ssl_cert_reqs"] == ssl.CERT_NONE + + # Check that SSL is also applied to Redis backend + assert "redis_backend_use_ssl" in celery_app.conf + assert celery_app.conf["redis_backend_use_ssl"] is not None diff --git a/api/uv.lock b/api/uv.lock index 870975418f..faf87fa698 100644 --- a/api/uv.lock +++ b/api/uv.lock @@ -1,5 +1,5 @@ version = 1 -revision = 2 +revision = 3 requires-python = ">=3.11, <3.13" resolution-markers = [ "python_full_version >= '3.12.4' and platform_python_implementation != 'PyPy' and sys_platform == 'linux'", @@ -1253,6 +1253,7 @@ dependencies = [ { name = "flask-cors" }, { name = "flask-login" }, { name = "flask-migrate" }, + { name = "flask-orjson" }, { name = "flask-restful" }, { name = "flask-sqlalchemy" }, { name = "gevent" }, @@ -1440,6 +1441,7 @@ requires-dist = [ { name = "flask-cors", specifier = "~=6.0.0" }, { name = "flask-login", specifier = "~=0.6.3" }, { name = "flask-migrate", specifier = "~=4.0.7" }, + { name = "flask-orjson", specifier = "~=2.0.0" }, { name = "flask-restful", specifier = "~=0.3.10" }, { name = "flask-sqlalchemy", specifier = "~=3.1.1" }, { name = "gevent", specifier = "~=24.11.1" }, @@ -1600,7 +1602,7 @@ vdb = [ { name = "pgvector", specifier = "==0.2.5" }, { name = "pymilvus", specifier = "~=2.5.0" }, { name = "pymochow", specifier = "==1.3.1" }, - { name = "pyobvector", specifier = "~=0.1.6" }, + { name = "pyobvector", specifier = "~=0.2.15" }, { name = "qdrant-client", specifier = "==1.9.0" }, { name = "tablestore", specifier = "==6.2.0" }, { name = "tcvectordb", specifier = "~=1.6.4" }, @@ -1859,6 +1861,19 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/93/01/587023575286236f95d2ab8a826c320375ed5ea2102bb103ed89704ffa6b/Flask_Migrate-4.0.7-py3-none-any.whl", hash = "sha256:5c532be17e7b43a223b7500d620edae33795df27c75811ddf32560f7d48ec617", size = 21127, upload-time = "2024-03-11T18:42:59.462Z" }, ] +[[package]] +name = "flask-orjson" +version = "2.0.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "flask" }, + { name = "orjson" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/a3/49/575796f6ddca171d82dbb12762e33166c8b8f8616c946f0a6dfbb9bc3cd6/flask_orjson-2.0.0.tar.gz", hash = "sha256:6df6631437f9bc52cf9821735f896efa5583b5f80712f7d29d9ef69a79986a9c", size = 2974, upload-time = "2024-01-15T00:03:22.236Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/f3/ca/53e14be018a2284acf799830e8cd8e0b263c0fd3dff1ad7b35f8417e7067/flask_orjson-2.0.0-py3-none-any.whl", hash = "sha256:5d15f2ba94b8d6c02aee88fc156045016e83db9eda2c30545fabd640aebaec9d", size = 3622, upload-time = "2024-01-15T00:03:17.511Z" }, +] + [[package]] name = "flask-restful" version = "0.3.10" @@ -4554,17 +4569,19 @@ wheels = [ [[package]] name = "pyobvector" -version = "0.1.14" +version = "0.2.15" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "aiomysql" }, { name = "numpy" }, + { name = "pydantic" }, { name = "pymysql" }, { name = "sqlalchemy" }, + { name = "sqlglot" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/dc/59/7d762061808948dd6aad165a000b34e22163dc83fb5014184eeacc0fabe5/pyobvector-0.1.14.tar.gz", hash = "sha256:4f85cdd63064d040e94c0a96099a0cd5cda18ce625865382e89429f28422fc02", size = 26780, upload-time = "2024-11-20T11:46:18.017Z" } +sdist = { url = "https://files.pythonhosted.org/packages/0b/7d/3f3aac6acf1fdd1782042d6eecd48efaa2ee355af0dbb61e93292d629391/pyobvector-0.2.15.tar.gz", hash = "sha256:5de258c1e952c88b385b5661e130c1cf8262c498c1f8a4a348a35962d379fce4", size = 39611, upload-time = "2025-08-18T02:49:26.683Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/88/68/ecb21b74c974e7be7f9034e205d08db62d614ff5c221581ae96d37ef853e/pyobvector-0.1.14-py3-none-any.whl", hash = "sha256:828e0bec49a177355b70c7a1270af3b0bf5239200ee0d096e4165b267eeff97c", size = 35526, upload-time = "2024-11-20T11:46:16.809Z" }, + { url = "https://files.pythonhosted.org/packages/5f/1f/a62754ba9b8a02c038d2a96cb641b71d3809f34d2ba4f921fecd7840d7fb/pyobvector-0.2.15-py3-none-any.whl", hash = "sha256:feeefe849ee5400e72a9a4d3844e425a58a99053dd02abe06884206923065ebb", size = 52680, upload-time = "2025-08-18T02:49:25.452Z" }, ] [[package]] @@ -5417,6 +5434,15 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/1c/fc/9ba22f01b5cdacc8f5ed0d22304718d2c758fce3fd49a5372b886a86f37c/sqlalchemy-2.0.41-py3-none-any.whl", hash = "sha256:57df5dc6fdb5ed1a88a1ed2195fd31927e705cad62dedd86b46972752a80f576", size = 1911224, upload-time = "2025-05-14T17:39:42.154Z" }, ] +[[package]] +name = "sqlglot" +version = "26.33.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/25/9d/fcd59b4612d5ad1e2257c67c478107f073b19e1097d3bfde2fb517884416/sqlglot-26.33.0.tar.gz", hash = "sha256:2817278779fa51d6def43aa0d70690b93a25c83eb18ec97130fdaf707abc0d73", size = 5353340, upload-time = "2025-07-01T13:09:06.311Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/31/8d/f1d9cb5b18e06aa45689fbeaaea6ebab66d5f01d1e65029a8f7657c06be5/sqlglot-26.33.0-py3-none-any.whl", hash = "sha256:031cee20c0c796a83d26d079a47fdce667604df430598c7eabfa4e4dfd147033", size = 477610, upload-time = "2025-07-01T13:09:03.926Z" }, +] + [[package]] name = "sseclient-py" version = "1.8.0" diff --git a/docker/.env.example b/docker/.env.example index 7a435ad66c..826b7b9fe6 100644 --- a/docker/.env.example +++ b/docker/.env.example @@ -264,6 +264,15 @@ REDIS_PORT=6379 REDIS_USERNAME= REDIS_PASSWORD=difyai123456 REDIS_USE_SSL=false +# SSL configuration for Redis (when REDIS_USE_SSL=true) +REDIS_SSL_CERT_REQS=CERT_NONE +# Options: CERT_NONE, CERT_OPTIONAL, CERT_REQUIRED +REDIS_SSL_CA_CERTS= +# Path to CA certificate file for SSL verification +REDIS_SSL_CERTFILE= +# Path to client certificate file for SSL authentication +REDIS_SSL_KEYFILE= +# Path to client private key file for SSL authentication REDIS_DB=0 # Whether to use Redis Sentinel mode. @@ -861,7 +870,7 @@ WORKFLOW_NODE_EXECUTION_STORAGE=rdbms # Repository configuration # Core workflow execution repository implementation -# Options: +# Options: # - core.repositories.sqlalchemy_workflow_execution_repository.SQLAlchemyWorkflowExecutionRepository (default) # - core.repositories.celery_workflow_execution_repository.CeleryWorkflowExecutionRepository CORE_WORKFLOW_EXECUTION_REPOSITORY=core.repositories.sqlalchemy_workflow_execution_repository.SQLAlchemyWorkflowExecutionRepository @@ -878,6 +887,14 @@ API_WORKFLOW_RUN_REPOSITORY=repositories.sqlalchemy_api_workflow_run_repository. # API workflow node execution repository implementation API_WORKFLOW_NODE_EXECUTION_REPOSITORY=repositories.sqlalchemy_api_workflow_node_execution_repository.DifyAPISQLAlchemyWorkflowNodeExecutionRepository +# Workflow log cleanup configuration +# Enable automatic cleanup of workflow run logs to manage database size +WORKFLOW_LOG_CLEANUP_ENABLED=false +# Number of days to retain workflow run logs (default: 30 days) +WORKFLOW_LOG_RETENTION_DAYS=30 +# Batch size for workflow log cleanup operations (default: 100) +WORKFLOW_LOG_CLEANUP_BATCH_SIZE=100 + # HTTP request node in workflow configuration HTTP_REQUEST_NODE_MAX_BINARY_SIZE=10485760 HTTP_REQUEST_NODE_MAX_TEXT_SIZE=1048576 @@ -1157,6 +1174,9 @@ MARKETPLACE_API_URL=https://marketplace.dify.ai FORCE_VERIFYING_SIGNATURE=true +PLUGIN_STDIO_BUFFER_SIZE=1024 +PLUGIN_STDIO_MAX_BUFFER_SIZE=5242880 + PLUGIN_PYTHON_ENV_INIT_TIMEOUT=120 PLUGIN_MAX_EXECUTION_TIMEOUT=600 # PIP_MIRROR_URL=https://pypi.tuna.tsinghua.edu.cn/simple diff --git a/docker/README.md b/docker/README.md index 22dfe2c91c..b5c46eb9fc 100644 --- a/docker/README.md +++ b/docker/README.md @@ -4,7 +4,7 @@ Welcome to the new `docker` directory for deploying Dify using Docker Compose. T ### What's Updated -- **Certbot Container**: `docker-compose.yaml` now contains `certbot` for managing SSL certificates. This container automatically renews certificates and ensures secure HTTPS connections. +- **Certbot Container**: `docker-compose.yaml` now contains `certbot` for managing SSL certificates. This container automatically renews certificates and ensures secure HTTPS connections.\ For more information, refer `docker/certbot/README.md`. - **Persistent Environment Variables**: Environment variables are now managed through a `.env` file, ensuring that your configurations persist across deployments. @@ -13,43 +13,44 @@ Welcome to the new `docker` directory for deploying Dify using Docker Compose. T > The `.env` file is a crucial component in Docker and Docker Compose environments, serving as a centralized configuration file where you can define environment variables that are accessible to the containers at runtime. This file simplifies the management of environment settings across different stages of development, testing, and production, providing consistency and ease of configuration to deployments. - **Unified Vector Database Services**: All vector database services are now managed from a single Docker Compose file `docker-compose.yaml`. You can switch between different vector databases by setting the `VECTOR_STORE` environment variable in your `.env` file. + - **Mandatory .env File**: A `.env` file is now required to run `docker compose up`. This file is crucial for configuring your deployment and for any custom settings to persist through upgrades. ### How to Deploy Dify with `docker-compose.yaml` 1. **Prerequisites**: Ensure Docker and Docker Compose are installed on your system. -2. **Environment Setup**: - - Navigate to the `docker` directory. - - Copy the `.env.example` file to a new file named `.env` by running `cp .env.example .env`. - - Customize the `.env` file as needed. Refer to the `.env.example` file for detailed configuration options. -3. **Running the Services**: - - Execute `docker compose up` from the `docker` directory to start the services. - - To specify a vector database, set the `VECTOR_STORE` variable in your `.env` file to your desired vector database service, such as `milvus`, `weaviate`, or `opensearch`. -4. **SSL Certificate Setup**: - - Refer `docker/certbot/README.md` to set up SSL certificates using Certbot. -5. **OpenTelemetry Collector Setup**: +1. **Environment Setup**: + - Navigate to the `docker` directory. + - Copy the `.env.example` file to a new file named `.env` by running `cp .env.example .env`. + - Customize the `.env` file as needed. Refer to the `.env.example` file for detailed configuration options. +1. **Running the Services**: + - Execute `docker compose up` from the `docker` directory to start the services. + - To specify a vector database, set the `VECTOR_STORE` variable in your `.env` file to your desired vector database service, such as `milvus`, `weaviate`, or `opensearch`. +1. **SSL Certificate Setup**: + - Refer `docker/certbot/README.md` to set up SSL certificates using Certbot. +1. **OpenTelemetry Collector Setup**: - Change `ENABLE_OTEL` to `true` in `.env`. - Configure `OTLP_BASE_ENDPOINT` properly. ### How to Deploy Middleware for Developing Dify 1. **Middleware Setup**: - - Use the `docker-compose.middleware.yaml` for setting up essential middleware services like databases and caches. - - Navigate to the `docker` directory. - - Ensure the `middleware.env` file is created by running `cp middleware.env.example middleware.env` (refer to the `middleware.env.example` file). -2. **Running Middleware Services**: - - Navigate to the `docker` directory. - - Execute `docker compose -f docker-compose.middleware.yaml --profile weaviate -p dify up -d` to start the middleware services. (Change the profile to other vector database if you are not using weaviate) + - Use the `docker-compose.middleware.yaml` for setting up essential middleware services like databases and caches. + - Navigate to the `docker` directory. + - Ensure the `middleware.env` file is created by running `cp middleware.env.example middleware.env` (refer to the `middleware.env.example` file). +1. **Running Middleware Services**: + - Navigate to the `docker` directory. + - Execute `docker compose -f docker-compose.middleware.yaml --profile weaviate -p dify up -d` to start the middleware services. (Change the profile to other vector database if you are not using weaviate) ### Migration for Existing Users For users migrating from the `docker-legacy` setup: 1. **Review Changes**: Familiarize yourself with the new `.env` configuration and Docker Compose setup. -2. **Transfer Customizations**: - - If you have customized configurations such as `docker-compose.yaml`, `ssrf_proxy/squid.conf`, or `nginx/conf.d/default.conf`, you will need to reflect these changes in the `.env` file you create. -3. **Data Migration**: - - Ensure that data from services like databases and caches is backed up and migrated appropriately to the new structure if necessary. +1. **Transfer Customizations**: + - If you have customized configurations such as `docker-compose.yaml`, `ssrf_proxy/squid.conf`, or `nginx/conf.d/default.conf`, you will need to reflect these changes in the `.env` file you create. +1. **Data Migration**: + - Ensure that data from services like databases and caches is backed up and migrated appropriately to the new structure if necessary. ### Overview of `.env` @@ -64,39 +65,49 @@ For users migrating from the `docker-legacy` setup: The `.env.example` file provided in the Docker setup is extensive and covers a wide range of configuration options. It is structured into several sections, each pertaining to different aspects of the application and its services. Here are some of the key sections and variables: 1. **Common Variables**: - - `CONSOLE_API_URL`, `SERVICE_API_URL`: URLs for different API services. - - `APP_WEB_URL`: Frontend application URL. - - `FILES_URL`: Base URL for file downloads and previews. -2. **Server Configuration**: - - `LOG_LEVEL`, `DEBUG`, `FLASK_DEBUG`: Logging and debug settings. - - `SECRET_KEY`: A key for encrypting session cookies and other sensitive data. + - `CONSOLE_API_URL`, `SERVICE_API_URL`: URLs for different API services. + - `APP_WEB_URL`: Frontend application URL. + - `FILES_URL`: Base URL for file downloads and previews. -3. **Database Configuration**: - - `DB_USERNAME`, `DB_PASSWORD`, `DB_HOST`, `DB_PORT`, `DB_DATABASE`: PostgreSQL database credentials and connection details. +1. **Server Configuration**: -4. **Redis Configuration**: - - `REDIS_HOST`, `REDIS_PORT`, `REDIS_PASSWORD`: Redis server connection settings. + - `LOG_LEVEL`, `DEBUG`, `FLASK_DEBUG`: Logging and debug settings. + - `SECRET_KEY`: A key for encrypting session cookies and other sensitive data. -5. **Celery Configuration**: - - `CELERY_BROKER_URL`: Configuration for Celery message broker. +1. **Database Configuration**: -6. **Storage Configuration**: - - `STORAGE_TYPE`, `S3_BUCKET_NAME`, `AZURE_BLOB_ACCOUNT_NAME`: Settings for file storage options like local, S3, Azure Blob, etc. + - `DB_USERNAME`, `DB_PASSWORD`, `DB_HOST`, `DB_PORT`, `DB_DATABASE`: PostgreSQL database credentials and connection details. -7. **Vector Database Configuration**: - - `VECTOR_STORE`: Type of vector database (e.g., `weaviate`, `milvus`). - - Specific settings for each vector store like `WEAVIATE_ENDPOINT`, `MILVUS_URI`. +1. **Redis Configuration**: -8. **CORS Configuration**: - - `WEB_API_CORS_ALLOW_ORIGINS`, `CONSOLE_CORS_ALLOW_ORIGINS`: Settings for cross-origin resource sharing. + - `REDIS_HOST`, `REDIS_PORT`, `REDIS_PASSWORD`: Redis server connection settings. -9. **OpenTelemetry Configuration**: - - `ENABLE_OTEL`: Enable OpenTelemetry collector in api. - - `OTLP_BASE_ENDPOINT`: Endpoint for your OTLP exporter. - -10. **Other Service-Specific Environment Variables**: - - Each service like `nginx`, `redis`, `db`, and vector databases have specific environment variables that are directly referenced in the `docker-compose.yaml`. +1. **Celery Configuration**: + + - `CELERY_BROKER_URL`: Configuration for Celery message broker. + +1. **Storage Configuration**: + + - `STORAGE_TYPE`, `S3_BUCKET_NAME`, `AZURE_BLOB_ACCOUNT_NAME`: Settings for file storage options like local, S3, Azure Blob, etc. + +1. **Vector Database Configuration**: + + - `VECTOR_STORE`: Type of vector database (e.g., `weaviate`, `milvus`). + - Specific settings for each vector store like `WEAVIATE_ENDPOINT`, `MILVUS_URI`. + +1. **CORS Configuration**: + + - `WEB_API_CORS_ALLOW_ORIGINS`, `CONSOLE_CORS_ALLOW_ORIGINS`: Settings for cross-origin resource sharing. + +1. **OpenTelemetry Configuration**: + + - `ENABLE_OTEL`: Enable OpenTelemetry collector in api. + - `OTLP_BASE_ENDPOINT`: Endpoint for your OTLP exporter. + +1. **Other Service-Specific Environment Variables**: + + - Each service like `nginx`, `redis`, `db`, and vector databases have specific environment variables that are directly referenced in the `docker-compose.yaml`. ### Additional Information diff --git a/docker/certbot/README.md b/docker/certbot/README.md index 21be34b33a..62b1eee395 100644 --- a/docker/certbot/README.md +++ b/docker/certbot/README.md @@ -2,12 +2,12 @@ ## Short description -docker compose certbot configurations with Backward compatibility (without certbot container). +docker compose certbot configurations with Backward compatibility (without certbot container).\ Use `docker compose --profile certbot up` to use this features. ## The simplest way for launching new servers with SSL certificates -1. Get letsencrypt certs +1. Get letsencrypt certs\ set `.env` values ```properties NGINX_SSL_CERT_FILENAME=fullchain.pem @@ -25,7 +25,7 @@ Use `docker compose --profile certbot up` to use this features. ```shell docker compose exec -it certbot /bin/sh /update-cert.sh ``` -2. Edit `.env` file and `docker compose --profile certbot up` again. +1. Edit `.env` file and `docker compose --profile certbot up` again.\ set `.env` value additionally ```properties NGINX_HTTPS_ENABLED=true @@ -34,7 +34,7 @@ Use `docker compose --profile certbot up` to use this features. ```shell docker compose --profile certbot up -d --no-deps --force-recreate nginx ``` - Then you can access your serve with HTTPS. + Then you can access your serve with HTTPS.\ [https://your_domain.com](https://your_domain.com) ## SSL certificates renewal diff --git a/docker/docker-compose-template.yaml b/docker/docker-compose-template.yaml index 1dbd9b3993..04981f6b7f 100644 --- a/docker/docker-compose-template.yaml +++ b/docker/docker-compose-template.yaml @@ -181,6 +181,8 @@ services: FORCE_VERIFYING_SIGNATURE: ${FORCE_VERIFYING_SIGNATURE:-true} PYTHON_ENV_INIT_TIMEOUT: ${PLUGIN_PYTHON_ENV_INIT_TIMEOUT:-120} PLUGIN_MAX_EXECUTION_TIMEOUT: ${PLUGIN_MAX_EXECUTION_TIMEOUT:-600} + PLUGIN_STDIO_BUFFER_SIZE: ${PLUGIN_STDIO_BUFFER_SIZE:-1024} + PLUGIN_STDIO_MAX_BUFFER_SIZE: ${PLUGIN_STDIO_MAX_BUFFER_SIZE:-5242880} PIP_MIRROR_URL: ${PIP_MIRROR_URL:-} PLUGIN_STORAGE_TYPE: ${PLUGIN_STORAGE_TYPE:-local} PLUGIN_STORAGE_LOCAL_ROOT: ${PLUGIN_STORAGE_LOCAL_ROOT:-/app/storage} diff --git a/docker/docker-compose.yaml b/docker/docker-compose.yaml index 101f8eb323..0c352e4658 100644 --- a/docker/docker-compose.yaml +++ b/docker/docker-compose.yaml @@ -71,6 +71,10 @@ x-shared-env: &shared-api-worker-env REDIS_USERNAME: ${REDIS_USERNAME:-} REDIS_PASSWORD: ${REDIS_PASSWORD:-difyai123456} REDIS_USE_SSL: ${REDIS_USE_SSL:-false} + REDIS_SSL_CERT_REQS: ${REDIS_SSL_CERT_REQS:-CERT_NONE} + REDIS_SSL_CA_CERTS: ${REDIS_SSL_CA_CERTS:-} + REDIS_SSL_CERTFILE: ${REDIS_SSL_CERTFILE:-} + REDIS_SSL_KEYFILE: ${REDIS_SSL_KEYFILE:-} REDIS_DB: ${REDIS_DB:-0} REDIS_USE_SENTINEL: ${REDIS_USE_SENTINEL:-false} REDIS_SENTINELS: ${REDIS_SENTINELS:-} @@ -392,6 +396,9 @@ x-shared-env: &shared-api-worker-env CORE_WORKFLOW_NODE_EXECUTION_REPOSITORY: ${CORE_WORKFLOW_NODE_EXECUTION_REPOSITORY:-core.repositories.sqlalchemy_workflow_node_execution_repository.SQLAlchemyWorkflowNodeExecutionRepository} API_WORKFLOW_RUN_REPOSITORY: ${API_WORKFLOW_RUN_REPOSITORY:-repositories.sqlalchemy_api_workflow_run_repository.DifyAPISQLAlchemyWorkflowRunRepository} API_WORKFLOW_NODE_EXECUTION_REPOSITORY: ${API_WORKFLOW_NODE_EXECUTION_REPOSITORY:-repositories.sqlalchemy_api_workflow_node_execution_repository.DifyAPISQLAlchemyWorkflowNodeExecutionRepository} + WORKFLOW_LOG_CLEANUP_ENABLED: ${WORKFLOW_LOG_CLEANUP_ENABLED:-false} + WORKFLOW_LOG_RETENTION_DAYS: ${WORKFLOW_LOG_RETENTION_DAYS:-30} + WORKFLOW_LOG_CLEANUP_BATCH_SIZE: ${WORKFLOW_LOG_CLEANUP_BATCH_SIZE:-100} HTTP_REQUEST_NODE_MAX_BINARY_SIZE: ${HTTP_REQUEST_NODE_MAX_BINARY_SIZE:-10485760} HTTP_REQUEST_NODE_MAX_TEXT_SIZE: ${HTTP_REQUEST_NODE_MAX_TEXT_SIZE:-1048576} HTTP_REQUEST_NODE_SSL_VERIFY: ${HTTP_REQUEST_NODE_SSL_VERIFY:-True} @@ -506,6 +513,8 @@ x-shared-env: &shared-api-worker-env MARKETPLACE_ENABLED: ${MARKETPLACE_ENABLED:-true} MARKETPLACE_API_URL: ${MARKETPLACE_API_URL:-https://marketplace.dify.ai} FORCE_VERIFYING_SIGNATURE: ${FORCE_VERIFYING_SIGNATURE:-true} + PLUGIN_STDIO_BUFFER_SIZE: ${PLUGIN_STDIO_BUFFER_SIZE:-1024} + PLUGIN_STDIO_MAX_BUFFER_SIZE: ${PLUGIN_STDIO_MAX_BUFFER_SIZE:-5242880} PLUGIN_PYTHON_ENV_INIT_TIMEOUT: ${PLUGIN_PYTHON_ENV_INIT_TIMEOUT:-120} PLUGIN_MAX_EXECUTION_TIMEOUT: ${PLUGIN_MAX_EXECUTION_TIMEOUT:-600} PIP_MIRROR_URL: ${PIP_MIRROR_URL:-} @@ -747,6 +756,8 @@ services: FORCE_VERIFYING_SIGNATURE: ${FORCE_VERIFYING_SIGNATURE:-true} PYTHON_ENV_INIT_TIMEOUT: ${PLUGIN_PYTHON_ENV_INIT_TIMEOUT:-120} PLUGIN_MAX_EXECUTION_TIMEOUT: ${PLUGIN_MAX_EXECUTION_TIMEOUT:-600} + PLUGIN_STDIO_BUFFER_SIZE: ${PLUGIN_STDIO_BUFFER_SIZE:-1024} + PLUGIN_STDIO_MAX_BUFFER_SIZE: ${PLUGIN_STDIO_MAX_BUFFER_SIZE:-5242880} PIP_MIRROR_URL: ${PIP_MIRROR_URL:-} PLUGIN_STORAGE_TYPE: ${PLUGIN_STORAGE_TYPE:-local} PLUGIN_STORAGE_LOCAL_ROOT: ${PLUGIN_STORAGE_LOCAL_ROOT:-/app/storage} diff --git a/sdks/nodejs-client/README.md b/sdks/nodejs-client/README.md index 37b5ca2d0a..3a5688bcbe 100644 --- a/sdks/nodejs-client/README.md +++ b/sdks/nodejs-client/README.md @@ -1,12 +1,15 @@ # Dify Node.js SDK + This is the Node.js SDK for the Dify API, which allows you to easily integrate Dify into your Node.js applications. ## Install + ```bash npm install dify-client ``` ## Usage + After installing the SDK, you can use it in your project like this: ```js @@ -60,4 +63,5 @@ client.messageFeedback(messageId, rating, user) Replace 'your-api-key-here' with your actual Dify API key.Replace 'your-app-id-here' with your actual Dify APP ID. ## License + This SDK is released under the MIT License. diff --git a/sdks/php-client/README.md b/sdks/php-client/README.md index 91e77ad9ff..444b16a565 100644 --- a/sdks/php-client/README.md +++ b/sdks/php-client/README.md @@ -11,7 +11,7 @@ This is the PHP SDK for the Dify API, which allows you to easily integrate Dify If you want to try the example, you can run `composer install` in this directory. -In exist project, copy the `dify-client.php` to you project, and merge the following to your `composer.json` file, then run `composer install && composer dump-autoload` to install. Guzzle does not require 7.9, other versions have not been tested, but you can try. +In exist project, copy the `dify-client.php` to you project, and merge the following to your `composer.json` file, then run `composer install && composer dump-autoload` to install. Guzzle does not require 7.9, other versions have not been tested, but you can try. ```json { diff --git a/sdks/python-client/README.md b/sdks/python-client/README.md index 7401fd2fd4..34b14b3a94 100644 --- a/sdks/python-client/README.md +++ b/sdks/python-client/README.md @@ -141,8 +141,6 @@ with open(file_path, "rb") as file: result = response.json() print(f'upload_file_id: {result.get("id")}') ``` - - - Others @@ -184,7 +182,8 @@ print('[rename result]') print(rename_conversation_response.json()) ``` -* Using the Workflow Client +- Using the Workflow Client + ```python import json import requests diff --git a/web/Dockerfile b/web/Dockerfile index d59039528c..d284efca87 100644 --- a/web/Dockerfile +++ b/web/Dockerfile @@ -6,7 +6,7 @@ LABEL maintainer="takatost@gmail.com" # RUN sed -i 's/dl-cdn.alpinelinux.org/mirrors.aliyun.com/g' /etc/apk/repositories RUN apk add --no-cache tzdata -RUN npm install -g pnpm@10.13.1 +RUN corepack enable ENV PNPM_HOME="/pnpm" ENV PATH="$PNPM_HOME:$PATH" @@ -19,6 +19,9 @@ WORKDIR /app/web COPY package.json . COPY pnpm-lock.yaml . +# Use packageManager from package.json +RUN corepack install + # if you located in China, you can use taobao registry to speed up # RUN pnpm install --frozen-lockfile --registry https://registry.npmmirror.com/ diff --git a/web/README.md b/web/README.md index 3d9fd2de87..a47cfab041 100644 --- a/web/README.md +++ b/web/README.md @@ -7,6 +7,7 @@ This is a [Next.js](https://nextjs.org/) project bootstrapped with [`create-next ### Run by source code Before starting the web frontend service, please make sure the following environment is ready. + - [Node.js](https://nodejs.org) >= v22.11.x - [pnpm](https://pnpm.io) v10.x @@ -103,11 +104,9 @@ pnpm run test ``` If you are not familiar with writing tests, here is some code to refer to: -* [classnames.spec.ts](./utils/classnames.spec.ts) -* [index.spec.tsx](./app/components/base/button/index.spec.tsx) - - +- [classnames.spec.ts](./utils/classnames.spec.ts) +- [index.spec.tsx](./app/components/base/button/index.spec.tsx) ## Documentation diff --git a/web/app/(commonLayout)/datasets/dataset-card.tsx b/web/app/(commonLayout)/datasets/dataset-card.tsx index 2f0563d47e..3e913ca52f 100644 --- a/web/app/(commonLayout)/datasets/dataset-card.tsx +++ b/web/app/(commonLayout)/datasets/dataset-card.tsx @@ -216,8 +216,8 @@ const DatasetCard = ({ } btnClassName={open => cn( - open ? '!bg-black/5 !shadow-none' : '!bg-transparent', - 'h-8 w-8 rounded-md border-none !p-2 hover:!bg-black/5', + open ? '!bg-state-base-hover !shadow-none' : '!bg-transparent', + 'h-8 w-8 rounded-md border-none !p-2 hover:!bg-state-base-hover', ) } className={'!z-20 h-fit !w-[128px]'} diff --git a/web/app/(commonLayout)/education-apply/page.tsx b/web/app/(commonLayout)/education-apply/page.tsx index 873034452e..5dd3c35519 100644 --- a/web/app/(commonLayout)/education-apply/page.tsx +++ b/web/app/(commonLayout)/education-apply/page.tsx @@ -13,12 +13,12 @@ import { useProviderContext } from '@/context/provider-context' export default function EducationApply() { const router = useRouter() - const { enableEducationPlan, isEducationAccount } = useProviderContext() + const { enableEducationPlan } = useProviderContext() const searchParams = useSearchParams() const token = searchParams.get('token') const showEducationApplyPage = useMemo(() => { - return enableEducationPlan && !isEducationAccount && token - }, [enableEducationPlan, isEducationAccount, token]) + return enableEducationPlan && token + }, [enableEducationPlan, token]) useEffect(() => { if (!showEducationApplyPage) diff --git a/web/app/account/account-page/AvatarWithEdit.tsx b/web/app/account/account-page/AvatarWithEdit.tsx index 41a6971bf5..88e3a7b343 100644 --- a/web/app/account/account-page/AvatarWithEdit.tsx +++ b/web/app/account/account-page/AvatarWithEdit.tsx @@ -4,7 +4,7 @@ import type { Area } from 'react-easy-crop' import React, { useCallback, useState } from 'react' import { useTranslation } from 'react-i18next' import { useContext } from 'use-context-selector' -import { RiPencilLine } from '@remixicon/react' +import { RiDeleteBin5Line, RiPencilLine } from '@remixicon/react' import { updateUserProfile } from '@/service/common' import { ToastContext } from '@/app/components/base/toast' import ImageInput, { type OnImageInput } from '@/app/components/base/app-icon-picker/ImageInput' @@ -27,6 +27,8 @@ const AvatarWithEdit = ({ onSave, ...props }: AvatarWithEditProps) => { const [inputImageInfo, setInputImageInfo] = useState() const [isShowAvatarPicker, setIsShowAvatarPicker] = useState(false) const [uploading, setUploading] = useState(false) + const [isShowDeleteConfirm, setIsShowDeleteConfirm] = useState(false) + const [hoverArea, setHoverArea] = useState('left') const handleImageInput: OnImageInput = useCallback(async (isCropped: boolean, fileOrTempUrl: string | File, croppedAreaPixels?: Area, fileName?: string) => { setInputImageInfo( @@ -48,6 +50,18 @@ const AvatarWithEdit = ({ onSave, ...props }: AvatarWithEditProps) => { } }, [notify, onSave, t]) + const handleDeleteAvatar = useCallback(async () => { + try { + await updateUserProfile({ url: 'account/avatar', body: { avatar: '' } }) + notify({ type: 'success', message: t('common.actionMsg.modifiedSuccessfully') }) + setIsShowDeleteConfirm(false) + onSave?.() + } + catch (e) { + notify({ type: 'error', message: (e as Error).message }) + } + }, [notify, onSave, t]) + const { handleLocalFileUpload } = useLocalFileUploader({ limit: 3, disabled: false, @@ -86,12 +100,21 @@ const AvatarWithEdit = ({ onSave, ...props }: AvatarWithEditProps) => {
{ setIsShowAvatarPicker(true) }} className="absolute inset-0 flex cursor-pointer items-center justify-center rounded-full bg-black/50 opacity-0 transition-opacity group-hover:opacity-100" + onClick={() => hoverArea === 'right' ? setIsShowDeleteConfirm(true) : setIsShowAvatarPicker(true)} + onMouseMove={(e) => { + const rect = e.currentTarget.getBoundingClientRect() + const x = e.clientX - rect.left + const isRight = x > rect.width / 2 + setHoverArea(isRight ? 'right' : 'left') + }} > - + {hoverArea === 'right' ? + + : - + } +
@@ -115,6 +138,26 @@ const AvatarWithEdit = ({ onSave, ...props }: AvatarWithEditProps) => { + + setIsShowDeleteConfirm(false)} + > +
{t('common.avatar.deleteTitle')}
+

{t('common.avatar.deleteDescription')}

+ +
+ + + +
+ ) } diff --git a/web/app/components/app/configuration/config-prompt/simple-prompt-input.tsx b/web/app/components/app/configuration/config-prompt/simple-prompt-input.tsx index eb0f524386..a7bdc550d1 100644 --- a/web/app/components/app/configuration/config-prompt/simple-prompt-input.tsx +++ b/web/app/components/app/configuration/config-prompt/simple-prompt-input.tsx @@ -13,7 +13,7 @@ import Tooltip from '@/app/components/base/tooltip' import { AppType } from '@/types/app' import { getNewVar, getVars } from '@/utils/var' import AutomaticBtn from '@/app/components/app/configuration/config/automatic/automatic-btn' -import type { AutomaticRes } from '@/service/debug' +import type { GenRes } from '@/service/debug' import GetAutomaticResModal from '@/app/components/app/configuration/config/automatic/get-automatic-res' import PromptEditor from '@/app/components/base/prompt-editor' import ConfigContext from '@/context/debug-configuration' @@ -61,6 +61,7 @@ const Prompt: FC = ({ const { eventEmitter } = useEventEmitterContextContext() const { + appId, modelConfig, dataSets, setModelConfig, @@ -139,21 +140,21 @@ const Prompt: FC = ({ } const [showAutomatic, { setTrue: showAutomaticTrue, setFalse: showAutomaticFalse }] = useBoolean(false) - const handleAutomaticRes = (res: AutomaticRes) => { + const handleAutomaticRes = (res: GenRes) => { // put eventEmitter in first place to prevent overwrite the configs.prompt_variables.But another problem is that prompt won't hight the prompt_variables. eventEmitter?.emit({ type: PROMPT_EDITOR_UPDATE_VALUE_BY_EVENT_EMITTER, - payload: res.prompt, + payload: res.modified, } as any) const newModelConfig = produce(modelConfig, (draft) => { - draft.configs.prompt_template = res.prompt - draft.configs.prompt_variables = res.variables.map(key => ({ key, name: key, type: 'string', required: true })) + draft.configs.prompt_template = res.modified + draft.configs.prompt_variables = (res.variables || []).map(key => ({ key, name: key, type: 'string', required: true })) }) setModelConfig(newModelConfig) setPrevPromptConfig(modelConfig.configs) if (mode !== AppType.completion) { - setIntroduction(res.opening_statement) + setIntroduction(res.opening_statement || '') const newFeatures = produce(features, (draft) => { draft.opening = { ...draft.opening, @@ -272,10 +273,13 @@ const Prompt: FC = ({ {showAutomatic && ( )} diff --git a/web/app/components/app/configuration/config/automatic/get-automatic-res.tsx b/web/app/components/app/configuration/config/automatic/get-automatic-res.tsx index aacaa81ac2..31f81d274d 100644 --- a/web/app/components/app/configuration/config/automatic/get-automatic-res.tsx +++ b/web/app/components/app/configuration/config/automatic/get-automatic-res.tsx @@ -2,7 +2,7 @@ import type { FC } from 'react' import React, { useCallback, useEffect, useState } from 'react' import { useTranslation } from 'react-i18next' -import { useBoolean } from 'ahooks' +import { useBoolean, useSessionStorageState } from 'ahooks' import { RiDatabase2Line, RiFileExcel2Line, @@ -14,24 +14,18 @@ import { RiTranslate, RiUser2Line, } from '@remixicon/react' -import cn from 'classnames' import s from './style.module.css' import Modal from '@/app/components/base/modal' import Button from '@/app/components/base/button' -import Textarea from '@/app/components/base/textarea' import Toast from '@/app/components/base/toast' -import { generateRule } from '@/service/debug' -import ConfigPrompt from '@/app/components/app/configuration/config-prompt' +import { generateBasicAppFistTimeRule, generateRule } from '@/service/debug' import type { CompletionParams, Model } from '@/types/app' -import { AppType } from '@/types/app' -import ConfigVar from '@/app/components/app/configuration/config-var' -import GroupName from '@/app/components/app/configuration/base/group-name' +import type { AppType } from '@/types/app' import Loading from '@/app/components/base/loading' import Confirm from '@/app/components/base/confirm' -import { LoveMessage } from '@/app/components/base/icons/src/vender/features' // type -import type { AutomaticRes } from '@/service/debug' +import type { GenRes } from '@/service/debug' import { Generator } from '@/app/components/base/icons/src/vender/other' import ModelParameterModal from '@/app/components/header/account-setting/model-provider-page/model-parameter-modal' @@ -39,13 +33,25 @@ import { ModelTypeEnum } from '@/app/components/header/account-setting/model-pro import { useModelListAndDefaultModelAndCurrentProviderAndModel } from '@/app/components/header/account-setting/model-provider-page/hooks' import type { ModelModeType } from '@/types/app' import type { FormValue } from '@/app/components/header/account-setting/model-provider-page/declarations' +import InstructionEditorInWorkflow from './instruction-editor-in-workflow' +import InstructionEditorInBasic from './instruction-editor' +import { GeneratorType } from './types' +import Result from './result' +import useGenData from './use-gen-data' +import IdeaOutput from './idea-output' +import ResPlaceholder from './res-placeholder' +import { useGenerateRuleTemplate } from '@/service/use-apps' +const i18nPrefix = 'appDebug.generate' export type IGetAutomaticResProps = { mode: AppType isShow: boolean onClose: () => void - onFinished: (res: AutomaticRes) => void - isInLLMNode?: boolean + onFinished: (res: GenRes) => void + flowId?: string + nodeId?: string + currentPrompt?: string + isBasicMode?: boolean } const TryLabel: FC<{ @@ -68,7 +74,10 @@ const GetAutomaticRes: FC = ({ mode, isShow, onClose, - isInLLMNode, + flowId, + nodeId, + currentPrompt, + isBasicMode, onFinished, }) => { const { t } = useTranslation() @@ -123,13 +132,27 @@ const GetAutomaticRes: FC = ({ }, ] - const [instruction, setInstruction] = useState('') + const [instructionFromSessionStorage, setInstruction] = useSessionStorageState(`improve-instruction-${flowId}${isBasicMode ? '' : `-${nodeId}`}`) + const instruction = instructionFromSessionStorage || '' + const [ideaOutput, setIdeaOutput] = useState('') + + const [editorKey, setEditorKey] = useState(`${flowId}-0`) const handleChooseTemplate = useCallback((key: string) => { return () => { const template = t(`appDebug.generate.template.${key}.instruction`) setInstruction(template) + setEditorKey(`${flowId}-${Date.now()}`) } }, [t]) + + const { data: instructionTemplate } = useGenerateRuleTemplate(GeneratorType.prompt, isBasicMode) + useEffect(() => { + if (!instruction && instructionTemplate) + setInstruction(instructionTemplate.data) + + setEditorKey(`${flowId}-${Date.now()}`) + }, [instructionTemplate]) + const isValid = () => { if (instruction.trim() === '') { Toast.notify({ @@ -143,7 +166,10 @@ const GetAutomaticRes: FC = ({ return true } const [isLoading, { setTrue: setLoadingTrue, setFalse: setLoadingFalse }] = useBoolean(false) - const [res, setRes] = useState(null) + const storageKey = `${flowId}${isBasicMode ? '' : `-${nodeId}`}` + const { addVersion, current, currentVersionIndex, setCurrentVersionIndex, versions } = useGenData({ + storageKey, + }) useEffect(() => { if (defaultModel) { @@ -170,16 +196,6 @@ const GetAutomaticRes: FC = ({ ) - const renderNoData = ( -
- -
-
{t('appDebug.generate.noDataLine1')}
-
{t('appDebug.generate.noDataLine2')}
-
-
- ) - const handleModelChange = useCallback((newValue: { modelId: string; provider: string; mode?: string; features?: string[] }) => { const newModel = { ...model, @@ -207,28 +223,59 @@ const GetAutomaticRes: FC = ({ return setLoadingTrue() try { - const { error, ...res } = await generateRule({ - instruction, - model_config: model, - no_variable: !!isInLLMNode, - }) - setRes(res) - if (error) { - Toast.notify({ - type: 'error', - message: error, + let apiRes: GenRes + let hasError = false + if (isBasicMode || !currentPrompt) { + const { error, ...res } = await generateBasicAppFistTimeRule({ + instruction, + model_config: model, + no_variable: false, }) + apiRes = { + ...res, + modified: res.prompt, + } as GenRes + if (error) { + hasError = true + Toast.notify({ + type: 'error', + message: error, + }) + } } + else { + const { error, ...res } = await generateRule({ + flow_id: flowId, + node_id: nodeId, + current: currentPrompt, + instruction, + ideal_output: ideaOutput, + model_config: model, + }) + apiRes = res + if (error) { + hasError = true + Toast.notify({ + type: 'error', + message: error, + }) + } + } + if (!hasError) + addVersion(apiRes) } finally { setLoadingFalse() } } - const [showConfirmOverwrite, setShowConfirmOverwrite] = React.useState(false) + const [isShowConfirmOverwrite, { + setTrue: showConfirmOverwrite, + setFalse: hideShowConfirmOverwrite, + }] = useBoolean(false) const isShowAutoPromptResPlaceholder = () => { - return !isLoading && !res + return !isLoading && !current } return ( @@ -236,15 +283,14 @@ const GetAutomaticRes: FC = ({ isShow={isShow} onClose={onClose} className='min-w-[1140px] !p-0' - closable >
-
+
{t('appDebug.generate.title')}
{t('appDebug.generate.description')}
-
+
= ({ hideDebugWithMultipleModel />
-
-
-
{t('appDebug.generate.tryIt')}
-
-
-
- {tryList.map(item => ( - - ))} -
-
- {/* inputs */} -
-
-
{t('appDebug.generate.instruction')}
-
Tính năng