From 926546b153a701dfbfc71eb8157f9a41320444f8 Mon Sep 17 00:00:00 2001 From: -LAN- Date: Wed, 18 Dec 2024 16:35:54 +0800 Subject: [PATCH 01/16] chore: bump version to 0.14.1 (#11784) Signed-off-by: -LAN- --- api/configs/packaging/__init__.py | 2 +- docker-legacy/docker-compose.yaml | 6 +++--- docker/docker-compose-template.yaml | 6 +++--- docker/docker-compose.yaml | 6 +++--- web/package.json | 2 +- 5 files changed, 11 insertions(+), 11 deletions(-) diff --git a/api/configs/packaging/__init__.py b/api/configs/packaging/__init__.py index 51db50ec3d..57cd74af1f 100644 --- a/api/configs/packaging/__init__.py +++ b/api/configs/packaging/__init__.py @@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings): CURRENT_VERSION: str = Field( description="Dify version", - default="0.14.0", + default="0.14.1", ) COMMIT_SHA: str = Field( diff --git a/docker-legacy/docker-compose.yaml b/docker-legacy/docker-compose.yaml index 6c38b5c4f9..3bf4333ad1 100644 --- a/docker-legacy/docker-compose.yaml +++ b/docker-legacy/docker-compose.yaml @@ -2,7 +2,7 @@ version: '3' services: # API service api: - image: langgenius/dify-api:0.14.0 + image: langgenius/dify-api:0.14.1 restart: always environment: # Startup mode, 'api' starts the API server. @@ -227,7 +227,7 @@ services: # worker service # The Celery worker for processing the queue. worker: - image: langgenius/dify-api:0.14.0 + image: langgenius/dify-api:0.14.1 restart: always environment: CONSOLE_WEB_URL: '' @@ -397,7 +397,7 @@ services: # Frontend web application. web: - image: langgenius/dify-web:0.14.0 + image: langgenius/dify-web:0.14.1 restart: always environment: # The base URL of console application api server, refers to the Console base URL of WEB service if console domain is diff --git a/docker/docker-compose-template.yaml b/docker/docker-compose-template.yaml index 23fc9692ca..8370d82daa 100644 --- a/docker/docker-compose-template.yaml +++ b/docker/docker-compose-template.yaml @@ -2,7 +2,7 @@ x-shared-env: &shared-api-worker-env services: # API service api: - image: langgenius/dify-api:0.14.0 + image: langgenius/dify-api:0.14.1 restart: always environment: # Use the shared environment variables. @@ -25,7 +25,7 @@ services: # worker service # The Celery worker for processing the queue. worker: - image: langgenius/dify-api:0.14.0 + image: langgenius/dify-api:0.14.1 restart: always environment: # Use the shared environment variables. @@ -47,7 +47,7 @@ services: # Frontend web application. web: - image: langgenius/dify-web:0.14.0 + image: langgenius/dify-web:0.14.1 restart: always environment: CONSOLE_API_URL: ${CONSOLE_API_URL:-} diff --git a/docker/docker-compose.yaml b/docker/docker-compose.yaml index 5cda756b1b..3c5e6d3a4d 100644 --- a/docker/docker-compose.yaml +++ b/docker/docker-compose.yaml @@ -389,7 +389,7 @@ x-shared-env: &shared-api-worker-env services: # API service api: - image: langgenius/dify-api:0.14.0 + image: langgenius/dify-api:0.14.1 restart: always environment: # Use the shared environment variables. @@ -412,7 +412,7 @@ services: # worker service # The Celery worker for processing the queue. worker: - image: langgenius/dify-api:0.14.0 + image: langgenius/dify-api:0.14.1 restart: always environment: # Use the shared environment variables. @@ -434,7 +434,7 @@ services: # Frontend web application. web: - image: langgenius/dify-web:0.14.0 + image: langgenius/dify-web:0.14.1 restart: always environment: CONSOLE_API_URL: ${CONSOLE_API_URL:-} diff --git a/web/package.json b/web/package.json index c2ed7502f1..a1ba2cbd43 100644 --- a/web/package.json +++ b/web/package.json @@ -1,6 +1,6 @@ { "name": "dify-web", - "version": "0.14.0", + "version": "0.14.1", "private": true, "engines": { "node": ">=18.17.0" From 493834d45dd117f8324dd746fd28a4d1b46429ce Mon Sep 17 00:00:00 2001 From: yihong Date: Wed, 18 Dec 2024 17:36:36 +0800 Subject: [PATCH 02/16] ci: add config ci more disscuss check #11706 (#11752) Signed-off-by: yihong0618 --- .github/workflows/api-tests.yml | 3 + dev/pytest/pytest_config_tests.py | 111 ++++++++++++++++++++++++++++++ 2 files changed, 114 insertions(+) create mode 100644 dev/pytest/pytest_config_tests.py diff --git a/.github/workflows/api-tests.yml b/.github/workflows/api-tests.yml index e1c0bf33a4..2cd0b2a7d4 100644 --- a/.github/workflows/api-tests.yml +++ b/.github/workflows/api-tests.yml @@ -50,6 +50,9 @@ jobs: - name: Run ModelRuntime run: poetry run -C api bash dev/pytest/pytest_model_runtime.sh + - name: Run dify config tests + run: poetry run -C api python dev/pytest/pytest_config_tests.py + - name: Run Tool run: poetry run -C api bash dev/pytest/pytest_tools.sh diff --git a/dev/pytest/pytest_config_tests.py b/dev/pytest/pytest_config_tests.py new file mode 100644 index 0000000000..08adc9ebe9 --- /dev/null +++ b/dev/pytest/pytest_config_tests.py @@ -0,0 +1,111 @@ +import yaml # type: ignore +from dotenv import dotenv_values +from pathlib import Path + +BASE_API_AND_DOCKER_CONFIG_SET_DIFF = { + "APP_MAX_EXECUTION_TIME", + "BATCH_UPLOAD_LIMIT", + "CELERY_BEAT_SCHEDULER_TIME", + "CODE_EXECUTION_API_KEY", + "HTTP_REQUEST_MAX_CONNECT_TIMEOUT", + "HTTP_REQUEST_MAX_READ_TIMEOUT", + "HTTP_REQUEST_MAX_WRITE_TIMEOUT", + "KEYWORD_DATA_SOURCE_TYPE", + "LOGIN_LOCKOUT_DURATION", + "LOG_FORMAT", + "OCI_ACCESS_KEY", + "OCI_BUCKET_NAME", + "OCI_ENDPOINT", + "OCI_REGION", + "OCI_SECRET_KEY", + "REDIS_DB", + "RESEND_API_URL", + "RESPECT_XFORWARD_HEADERS_ENABLED", + "SENTRY_DSN", + "SSRF_DEFAULT_CONNECT_TIME_OUT", + "SSRF_DEFAULT_MAX_RETRIES", + "SSRF_DEFAULT_READ_TIME_OUT", + "SSRF_DEFAULT_TIME_OUT", + "SSRF_DEFAULT_WRITE_TIME_OUT", + "UPSTASH_VECTOR_TOKEN", + "UPSTASH_VECTOR_URL", + "USING_UGC_INDEX", + "WEAVIATE_BATCH_SIZE", + "WEAVIATE_GRPC_ENABLED", +} + +BASE_API_AND_DOCKER_COMPOSE_CONFIG_SET_DIFF = { + "BATCH_UPLOAD_LIMIT", + "CELERY_BEAT_SCHEDULER_TIME", + "HTTP_REQUEST_MAX_CONNECT_TIMEOUT", + "HTTP_REQUEST_MAX_READ_TIMEOUT", + "HTTP_REQUEST_MAX_WRITE_TIMEOUT", + "KEYWORD_DATA_SOURCE_TYPE", + "LOGIN_LOCKOUT_DURATION", + "LOG_FORMAT", + "OPENDAL_FS_ROOT", + "OPENDAL_S3_ACCESS_KEY_ID", + "OPENDAL_S3_BUCKET", + "OPENDAL_S3_ENDPOINT", + "OPENDAL_S3_REGION", + "OPENDAL_S3_ROOT", + "OPENDAL_S3_SECRET_ACCESS_KEY", + "OPENDAL_S3_SERVER_SIDE_ENCRYPTION", + "PGVECTOR_MAX_CONNECTION", + "PGVECTOR_MIN_CONNECTION", + "PGVECTO_RS_DATABASE", + "PGVECTO_RS_HOST", + "PGVECTO_RS_PASSWORD", + "PGVECTO_RS_PORT", + "PGVECTO_RS_USER", + "RESPECT_XFORWARD_HEADERS_ENABLED", + "SCARF_NO_ANALYTICS", + "SSRF_DEFAULT_CONNECT_TIME_OUT", + "SSRF_DEFAULT_MAX_RETRIES", + "SSRF_DEFAULT_READ_TIME_OUT", + "SSRF_DEFAULT_TIME_OUT", + "SSRF_DEFAULT_WRITE_TIME_OUT", + "STORAGE_OPENDAL_SCHEME", + "SUPABASE_API_KEY", + "SUPABASE_BUCKET_NAME", + "SUPABASE_URL", + "USING_UGC_INDEX", + "VIKINGDB_CONNECTION_TIMEOUT", + "VIKINGDB_SOCKET_TIMEOUT", + "WEAVIATE_BATCH_SIZE", + "WEAVIATE_GRPC_ENABLED", +} + +API_CONFIG_SET = set(dotenv_values(Path("api") / Path(".env.example")).keys()) +DOCKER_CONFIG_SET = set(dotenv_values(Path("docker") / Path(".env.example")).keys()) +DOCKER_COMPOSE_CONFIG_SET = set() + +with open(Path("docker") / Path("docker-compose.yaml")) as f: + DOCKER_COMPOSE_CONFIG_SET = set(yaml.safe_load(f.read())["x-shared-env"].keys()) + + +def test_yaml_config(): + # python set == operator is used to compare two sets + DIFF_API_WITH_DOCKER = ( + API_CONFIG_SET - DOCKER_CONFIG_SET - BASE_API_AND_DOCKER_CONFIG_SET_DIFF + ) + if DIFF_API_WITH_DOCKER: + print( + f"API and Docker config sets are different with key: {DIFF_API_WITH_DOCKER}" + ) + raise Exception("API and Docker config sets are different") + DIFF_API_WITH_DOCKER_COMPOSE = ( + API_CONFIG_SET + - DOCKER_COMPOSE_CONFIG_SET + - BASE_API_AND_DOCKER_COMPOSE_CONFIG_SET_DIFF + ) + if DIFF_API_WITH_DOCKER_COMPOSE: + print( + f"API and Docker Compose config sets are different with key: {DIFF_API_WITH_DOCKER_COMPOSE}" + ) + raise Exception("API and Docker Compose config sets are different") + print("All tests passed!") + + +if __name__ == "__main__": + test_yaml_config() From b5c2785e108e40eb43775e10e88714ab23705128 Mon Sep 17 00:00:00 2001 From: yihong Date: Wed, 18 Dec 2024 20:17:10 +0800 Subject: [PATCH 03/16] ci: fix config ci and it works (#11807) Signed-off-by: yihong0618 --- docker/.env.example | 2 ++ docker/docker-compose.yaml | 2 ++ 2 files changed, 4 insertions(+) diff --git a/docker/.env.example b/docker/.env.example index 0a5dffc570..e5bddf7ae1 100644 --- a/docker/.env.example +++ b/docker/.env.example @@ -107,6 +107,7 @@ ACCESS_TOKEN_EXPIRE_MINUTES=60 # 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 @@ -606,6 +607,7 @@ 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. diff --git a/docker/docker-compose.yaml b/docker/docker-compose.yaml index 3c5e6d3a4d..75f53f5ec3 100644 --- a/docker/docker-compose.yaml +++ b/docker/docker-compose.yaml @@ -18,6 +18,7 @@ x-shared-env: &shared-api-worker-env LOG_DATEFORMAT: ${LOG_DATEFORMAT:-"%Y-%m-%d %H:%M:%S"} LOG_TZ: ${LOG_TZ:-UTC} DEBUG: ${DEBUG:-false} + SENTRY_DSN: ${SENTRY_DSN:-} FLASK_DEBUG: ${FLASK_DEBUG:-false} SECRET_KEY: ${SECRET_KEY:-sk-9f73s3ljTXVcMT3Blb3ljTqtsKiGHXVcMT3BlbkFJLK7U} INIT_PASSWORD: ${INIT_PASSWORD:-} @@ -28,6 +29,7 @@ x-shared-env: &shared-api-worker-env FILES_ACCESS_TIMEOUT: ${FILES_ACCESS_TIMEOUT:-300} ACCESS_TOKEN_EXPIRE_MINUTES: ${ACCESS_TOKEN_EXPIRE_MINUTES:-60} APP_MAX_ACTIVE_REQUESTS: ${APP_MAX_ACTIVE_REQUESTS:-0} + APP_MAX_EXECUTION_TIME: ${APP_MAX_EXECUTION_TIME:-1200} DIFY_BIND_ADDRESS: ${DIFY_BIND_ADDRESS:-0.0.0.0} DIFY_PORT: ${DIFY_PORT:-5001} SERVER_WORKER_AMOUNT: ${SERVER_WORKER_AMOUNT:-} From 2624a6dcd0b89dd7c1aac2d7bfe7f769e9e3c992 Mon Sep 17 00:00:00 2001 From: "Charlie.Wei" Date: Wed, 18 Dec 2024 21:24:21 +0800 Subject: [PATCH 04/16] Fix explore app icon (#11808) Co-authored-by: luowei Co-authored-by: crazywoola <427733928@qq.com> Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com> --- api/controllers/console/explore/recommended_app.py | 1 + 1 file changed, 1 insertion(+) diff --git a/api/controllers/console/explore/recommended_app.py b/api/controllers/console/explore/recommended_app.py index baf1f591b9..ce85f495aa 100644 --- a/api/controllers/console/explore/recommended_app.py +++ b/api/controllers/console/explore/recommended_app.py @@ -13,6 +13,7 @@ app_fields = { "name": fields.String, "mode": fields.String, "icon": fields.String, + "icon_type": fields.String, "icon_url": AppIconUrlField, "icon_background": fields.String, } From 3388d6636cb5aab1f1d18aed8a7be1df9b2e463a Mon Sep 17 00:00:00 2001 From: Agung Besti <35904444+agungbesti@users.noreply.github.com> Date: Thu, 19 Dec 2024 11:36:11 +0700 Subject: [PATCH 05/16] add-model-azure-gpt-4o-2024-11-20 (#11803) Co-authored-by: agungbesti --- .../model_providers/azure_openai/_constant.py | 76 +++++++++++++++++++ .../azure_openai/azure_openai.yaml | 6 ++ 2 files changed, 82 insertions(+) diff --git a/api/core/model_runtime/model_providers/azure_openai/_constant.py b/api/core/model_runtime/model_providers/azure_openai/_constant.py index 4cf58275d7..3bd6375aa9 100644 --- a/api/core/model_runtime/model_providers/azure_openai/_constant.py +++ b/api/core/model_runtime/model_providers/azure_openai/_constant.py @@ -819,6 +819,82 @@ LLM_BASE_MODELS = [ ), ), ), + AzureBaseModel( + base_model_name="gpt-4o-2024-11-20", + entity=AIModelEntity( + model="fake-deployment-name", + label=I18nObject( + en_US="fake-deployment-name-label", + ), + model_type=ModelType.LLM, + features=[ + ModelFeature.AGENT_THOUGHT, + ModelFeature.VISION, + ModelFeature.MULTI_TOOL_CALL, + ModelFeature.STREAM_TOOL_CALL, + ], + fetch_from=FetchFrom.CUSTOMIZABLE_MODEL, + model_properties={ + ModelPropertyKey.MODE: LLMMode.CHAT.value, + ModelPropertyKey.CONTEXT_SIZE: 128000, + }, + parameter_rules=[ + ParameterRule( + name="temperature", + **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TEMPERATURE], + ), + ParameterRule( + name="top_p", + **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TOP_P], + ), + ParameterRule( + name="presence_penalty", + **PARAMETER_RULE_TEMPLATE[DefaultParameterName.PRESENCE_PENALTY], + ), + ParameterRule( + name="frequency_penalty", + **PARAMETER_RULE_TEMPLATE[DefaultParameterName.FREQUENCY_PENALTY], + ), + _get_max_tokens(default=512, min_val=1, max_val=16384), + ParameterRule( + name="seed", + label=I18nObject(zh_Hans="种子", en_US="Seed"), + type="int", + help=AZURE_DEFAULT_PARAM_SEED_HELP, + required=False, + precision=2, + min=0, + max=1, + ), + ParameterRule( + name="response_format", + label=I18nObject(zh_Hans="回复格式", en_US="response_format"), + type="string", + help=I18nObject( + zh_Hans="指定模型必须输出的格式", en_US="specifying the format that the model must output" + ), + required=False, + options=["text", "json_object", "json_schema"], + ), + ParameterRule( + name="json_schema", + label=I18nObject(en_US="JSON Schema"), + type="text", + help=I18nObject( + zh_Hans="设置返回的json schema，llm将按照它返回", + en_US="Set a response json schema will ensure LLM to adhere it.", + ), + required=False, + ), + ], + pricing=PriceConfig( + input=5.00, + output=15.00, + unit=0.000001, + currency="USD", + ), + ), + ), AzureBaseModel( base_model_name="gpt-4-turbo", entity=AIModelEntity( diff --git a/api/core/model_runtime/model_providers/azure_openai/azure_openai.yaml b/api/core/model_runtime/model_providers/azure_openai/azure_openai.yaml index 66c523504e..a6ae47b28e 100644 --- a/api/core/model_runtime/model_providers/azure_openai/azure_openai.yaml +++ b/api/core/model_runtime/model_providers/azure_openai/azure_openai.yaml @@ -171,6 +171,12 @@ model_credential_schema: show_on: - variable: __model_type value: llm + - label: + en_US: gpt-4o-2024-11-20 + value: gpt-4o-2024-11-20 + show_on: + - variable: __model_type + value: llm - label: en_US: gpt-4-turbo value: gpt-4-turbo From 560d375e0f3f1404cde54a012ad7602e9b8cca53 Mon Sep 17 00:00:00 2001 From: sino Date: Thu, 19 Dec 2024 17:49:31 +0800 Subject: [PATCH 06/16] feat(ark): add doubao-pro-256k and doubao-embedding-large (#11831) --- .../model_providers/volcengine_maas/llm/models.py | 4 ++++ .../volcengine_maas/text_embedding/models.py | 3 ++- .../volcengine_maas/volcengine_maas.yaml | 12 ++++++++++++ 3 files changed, 18 insertions(+), 1 deletion(-) diff --git a/api/core/model_runtime/model_providers/volcengine_maas/llm/models.py b/api/core/model_runtime/model_providers/volcengine_maas/llm/models.py index f7698f9443..cf3cf23cfb 100644 --- a/api/core/model_runtime/model_providers/volcengine_maas/llm/models.py +++ b/api/core/model_runtime/model_providers/volcengine_maas/llm/models.py @@ -40,6 +40,10 @@ configs: dict[str, ModelConfig] = { properties=ModelProperties(context_size=32768, max_tokens=4096, mode=LLMMode.CHAT), features=[ModelFeature.TOOL_CALL], ), + "Doubao-pro-256k": ModelConfig( + properties=ModelProperties(context_size=262144, max_tokens=4096, mode=LLMMode.CHAT), + features=[], + ), "Doubao-pro-128k": ModelConfig( properties=ModelProperties(context_size=131072, max_tokens=4096, mode=LLMMode.CHAT), features=[ModelFeature.TOOL_CALL], diff --git a/api/core/model_runtime/model_providers/volcengine_maas/text_embedding/models.py b/api/core/model_runtime/model_providers/volcengine_maas/text_embedding/models.py index 4a6f5b6f7b..be9bba5f24 100644 --- a/api/core/model_runtime/model_providers/volcengine_maas/text_embedding/models.py +++ b/api/core/model_runtime/model_providers/volcengine_maas/text_embedding/models.py @@ -12,6 +12,7 @@ class ModelConfig(BaseModel): ModelConfigs = { "Doubao-embedding": ModelConfig(properties=ModelProperties(context_size=4096, max_chunks=32)), + "Doubao-embedding-large": ModelConfig(properties=ModelProperties(context_size=4096, max_chunks=32)), } @@ -21,7 +22,7 @@ def get_model_config(credentials: dict) -> ModelConfig: if not model_configs: return ModelConfig( properties=ModelProperties( - context_size=int(credentials.get("context_size", 0)), + context_size=int(credentials.get("context_size", 4096)), max_chunks=int(credentials.get("max_chunks", 1)), ) ) diff --git a/api/core/model_runtime/model_providers/volcengine_maas/volcengine_maas.yaml b/api/core/model_runtime/model_providers/volcengine_maas/volcengine_maas.yaml index 57492b6d9f..2ddb612546 100644 --- a/api/core/model_runtime/model_providers/volcengine_maas/volcengine_maas.yaml +++ b/api/core/model_runtime/model_providers/volcengine_maas/volcengine_maas.yaml @@ -166,6 +166,12 @@ model_credential_schema: show_on: - variable: __model_type value: llm + - label: + en_US: Doubao-pro-256k + value: Doubao-pro-256k + show_on: + - variable: __model_type + value: llm - label: en_US: Llama3-8B value: Llama3-8B @@ -220,6 +226,12 @@ model_credential_schema: show_on: - variable: __model_type value: text-embedding + - label: + en_US: Doubao-embedding-large + value: Doubao-embedding-large + show_on: + - variable: __model_type + value: text-embedding - label: en_US: Custom zh_Hans: 自定义 From d0570675436e314c335d1350010e074ef90dffb6 Mon Sep 17 00:00:00 2001 From: barabicu Date: Thu, 19 Dec 2024 19:30:51 +0900 Subject: [PATCH 07/16] fix: remove ruff ignore SIM300 (#11810) --- api/.ruff.toml | 1 - api/controllers/console/admin.py | 2 +- .../replicate/text_embedding/text_embedding.py | 2 +- .../model_runtime/__mock/xinference.py | 8 ++++---- .../integration_tests/tools/api_tool/test_api_tool.py | 10 +++++----- .../integration_tests/workflow/nodes/test_http.py | 2 +- 6 files changed, 12 insertions(+), 13 deletions(-) diff --git a/api/.ruff.toml b/api/.ruff.toml index 0f3185223c..26a1b977a9 100644 --- a/api/.ruff.toml +++ b/api/.ruff.toml @@ -70,7 +70,6 @@ ignore = [ "SIM113", # eumerate-for-loop "SIM117", # multiple-with-statements "SIM210", # if-expr-with-true-false - "SIM300", # yoda-conditions, ] [lint.per-file-ignores] diff --git a/api/controllers/console/admin.py b/api/controllers/console/admin.py index a70c4a31c7..8c0bf8710d 100644 --- a/api/controllers/console/admin.py +++ b/api/controllers/console/admin.py @@ -31,7 +31,7 @@ def admin_required(view): if auth_scheme != "bearer": raise Unauthorized("Invalid Authorization header format. Expected 'Bearer ' format.") - if dify_config.ADMIN_API_KEY != auth_token: + if auth_token != dify_config.ADMIN_API_KEY: raise Unauthorized("API key is invalid.") return view(*args, **kwargs) diff --git a/api/core/model_runtime/model_providers/replicate/text_embedding/text_embedding.py b/api/core/model_runtime/model_providers/replicate/text_embedding/text_embedding.py index c4e9d0b9c6..41759fe07d 100644 --- a/api/core/model_runtime/model_providers/replicate/text_embedding/text_embedding.py +++ b/api/core/model_runtime/model_providers/replicate/text_embedding/text_embedding.py @@ -119,7 +119,7 @@ class ReplicateEmbeddingModel(_CommonReplicate, TextEmbeddingModel): embeddings.append(result[0].get("embedding")) return [list(map(float, e)) for e in embeddings] - elif "texts" == text_input_key: + elif text_input_key == "texts": result = client.run( replicate_model_version, input={ diff --git a/api/tests/integration_tests/model_runtime/__mock/xinference.py b/api/tests/integration_tests/model_runtime/__mock/xinference.py index 5f7dad50c1..794f4b0585 100644 --- a/api/tests/integration_tests/model_runtime/__mock/xinference.py +++ b/api/tests/integration_tests/model_runtime/__mock/xinference.py @@ -21,13 +21,13 @@ class MockXinferenceClass: if not re.match(r"https?:\/\/[^\s\/$.?#].[^\s]*$", self.base_url): raise RuntimeError("404 Not Found") - if "generate" == model_uid: + if model_uid == "generate": return RESTfulGenerateModelHandle(model_uid, base_url=self.base_url, auth_headers={}) - if "chat" == model_uid: + if model_uid == "chat": return RESTfulChatModelHandle(model_uid, base_url=self.base_url, auth_headers={}) - if "embedding" == model_uid: + if model_uid == "embedding": return RESTfulEmbeddingModelHandle(model_uid, base_url=self.base_url, auth_headers={}) - if "rerank" == model_uid: + if model_uid == "rerank": return RESTfulRerankModelHandle(model_uid, base_url=self.base_url, auth_headers={}) raise RuntimeError("404 Not Found") diff --git a/api/tests/integration_tests/tools/api_tool/test_api_tool.py b/api/tests/integration_tests/tools/api_tool/test_api_tool.py index 09729a961e..1bd75b91f7 100644 --- a/api/tests/integration_tests/tools/api_tool/test_api_tool.py +++ b/api/tests/integration_tests/tools/api_tool/test_api_tool.py @@ -34,9 +34,9 @@ def test_api_tool(setup_http_mock): response = tool.do_http_request(tool.api_bundle.server_url, tool.api_bundle.method, headers, parameters) assert response.status_code == 200 - assert "/p_param" == response.request.url.path - assert b"query_param=q_param" == response.request.url.query - assert "h_param" == response.request.headers.get("header_param") - assert "application/json" == response.request.headers.get("content-type") - assert "cookie_param=c_param" == response.request.headers.get("cookie") + assert response.request.url.path == "/p_param" + assert response.request.url.query == b"query_param=q_param" + assert response.request.headers.get("header_param") == "h_param" + assert response.request.headers.get("content-type") == "application/json" + assert response.request.headers.get("cookie") == "cookie_param=c_param" assert "b_param" in response.content.decode() diff --git a/api/tests/integration_tests/workflow/nodes/test_http.py b/api/tests/integration_tests/workflow/nodes/test_http.py index 9eea63f722..0507fc7075 100644 --- a/api/tests/integration_tests/workflow/nodes/test_http.py +++ b/api/tests/integration_tests/workflow/nodes/test_http.py @@ -384,7 +384,7 @@ def test_mock_404(setup_http_mock): assert result.outputs is not None resp = result.outputs - assert 404 == resp.get("status_code") + assert resp.get("status_code") == 404 assert "Not Found" in resp.get("body", "") From 12d45e9114cddf19767cbf5e267b5dd89f59792e Mon Sep 17 00:00:00 2001 From: yihong Date: Thu, 19 Dec 2024 20:50:09 +0800 Subject: [PATCH 08/16] fix: silicon change its model fix #11844 (#11847) Signed-off-by: yihong0618 --- .../model_runtime/model_providers/siliconflow/siliconflow.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/api/core/model_runtime/model_providers/siliconflow/siliconflow.py b/api/core/model_runtime/model_providers/siliconflow/siliconflow.py index e121ab8c7e..03c4306144 100644 --- a/api/core/model_runtime/model_providers/siliconflow/siliconflow.py +++ b/api/core/model_runtime/model_providers/siliconflow/siliconflow.py @@ -18,7 +18,7 @@ class SiliconflowProvider(ModelProvider): try: model_instance = self.get_model_instance(ModelType.LLM) - model_instance.validate_credentials(model="deepseek-ai/DeepSeek-V2-Chat", credentials=credentials) + model_instance.validate_credentials(model="deepseek-ai/DeepSeek-V2.5", credentials=credentials) except CredentialsValidateFailedError as ex: raise ex except Exception as ex: From 5a8a901560228a1556611ecaa67bcf5ddac22ce5 Mon Sep 17 00:00:00 2001 From: yihong Date: Thu, 19 Dec 2024 20:50:20 +0800 Subject: [PATCH 09/16] fix: float values are not json for nan value close #11827 (#11840) Signed-off-by: yihong0618 --- api/core/rag/embedding/cached_embedding.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/api/core/rag/embedding/cached_embedding.py b/api/core/rag/embedding/cached_embedding.py index fc8e0440c3..652f7e145f 100644 --- a/api/core/rag/embedding/cached_embedding.py +++ b/api/core/rag/embedding/cached_embedding.py @@ -65,6 +65,11 @@ class CacheEmbedding(Embeddings): for vector in embedding_result.embeddings: try: normalized_embedding = (vector / np.linalg.norm(vector)).tolist() + # stackoverflow best way: https://stackoverflow.com/questions/20319813/how-to-check-list-containing-nan + if np.isnan(normalized_embedding).any(): + # for issue #11827 float values are not json compliant + logger.warning(f"Normalized embedding is nan: {normalized_embedding}") + continue embedding_queue_embeddings.append(normalized_embedding) except IntegrityError: db.session.rollback() From de3911e930e859b7e3fdf6f0c1ab181999c826dd Mon Sep 17 00:00:00 2001 From: crazywoola <100913391+crazywoola@users.noreply.github.com> Date: Thu, 19 Dec 2024 21:19:08 +0800 Subject: [PATCH 10/16] Fix/10584 wrong message when no custom tool available in custom tool list (#11851) --- web/app/components/tools/add-tool-modal/empty.tsx | 12 +++++++++--- web/i18n/en-US/tools.ts | 2 ++ web/i18n/zh-Hans/tools.ts | 2 ++ 3 files changed, 13 insertions(+), 3 deletions(-) diff --git a/web/app/components/tools/add-tool-modal/empty.tsx b/web/app/components/tools/add-tool-modal/empty.tsx index 051ae446d4..794d2a585c 100644 --- a/web/app/components/tools/add-tool-modal/empty.tsx +++ b/web/app/components/tools/add-tool-modal/empty.tsx @@ -1,13 +1,19 @@ +'use client' +import { useSearchParams } from 'next/navigation' import { useTranslation } from 'react-i18next' - const Empty = () => { const { t } = useTranslation() + const searchParams = useSearchParams() return (
-
{t('tools.addToolModal.emptyTitle')}
-
{t('tools.addToolModal.emptyTip')}
+
+ {t(`tools.addToolModal.${searchParams.get('category') === 'workflow' ? 'emptyTitle' : 'emptyTitleCustom'}`)} +
+
+ {t(`tools.addToolModal.${searchParams.get('category') === 'workflow' ? 'emptyTip' : 'emptyTipCustom'}`)} +
) } diff --git a/web/i18n/en-US/tools.ts b/web/i18n/en-US/tools.ts index f96ae8144e..b1f278f9ce 100644 --- a/web/i18n/en-US/tools.ts +++ b/web/i18n/en-US/tools.ts @@ -31,6 +31,8 @@ const translation = { manageInTools: 'Manage in Tools', emptyTitle: 'No workflow tool available', emptyTip: 'Go to "Workflow -> Publish as Tool"', + emptyTitleCustom: 'No custom tool available', + emptyTipCustom: 'Create a custom tool', }, createTool: { title: 'Create Custom Tool', diff --git a/web/i18n/zh-Hans/tools.ts b/web/i18n/zh-Hans/tools.ts index 1473fc23d3..a788ef0abe 100644 --- a/web/i18n/zh-Hans/tools.ts +++ b/web/i18n/zh-Hans/tools.ts @@ -31,6 +31,8 @@ const translation = { manageInTools: '去工具列表管理', emptyTitle: '没有可用的工作流工具', emptyTip: '去 “工作流 -> 发布为工具” 添加', + emptyTitleCustom: '没有可用的自定义工具', + emptyTipCustom: '创建自定义工具', }, createTool: { title: '创建自定义工具', From 15485010505c46f2195a4971817cbeafaa85d024 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E5=82=BB=E7=AC=91zz?= <43721571+shaxiaozz@users.noreply.github.com> Date: Thu, 19 Dec 2024 23:05:27 +0800 Subject: [PATCH 11/16] fix: comfyui tool supports https (#11823) --- api/core/tools/provider/builtin/comfyui/comfyui.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/api/core/tools/provider/builtin/comfyui/comfyui.py b/api/core/tools/provider/builtin/comfyui/comfyui.py index bab690af82..a8127dd23f 100644 --- a/api/core/tools/provider/builtin/comfyui/comfyui.py +++ b/api/core/tools/provider/builtin/comfyui/comfyui.py @@ -11,7 +11,10 @@ class ComfyUIProvider(BuiltinToolProviderController): def _validate_credentials(self, credentials: dict[str, Any]) -> None: ws = websocket.WebSocket() base_url = URL(credentials.get("base_url")) - ws_address = f"ws://{base_url.authority}/ws?clientId=test123" + ws_protocol = "ws" + if base_url.scheme == "https": + ws_protocol = "wss" + ws_address = f"{ws_protocol}://{base_url.authority}/ws?clientId=test123" try: ws.connect(ws_address) From 44104797d662e64775405518d29bfb7807bdb349 Mon Sep 17 00:00:00 2001 From: stardust <642720202@qq.com> Date: Fri, 20 Dec 2024 02:21:41 +0800 Subject: [PATCH 12/16] fix: Enhance file type detection in HTTP Request node (#11797) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: -LAN- Co-authored-by: 谭成 Co-authored-by: -LAN- --- api/core/workflow/nodes/http_request/node.py | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/api/core/workflow/nodes/http_request/node.py b/api/core/workflow/nodes/http_request/node.py index d040cc9f55..a0fc8acaef 100644 --- a/api/core/workflow/nodes/http_request/node.py +++ b/api/core/workflow/nodes/http_request/node.py @@ -1,4 +1,5 @@ import logging +import mimetypes from collections.abc import Mapping, Sequence from typing import Any @@ -156,20 +157,24 @@ class HttpRequestNode(BaseNode[HttpRequestNodeData]): def extract_files(self, url: str, response: Response) -> list[File]: """ - Extract files from response + Extract files from response by checking both Content-Type header and URL """ files = [] is_file = response.is_file content_type = response.content_type content = response.content - if is_file and content_type: + if is_file: + # Guess file extension from URL or Content-Type header + filename = url.split("?")[0].split("/")[-1] or "" + mime_type = content_type or mimetypes.guess_type(filename)[0] or "application/octet-stream" + tool_file = ToolFileManager.create_file_by_raw( user_id=self.user_id, tenant_id=self.tenant_id, conversation_id=None, file_binary=content, - mimetype=content_type, + mimetype=mime_type, ) mapping = { From 9d93ad1f16daa019890d278395a8c004f1ae07d2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=9D=9E=E6=B3=95=E6=93=8D=E4=BD=9C?= Date: Fri, 20 Dec 2024 09:26:31 +0800 Subject: [PATCH 13/16] feat: add gemini-2.0-flash-thinking-exp-1219 (#11863) --- .../model_providers/google/llm/_position.yaml | 1 + .../gemini-2.0-flash-thinking-exp-1219.yaml | 39 +++++++++++++++++++ 2 files changed, 40 insertions(+) create mode 100644 api/core/model_runtime/model_providers/google/llm/gemini-2.0-flash-thinking-exp-1219.yaml diff --git a/api/core/model_runtime/model_providers/google/llm/_position.yaml b/api/core/model_runtime/model_providers/google/llm/_position.yaml index 0b5e1025bf..4ad0670e11 100644 --- a/api/core/model_runtime/model_providers/google/llm/_position.yaml +++ b/api/core/model_runtime/model_providers/google/llm/_position.yaml @@ -1,4 +1,5 @@ - gemini-2.0-flash-exp +- gemini-2.0-flash-thinking-exp-1219 - gemini-1.5-pro - gemini-1.5-pro-latest - gemini-1.5-pro-001 diff --git a/api/core/model_runtime/model_providers/google/llm/gemini-2.0-flash-thinking-exp-1219.yaml b/api/core/model_runtime/model_providers/google/llm/gemini-2.0-flash-thinking-exp-1219.yaml new file mode 100644 index 0000000000..dfcf8fd050 --- /dev/null +++ b/api/core/model_runtime/model_providers/google/llm/gemini-2.0-flash-thinking-exp-1219.yaml @@ -0,0 +1,39 @@ +model: gemini-2.0-flash-thinking-exp-1219 +label: + en_US: Gemini 2.0 Flash Thinking Exp 1219 +model_type: llm +features: + - agent-thought + - vision + - document + - video + - audio +model_properties: + mode: chat + context_size: 32767 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: top_k + label: + zh_Hans: 取样数量 + en_US: Top k + type: int + help: + zh_Hans: 仅从每个后续标记的前 K 个选项中采样。 + en_US: Only sample from the top K options for each subsequent token. + required: false + - name: max_output_tokens + use_template: max_tokens + default: 8192 + min: 1 + max: 8192 + - name: json_schema + use_template: json_schema +pricing: + input: '0.00' + output: '0.00' + unit: '0.000001' + currency: USD From 95a7e5013707277c8d7440cf20f4b61e81b10a36 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E5=82=BB=E7=AC=91zz?= <43721571+shaxiaozz@users.noreply.github.com> Date: Fri, 20 Dec 2024 09:27:21 +0800 Subject: [PATCH 14/16] Fix comfyui tool https (#11859) --- .../tools/provider/builtin/comfyui/tools/comfyui_client.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/api/core/tools/provider/builtin/comfyui/tools/comfyui_client.py b/api/core/tools/provider/builtin/comfyui/tools/comfyui_client.py index bed9cd1882..f994cdbf66 100644 --- a/api/core/tools/provider/builtin/comfyui/tools/comfyui_client.py +++ b/api/core/tools/provider/builtin/comfyui/tools/comfyui_client.py @@ -40,7 +40,10 @@ class ComfyUiClient: def open_websocket_connection(self) -> tuple[WebSocket, str]: client_id = str(uuid.uuid4()) ws = WebSocket() - ws_address = f"ws://{self.base_url.authority}/ws?clientId={client_id}" + ws_protocol = "ws" + if self.base_url.scheme == "https": + ws_protocol = "wss" + ws_address = f"{ws_protocol}://{self.base_url.authority}/ws?clientId={client_id}" ws.connect(ws_address) return ws, client_id From 463fbe268047520fba99b60c123a88a4c5141884 Mon Sep 17 00:00:00 2001 From: yihong Date: Fri, 20 Dec 2024 09:28:32 +0800 Subject: [PATCH 15/16] fix: better gard nan value from numpy for issue #11827 (#11864) Signed-off-by: yihong0618 --- .../azure_openai/text_embedding/text_embedding.py | 5 ++++- .../model_providers/cohere/text_embedding/text_embedding.py | 5 ++++- .../model_providers/openai/text_embedding/text_embedding.py | 5 ++++- .../model_providers/upstage/text_embedding/text_embedding.py | 5 ++++- api/core/rag/embedding/cached_embedding.py | 2 ++ 5 files changed, 18 insertions(+), 4 deletions(-) diff --git a/api/core/model_runtime/model_providers/azure_openai/text_embedding/text_embedding.py b/api/core/model_runtime/model_providers/azure_openai/text_embedding/text_embedding.py index c45ce87ea7..69d2cfaded 100644 --- a/api/core/model_runtime/model_providers/azure_openai/text_embedding/text_embedding.py +++ b/api/core/model_runtime/model_providers/azure_openai/text_embedding/text_embedding.py @@ -92,7 +92,10 @@ class AzureOpenAITextEmbeddingModel(_CommonAzureOpenAI, TextEmbeddingModel): average = embeddings_batch[0] else: average = np.average(_result, axis=0, weights=num_tokens_in_batch[i]) - embeddings[i] = (average / np.linalg.norm(average)).tolist() + embedding = (average / np.linalg.norm(average)).tolist() + if np.isnan(embedding).any(): + raise ValueError("Normalized embedding is nan please try again") + embeddings[i] = embedding # calc usage usage = self._calc_response_usage(model=model, credentials=credentials, tokens=used_tokens) diff --git a/api/core/model_runtime/model_providers/cohere/text_embedding/text_embedding.py b/api/core/model_runtime/model_providers/cohere/text_embedding/text_embedding.py index 5fd4d637be..9e4df27060 100644 --- a/api/core/model_runtime/model_providers/cohere/text_embedding/text_embedding.py +++ b/api/core/model_runtime/model_providers/cohere/text_embedding/text_embedding.py @@ -88,7 +88,10 @@ class CohereTextEmbeddingModel(TextEmbeddingModel): average = embeddings_batch[0] else: average = np.average(_result, axis=0, weights=num_tokens_in_batch[i]) - embeddings[i] = (average / np.linalg.norm(average)).tolist() + embedding = (average / np.linalg.norm(average)).tolist() + if np.isnan(embedding).any(): + raise ValueError("Normalized embedding is nan please try again") + embeddings[i] = embedding # calc usage usage = self._calc_response_usage(model=model, credentials=credentials, tokens=used_tokens) diff --git a/api/core/model_runtime/model_providers/openai/text_embedding/text_embedding.py b/api/core/model_runtime/model_providers/openai/text_embedding/text_embedding.py index bec01fe679..9c8c8d5882 100644 --- a/api/core/model_runtime/model_providers/openai/text_embedding/text_embedding.py +++ b/api/core/model_runtime/model_providers/openai/text_embedding/text_embedding.py @@ -97,7 +97,10 @@ class OpenAITextEmbeddingModel(_CommonOpenAI, TextEmbeddingModel): average = embeddings_batch[0] else: average = np.average(_result, axis=0, weights=num_tokens_in_batch[i]) - embeddings[i] = (average / np.linalg.norm(average)).tolist() + embedding = (average / np.linalg.norm(average)).tolist() + if np.isnan(embedding).any(): + raise ValueError("Normalized embedding is nan please try again") + embeddings[i] = embedding # calc usage usage = self._calc_response_usage(model=model, credentials=credentials, tokens=used_tokens) diff --git a/api/core/model_runtime/model_providers/upstage/text_embedding/text_embedding.py b/api/core/model_runtime/model_providers/upstage/text_embedding/text_embedding.py index 7dd495b55e..5b340e53bb 100644 --- a/api/core/model_runtime/model_providers/upstage/text_embedding/text_embedding.py +++ b/api/core/model_runtime/model_providers/upstage/text_embedding/text_embedding.py @@ -100,7 +100,10 @@ class UpstageTextEmbeddingModel(_CommonUpstage, TextEmbeddingModel): average = embeddings_batch[0] else: average = np.average(_result, axis=0, weights=num_tokens_in_batch[i]) - embeddings[i] = (average / np.linalg.norm(average)).tolist() + embedding = (average / np.linalg.norm(average)).tolist() + if np.isnan(embedding).any(): + raise ValueError("Normalized embedding is nan please try again") + embeddings[i] = embedding usage = self._calc_response_usage(model=model, credentials=credentials, tokens=used_tokens) diff --git a/api/core/rag/embedding/cached_embedding.py b/api/core/rag/embedding/cached_embedding.py index 652f7e145f..8ddda7e983 100644 --- a/api/core/rag/embedding/cached_embedding.py +++ b/api/core/rag/embedding/cached_embedding.py @@ -116,6 +116,8 @@ class CacheEmbedding(Embeddings): embedding_results = embedding_result.embeddings[0] embedding_results = (embedding_results / np.linalg.norm(embedding_results)).tolist() + if np.isnan(embedding_results).any(): + raise ValueError("Normalized embedding is nan please try again") except Exception as ex: if dify_config.DEBUG: logging.exception(f"Failed to embed query text '{text[:10]}...({len(text)} chars)'") From bb2f46d7cc9ecf92e297d5655c5514429b72a693 Mon Sep 17 00:00:00 2001 From: "Dr.MerdanBay" <110794035+KMerdan@users.noreply.github.com> Date: Fri, 20 Dec 2024 12:13:39 +0900 Subject: [PATCH 16/16] fix: add safe dictionary access for bedrock credentials (#11860) --- .../bedrock/get_bedrock_client.py | 16 ++++++++++++---- .../model_providers/bedrock/rerank/rerank.py | 5 ++++- 2 files changed, 16 insertions(+), 5 deletions(-) diff --git a/api/core/model_runtime/model_providers/bedrock/get_bedrock_client.py b/api/core/model_runtime/model_providers/bedrock/get_bedrock_client.py index a19ffbb20a..2ad37cef3b 100644 --- a/api/core/model_runtime/model_providers/bedrock/get_bedrock_client.py +++ b/api/core/model_runtime/model_providers/bedrock/get_bedrock_client.py @@ -1,11 +1,19 @@ +from collections.abc import Mapping + import boto3 from botocore.config import Config +from core.model_runtime.errors.invoke import InvokeBadRequestError + + +def get_bedrock_client(service_name: str, credentials: Mapping[str, str]): + region_name = credentials.get("aws_region") + if not region_name: + raise InvokeBadRequestError("aws_region is required") + client_config = Config(region_name=region_name) + aws_access_key_id = credentials.get("aws_access_key_id") + aws_secret_access_key = credentials.get("aws_secret_access_key") -def get_bedrock_client(service_name, credentials=None): - client_config = Config(region_name=credentials["aws_region"]) - aws_access_key_id = credentials["aws_access_key_id"] - aws_secret_access_key = credentials["aws_secret_access_key"] if aws_access_key_id and aws_secret_access_key: # use aksk to call bedrock client = boto3.client( diff --git a/api/core/model_runtime/model_providers/bedrock/rerank/rerank.py b/api/core/model_runtime/model_providers/bedrock/rerank/rerank.py index e134db646f..9da23ba1b0 100644 --- a/api/core/model_runtime/model_providers/bedrock/rerank/rerank.py +++ b/api/core/model_runtime/model_providers/bedrock/rerank/rerank.py @@ -62,7 +62,10 @@ class BedrockRerankModel(RerankModel): } ) modelId = model - region = credentials["aws_region"] + region = credentials.get("aws_region") + # region is a required field + if not region: + raise InvokeBadRequestError("aws_region is required in credentials") model_package_arn = f"arn:aws:bedrock:{region}::foundation-model/{modelId}" rerankingConfiguration = { "type": "BEDROCK_RERANKING_MODEL",