mirror of https://github.com/langgenius/dify.git
merge main
This commit is contained in:
StyleZhang
commit
0f4291bd36
|
|
@ -78,7 +78,7 @@ jobs:
|
|||
- name: Run Workflow
|
||||
run: poetry run -C api bash dev/pytest/pytest_workflow.sh
|
||||
|
||||
- name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch)
|
||||
- name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase)
|
||||
uses: hoverkraft-tech/compose-action@v2.0.0
|
||||
with:
|
||||
compose-file: |
|
||||
|
|
@ -86,6 +86,7 @@ jobs:
|
|||
services: |
|
||||
weaviate
|
||||
qdrant
|
||||
couchbase-server
|
||||
etcd
|
||||
minio
|
||||
milvus-standalone
|
||||
|
|
|
|||
|
|
@ -7,5 +7,7 @@ yq eval '.services["milvus-standalone"].ports += ["19530:19530"]' -i docker/dock
|
|||
yq eval '.services.pgvector.ports += ["5433:5432"]' -i docker/docker-compose.yaml
|
||||
yq eval '.services["pgvecto-rs"].ports += ["5431:5432"]' -i docker/docker-compose.yaml
|
||||
yq eval '.services["elasticsearch"].ports += ["9200:9200"]' -i docker/docker-compose.yaml
|
||||
yq eval '.services.couchbase-server.ports += ["8091-8096:8091-8096"]' -i docker/docker-compose.yaml
|
||||
yq eval '.services.couchbase-server.ports += ["11210:11210"]' -i docker/docker-compose.yaml
|
||||
|
||||
echo "Ports exposed for sandbox, weaviate, qdrant, chroma, milvus, pgvector, pgvecto-rs, elasticsearch"
|
||||
echo "Ports exposed for sandbox, weaviate, qdrant, chroma, milvus, pgvector, pgvecto-rs, elasticsearch, couchbase"
|
||||
|
|
|
|||
|
|
@ -173,6 +173,8 @@ docker/volumes/myscale/log/*
|
|||
docker/volumes/unstructured/*
|
||||
docker/volumes/pgvector/data/*
|
||||
docker/volumes/pgvecto_rs/data/*
|
||||
docker/volumes/couchbase/*
|
||||
docker/volumes/oceanbase/*
|
||||
|
||||
docker/nginx/conf.d/default.conf
|
||||
docker/nginx/ssl/*
|
||||
|
|
|
|||
|
|
@ -0,0 +1,241 @@
|
|||
|
||||
|
||||
<p align="center">
|
||||
📌 <a href="https://dify.ai/blog/introducing-dify-workflow-file-upload-a-demo-on-ai-podcast">Introduzindo o Dify Workflow com Upload de Arquivo: Recrie o Podcast Google NotebookLM</a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="https://cloud.dify.ai">Dify Cloud</a> ·
|
||||
<a href="https://docs.dify.ai/getting-started/install-self-hosted">Auto-hospedagem</a> ·
|
||||
<a href="https://docs.dify.ai">Documentação</a> ·
|
||||
<a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Consultas empresariais</a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="https://dify.ai" target="_blank">
|
||||
<img alt="Static Badge" src="https://img.shields.io/badge/Product-F04438"></a>
|
||||
<a href="https://dify.ai/pricing" target="_blank">
|
||||
<img alt="Static Badge" src="https://img.shields.io/badge/free-pricing?logo=free&color=%20%23155EEF&label=pricing&labelColor=%20%23528bff"></a>
|
||||
<a href="https://discord.gg/FngNHpbcY7" target="_blank">
|
||||
<img src="https://img.shields.io/discord/1082486657678311454?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb"
|
||||
alt="chat on Discord"></a>
|
||||
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
|
||||
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
|
||||
alt="follow on X(Twitter)"></a>
|
||||
<a href="https://hub.docker.com/u/langgenius" target="_blank">
|
||||
<img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
|
||||
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
|
||||
<img alt="Commits last month" src="https://img.shields.io/github/commit-activity/m/langgenius/dify?labelColor=%20%2332b583&color=%20%2312b76a"></a>
|
||||
<a href="https://github.com/langgenius/dify/" target="_blank">
|
||||
<img alt="Issues closed" src="https://img.shields.io/github/issues-search?query=repo%3Alanggenius%2Fdify%20is%3Aclosed&label=issues%20closed&labelColor=%20%237d89b0&color=%20%235d6b98"></a>
|
||||
<a href="https://github.com/langgenius/dify/discussions/" target="_blank">
|
||||
<img alt="Discussion posts" src="https://img.shields.io/github/discussions/langgenius/dify?labelColor=%20%239b8afb&color=%20%237a5af8"></a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="./README.md"><img alt="README em Inglês" src="https://img.shields.io/badge/English-d9d9d9"></a>
|
||||
<a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
|
||||
<a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
|
||||
<a href="./README_ES.md"><img alt="README em Espanhol" src="https://img.shields.io/badge/Español-d9d9d9"></a>
|
||||
<a href="./README_FR.md"><img alt="README em Francês" src="https://img.shields.io/badge/Français-d9d9d9"></a>
|
||||
<a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
|
||||
<a href="./README_KR.md"><img alt="README em Coreano" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
|
||||
<a href="./README_AR.md"><img alt="README em Árabe" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
|
||||
<a href="./README_TR.md"><img alt="README em Turco" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
|
||||
<a href="./README_VI.md"><img alt="README em Vietnamita" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
|
||||
<a href="./README_PT.md"><img alt="README em Português - BR" src="https://img.shields.io/badge/Portugu%C3%AAs-BR?style=flat&label=BR&color=d9d9d9"></a>
|
||||
</p>
|
||||
|
||||
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:
|
||||
</br> </br>
|
||||
|
||||
**1. Workflow**:
|
||||
Construa e teste workflows poderosos de IA em uma interface visual, aproveitando todos os recursos a seguir e muito mais.
|
||||
|
||||
|
||||
https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
|
||||
|
||||
|
||||
|
||||
**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).
|
||||
|
||||
|
||||
|
||||
|
||||
**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.
|
||||
|
||||
**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.
|
||||
|
||||
|
||||
## Comparação de recursos
|
||||
<table style="width: 100%;">
|
||||
<tr>
|
||||
<th align="center">Recurso</th>
|
||||
<th align="center">Dify.AI</th>
|
||||
<th align="center">LangChain</th>
|
||||
<th align="center">Flowise</th>
|
||||
<th align="center">OpenAI Assistants API</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">Abordagem de Programação</td>
|
||||
<td align="center">Orientada a API + Aplicativo</td>
|
||||
<td align="center">Código Python</td>
|
||||
<td align="center">Orientada a Aplicativo</td>
|
||||
<td align="center">Orientada a API</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">LLMs Suportados</td>
|
||||
<td align="center">Variedade Rica</td>
|
||||
<td align="center">Variedade Rica</td>
|
||||
<td align="center">Variedade Rica</td>
|
||||
<td align="center">Apenas OpenAI</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">RAG Engine</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">Agente</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">❌</td>
|
||||
<td align="center">✅</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">Workflow</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">❌</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">❌</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">Observabilidade</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">❌</td>
|
||||
<td align="center">❌</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">Recursos Empresariais (SSO/Controle de Acesso)</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">❌</td>
|
||||
<td align="center">❌</td>
|
||||
<td align="center">❌</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">Implantação Local</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">✅</td>
|
||||
<td align="center">❌</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
## Usando o Dify
|
||||
|
||||
- **Nuvem </br>**
|
||||
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</br>**
|
||||
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</br>**
|
||||
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. </br>
|
||||
> 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
|
||||
|
||||
Dê uma estrela no Dify no GitHub e seja notificado imediatamente sobre novos lançamentos.
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
## 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
|
||||
|
||||
</br>
|
||||
|
||||
A maneira mais fácil de iniciar o servidor Dify é executar nosso arquivo [docker-compose.yml](docker/docker-compose.yaml). Antes de rodar o comando de instalação, certifique-se de que o [Docker](https://docs.docker.com/get-docker/) e o [Docker Compose](https://docs.docker.com/compose/install/) estão instalados na sua máquina:
|
||||
|
||||
```bash
|
||||
cd docker
|
||||
cp .env.example .env
|
||||
docker compose up -d
|
||||
```
|
||||
|
||||
Após a execução, você pode acessar o painel do Dify no navegador em [http://localhost/install](http://localhost/install) e iniciar o processo de inicialização.
|
||||
|
||||
> Se você deseja contribuir com o Dify ou fazer desenvolvimento adicional, consulte nosso [guia para implantar a partir do código fonte](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code).
|
||||
|
||||
## Próximos passos
|
||||
|
||||
Se precisar personalizar a configuração, consulte os comentários no nosso arquivo [.env.example](docker/.env.example) e atualize os valores correspondentes no seu arquivo `.env`. Além disso, talvez seja necessário fazer ajustes no próprio arquivo `docker-compose.yaml`, como alterar versões de imagem, mapeamentos de portas ou montagens de volumes, com base no seu ambiente de implantação específico e nas suas necessidades. Após fazer quaisquer alterações, execute novamente `docker-compose up -d`. Você pode encontrar a lista completa de variáveis de ambiente disponíveis [aqui](https://docs.dify.ai/getting-started/install-self-hosted/environments).
|
||||
|
||||
Se deseja configurar uma instalação de alta disponibilidade, há [Helm Charts](https://helm.sh/) e arquivos YAML contribuídos pela comunidade que permitem a implantação do Dify no Kubernetes.
|
||||
|
||||
- [Helm Chart de @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
|
||||
- [Helm Chart de @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
|
||||
- [Arquivo YAML de @Winson-030](https://github.com/Winson-030/dify-kubernetes)
|
||||
|
||||
#### Usando o Terraform para Implantação
|
||||
|
||||
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)
|
||||
|
||||
## Contribuindo
|
||||
|
||||
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/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).
|
||||
|
||||
**Contribuidores**
|
||||
|
||||
<a href="https://github.com/langgenius/dify/graphs/contributors">
|
||||
<img src="https://contrib.rocks/image?repo=langgenius/dify" />
|
||||
</a>
|
||||
|
||||
## 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.
|
||||
|
||||
## Histórico de estrelas
|
||||
|
||||
[](https://star-history.com/#langgenius/dify&Date)
|
||||
|
||||
## Divulgação de segurança
|
||||
|
||||
Para proteger sua privacidade, evite postar problemas de segurança no GitHub. Em vez disso, envie suas perguntas para security@dify.ai e forneceremos uma resposta mais detalhada.
|
||||
|
||||
## Licença
|
||||
|
||||
Este repositório está disponível sob a [Licença de Código Aberto Dify](LICENSE), que é essencialmente Apache 2.0 com algumas restrições adicionais.
|
||||
|
|
@ -120,7 +120,7 @@ SUPABASE_URL=your-server-url
|
|||
WEB_API_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
|
||||
CONSOLE_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
|
||||
|
||||
# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, vikingdb, upstash
|
||||
# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, couchbase, vikingdb, upstash
|
||||
VECTOR_STORE=weaviate
|
||||
|
||||
# Weaviate configuration
|
||||
|
|
@ -136,6 +136,13 @@ QDRANT_CLIENT_TIMEOUT=20
|
|||
QDRANT_GRPC_ENABLED=false
|
||||
QDRANT_GRPC_PORT=6334
|
||||
|
||||
#Couchbase configuration
|
||||
COUCHBASE_CONNECTION_STRING=127.0.0.1
|
||||
COUCHBASE_USER=Administrator
|
||||
COUCHBASE_PASSWORD=password
|
||||
COUCHBASE_BUCKET_NAME=Embeddings
|
||||
COUCHBASE_SCOPE_NAME=_default
|
||||
|
||||
# Milvus configuration
|
||||
MILVUS_URI=http://127.0.0.1:19530
|
||||
MILVUS_TOKEN=
|
||||
|
|
@ -195,6 +202,20 @@ TIDB_VECTOR_USER=xxx.root
|
|||
TIDB_VECTOR_PASSWORD=xxxxxx
|
||||
TIDB_VECTOR_DATABASE=dify
|
||||
|
||||
# Tidb on qdrant configuration
|
||||
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
|
||||
CHROMA_HOST=127.0.0.1
|
||||
CHROMA_PORT=8000
|
||||
|
|
@ -242,6 +263,14 @@ VIKINGDB_SCHEMA=http
|
|||
VIKINGDB_CONNECTION_TIMEOUT=30
|
||||
VIKINGDB_SOCKET_TIMEOUT=30
|
||||
|
||||
# OceanBase Vector configuration
|
||||
OCEANBASE_VECTOR_HOST=127.0.0.1
|
||||
OCEANBASE_VECTOR_PORT=2881
|
||||
OCEANBASE_VECTOR_USER=root@test
|
||||
OCEANBASE_VECTOR_PASSWORD=
|
||||
OCEANBASE_VECTOR_DATABASE=test
|
||||
OCEANBASE_MEMORY_LIMIT=6G
|
||||
|
||||
# Upload configuration
|
||||
UPLOAD_FILE_SIZE_LIMIT=15
|
||||
UPLOAD_FILE_BATCH_LIMIT=5
|
||||
|
|
|
|||
|
|
@ -278,6 +278,8 @@ def migrate_knowledge_vector_database():
|
|||
VectorType.BAIDU,
|
||||
VectorType.VIKINGDB,
|
||||
VectorType.UPSTASH,
|
||||
VectorType.COUCHBASE,
|
||||
VectorType.OCEANBASE,
|
||||
}
|
||||
page = 1
|
||||
while True:
|
||||
|
|
|
|||
|
|
@ -10,6 +10,7 @@ from pydantic import (
|
|||
PositiveInt,
|
||||
computed_field,
|
||||
)
|
||||
from pydantic_extra_types.timezone_name import TimeZoneName
|
||||
from pydantic_settings import BaseSettings
|
||||
|
||||
from configs.feature.hosted_service import HostedServiceConfig
|
||||
|
|
@ -339,8 +340,9 @@ class LoggingConfig(BaseSettings):
|
|||
default=None,
|
||||
)
|
||||
|
||||
LOG_TZ: Optional[str] = Field(
|
||||
description="Timezone for log timestamps (e.g., 'America/New_York')",
|
||||
LOG_TZ: Optional[TimeZoneName] = Field(
|
||||
description="Timezone for log timestamps. Allowed timezone values can be referred to IANA Time Zone Database,"
|
||||
" e.g., 'America/New_York')",
|
||||
default=None,
|
||||
)
|
||||
|
||||
|
|
|
|||
|
|
@ -17,9 +17,11 @@ from configs.middleware.storage.tencent_cos_storage_config import TencentCloudCO
|
|||
from configs.middleware.storage.volcengine_tos_storage_config import VolcengineTOSStorageConfig
|
||||
from configs.middleware.vdb.analyticdb_config import AnalyticdbConfig
|
||||
from configs.middleware.vdb.chroma_config import ChromaConfig
|
||||
from configs.middleware.vdb.couchbase_config import CouchbaseConfig
|
||||
from configs.middleware.vdb.elasticsearch_config import ElasticsearchConfig
|
||||
from configs.middleware.vdb.milvus_config import MilvusConfig
|
||||
from configs.middleware.vdb.myscale_config import MyScaleConfig
|
||||
from configs.middleware.vdb.oceanbase_config import OceanBaseVectorConfig
|
||||
from configs.middleware.vdb.opensearch_config import OpenSearchConfig
|
||||
from configs.middleware.vdb.oracle_config import OracleConfig
|
||||
from configs.middleware.vdb.pgvector_config import PGVectorConfig
|
||||
|
|
@ -251,9 +253,11 @@ class MiddlewareConfig(
|
|||
TiDBVectorConfig,
|
||||
WeaviateConfig,
|
||||
ElasticsearchConfig,
|
||||
CouchbaseConfig,
|
||||
InternalTestConfig,
|
||||
VikingDBConfig,
|
||||
UpstashConfig,
|
||||
TidbOnQdrantConfig,
|
||||
OceanBaseVectorConfig,
|
||||
):
|
||||
pass
|
||||
|
|
|
|||
|
|
@ -0,0 +1,34 @@
|
|||
from typing import Optional
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
class CouchbaseConfig(BaseModel):
|
||||
"""
|
||||
Couchbase configs
|
||||
"""
|
||||
|
||||
COUCHBASE_CONNECTION_STRING: Optional[str] = Field(
|
||||
description="COUCHBASE connection string",
|
||||
default=None,
|
||||
)
|
||||
|
||||
COUCHBASE_USER: Optional[str] = Field(
|
||||
description="COUCHBASE user",
|
||||
default=None,
|
||||
)
|
||||
|
||||
COUCHBASE_PASSWORD: Optional[str] = Field(
|
||||
description="COUCHBASE password",
|
||||
default=None,
|
||||
)
|
||||
|
||||
COUCHBASE_BUCKET_NAME: Optional[str] = Field(
|
||||
description="COUCHBASE bucket name",
|
||||
default=None,
|
||||
)
|
||||
|
||||
COUCHBASE_SCOPE_NAME: Optional[str] = Field(
|
||||
description="COUCHBASE scope name",
|
||||
default=None,
|
||||
)
|
||||
|
|
@ -0,0 +1,35 @@
|
|||
from typing import Optional
|
||||
|
||||
from pydantic import Field, PositiveInt
|
||||
from pydantic_settings import BaseSettings
|
||||
|
||||
|
||||
class OceanBaseVectorConfig(BaseSettings):
|
||||
"""
|
||||
Configuration settings for OceanBase Vector database
|
||||
"""
|
||||
|
||||
OCEANBASE_VECTOR_HOST: Optional[str] = Field(
|
||||
description="Hostname or IP address of the OceanBase Vector server (e.g. 'localhost')",
|
||||
default=None,
|
||||
)
|
||||
|
||||
OCEANBASE_VECTOR_PORT: Optional[PositiveInt] = Field(
|
||||
description="Port number on which the OceanBase Vector server is listening (default is 2881)",
|
||||
default=2881,
|
||||
)
|
||||
|
||||
OCEANBASE_VECTOR_USER: Optional[str] = Field(
|
||||
description="Username for authenticating with the OceanBase Vector database",
|
||||
default=None,
|
||||
)
|
||||
|
||||
OCEANBASE_VECTOR_PASSWORD: Optional[str] = Field(
|
||||
description="Password for authenticating with the OceanBase Vector database",
|
||||
default=None,
|
||||
)
|
||||
|
||||
OCEANBASE_VECTOR_DATABASE: Optional[str] = Field(
|
||||
description="Name of the OceanBase Vector database to connect to",
|
||||
default=None,
|
||||
)
|
||||
|
|
@ -63,3 +63,8 @@ class TidbOnQdrantConfig(BaseSettings):
|
|||
description="Tidb project id",
|
||||
default=None,
|
||||
)
|
||||
|
||||
TIDB_SPEND_LIMIT: Optional[int] = Field(
|
||||
description="Tidb spend limit",
|
||||
default=100,
|
||||
)
|
||||
|
|
|
|||
|
|
@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
|
|||
|
||||
CURRENT_VERSION: str = Field(
|
||||
description="Dify version",
|
||||
default="0.10.1",
|
||||
default="0.10.2",
|
||||
)
|
||||
|
||||
COMMIT_SHA: str = Field(
|
||||
|
|
|
|||
|
|
@ -628,6 +628,7 @@ class DatasetRetrievalSettingApi(Resource):
|
|||
| VectorType.BAIDU
|
||||
| VectorType.VIKINGDB
|
||||
| VectorType.UPSTASH
|
||||
| VectorType.OCEANBASE
|
||||
):
|
||||
return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
|
||||
case (
|
||||
|
|
@ -640,6 +641,7 @@ class DatasetRetrievalSettingApi(Resource):
|
|||
| VectorType.ELASTICSEARCH
|
||||
| VectorType.PGVECTOR
|
||||
| VectorType.TIDB_ON_QDRANT
|
||||
| VectorType.COUCHBASE
|
||||
):
|
||||
return {
|
||||
"retrieval_method": [
|
||||
|
|
@ -668,6 +670,7 @@ class DatasetRetrievalSettingMockApi(Resource):
|
|||
| VectorType.BAIDU
|
||||
| VectorType.VIKINGDB
|
||||
| VectorType.UPSTASH
|
||||
| VectorType.OCEANBASE
|
||||
):
|
||||
return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
|
||||
case (
|
||||
|
|
@ -678,6 +681,7 @@ class DatasetRetrievalSettingMockApi(Resource):
|
|||
| VectorType.MYSCALE
|
||||
| VectorType.ORACLE
|
||||
| VectorType.ELASTICSEARCH
|
||||
| VectorType.COUCHBASE
|
||||
| VectorType.PGVECTOR
|
||||
):
|
||||
return {
|
||||
|
|
|
|||
|
|
@ -230,7 +230,7 @@ class DocumentUpdateByFileApi(DatasetApiResource):
|
|||
except ProviderTokenNotInitError as ex:
|
||||
raise ProviderNotInitializeError(ex.description)
|
||||
document = documents[0]
|
||||
documents_and_batch_fields = {"document": marshal(document, document_fields), "batch": batch}
|
||||
documents_and_batch_fields = {"document": marshal(document, document_fields), "batch": document.batch}
|
||||
return documents_and_batch_fields, 200
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -165,6 +165,12 @@ class BaseAgentRunner(AppRunner):
|
|||
continue
|
||||
|
||||
parameter_type = parameter.type.as_normal_type()
|
||||
if parameter.type in {
|
||||
ToolParameter.ToolParameterType.SYSTEM_FILES,
|
||||
ToolParameter.ToolParameterType.FILE,
|
||||
ToolParameter.ToolParameterType.FILES,
|
||||
}:
|
||||
continue
|
||||
enum = []
|
||||
if parameter.type == ToolParameter.ToolParameterType.SELECT:
|
||||
enum = [option.value for option in parameter.options]
|
||||
|
|
@ -250,6 +256,12 @@ class BaseAgentRunner(AppRunner):
|
|||
continue
|
||||
|
||||
parameter_type = parameter.type.as_normal_type()
|
||||
if parameter.type in {
|
||||
ToolParameter.ToolParameterType.SYSTEM_FILES,
|
||||
ToolParameter.ToolParameterType.FILE,
|
||||
ToolParameter.ToolParameterType.FILES,
|
||||
}:
|
||||
continue
|
||||
enum = []
|
||||
if parameter.type == ToolParameter.ToolParameterType.SELECT:
|
||||
enum = [option.value for option in parameter.options]
|
||||
|
|
|
|||
|
|
@ -76,8 +76,16 @@ def to_prompt_message_content(f: File, /):
|
|||
|
||||
|
||||
def download(f: File, /):
|
||||
upload_file = file_repository.get_upload_file(session=db.session(), file=f)
|
||||
return _download_file_content(upload_file.key)
|
||||
if f.transfer_method == FileTransferMethod.TOOL_FILE:
|
||||
tool_file = file_repository.get_tool_file(session=db.session(), file=f)
|
||||
return _download_file_content(tool_file.file_key)
|
||||
elif f.transfer_method == FileTransferMethod.LOCAL_FILE:
|
||||
upload_file = file_repository.get_upload_file(session=db.session(), file=f)
|
||||
return _download_file_content(upload_file.key)
|
||||
# remote file
|
||||
response = ssrf_proxy.get(f.remote_url, follow_redirects=True)
|
||||
response.raise_for_status()
|
||||
return response.content
|
||||
|
||||
|
||||
def _download_file_content(path: str, /):
|
||||
|
|
|
|||
File diff suppressed because one or more lines are too long
|
After Width: | Height: | Size: 9.8 KiB |
|
|
@ -0,0 +1,3 @@
|
|||
<svg width="40" height="40" viewBox="0 0 40 40" fill="none" xmlns="http://www.w3.org/2000/svg">
|
||||
<path fill-rule="evenodd" clip-rule="evenodd" d="M25.132 24.3947C25.497 25.7527 25.8984 27.1413 26.3334 28.5834C26.7302 29.8992 25.5459 30.4167 25.0752 29.1758C24.571 27.8466 24.0885 26.523 23.6347 25.1729C21.065 26.4654 18.5025 27.5424 15.5961 28.7541C16.7581 33.0256 17.8309 36.5984 19.4952 39.9935C19.4953 39.9936 19.4953 39.9937 19.4954 39.9938C19.6631 39.9979 19.8313 40 20 40C31.0457 40 40 31.0457 40 20C40 16.0335 38.8453 12.3366 36.8537 9.22729C31.6585 9.69534 27.0513 10.4562 22.8185 11.406C22.8882 12.252 22.9677 13.0739 23.0555 13.855C23.3824 16.7604 23.9112 19.5281 24.6137 22.3836C27.0581 21.2848 29.084 20.3225 30.6816 19.522C32.2154 18.7535 33.6943 18.7062 31.2018 20.6594C29.0388 22.1602 27.0644 23.3566 25.132 24.3947ZM36.1559 8.20846C33.0001 3.89184 28.1561 0.887462 22.5955 0.166882C22.4257 2.86234 22.4785 6.26344 22.681 9.50447C26.7473 8.88859 31.1721 8.46032 36.1559 8.20846ZM19.9369 9.73661e-05C19.7594 2.92694 19.8384 6.65663 20.19 9.91293C17.3748 10.4109 14.7225 11.0064 12.1592 11.7038C12.0486 10.4257 11.9927 9.25764 11.9927 8.24178C11.9927 7.5054 11.3957 6.90844 10.6593 6.90844C9.92296 6.90844 9.32601 7.5054 9.32601 8.24178C9.32601 9.47868 9.42873 10.898 9.61402 12.438C8.33567 12.8278 7.07397 13.2443 5.81918 13.688C5.12493 13.9336 4.76118 14.6954 5.0067 15.3896C5.25223 16.0839 6.01406 16.4476 6.7083 16.2021C7.7931 15.8185 8.88482 15.4388 9.98927 15.0659C10.5222 18.3344 11.3344 21.9428 12.2703 25.4156C12.4336 26.0218 12.6062 26.6262 12.7863 27.2263C9.34168 28.4135 5.82612 29.3782 2.61128 29.8879C0.949407 26.9716 0 23.5967 0 20C0 8.97534 8.92023 0.0341108 19.9369 9.73661e-05ZM4.19152 32.2527C7.45069 36.4516 12.3458 39.3173 17.9204 39.8932C16.5916 37.455 14.9338 33.717 13.5405 29.5901C10.4404 30.7762 7.25883 31.6027 4.19152 32.2527ZM22.9735 23.1135C22.1479 20.41 21.4462 17.5441 20.9225 14.277C20.746 13.5841 20.5918 12.8035 20.4593 11.9636C17.6508 12.6606 14.9992 13.4372 12.4356 14.2598C12.8479 17.4766 13.5448 21.1334 14.5118 24.7218C14.662 25.2792 14.8081 25.8248 14.9514 26.3594L14.9516 26.3603L14.9524 26.3634L14.9526 26.3639L14.973 26.4401C16.1833 25.9872 17.3746 25.5123 18.53 25.0259C20.1235 24.3552 21.6051 23.7165 22.9735 23.1135Z" fill="#141519"/>
|
||||
</svg>
|
||||
|
After Width: | Height: | Size: 2.2 KiB |
|
|
@ -0,0 +1,47 @@
|
|||
from dashscope.common.error import (
|
||||
AuthenticationError,
|
||||
InvalidParameter,
|
||||
RequestFailure,
|
||||
ServiceUnavailableError,
|
||||
UnsupportedHTTPMethod,
|
||||
UnsupportedModel,
|
||||
)
|
||||
|
||||
from core.model_runtime.errors.invoke import (
|
||||
InvokeAuthorizationError,
|
||||
InvokeBadRequestError,
|
||||
InvokeConnectionError,
|
||||
InvokeError,
|
||||
InvokeRateLimitError,
|
||||
InvokeServerUnavailableError,
|
||||
)
|
||||
|
||||
|
||||
class _CommonGiteeAI:
|
||||
@property
|
||||
def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
|
||||
"""
|
||||
Map model invoke error to unified error
|
||||
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
|
||||
"""
|
||||
return {
|
||||
InvokeConnectionError: [
|
||||
RequestFailure,
|
||||
],
|
||||
InvokeServerUnavailableError: [
|
||||
ServiceUnavailableError,
|
||||
],
|
||||
InvokeRateLimitError: [],
|
||||
InvokeAuthorizationError: [
|
||||
AuthenticationError,
|
||||
],
|
||||
InvokeBadRequestError: [
|
||||
InvalidParameter,
|
||||
UnsupportedModel,
|
||||
UnsupportedHTTPMethod,
|
||||
],
|
||||
}
|
||||
|
|
@ -0,0 +1,25 @@
|
|||
import logging
|
||||
|
||||
from core.model_runtime.entities.model_entities import ModelType
|
||||
from core.model_runtime.errors.validate import CredentialsValidateFailedError
|
||||
from core.model_runtime.model_providers.__base.model_provider import ModelProvider
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class GiteeAIProvider(ModelProvider):
|
||||
def validate_provider_credentials(self, credentials: dict) -> None:
|
||||
"""
|
||||
Validate provider credentials
|
||||
if validate failed, raise exception
|
||||
|
||||
:param credentials: provider credentials, credentials form defined in `provider_credential_schema`.
|
||||
"""
|
||||
try:
|
||||
model_instance = self.get_model_instance(ModelType.LLM)
|
||||
model_instance.validate_credentials(model="Qwen2-7B-Instruct", credentials=credentials)
|
||||
except CredentialsValidateFailedError as ex:
|
||||
raise ex
|
||||
except Exception as ex:
|
||||
logger.exception(f"{self.get_provider_schema().provider} credentials validate failed")
|
||||
raise ex
|
||||
|
|
@ -0,0 +1,35 @@
|
|||
provider: gitee_ai
|
||||
label:
|
||||
en_US: Gitee AI
|
||||
zh_Hans: Gitee AI
|
||||
description:
|
||||
en_US: 快速体验大模型，领先探索 AI 开源世界
|
||||
zh_Hans: 快速体验大模型，领先探索 AI 开源世界
|
||||
icon_small:
|
||||
en_US: Gitee-AI-Logo.svg
|
||||
icon_large:
|
||||
en_US: Gitee-AI-Logo-full.svg
|
||||
help:
|
||||
title:
|
||||
en_US: Get your token from Gitee AI
|
||||
zh_Hans: 从 Gitee AI 获取 token
|
||||
url:
|
||||
en_US: https://ai.gitee.com/dashboard/settings/tokens
|
||||
supported_model_types:
|
||||
- llm
|
||||
- text-embedding
|
||||
- rerank
|
||||
- speech2text
|
||||
- tts
|
||||
configurate_methods:
|
||||
- predefined-model
|
||||
provider_credential_schema:
|
||||
credential_form_schemas:
|
||||
- variable: api_key
|
||||
label:
|
||||
en_US: API Key
|
||||
type: secret-input
|
||||
required: true
|
||||
placeholder:
|
||||
zh_Hans: 在此输入您的 API Key
|
||||
en_US: Enter your API Key
|
||||
|
|
@ -0,0 +1,105 @@
|
|||
model: Qwen2-72B-Instruct
|
||||
label:
|
||||
zh_Hans: Qwen2-72B-Instruct
|
||||
en_US: Qwen2-72B-Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 6400
|
||||
parameter_rules:
|
||||
- name: stream
|
||||
use_template: boolean
|
||||
label:
|
||||
en_US: "Stream"
|
||||
zh_Hans: "流式"
|
||||
type: boolean
|
||||
default: true
|
||||
required: true
|
||||
help:
|
||||
en_US: "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process."
|
||||
zh_Hans: "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
|
||||
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
label:
|
||||
en_US: "Max Tokens"
|
||||
zh_Hans: "最大Token数"
|
||||
type: int
|
||||
default: 512
|
||||
min: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The maximum number of tokens that can be generated by the model varies depending on the model."
|
||||
zh_Hans: "模型可生成的最大 token 个数，不同模型上限不同。"
|
||||
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
label:
|
||||
en_US: "Temperature"
|
||||
zh_Hans: "采样温度"
|
||||
type: float
|
||||
default: 0.7
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
|
||||
zh_Hans: "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
|
||||
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
label:
|
||||
en_US: "Top P"
|
||||
zh_Hans: "Top P"
|
||||
type: float
|
||||
default: 0.7
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
|
||||
zh_Hans: "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
|
||||
|
||||
- name: top_k
|
||||
use_template: top_k
|
||||
label:
|
||||
en_US: "Top K"
|
||||
zh_Hans: "Top K"
|
||||
type: int
|
||||
default: 50
|
||||
min: 0
|
||||
max: 100
|
||||
required: true
|
||||
help:
|
||||
en_US: "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be."
|
||||
zh_Hans: "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
|
||||
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
label:
|
||||
en_US: "Frequency Penalty"
|
||||
zh_Hans: "频率惩罚"
|
||||
type: float
|
||||
default: 0
|
||||
min: -1.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: false
|
||||
help:
|
||||
en_US: "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation."
|
||||
zh_Hans: "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
|
||||
|
||||
- name: user
|
||||
use_template: text
|
||||
label:
|
||||
en_US: "User"
|
||||
zh_Hans: "用户"
|
||||
type: string
|
||||
required: false
|
||||
help:
|
||||
en_US: "Used to track and differentiate conversation requests from different users."
|
||||
zh_Hans: "用于追踪和区分不同用户的对话请求。"
|
||||
|
|
@ -0,0 +1,105 @@
|
|||
model: Qwen2-7B-Instruct
|
||||
label:
|
||||
zh_Hans: Qwen2-7B-Instruct
|
||||
en_US: Qwen2-7B-Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32768
|
||||
parameter_rules:
|
||||
- name: stream
|
||||
use_template: boolean
|
||||
label:
|
||||
en_US: "Stream"
|
||||
zh_Hans: "流式"
|
||||
type: boolean
|
||||
default: true
|
||||
required: true
|
||||
help:
|
||||
en_US: "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process."
|
||||
zh_Hans: "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
|
||||
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
label:
|
||||
en_US: "Max Tokens"
|
||||
zh_Hans: "最大Token数"
|
||||
type: int
|
||||
default: 512
|
||||
min: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The maximum number of tokens that can be generated by the model varies depending on the model."
|
||||
zh_Hans: "模型可生成的最大 token 个数，不同模型上限不同。"
|
||||
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
label:
|
||||
en_US: "Temperature"
|
||||
zh_Hans: "采样温度"
|
||||
type: float
|
||||
default: 0.7
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
|
||||
zh_Hans: "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
|
||||
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
label:
|
||||
en_US: "Top P"
|
||||
zh_Hans: "Top P"
|
||||
type: float
|
||||
default: 0.7
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
|
||||
zh_Hans: "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
|
||||
|
||||
- name: top_k
|
||||
use_template: top_k
|
||||
label:
|
||||
en_US: "Top K"
|
||||
zh_Hans: "Top K"
|
||||
type: int
|
||||
default: 50
|
||||
min: 0
|
||||
max: 100
|
||||
required: true
|
||||
help:
|
||||
en_US: "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be."
|
||||
zh_Hans: "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
|
||||
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
label:
|
||||
en_US: "Frequency Penalty"
|
||||
zh_Hans: "频率惩罚"
|
||||
type: float
|
||||
default: 0
|
||||
min: -1.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: false
|
||||
help:
|
||||
en_US: "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation."
|
||||
zh_Hans: "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
|
||||
|
||||
- name: user
|
||||
use_template: text
|
||||
label:
|
||||
en_US: "User"
|
||||
zh_Hans: "用户"
|
||||
type: string
|
||||
required: false
|
||||
help:
|
||||
en_US: "Used to track and differentiate conversation requests from different users."
|
||||
zh_Hans: "用于追踪和区分不同用户的对话请求。"
|
||||
|
|
@ -0,0 +1,105 @@
|
|||
model: Yi-1.5-34B-Chat
|
||||
label:
|
||||
zh_Hans: Yi-1.5-34B-Chat
|
||||
en_US: Yi-1.5-34B-Chat
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 4096
|
||||
parameter_rules:
|
||||
- name: stream
|
||||
use_template: boolean
|
||||
label:
|
||||
en_US: "Stream"
|
||||
zh_Hans: "流式"
|
||||
type: boolean
|
||||
default: true
|
||||
required: true
|
||||
help:
|
||||
en_US: "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process."
|
||||
zh_Hans: "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
|
||||
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
label:
|
||||
en_US: "Max Tokens"
|
||||
zh_Hans: "最大Token数"
|
||||
type: int
|
||||
default: 512
|
||||
min: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The maximum number of tokens that can be generated by the model varies depending on the model."
|
||||
zh_Hans: "模型可生成的最大 token 个数，不同模型上限不同。"
|
||||
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
label:
|
||||
en_US: "Temperature"
|
||||
zh_Hans: "采样温度"
|
||||
type: float
|
||||
default: 0.7
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
|
||||
zh_Hans: "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
|
||||
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
label:
|
||||
en_US: "Top P"
|
||||
zh_Hans: "Top P"
|
||||
type: float
|
||||
default: 0.7
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
|
||||
zh_Hans: "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
|
||||
|
||||
- name: top_k
|
||||
use_template: top_k
|
||||
label:
|
||||
en_US: "Top K"
|
||||
zh_Hans: "Top K"
|
||||
type: int
|
||||
default: 50
|
||||
min: 0
|
||||
max: 100
|
||||
required: true
|
||||
help:
|
||||
en_US: "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be."
|
||||
zh_Hans: "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
|
||||
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
label:
|
||||
en_US: "Frequency Penalty"
|
||||
zh_Hans: "频率惩罚"
|
||||
type: float
|
||||
default: 0
|
||||
min: -1.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: false
|
||||
help:
|
||||
en_US: "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation."
|
||||
zh_Hans: "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
|
||||
|
||||
- name: user
|
||||
use_template: text
|
||||
label:
|
||||
en_US: "User"
|
||||
zh_Hans: "用户"
|
||||
type: string
|
||||
required: false
|
||||
help:
|
||||
en_US: "Used to track and differentiate conversation requests from different users."
|
||||
zh_Hans: "用于追踪和区分不同用户的对话请求。"
|
||||
|
|
@ -0,0 +1,7 @@
|
|||
- Qwen2-7B-Instruct
|
||||
- Qwen2-72B-Instruct
|
||||
- Yi-1.5-34B-Chat
|
||||
- glm-4-9b-chat
|
||||
- deepseek-coder-33B-instruct-chat
|
||||
- deepseek-coder-33B-instruct-completions
|
||||
- codegeex4-all-9b
|
||||
|
|
@ -0,0 +1,105 @@
|
|||
model: codegeex4-all-9b
|
||||
label:
|
||||
zh_Hans: codegeex4-all-9b
|
||||
en_US: codegeex4-all-9b
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 40960
|
||||
parameter_rules:
|
||||
- name: stream
|
||||
use_template: boolean
|
||||
label:
|
||||
en_US: "Stream"
|
||||
zh_Hans: "流式"
|
||||
type: boolean
|
||||
default: true
|
||||
required: true
|
||||
help:
|
||||
en_US: "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process."
|
||||
zh_Hans: "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
|
||||
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
label:
|
||||
en_US: "Max Tokens"
|
||||
zh_Hans: "最大Token数"
|
||||
type: int
|
||||
default: 512
|
||||
min: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The maximum number of tokens that can be generated by the model varies depending on the model."
|
||||
zh_Hans: "模型可生成的最大 token 个数，不同模型上限不同。"
|
||||
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
label:
|
||||
en_US: "Temperature"
|
||||
zh_Hans: "采样温度"
|
||||
type: float
|
||||
default: 0.7
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
|
||||
zh_Hans: "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
|
||||
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
label:
|
||||
en_US: "Top P"
|
||||
zh_Hans: "Top P"
|
||||
type: float
|
||||
default: 0.7
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
|
||||
zh_Hans: "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
|
||||
|
||||
- name: top_k
|
||||
use_template: top_k
|
||||
label:
|
||||
en_US: "Top K"
|
||||
zh_Hans: "Top K"
|
||||
type: int
|
||||
default: 50
|
||||
min: 0
|
||||
max: 100
|
||||
required: true
|
||||
help:
|
||||
en_US: "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be."
|
||||
zh_Hans: "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
|
||||
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
label:
|
||||
en_US: "Frequency Penalty"
|
||||
zh_Hans: "频率惩罚"
|
||||
type: float
|
||||
default: 0
|
||||
min: -1.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: false
|
||||
help:
|
||||
en_US: "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation."
|
||||
zh_Hans: "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
|
||||
|
||||
- name: user
|
||||
use_template: text
|
||||
label:
|
||||
en_US: "User"
|
||||
zh_Hans: "用户"
|
||||
type: string
|
||||
required: false
|
||||
help:
|
||||
en_US: "Used to track and differentiate conversation requests from different users."
|
||||
zh_Hans: "用于追踪和区分不同用户的对话请求。"
|
||||
|
|
@ -0,0 +1,105 @@
|
|||
model: deepseek-coder-33B-instruct-chat
|
||||
label:
|
||||
zh_Hans: deepseek-coder-33B-instruct-chat
|
||||
en_US: deepseek-coder-33B-instruct-chat
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 9000
|
||||
parameter_rules:
|
||||
- name: stream
|
||||
use_template: boolean
|
||||
label:
|
||||
en_US: "Stream"
|
||||
zh_Hans: "流式"
|
||||
type: boolean
|
||||
default: true
|
||||
required: true
|
||||
help:
|
||||
en_US: "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process."
|
||||
zh_Hans: "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
|
||||
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
label:
|
||||
en_US: "Max Tokens"
|
||||
zh_Hans: "最大Token数"
|
||||
type: int
|
||||
default: 512
|
||||
min: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The maximum number of tokens that can be generated by the model varies depending on the model."
|
||||
zh_Hans: "模型可生成的最大 token 个数，不同模型上限不同。"
|
||||
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
label:
|
||||
en_US: "Temperature"
|
||||
zh_Hans: "采样温度"
|
||||
type: float
|
||||
default: 0.7
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
|
||||
zh_Hans: "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
|
||||
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
label:
|
||||
en_US: "Top P"
|
||||
zh_Hans: "Top P"
|
||||
type: float
|
||||
default: 0.7
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
|
||||
zh_Hans: "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
|
||||
|
||||
- name: top_k
|
||||
use_template: top_k
|
||||
label:
|
||||
en_US: "Top K"
|
||||
zh_Hans: "Top K"
|
||||
type: int
|
||||
default: 50
|
||||
min: 0
|
||||
max: 100
|
||||
required: true
|
||||
help:
|
||||
en_US: "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be."
|
||||
zh_Hans: "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
|
||||
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
label:
|
||||
en_US: "Frequency Penalty"
|
||||
zh_Hans: "频率惩罚"
|
||||
type: float
|
||||
default: 0
|
||||
min: -1.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: false
|
||||
help:
|
||||
en_US: "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation."
|
||||
zh_Hans: "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
|
||||
|
||||
- name: user
|
||||
use_template: text
|
||||
label:
|
||||
en_US: "User"
|
||||
zh_Hans: "用户"
|
||||
type: string
|
||||
required: false
|
||||
help:
|
||||
en_US: "Used to track and differentiate conversation requests from different users."
|
||||
zh_Hans: "用于追踪和区分不同用户的对话请求。"
|
||||
|
|
@ -0,0 +1,91 @@
|
|||
model: deepseek-coder-33B-instruct-completions
|
||||
label:
|
||||
zh_Hans: deepseek-coder-33B-instruct-completions
|
||||
en_US: deepseek-coder-33B-instruct-completions
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 9000
|
||||
parameter_rules:
|
||||
- name: stream
|
||||
use_template: boolean
|
||||
label:
|
||||
en_US: "Stream"
|
||||
zh_Hans: "流式"
|
||||
type: boolean
|
||||
default: true
|
||||
required: true
|
||||
help:
|
||||
en_US: "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process."
|
||||
zh_Hans: "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
|
||||
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
label:
|
||||
en_US: "Max Tokens"
|
||||
zh_Hans: "最大Token数"
|
||||
type: int
|
||||
default: 512
|
||||
min: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The maximum number of tokens that can be generated by the model varies depending on the model."
|
||||
zh_Hans: "模型可生成的最大 token 个数，不同模型上限不同。"
|
||||
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
label:
|
||||
en_US: "Temperature"
|
||||
zh_Hans: "采样温度"
|
||||
type: float
|
||||
default: 0.7
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
|
||||
zh_Hans: "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
|
||||
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
label:
|
||||
en_US: "Top P"
|
||||
zh_Hans: "Top P"
|
||||
type: float
|
||||
default: 0.7
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
|
||||
zh_Hans: "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
|
||||
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
label:
|
||||
en_US: "Frequency Penalty"
|
||||
zh_Hans: "频率惩罚"
|
||||
type: float
|
||||
default: 0
|
||||
min: -1.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: false
|
||||
help:
|
||||
en_US: "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation."
|
||||
zh_Hans: "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
|
||||
|
||||
- name: user
|
||||
use_template: text
|
||||
label:
|
||||
en_US: "User"
|
||||
zh_Hans: "用户"
|
||||
type: string
|
||||
required: false
|
||||
help:
|
||||
en_US: "Used to track and differentiate conversation requests from different users."
|
||||
zh_Hans: "用于追踪和区分不同用户的对话请求。"
|
||||
|
|
@ -0,0 +1,105 @@
|
|||
model: glm-4-9b-chat
|
||||
label:
|
||||
zh_Hans: glm-4-9b-chat
|
||||
en_US: glm-4-9b-chat
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32768
|
||||
parameter_rules:
|
||||
- name: stream
|
||||
use_template: boolean
|
||||
label:
|
||||
en_US: "Stream"
|
||||
zh_Hans: "流式"
|
||||
type: boolean
|
||||
default: true
|
||||
required: true
|
||||
help:
|
||||
en_US: "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process."
|
||||
zh_Hans: "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
|
||||
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
label:
|
||||
en_US: "Max Tokens"
|
||||
zh_Hans: "最大Token数"
|
||||
type: int
|
||||
default: 512
|
||||
min: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The maximum number of tokens that can be generated by the model varies depending on the model."
|
||||
zh_Hans: "模型可生成的最大 token 个数，不同模型上限不同。"
|
||||
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
label:
|
||||
en_US: "Temperature"
|
||||
zh_Hans: "采样温度"
|
||||
type: float
|
||||
default: 0.7
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
|
||||
zh_Hans: "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
|
||||
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
label:
|
||||
en_US: "Top P"
|
||||
zh_Hans: "Top P"
|
||||
type: float
|
||||
default: 0.7
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
|
||||
zh_Hans: "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
|
||||
|
||||
- name: top_k
|
||||
use_template: top_k
|
||||
label:
|
||||
en_US: "Top K"
|
||||
zh_Hans: "Top K"
|
||||
type: int
|
||||
default: 50
|
||||
min: 0
|
||||
max: 100
|
||||
required: true
|
||||
help:
|
||||
en_US: "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be."
|
||||
zh_Hans: "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
|
||||
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
label:
|
||||
en_US: "Frequency Penalty"
|
||||
zh_Hans: "频率惩罚"
|
||||
type: float
|
||||
default: 0
|
||||
min: -1.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: false
|
||||
help:
|
||||
en_US: "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation."
|
||||
zh_Hans: "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
|
||||
|
||||
- name: user
|
||||
use_template: text
|
||||
label:
|
||||
en_US: "User"
|
||||
zh_Hans: "用户"
|
||||
type: string
|
||||
required: false
|
||||
help:
|
||||
en_US: "Used to track and differentiate conversation requests from different users."
|
||||
zh_Hans: "用于追踪和区分不同用户的对话请求。"
|
||||
|
|
@ -0,0 +1,47 @@
|
|||
from collections.abc import Generator
|
||||
from typing import Optional, Union
|
||||
|
||||
from core.model_runtime.entities.llm_entities import LLMMode, LLMResult
|
||||
from core.model_runtime.entities.message_entities import (
|
||||
PromptMessage,
|
||||
PromptMessageTool,
|
||||
)
|
||||
from core.model_runtime.model_providers.openai_api_compatible.llm.llm import OAIAPICompatLargeLanguageModel
|
||||
|
||||
|
||||
class GiteeAILargeLanguageModel(OAIAPICompatLargeLanguageModel):
|
||||
MODEL_TO_IDENTITY: dict[str, str] = {
|
||||
"Yi-1.5-34B-Chat": "Yi-34B-Chat",
|
||||
"deepseek-coder-33B-instruct-completions": "deepseek-coder-33B-instruct",
|
||||
"deepseek-coder-33B-instruct-chat": "deepseek-coder-33B-instruct",
|
||||
}
|
||||
|
||||
def _invoke(
|
||||
self,
|
||||
model: str,
|
||||
credentials: dict,
|
||||
prompt_messages: list[PromptMessage],
|
||||
model_parameters: dict,
|
||||
tools: Optional[list[PromptMessageTool]] = None,
|
||||
stop: Optional[list[str]] = None,
|
||||
stream: bool = True,
|
||||
user: Optional[str] = None,
|
||||
) -> Union[LLMResult, Generator]:
|
||||
self._add_custom_parameters(credentials, model, model_parameters)
|
||||
return super()._invoke(model, credentials, prompt_messages, model_parameters, tools, stop, stream)
|
||||
|
||||
def validate_credentials(self, model: str, credentials: dict) -> None:
|
||||
self._add_custom_parameters(credentials, model, None)
|
||||
super().validate_credentials(model, credentials)
|
||||
|
||||
@staticmethod
|
||||
def _add_custom_parameters(credentials: dict, model: str, model_parameters: dict) -> None:
|
||||
if model is None:
|
||||
model = "bge-large-zh-v1.5"
|
||||
|
||||
model_identity = GiteeAILargeLanguageModel.MODEL_TO_IDENTITY.get(model, model)
|
||||
credentials["endpoint_url"] = f"https://ai.gitee.com/api/serverless/{model_identity}/"
|
||||
if model.endswith("completions"):
|
||||
credentials["mode"] = LLMMode.COMPLETION.value
|
||||
else:
|
||||
credentials["mode"] = LLMMode.CHAT.value
|
||||
|
|
@ -0,0 +1 @@
|
|||
- bge-reranker-v2-m3
|
||||
|
|
@ -0,0 +1,4 @@
|
|||
model: bge-reranker-v2-m3
|
||||
model_type: rerank
|
||||
model_properties:
|
||||
context_size: 1024
|
||||
|
|
@ -0,0 +1,128 @@
|
|||
from typing import Optional
|
||||
|
||||
import httpx
|
||||
|
||||
from core.model_runtime.entities.common_entities import I18nObject
|
||||
from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType
|
||||
from core.model_runtime.entities.rerank_entities import RerankDocument, RerankResult
|
||||
from core.model_runtime.errors.invoke import (
|
||||
InvokeAuthorizationError,
|
||||
InvokeBadRequestError,
|
||||
InvokeConnectionError,
|
||||
InvokeError,
|
||||
InvokeRateLimitError,
|
||||
InvokeServerUnavailableError,
|
||||
)
|
||||
from core.model_runtime.errors.validate import CredentialsValidateFailedError
|
||||
from core.model_runtime.model_providers.__base.rerank_model import RerankModel
|
||||
|
||||
|
||||
class GiteeAIRerankModel(RerankModel):
|
||||
"""
|
||||
Model class for rerank model.
|
||||
"""
|
||||
|
||||
def _invoke(
|
||||
self,
|
||||
model: str,
|
||||
credentials: dict,
|
||||
query: str,
|
||||
docs: list[str],
|
||||
score_threshold: Optional[float] = None,
|
||||
top_n: Optional[int] = None,
|
||||
user: Optional[str] = None,
|
||||
) -> RerankResult:
|
||||
"""
|
||||
Invoke rerank model
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:param query: search query
|
||||
:param docs: docs for reranking
|
||||
:param score_threshold: score threshold
|
||||
:param top_n: top n documents to return
|
||||
:param user: unique user id
|
||||
:return: rerank result
|
||||
"""
|
||||
if len(docs) == 0:
|
||||
return RerankResult(model=model, docs=[])
|
||||
|
||||
base_url = credentials.get("base_url", "https://ai.gitee.com/api/serverless")
|
||||
base_url = base_url.removesuffix("/")
|
||||
|
||||
try:
|
||||
body = {"model": model, "query": query, "documents": docs}
|
||||
if top_n is not None:
|
||||
body["top_n"] = top_n
|
||||
response = httpx.post(
|
||||
f"{base_url}/{model}/rerank",
|
||||
json=body,
|
||||
headers={"Authorization": f"Bearer {credentials.get('api_key')}"},
|
||||
)
|
||||
|
||||
response.raise_for_status()
|
||||
results = response.json()
|
||||
|
||||
rerank_documents = []
|
||||
for result in results["results"]:
|
||||
rerank_document = RerankDocument(
|
||||
index=result["index"],
|
||||
text=result["document"]["text"],
|
||||
score=result["relevance_score"],
|
||||
)
|
||||
if score_threshold is None or result["relevance_score"] >= score_threshold:
|
||||
rerank_documents.append(rerank_document)
|
||||
return RerankResult(model=model, docs=rerank_documents)
|
||||
except httpx.HTTPStatusError as e:
|
||||
raise InvokeServerUnavailableError(str(e))
|
||||
|
||||
def validate_credentials(self, model: str, credentials: dict) -> None:
|
||||
"""
|
||||
Validate model credentials
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:return:
|
||||
"""
|
||||
try:
|
||||
self._invoke(
|
||||
model=model,
|
||||
credentials=credentials,
|
||||
query="What is the capital of the United States?",
|
||||
docs=[
|
||||
"Carson City is the capital city of the American state of Nevada. At the 2010 United States "
|
||||
"Census, Carson City had a population of 55,274.",
|
||||
"The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean that "
|
||||
"are a political division controlled by the United States. Its capital is Saipan.",
|
||||
],
|
||||
score_threshold=0.01,
|
||||
)
|
||||
except Exception as ex:
|
||||
raise CredentialsValidateFailedError(str(ex))
|
||||
|
||||
@property
|
||||
def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
|
||||
"""
|
||||
Map model invoke error to unified error
|
||||
"""
|
||||
return {
|
||||
InvokeConnectionError: [httpx.ConnectError],
|
||||
InvokeServerUnavailableError: [httpx.RemoteProtocolError],
|
||||
InvokeRateLimitError: [],
|
||||
InvokeAuthorizationError: [httpx.HTTPStatusError],
|
||||
InvokeBadRequestError: [httpx.RequestError],
|
||||
}
|
||||
|
||||
def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity:
|
||||
"""
|
||||
generate custom model entities from credentials
|
||||
"""
|
||||
entity = AIModelEntity(
|
||||
model=model,
|
||||
label=I18nObject(en_US=model),
|
||||
model_type=ModelType.RERANK,
|
||||
fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
|
||||
model_properties={ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size"))},
|
||||
)
|
||||
|
||||
return entity
|
||||
|
|
@ -0,0 +1,2 @@
|
|||
- whisper-base
|
||||
- whisper-large
|
||||
|
|
@ -0,0 +1,53 @@
|
|||
import os
|
||||
from typing import IO, Optional
|
||||
|
||||
import requests
|
||||
|
||||
from core.model_runtime.errors.invoke import InvokeBadRequestError
|
||||
from core.model_runtime.errors.validate import CredentialsValidateFailedError
|
||||
from core.model_runtime.model_providers.__base.speech2text_model import Speech2TextModel
|
||||
from core.model_runtime.model_providers.gitee_ai._common import _CommonGiteeAI
|
||||
|
||||
|
||||
class GiteeAISpeech2TextModel(_CommonGiteeAI, Speech2TextModel):
|
||||
"""
|
||||
Model class for OpenAI Compatible Speech to text model.
|
||||
"""
|
||||
|
||||
def _invoke(self, model: str, credentials: dict, file: IO[bytes], user: Optional[str] = None) -> str:
|
||||
"""
|
||||
Invoke speech2text model
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:param file: audio file
|
||||
:param user: unique user id
|
||||
:return: text for given audio file
|
||||
"""
|
||||
# doc: https://ai.gitee.com/docs/openapi/serverless#tag/serverless/POST/{service}/speech-to-text
|
||||
|
||||
endpoint_url = f"https://ai.gitee.com/api/serverless/{model}/speech-to-text"
|
||||
files = [("file", file)]
|
||||
_, file_ext = os.path.splitext(file.name)
|
||||
headers = {"Content-Type": f"audio/{file_ext}", "Authorization": f"Bearer {credentials.get('api_key')}"}
|
||||
response = requests.post(endpoint_url, headers=headers, files=files)
|
||||
if response.status_code != 200:
|
||||
raise InvokeBadRequestError(response.text)
|
||||
response_data = response.json()
|
||||
return response_data["text"]
|
||||
|
||||
def validate_credentials(self, model: str, credentials: dict) -> None:
|
||||
"""
|
||||
Validate model credentials
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:return:
|
||||
"""
|
||||
try:
|
||||
audio_file_path = self._get_demo_file_path()
|
||||
|
||||
with open(audio_file_path, "rb") as audio_file:
|
||||
self._invoke(model, credentials, audio_file)
|
||||
except Exception as ex:
|
||||
raise CredentialsValidateFailedError(str(ex))
|
||||
|
|
@ -0,0 +1,5 @@
|
|||
model: whisper-base
|
||||
model_type: speech2text
|
||||
model_properties:
|
||||
file_upload_limit: 1
|
||||
supported_file_extensions: flac,mp3,mp4,mpeg,mpga,m4a,ogg,wav,webm
|
||||
|
|
@ -0,0 +1,5 @@
|
|||
model: whisper-large
|
||||
model_type: speech2text
|
||||
model_properties:
|
||||
file_upload_limit: 1
|
||||
supported_file_extensions: flac,mp3,mp4,mpeg,mpga,m4a,ogg,wav,webm
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
- bge-large-zh-v1.5
|
||||
- bge-small-zh-v1.5
|
||||
- bge-m3
|
||||
|
|
@ -0,0 +1,8 @@
|
|||
model: bge-large-zh-v1.5
|
||||
label:
|
||||
zh_Hans: bge-large-zh-v1.5
|
||||
en_US: bge-large-zh-v1.5
|
||||
model_type: text-embedding
|
||||
model_properties:
|
||||
context_size: 200000
|
||||
max_chunks: 20
|
||||
|
|
@ -0,0 +1,8 @@
|
|||
model: bge-m3
|
||||
label:
|
||||
zh_Hans: bge-m3
|
||||
en_US: bge-m3
|
||||
model_type: text-embedding
|
||||
model_properties:
|
||||
context_size: 200000
|
||||
max_chunks: 20
|
||||
|
|
@ -0,0 +1,8 @@
|
|||
model: bge-small-zh-v1.5
|
||||
label:
|
||||
zh_Hans: bge-small-zh-v1.5
|
||||
en_US: bge-small-zh-v1.5
|
||||
model_type: text-embedding
|
||||
model_properties:
|
||||
context_size: 200000
|
||||
max_chunks: 20
|
||||
|
|
@ -0,0 +1,31 @@
|
|||
from typing import Optional
|
||||
|
||||
from core.entities.embedding_type import EmbeddingInputType
|
||||
from core.model_runtime.entities.text_embedding_entities import TextEmbeddingResult
|
||||
from core.model_runtime.model_providers.openai_api_compatible.text_embedding.text_embedding import (
|
||||
OAICompatEmbeddingModel,
|
||||
)
|
||||
|
||||
|
||||
class GiteeAIEmbeddingModel(OAICompatEmbeddingModel):
|
||||
def _invoke(
|
||||
self,
|
||||
model: str,
|
||||
credentials: dict,
|
||||
texts: list[str],
|
||||
user: Optional[str] = None,
|
||||
input_type: EmbeddingInputType = EmbeddingInputType.DOCUMENT,
|
||||
) -> TextEmbeddingResult:
|
||||
self._add_custom_parameters(credentials, model)
|
||||
return super()._invoke(model, credentials, texts, user, input_type)
|
||||
|
||||
def validate_credentials(self, model: str, credentials: dict) -> None:
|
||||
self._add_custom_parameters(credentials, None)
|
||||
super().validate_credentials(model, credentials)
|
||||
|
||||
@staticmethod
|
||||
def _add_custom_parameters(credentials: dict, model: str) -> None:
|
||||
if model is None:
|
||||
model = "bge-m3"
|
||||
|
||||
credentials["endpoint_url"] = f"https://ai.gitee.com/api/serverless/{model}/v1/"
|
||||
|
|
@ -0,0 +1,11 @@
|
|||
model: ChatTTS
|
||||
model_type: tts
|
||||
model_properties:
|
||||
default_voice: 'default'
|
||||
voices:
|
||||
- mode: 'default'
|
||||
name: 'Default'
|
||||
language: [ 'zh-Hans', 'en-US', 'de-DE', 'fr-FR', 'es-ES', 'it-IT', 'th-TH', 'id-ID' ]
|
||||
word_limit: 3500
|
||||
audio_type: 'mp3'
|
||||
max_workers: 5
|
||||
|
|
@ -0,0 +1,11 @@
|
|||
model: FunAudioLLM-CosyVoice-300M
|
||||
model_type: tts
|
||||
model_properties:
|
||||
default_voice: 'default'
|
||||
voices:
|
||||
- mode: 'default'
|
||||
name: 'Default'
|
||||
language: [ 'zh-Hans', 'en-US', 'de-DE', 'fr-FR', 'es-ES', 'it-IT', 'th-TH', 'id-ID' ]
|
||||
word_limit: 3500
|
||||
audio_type: 'mp3'
|
||||
max_workers: 5
|
||||
|
|
@ -0,0 +1,4 @@
|
|||
- speecht5_tts
|
||||
- ChatTTS
|
||||
- fish-speech-1.2-sft
|
||||
- FunAudioLLM-CosyVoice-300M
|
||||
|
|
@ -0,0 +1,11 @@
|
|||
model: fish-speech-1.2-sft
|
||||
model_type: tts
|
||||
model_properties:
|
||||
default_voice: 'default'
|
||||
voices:
|
||||
- mode: 'default'
|
||||
name: 'Default'
|
||||
language: [ 'zh-Hans', 'en-US', 'de-DE', 'fr-FR', 'es-ES', 'it-IT', 'th-TH', 'id-ID' ]
|
||||
word_limit: 3500
|
||||
audio_type: 'mp3'
|
||||
max_workers: 5
|
||||
|
|
@ -0,0 +1,11 @@
|
|||
model: speecht5_tts
|
||||
model_type: tts
|
||||
model_properties:
|
||||
default_voice: 'default'
|
||||
voices:
|
||||
- mode: 'default'
|
||||
name: 'Default'
|
||||
language: [ 'zh-Hans', 'en-US', 'de-DE', 'fr-FR', 'es-ES', 'it-IT', 'th-TH', 'id-ID' ]
|
||||
word_limit: 3500
|
||||
audio_type: 'mp3'
|
||||
max_workers: 5
|
||||
|
|
@ -0,0 +1,79 @@
|
|||
from typing import Optional
|
||||
|
||||
import requests
|
||||
|
||||
from core.model_runtime.errors.invoke import InvokeBadRequestError
|
||||
from core.model_runtime.errors.validate import CredentialsValidateFailedError
|
||||
from core.model_runtime.model_providers.__base.tts_model import TTSModel
|
||||
from core.model_runtime.model_providers.gitee_ai._common import _CommonGiteeAI
|
||||
|
||||
|
||||
class GiteeAIText2SpeechModel(_CommonGiteeAI, TTSModel):
|
||||
"""
|
||||
Model class for OpenAI Speech to text model.
|
||||
"""
|
||||
|
||||
def _invoke(
|
||||
self, model: str, tenant_id: str, credentials: dict, content_text: str, voice: str, user: Optional[str] = None
|
||||
) -> any:
|
||||
"""
|
||||
_invoke text2speech model
|
||||
|
||||
:param model: model name
|
||||
:param tenant_id: user tenant id
|
||||
:param credentials: model credentials
|
||||
:param content_text: text content to be translated
|
||||
:param voice: model timbre
|
||||
:param user: unique user id
|
||||
:return: text translated to audio file
|
||||
"""
|
||||
return self._tts_invoke_streaming(model=model, credentials=credentials, content_text=content_text, voice=voice)
|
||||
|
||||
def validate_credentials(self, model: str, credentials: dict) -> None:
|
||||
"""
|
||||
validate credentials text2speech model
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:return: text translated to audio file
|
||||
"""
|
||||
try:
|
||||
self._tts_invoke_streaming(
|
||||
model=model,
|
||||
credentials=credentials,
|
||||
content_text="Hello Dify!",
|
||||
voice=self._get_model_default_voice(model, credentials),
|
||||
)
|
||||
except Exception as ex:
|
||||
raise CredentialsValidateFailedError(str(ex))
|
||||
|
||||
def _tts_invoke_streaming(self, model: str, credentials: dict, content_text: str, voice: str) -> any:
|
||||
"""
|
||||
_tts_invoke_streaming text2speech model
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:param content_text: text content to be translated
|
||||
:param voice: model timbre
|
||||
:return: text translated to audio file
|
||||
"""
|
||||
try:
|
||||
# doc: https://ai.gitee.com/docs/openapi/serverless#tag/serverless/POST/{service}/text-to-speech
|
||||
endpoint_url = "https://ai.gitee.com/api/serverless/" + model + "/text-to-speech"
|
||||
|
||||
headers = {"Content-Type": "application/json"}
|
||||
api_key = credentials.get("api_key")
|
||||
if api_key:
|
||||
headers["Authorization"] = f"Bearer {api_key}"
|
||||
|
||||
payload = {"inputs": content_text}
|
||||
response = requests.post(endpoint_url, headers=headers, json=payload)
|
||||
|
||||
if response.status_code != 200:
|
||||
raise InvokeBadRequestError(response.text)
|
||||
|
||||
data = response.content
|
||||
|
||||
for i in range(0, len(data), 1024):
|
||||
yield data[i : i + 1024]
|
||||
except Exception as ex:
|
||||
raise InvokeBadRequestError(str(ex))
|
||||
|
|
@ -116,26 +116,33 @@ class GoogleLargeLanguageModel(LargeLanguageModel):
|
|||
:param tools: tool messages
|
||||
:return: glm tools
|
||||
"""
|
||||
return glm.Tool(
|
||||
function_declarations=[
|
||||
glm.FunctionDeclaration(
|
||||
name=tool.name,
|
||||
parameters=glm.Schema(
|
||||
type=glm.Type.OBJECT,
|
||||
properties={
|
||||
key: {
|
||||
"type_": value.get("type", "string").upper(),
|
||||
"description": value.get("description", ""),
|
||||
"enum": value.get("enum", []),
|
||||
}
|
||||
for key, value in tool.parameters.get("properties", {}).items()
|
||||
},
|
||||
required=tool.parameters.get("required", []),
|
||||
),
|
||||
function_declarations = []
|
||||
for tool in tools:
|
||||
properties = {}
|
||||
for key, value in tool.parameters.get("properties", {}).items():
|
||||
properties[key] = {
|
||||
"type_": glm.Type.STRING,
|
||||
"description": value.get("description", ""),
|
||||
"enum": value.get("enum", []),
|
||||
}
|
||||
|
||||
if properties:
|
||||
parameters = glm.Schema(
|
||||
type=glm.Type.OBJECT,
|
||||
properties=properties,
|
||||
required=tool.parameters.get("required", []),
|
||||
)
|
||||
for tool in tools
|
||||
]
|
||||
)
|
||||
else:
|
||||
parameters = None
|
||||
|
||||
function_declaration = glm.FunctionDeclaration(
|
||||
name=tool.name,
|
||||
parameters=parameters,
|
||||
description=tool.description,
|
||||
)
|
||||
function_declarations.append(function_declaration)
|
||||
|
||||
return glm.Tool(function_declarations=function_declarations)
|
||||
|
||||
def validate_credentials(self, model: str, credentials: dict) -> None:
|
||||
"""
|
||||
|
|
|
|||
|
|
@ -0,0 +1,378 @@
|
|||
import json
|
||||
import logging
|
||||
import time
|
||||
import uuid
|
||||
from datetime import timedelta
|
||||
from typing import Any
|
||||
|
||||
from couchbase import search
|
||||
from couchbase.auth import PasswordAuthenticator
|
||||
from couchbase.cluster import Cluster
|
||||
from couchbase.management.search import SearchIndex
|
||||
|
||||
# needed for options -- cluster, timeout, SQL++ (N1QL) query, etc.
|
||||
from couchbase.options import ClusterOptions, SearchOptions
|
||||
from couchbase.vector_search import VectorQuery, VectorSearch
|
||||
from flask import current_app
|
||||
from pydantic import BaseModel, model_validator
|
||||
|
||||
from core.rag.datasource.vdb.vector_base import BaseVector
|
||||
from core.rag.datasource.vdb.vector_factory import AbstractVectorFactory
|
||||
from core.rag.datasource.vdb.vector_type import VectorType
|
||||
from core.rag.embedding.embedding_base import Embeddings
|
||||
from core.rag.models.document import Document
|
||||
from extensions.ext_redis import redis_client
|
||||
from models.dataset import Dataset
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class CouchbaseConfig(BaseModel):
|
||||
connection_string: str
|
||||
user: str
|
||||
password: str
|
||||
bucket_name: str
|
||||
scope_name: str
|
||||
|
||||
@model_validator(mode="before")
|
||||
@classmethod
|
||||
def validate_config(cls, values: dict) -> dict:
|
||||
if not values.get("connection_string"):
|
||||
raise ValueError("config COUCHBASE_CONNECTION_STRING is required")
|
||||
if not values.get("user"):
|
||||
raise ValueError("config COUCHBASE_USER is required")
|
||||
if not values.get("password"):
|
||||
raise ValueError("config COUCHBASE_PASSWORD is required")
|
||||
if not values.get("bucket_name"):
|
||||
raise ValueError("config COUCHBASE_PASSWORD is required")
|
||||
if not values.get("scope_name"):
|
||||
raise ValueError("config COUCHBASE_SCOPE_NAME is required")
|
||||
return values
|
||||
|
||||
|
||||
class CouchbaseVector(BaseVector):
|
||||
def __init__(self, collection_name: str, config: CouchbaseConfig):
|
||||
super().__init__(collection_name)
|
||||
self._client_config = config
|
||||
|
||||
"""Connect to couchbase"""
|
||||
|
||||
auth = PasswordAuthenticator(config.user, config.password)
|
||||
options = ClusterOptions(auth)
|
||||
self._cluster = Cluster(config.connection_string, options)
|
||||
self._bucket = self._cluster.bucket(config.bucket_name)
|
||||
self._scope = self._bucket.scope(config.scope_name)
|
||||
self._bucket_name = config.bucket_name
|
||||
self._scope_name = config.scope_name
|
||||
|
||||
# Wait until the cluster is ready for use.
|
||||
self._cluster.wait_until_ready(timedelta(seconds=5))
|
||||
|
||||
def create(self, texts: list[Document], embeddings: list[list[float]], **kwargs):
|
||||
index_id = str(uuid.uuid4()).replace("-", "")
|
||||
self._create_collection(uuid=index_id, vector_length=len(embeddings[0]))
|
||||
self.add_texts(texts, embeddings)
|
||||
|
||||
def _create_collection(self, vector_length: int, uuid: str):
|
||||
lock_name = "vector_indexing_lock_{}".format(self._collection_name)
|
||||
with redis_client.lock(lock_name, timeout=20):
|
||||
collection_exist_cache_key = "vector_indexing_{}".format(self._collection_name)
|
||||
if redis_client.get(collection_exist_cache_key):
|
||||
return
|
||||
if self._collection_exists(self._collection_name):
|
||||
return
|
||||
manager = self._bucket.collections()
|
||||
manager.create_collection(self._client_config.scope_name, self._collection_name)
|
||||
|
||||
index_manager = self._scope.search_indexes()
|
||||
|
||||
index_definition = json.loads("""
|
||||
{
|
||||
"type": "fulltext-index",
|
||||
"name": "Embeddings._default.Vector_Search",
|
||||
"uuid": "26d4db528e78b716",
|
||||
"sourceType": "gocbcore",
|
||||
"sourceName": "Embeddings",
|
||||
"sourceUUID": "2242e4a25b4decd6650c9c7b3afa1dbf",
|
||||
"planParams": {
|
||||
"maxPartitionsPerPIndex": 1024,
|
||||
"indexPartitions": 1
|
||||
},
|
||||
"params": {
|
||||
"doc_config": {
|
||||
"docid_prefix_delim": "",
|
||||
"docid_regexp": "",
|
||||
"mode": "scope.collection.type_field",
|
||||
"type_field": "type"
|
||||
},
|
||||
"mapping": {
|
||||
"analysis": { },
|
||||
"default_analyzer": "standard",
|
||||
"default_datetime_parser": "dateTimeOptional",
|
||||
"default_field": "_all",
|
||||
"default_mapping": {
|
||||
"dynamic": true,
|
||||
"enabled": true
|
||||
},
|
||||
"default_type": "_default",
|
||||
"docvalues_dynamic": false,
|
||||
"index_dynamic": true,
|
||||
"store_dynamic": true,
|
||||
"type_field": "_type",
|
||||
"types": {
|
||||
"collection_name": {
|
||||
"dynamic": true,
|
||||
"enabled": true,
|
||||
"properties": {
|
||||
"embedding": {
|
||||
"dynamic": false,
|
||||
"enabled": true,
|
||||
"fields": [
|
||||
{
|
||||
"dims": 1536,
|
||||
"index": true,
|
||||
"name": "embedding",
|
||||
"similarity": "dot_product",
|
||||
"type": "vector",
|
||||
"vector_index_optimized_for": "recall"
|
||||
}
|
||||
]
|
||||
},
|
||||
"metadata": {
|
||||
"dynamic": true,
|
||||
"enabled": true
|
||||
},
|
||||
"text": {
|
||||
"dynamic": false,
|
||||
"enabled": true,
|
||||
"fields": [
|
||||
{
|
||||
"index": true,
|
||||
"name": "text",
|
||||
"store": true,
|
||||
"type": "text"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"store": {
|
||||
"indexType": "scorch",
|
||||
"segmentVersion": 16
|
||||
}
|
||||
},
|
||||
"sourceParams": { }
|
||||
}
|
||||
""")
|
||||
index_definition["name"] = self._collection_name + "_search"
|
||||
index_definition["uuid"] = uuid
|
||||
index_definition["params"]["mapping"]["types"]["collection_name"]["properties"]["embedding"]["fields"][0][
|
||||
"dims"
|
||||
] = vector_length
|
||||
index_definition["params"]["mapping"]["types"][self._scope_name + "." + self._collection_name] = (
|
||||
index_definition["params"]["mapping"]["types"].pop("collection_name")
|
||||
)
|
||||
time.sleep(2)
|
||||
index_manager.upsert_index(
|
||||
SearchIndex(
|
||||
index_definition["name"],
|
||||
params=index_definition["params"],
|
||||
source_name=self._bucket_name,
|
||||
),
|
||||
)
|
||||
time.sleep(1)
|
||||
|
||||
redis_client.set(collection_exist_cache_key, 1, ex=3600)
|
||||
|
||||
def _collection_exists(self, name: str):
|
||||
scope_collection_map: dict[str, Any] = {}
|
||||
|
||||
# Get a list of all scopes in the bucket
|
||||
for scope in self._bucket.collections().get_all_scopes():
|
||||
scope_collection_map[scope.name] = []
|
||||
|
||||
# Get a list of all the collections in the scope
|
||||
for collection in scope.collections:
|
||||
scope_collection_map[scope.name].append(collection.name)
|
||||
|
||||
# Check if the collection exists in the scope
|
||||
return self._collection_name in scope_collection_map[self._scope_name]
|
||||
|
||||
def get_type(self) -> str:
|
||||
return VectorType.COUCHBASE
|
||||
|
||||
def add_texts(self, documents: list[Document], embeddings: list[list[float]], **kwargs):
|
||||
uuids = self._get_uuids(documents)
|
||||
texts = [d.page_content for d in documents]
|
||||
metadatas = [d.metadata for d in documents]
|
||||
|
||||
doc_ids = []
|
||||
|
||||
documents_to_insert = [
|
||||
{"text": text, "embedding": vector, "metadata": metadata}
|
||||
for id, text, vector, metadata in zip(uuids, texts, embeddings, metadatas)
|
||||
]
|
||||
for doc, id in zip(documents_to_insert, uuids):
|
||||
result = self._scope.collection(self._collection_name).upsert(id, doc)
|
||||
|
||||
doc_ids.extend(uuids)
|
||||
|
||||
return doc_ids
|
||||
|
||||
def text_exists(self, id: str) -> bool:
|
||||
# Use a parameterized query for safety and correctness
|
||||
query = f"""
|
||||
SELECT COUNT(1) AS count FROM
|
||||
`{self._client_config.bucket_name}`.{self._client_config.scope_name}.{self._collection_name}
|
||||
WHERE META().id = $doc_id
|
||||
"""
|
||||
# Pass the id as a parameter to the query
|
||||
result = self._cluster.query(query, named_parameters={"doc_id": id}).execute()
|
||||
for row in result:
|
||||
return row["count"] > 0
|
||||
return False # Return False if no rows are returned
|
||||
|
||||
def delete_by_ids(self, ids: list[str]) -> None:
|
||||
query = f"""
|
||||
DELETE FROM `{self._bucket_name}`.{self._client_config.scope_name}.{self._collection_name}
|
||||
WHERE META().id IN $doc_ids;
|
||||
"""
|
||||
try:
|
||||
self._cluster.query(query, named_parameters={"doc_ids": ids}).execute()
|
||||
except Exception as e:
|
||||
logger.error(e)
|
||||
|
||||
def delete_by_document_id(self, document_id: str):
|
||||
query = f"""
|
||||
DELETE FROM
|
||||
`{self._client_config.bucket_name}`.{self._client_config.scope_name}.{self._collection_name}
|
||||
WHERE META().id = $doc_id;
|
||||
"""
|
||||
self._cluster.query(query, named_parameters={"doc_id": document_id}).execute()
|
||||
|
||||
# def get_ids_by_metadata_field(self, key: str, value: str):
|
||||
# query = f"""
|
||||
# SELECT id FROM
|
||||
# `{self._client_config.bucket_name}`.{self._client_config.scope_name}.{self._collection_name}
|
||||
# WHERE `metadata.{key}` = $value;
|
||||
# """
|
||||
# result = self._cluster.query(query, named_parameters={'value':value})
|
||||
# return [row['id'] for row in result.rows()]
|
||||
|
||||
def delete_by_metadata_field(self, key: str, value: str) -> None:
|
||||
query = f"""
|
||||
DELETE FROM `{self._client_config.bucket_name}`.{self._client_config.scope_name}.{self._collection_name}
|
||||
WHERE metadata.{key} = $value;
|
||||
"""
|
||||
self._cluster.query(query, named_parameters={"value": value}).execute()
|
||||
|
||||
def search_by_vector(self, query_vector: list[float], **kwargs: Any) -> list[Document]:
|
||||
top_k = kwargs.get("top_k", 5)
|
||||
score_threshold = kwargs.get("score_threshold") or 0.0
|
||||
|
||||
search_req = search.SearchRequest.create(
|
||||
VectorSearch.from_vector_query(
|
||||
VectorQuery(
|
||||
"embedding",
|
||||
query_vector,
|
||||
top_k,
|
||||
)
|
||||
)
|
||||
)
|
||||
try:
|
||||
search_iter = self._scope.search(
|
||||
self._collection_name + "_search",
|
||||
search_req,
|
||||
SearchOptions(limit=top_k, collections=[self._collection_name], fields=["*"]),
|
||||
)
|
||||
|
||||
docs = []
|
||||
# Parse the results
|
||||
for row in search_iter.rows():
|
||||
text = row.fields.pop("text")
|
||||
metadata = self._format_metadata(row.fields)
|
||||
score = row.score
|
||||
metadata["score"] = score
|
||||
doc = Document(page_content=text, metadata=metadata)
|
||||
if score >= score_threshold:
|
||||
docs.append(doc)
|
||||
except Exception as e:
|
||||
raise ValueError(f"Search failed with error: {e}")
|
||||
|
||||
return docs
|
||||
|
||||
def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]:
|
||||
top_k = kwargs.get("top_k", 2)
|
||||
try:
|
||||
CBrequest = search.SearchRequest.create(search.QueryStringQuery("text:" + query))
|
||||
search_iter = self._scope.search(
|
||||
self._collection_name + "_search", CBrequest, SearchOptions(limit=top_k, fields=["*"])
|
||||
)
|
||||
|
||||
docs = []
|
||||
for row in search_iter.rows():
|
||||
text = row.fields.pop("text")
|
||||
metadata = self._format_metadata(row.fields)
|
||||
score = row.score
|
||||
metadata["score"] = score
|
||||
doc = Document(page_content=text, metadata=metadata)
|
||||
docs.append(doc)
|
||||
|
||||
except Exception as e:
|
||||
raise ValueError(f"Search failed with error: {e}")
|
||||
|
||||
return docs
|
||||
|
||||
def delete(self):
|
||||
manager = self._bucket.collections()
|
||||
scopes = manager.get_all_scopes()
|
||||
|
||||
for scope in scopes:
|
||||
for collection in scope.collections:
|
||||
if collection.name == self._collection_name:
|
||||
manager.drop_collection("_default", self._collection_name)
|
||||
|
||||
def _format_metadata(self, row_fields: dict[str, Any]) -> dict[str, Any]:
|
||||
"""Helper method to format the metadata from the Couchbase Search API.
|
||||
Args:
|
||||
row_fields (Dict[str, Any]): The fields to format.
|
||||
|
||||
Returns:
|
||||
Dict[str, Any]: The formatted metadata.
|
||||
"""
|
||||
metadata = {}
|
||||
for key, value in row_fields.items():
|
||||
# Couchbase Search returns the metadata key with a prefix
|
||||
# `metadata.` We remove it to get the original metadata key
|
||||
if key.startswith("metadata"):
|
||||
new_key = key.split("metadata" + ".")[-1]
|
||||
metadata[new_key] = value
|
||||
else:
|
||||
metadata[key] = value
|
||||
|
||||
return metadata
|
||||
|
||||
|
||||
class CouchbaseVectorFactory(AbstractVectorFactory):
|
||||
def init_vector(self, dataset: Dataset, attributes: list, embeddings: Embeddings) -> CouchbaseVector:
|
||||
if dataset.index_struct_dict:
|
||||
class_prefix: str = dataset.index_struct_dict["vector_store"]["class_prefix"]
|
||||
collection_name = class_prefix
|
||||
else:
|
||||
dataset_id = dataset.id
|
||||
collection_name = Dataset.gen_collection_name_by_id(dataset_id)
|
||||
dataset.index_struct = json.dumps(self.gen_index_struct_dict(VectorType.COUCHBASE, collection_name))
|
||||
|
||||
config = current_app.config
|
||||
return CouchbaseVector(
|
||||
collection_name=collection_name,
|
||||
config=CouchbaseConfig(
|
||||
connection_string=config.get("COUCHBASE_CONNECTION_STRING"),
|
||||
user=config.get("COUCHBASE_USER"),
|
||||
password=config.get("COUCHBASE_PASSWORD"),
|
||||
bucket_name=config.get("COUCHBASE_BUCKET_NAME"),
|
||||
scope_name=config.get("COUCHBASE_SCOPE_NAME"),
|
||||
),
|
||||
)
|
||||
|
|
@ -142,7 +142,7 @@ class ElasticSearchVector(BaseVector):
|
|||
|
||||
def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]:
|
||||
query_str = {"match": {Field.CONTENT_KEY.value: query}}
|
||||
results = self._client.search(index=self._collection_name, query=query_str)
|
||||
results = self._client.search(index=self._collection_name, query=query_str, size=kwargs.get("top_k", 4))
|
||||
docs = []
|
||||
for hit in results["hits"]["hits"]:
|
||||
docs.append(
|
||||
|
|
|
|||
|
|
@ -0,0 +1,209 @@
|
|||
import json
|
||||
import logging
|
||||
import math
|
||||
from typing import Any
|
||||
|
||||
from pydantic import BaseModel, model_validator
|
||||
from pyobvector import VECTOR, ObVecClient
|
||||
from sqlalchemy import JSON, Column, String, func
|
||||
from sqlalchemy.dialects.mysql import LONGTEXT
|
||||
|
||||
from configs import dify_config
|
||||
from core.rag.datasource.vdb.vector_base import BaseVector
|
||||
from core.rag.datasource.vdb.vector_factory import AbstractVectorFactory
|
||||
from core.rag.datasource.vdb.vector_type import VectorType
|
||||
from core.rag.embedding.embedding_base import Embeddings
|
||||
from core.rag.models.document import Document
|
||||
from extensions.ext_redis import redis_client
|
||||
from models.dataset import Dataset
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
DEFAULT_OCEANBASE_HNSW_BUILD_PARAM = {"M": 16, "efConstruction": 256}
|
||||
DEFAULT_OCEANBASE_HNSW_SEARCH_PARAM = {"efSearch": 64}
|
||||
OCEANBASE_SUPPORTED_VECTOR_INDEX_TYPE = "HNSW"
|
||||
DEFAULT_OCEANBASE_VECTOR_METRIC_TYPE = "l2"
|
||||
|
||||
|
||||
class OceanBaseVectorConfig(BaseModel):
|
||||
host: str
|
||||
port: int
|
||||
user: str
|
||||
password: str
|
||||
database: str
|
||||
|
||||
@model_validator(mode="before")
|
||||
@classmethod
|
||||
def validate_config(cls, values: dict) -> dict:
|
||||
if not values["host"]:
|
||||
raise ValueError("config OCEANBASE_VECTOR_HOST is required")
|
||||
if not values["port"]:
|
||||
raise ValueError("config OCEANBASE_VECTOR_PORT is required")
|
||||
if not values["user"]:
|
||||
raise ValueError("config OCEANBASE_VECTOR_USER is required")
|
||||
if not values["database"]:
|
||||
raise ValueError("config OCEANBASE_VECTOR_DATABASE is required")
|
||||
return values
|
||||
|
||||
|
||||
class OceanBaseVector(BaseVector):
|
||||
def __init__(self, collection_name: str, config: OceanBaseVectorConfig):
|
||||
super().__init__(collection_name)
|
||||
self._config = config
|
||||
self._hnsw_ef_search = -1
|
||||
self._client = ObVecClient(
|
||||
uri=f"{self._config.host}:{self._config.port}",
|
||||
user=self._config.user,
|
||||
password=self._config.password,
|
||||
db_name=self._config.database,
|
||||
)
|
||||
|
||||
def get_type(self) -> str:
|
||||
return VectorType.OCEANBASE
|
||||
|
||||
def create(self, texts: list[Document], embeddings: list[list[float]], **kwargs):
|
||||
self._vec_dim = len(embeddings[0])
|
||||
self._create_collection()
|
||||
self.add_texts(texts, embeddings)
|
||||
|
||||
def _create_collection(self) -> None:
|
||||
lock_name = "vector_indexing_lock_" + self._collection_name
|
||||
with redis_client.lock(lock_name, timeout=20):
|
||||
collection_exist_cache_key = "vector_indexing_" + self._collection_name
|
||||
if redis_client.get(collection_exist_cache_key):
|
||||
return
|
||||
|
||||
if self._client.check_table_exists(self._collection_name):
|
||||
return
|
||||
|
||||
self.delete()
|
||||
|
||||
cols = [
|
||||
Column("id", String(36), primary_key=True, autoincrement=False),
|
||||
Column("vector", VECTOR(self._vec_dim)),
|
||||
Column("text", LONGTEXT),
|
||||
Column("metadata", JSON),
|
||||
]
|
||||
vidx_params = self._client.prepare_index_params()
|
||||
vidx_params.add_index(
|
||||
field_name="vector",
|
||||
index_type=OCEANBASE_SUPPORTED_VECTOR_INDEX_TYPE,
|
||||
index_name="vector_index",
|
||||
metric_type=DEFAULT_OCEANBASE_VECTOR_METRIC_TYPE,
|
||||
params=DEFAULT_OCEANBASE_HNSW_BUILD_PARAM,
|
||||
)
|
||||
|
||||
self._client.create_table_with_index_params(
|
||||
table_name=self._collection_name,
|
||||
columns=cols,
|
||||
vidxs=vidx_params,
|
||||
)
|
||||
vals = []
|
||||
params = self._client.perform_raw_text_sql("SHOW PARAMETERS LIKE '%ob_vector_memory_limit_percentage%'")
|
||||
for row in params:
|
||||
val = int(row[6])
|
||||
vals.append(val)
|
||||
if len(vals) == 0:
|
||||
print("ob_vector_memory_limit_percentage not found in parameters.")
|
||||
exit(1)
|
||||
if any(val == 0 for val in vals):
|
||||
try:
|
||||
self._client.perform_raw_text_sql("ALTER SYSTEM SET ob_vector_memory_limit_percentage = 30")
|
||||
except Exception as e:
|
||||
raise Exception(
|
||||
"Failed to set ob_vector_memory_limit_percentage. "
|
||||
+ "Maybe the database user has insufficient privilege.",
|
||||
e,
|
||||
)
|
||||
redis_client.set(collection_exist_cache_key, 1, ex=3600)
|
||||
|
||||
def add_texts(self, documents: list[Document], embeddings: list[list[float]], **kwargs):
|
||||
ids = self._get_uuids(documents)
|
||||
for id, doc, emb in zip(ids, documents, embeddings):
|
||||
self._client.insert(
|
||||
table_name=self._collection_name,
|
||||
data={
|
||||
"id": id,
|
||||
"vector": emb,
|
||||
"text": doc.page_content,
|
||||
"metadata": doc.metadata,
|
||||
},
|
||||
)
|
||||
|
||||
def text_exists(self, id: str) -> bool:
|
||||
cur = self._client.get(table_name=self._collection_name, id=id)
|
||||
return cur.rowcount != 0
|
||||
|
||||
def delete_by_ids(self, ids: list[str]) -> None:
|
||||
self._client.delete(table_name=self._collection_name, ids=ids)
|
||||
|
||||
def get_ids_by_metadata_field(self, key: str, value: str) -> list[str]:
|
||||
cur = self._client.get(
|
||||
table_name=self._collection_name,
|
||||
where_clause=f"metadata->>'$.{key}' = '{value}'",
|
||||
output_column_name=["id"],
|
||||
)
|
||||
return [row[0] for row in cur]
|
||||
|
||||
def delete_by_metadata_field(self, key: str, value: str) -> None:
|
||||
ids = self.get_ids_by_metadata_field(key, value)
|
||||
self.delete_by_ids(ids)
|
||||
|
||||
def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]:
|
||||
return []
|
||||
|
||||
def search_by_vector(self, query_vector: list[float], **kwargs: Any) -> list[Document]:
|
||||
ef_search = kwargs.get("ef_search", self._hnsw_ef_search)
|
||||
if ef_search != self._hnsw_ef_search:
|
||||
self._client.set_ob_hnsw_ef_search(ef_search)
|
||||
self._hnsw_ef_search = ef_search
|
||||
topk = kwargs.get("top_k", 10)
|
||||
cur = self._client.ann_search(
|
||||
table_name=self._collection_name,
|
||||
vec_column_name="vector",
|
||||
vec_data=query_vector,
|
||||
topk=topk,
|
||||
distance_func=func.l2_distance,
|
||||
output_column_names=["text", "metadata"],
|
||||
with_dist=True,
|
||||
)
|
||||
docs = []
|
||||
for text, metadata, distance in cur:
|
||||
metadata = json.loads(metadata)
|
||||
metadata["score"] = 1 - distance / math.sqrt(2)
|
||||
docs.append(
|
||||
Document(
|
||||
page_content=text,
|
||||
metadata=metadata,
|
||||
)
|
||||
)
|
||||
return docs
|
||||
|
||||
def delete(self) -> None:
|
||||
self._client.drop_table_if_exist(self._collection_name)
|
||||
|
||||
|
||||
class OceanBaseVectorFactory(AbstractVectorFactory):
|
||||
def init_vector(
|
||||
self,
|
||||
dataset: Dataset,
|
||||
attributes: list,
|
||||
embeddings: Embeddings,
|
||||
) -> BaseVector:
|
||||
if dataset.index_struct_dict:
|
||||
class_prefix: str = dataset.index_struct_dict["vector_store"]["class_prefix"]
|
||||
collection_name = class_prefix.lower()
|
||||
else:
|
||||
dataset_id = dataset.id
|
||||
collection_name = Dataset.gen_collection_name_by_id(dataset_id).lower()
|
||||
dataset.index_struct = json.dumps(self.gen_index_struct_dict(VectorType.OCEANBASE, collection_name))
|
||||
return OceanBaseVector(
|
||||
collection_name,
|
||||
OceanBaseVectorConfig(
|
||||
host=dify_config.OCEANBASE_VECTOR_HOST,
|
||||
port=dify_config.OCEANBASE_VECTOR_PORT,
|
||||
user=dify_config.OCEANBASE_VECTOR_USER,
|
||||
password=(dify_config.OCEANBASE_VECTOR_PASSWORD or ""),
|
||||
database=dify_config.OCEANBASE_VECTOR_DATABASE,
|
||||
),
|
||||
)
|
||||
|
|
@ -4,6 +4,7 @@ import uuid
|
|||
import requests
|
||||
from requests.auth import HTTPDigestAuth
|
||||
|
||||
from configs import dify_config
|
||||
from extensions.ext_database import db
|
||||
from extensions.ext_redis import redis_client
|
||||
from models.dataset import TidbAuthBinding
|
||||
|
|
@ -208,7 +209,7 @@ class TidbService:
|
|||
}
|
||||
|
||||
spending_limit = {
|
||||
"monthly": 10,
|
||||
"monthly": dify_config.TIDB_SPEND_LIMIT,
|
||||
}
|
||||
password = str(uuid.uuid4()).replace("-", "")[:16]
|
||||
display_name = str(uuid.uuid4()).replace("-", "")
|
||||
|
|
|
|||
|
|
@ -114,6 +114,10 @@ class Vector:
|
|||
from core.rag.datasource.vdb.analyticdb.analyticdb_vector import AnalyticdbVectorFactory
|
||||
|
||||
return AnalyticdbVectorFactory
|
||||
case VectorType.COUCHBASE:
|
||||
from core.rag.datasource.vdb.couchbase.couchbase_vector import CouchbaseVectorFactory
|
||||
|
||||
return CouchbaseVectorFactory
|
||||
case VectorType.BAIDU:
|
||||
from core.rag.datasource.vdb.baidu.baidu_vector import BaiduVectorFactory
|
||||
|
||||
|
|
@ -130,6 +134,10 @@ class Vector:
|
|||
from core.rag.datasource.vdb.tidb_on_qdrant.tidb_on_qdrant_vector import TidbOnQdrantVectorFactory
|
||||
|
||||
return TidbOnQdrantVectorFactory
|
||||
case VectorType.OCEANBASE:
|
||||
from core.rag.datasource.vdb.oceanbase.oceanbase_vector import OceanBaseVectorFactory
|
||||
|
||||
return OceanBaseVectorFactory
|
||||
case _:
|
||||
raise ValueError(f"Vector store {vector_type} is not supported.")
|
||||
|
||||
|
|
|
|||
|
|
@ -16,7 +16,9 @@ class VectorType(str, Enum):
|
|||
TENCENT = "tencent"
|
||||
ORACLE = "oracle"
|
||||
ELASTICSEARCH = "elasticsearch"
|
||||
COUCHBASE = "couchbase"
|
||||
BAIDU = "baidu"
|
||||
VIKINGDB = "vikingdb"
|
||||
UPSTASH = "upstash"
|
||||
TIDB_ON_QDRANT = "tidb_on_qdrant"
|
||||
OCEANBASE = "oceanbase"
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
from enum import Enum
|
||||
|
||||
|
||||
class RerankMode(Enum):
|
||||
class RerankMode(str, Enum):
|
||||
RERANKING_MODEL = "reranking_model"
|
||||
WEIGHTED_SCORE = "weighted_score"
|
||||
|
|
|
|||
|
|
@ -22,6 +22,7 @@ from core.rag.datasource.keyword.jieba.jieba_keyword_table_handler import JiebaK
|
|||
from core.rag.datasource.retrieval_service import RetrievalService
|
||||
from core.rag.entities.context_entities import DocumentContext
|
||||
from core.rag.models.document import Document
|
||||
from core.rag.rerank.rerank_type import RerankMode
|
||||
from core.rag.retrieval.retrieval_methods import RetrievalMethod
|
||||
from core.rag.retrieval.router.multi_dataset_function_call_router import FunctionCallMultiDatasetRouter
|
||||
from core.rag.retrieval.router.multi_dataset_react_route import ReactMultiDatasetRouter
|
||||
|
|
@ -361,10 +362,39 @@ class DatasetRetrieval:
|
|||
reranking_enable: bool = True,
|
||||
message_id: Optional[str] = None,
|
||||
):
|
||||
if not available_datasets:
|
||||
return []
|
||||
threads = []
|
||||
all_documents = []
|
||||
dataset_ids = [dataset.id for dataset in available_datasets]
|
||||
index_type = None
|
||||
index_type_check = all(
|
||||
item.indexing_technique == available_datasets[0].indexing_technique for item in available_datasets
|
||||
)
|
||||
if not index_type_check and (not reranking_enable or reranking_mode != RerankMode.RERANKING_MODEL):
|
||||
raise ValueError(
|
||||
"The configured knowledge base list have different indexing technique, please set reranking model."
|
||||
)
|
||||
index_type = available_datasets[0].indexing_technique
|
||||
if index_type == "high_quality":
|
||||
embedding_model_check = all(
|
||||
item.embedding_model == available_datasets[0].embedding_model for item in available_datasets
|
||||
)
|
||||
embedding_model_provider_check = all(
|
||||
item.embedding_model_provider == available_datasets[0].embedding_model_provider
|
||||
for item in available_datasets
|
||||
)
|
||||
if (
|
||||
reranking_enable
|
||||
and reranking_mode == "weighted_score"
|
||||
and (not embedding_model_check or not embedding_model_provider_check)
|
||||
):
|
||||
raise ValueError(
|
||||
"The configured knowledge base list have different embedding model, please set reranking model."
|
||||
)
|
||||
if reranking_enable and reranking_mode == RerankMode.WEIGHTED_SCORE:
|
||||
weights["vector_setting"]["embedding_provider_name"] = available_datasets[0].embedding_model_provider
|
||||
weights["vector_setting"]["embedding_model_name"] = available_datasets[0].embedding_model
|
||||
|
||||
for dataset in available_datasets:
|
||||
index_type = dataset.indexing_technique
|
||||
retrieval_thread = threading.Thread(
|
||||
|
|
|
|||
Binary file not shown.
|
After Width: | Height: | Size: 16 KiB |
|
|
@ -0,0 +1,11 @@
|
|||
from hashlib import md5
|
||||
|
||||
|
||||
class BaiduTranslateToolBase:
|
||||
def _get_sign(self, appid, secret, salt, query):
|
||||
"""
|
||||
get baidu translate sign
|
||||
"""
|
||||
# concatenate the string in the order of appid+q+salt+secret
|
||||
str = appid + query + salt + secret
|
||||
return md5(str.encode("utf-8")).hexdigest()
|
||||
|
|
@ -0,0 +1,17 @@
|
|||
from typing import Any
|
||||
|
||||
from core.tools.errors import ToolProviderCredentialValidationError
|
||||
from core.tools.provider.builtin.baidu_translate.tools.translate import BaiduTranslateTool
|
||||
from core.tools.provider.builtin_tool_provider import BuiltinToolProviderController
|
||||
|
||||
|
||||
class BaiduTranslateProvider(BuiltinToolProviderController):
|
||||
def _validate_credentials(self, credentials: dict[str, Any]) -> None:
|
||||
try:
|
||||
BaiduTranslateTool().fork_tool_runtime(
|
||||
runtime={
|
||||
"credentials": credentials,
|
||||
}
|
||||
).invoke(user_id="", tool_parameters={"q": "这是一段测试文本", "from": "auto", "to": "en"})
|
||||
except Exception as e:
|
||||
raise ToolProviderCredentialValidationError(str(e))
|
||||
|
|
@ -0,0 +1,39 @@
|
|||
identity:
|
||||
author: Xiao Ley
|
||||
name: baidu_translate
|
||||
label:
|
||||
en_US: Baidu Translate
|
||||
zh_Hans: 百度翻译
|
||||
description:
|
||||
en_US: Translate text using Baidu
|
||||
zh_Hans: 使用百度进行翻译
|
||||
icon: icon.png
|
||||
tags:
|
||||
- utilities
|
||||
credentials_for_provider:
|
||||
appid:
|
||||
type: secret-input
|
||||
required: true
|
||||
label:
|
||||
en_US: Baidu translate appid
|
||||
zh_Hans: Baidu translate appid
|
||||
placeholder:
|
||||
en_US: Please input your Baidu translate appid
|
||||
zh_Hans: 请输入你的百度翻译 appid
|
||||
help:
|
||||
en_US: Get your Baidu translate appid from Baidu translate
|
||||
zh_Hans: 从百度翻译开放平台获取你的 appid
|
||||
url: https://api.fanyi.baidu.com
|
||||
secret:
|
||||
type: secret-input
|
||||
required: true
|
||||
label:
|
||||
en_US: Baidu translate secret
|
||||
zh_Hans: Baidu translate secret
|
||||
placeholder:
|
||||
en_US: Please input your Baidu translate secret
|
||||
zh_Hans: 请输入你的百度翻译 secret
|
||||
help:
|
||||
en_US: Get your Baidu translate secret from Baidu translate
|
||||
zh_Hans: 从百度翻译开放平台获取你的 secret
|
||||
url: https://api.fanyi.baidu.com
|
||||
|
|
@ -0,0 +1,78 @@
|
|||
import random
|
||||
from hashlib import md5
|
||||
from typing import Any, Union
|
||||
|
||||
import requests
|
||||
|
||||
from core.tools.entities.tool_entities import ToolInvokeMessage
|
||||
from core.tools.provider.builtin.baidu_translate._baidu_translate_tool_base import BaiduTranslateToolBase
|
||||
from core.tools.tool.builtin_tool import BuiltinTool
|
||||
|
||||
|
||||
class BaiduFieldTranslateTool(BuiltinTool, BaiduTranslateToolBase):
|
||||
def _invoke(
|
||||
self,
|
||||
user_id: str,
|
||||
tool_parameters: dict[str, Any],
|
||||
) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
|
||||
"""
|
||||
invoke tools
|
||||
"""
|
||||
BAIDU_FIELD_TRANSLATE_URL = "https://fanyi-api.baidu.com/api/trans/vip/fieldtranslate"
|
||||
|
||||
appid = self.runtime.credentials.get("appid", "")
|
||||
if not appid:
|
||||
raise ValueError("invalid baidu translate appid")
|
||||
|
||||
secret = self.runtime.credentials.get("secret", "")
|
||||
if not secret:
|
||||
raise ValueError("invalid baidu translate secret")
|
||||
|
||||
q = tool_parameters.get("q", "")
|
||||
if not q:
|
||||
raise ValueError("Please input text to translate")
|
||||
|
||||
from_ = tool_parameters.get("from", "")
|
||||
if not from_:
|
||||
raise ValueError("Please select source language")
|
||||
|
||||
to = tool_parameters.get("to", "")
|
||||
if not to:
|
||||
raise ValueError("Please select destination language")
|
||||
|
||||
domain = tool_parameters.get("domain", "")
|
||||
if not domain:
|
||||
raise ValueError("Please select domain")
|
||||
|
||||
salt = str(random.randint(32768, 16777215))
|
||||
sign = self._get_sign(appid, secret, salt, q, domain)
|
||||
|
||||
headers = {"Content-Type": "application/x-www-form-urlencoded"}
|
||||
params = {
|
||||
"q": q,
|
||||
"from": from_,
|
||||
"to": to,
|
||||
"appid": appid,
|
||||
"salt": salt,
|
||||
"domain": domain,
|
||||
"sign": sign,
|
||||
"needIntervene": 1,
|
||||
}
|
||||
try:
|
||||
response = requests.post(BAIDU_FIELD_TRANSLATE_URL, headers=headers, data=params)
|
||||
result = response.json()
|
||||
|
||||
if "trans_result" in result:
|
||||
result_text = result["trans_result"][0]["dst"]
|
||||
else:
|
||||
result_text = f'{result["error_code"]}: {result["error_msg"]}'
|
||||
|
||||
return self.create_text_message(str(result_text))
|
||||
except requests.RequestException as e:
|
||||
raise ValueError(f"Translation service error: {e}")
|
||||
except Exception:
|
||||
raise ValueError("Translation service error, please check the network")
|
||||
|
||||
def _get_sign(self, appid, secret, salt, query, domain):
|
||||
str = appid + query + salt + domain + secret
|
||||
return md5(str.encode("utf-8")).hexdigest()
|
||||
|
|
@ -0,0 +1,123 @@
|
|||
identity:
|
||||
name: field_translate
|
||||
author: Xiao Ley
|
||||
label:
|
||||
en_US: Field translate
|
||||
zh_Hans: 百度领域翻译
|
||||
description:
|
||||
human:
|
||||
en_US: A tool for Baidu Field translate (Currently, the fields of "novel" and "wiki" only support Chinese to English translation. If the language direction is set to English to Chinese, the default output will be a universal translation result).
|
||||
zh_Hans: 百度领域翻译，提供多种领域的文本翻译（目前“网络文学领域”和“人文社科领域”仅支持中到英，如设置语言方向为英到中，则默认输出通用翻译结果）
|
||||
llm: A tool for Baidu Field translate
|
||||
parameters:
|
||||
- name: q
|
||||
type: string
|
||||
required: true
|
||||
label:
|
||||
en_US: Text content
|
||||
zh_Hans: 文本内容
|
||||
human_description:
|
||||
en_US: Text content to be translated
|
||||
zh_Hans: 需要翻译的文本内容
|
||||
llm_description: Text content to be translated
|
||||
form: llm
|
||||
- name: from
|
||||
type: select
|
||||
required: true
|
||||
label:
|
||||
en_US: source language
|
||||
zh_Hans: 源语言
|
||||
human_description:
|
||||
en_US: The source language of the input text
|
||||
zh_Hans: 输入的文本的源语言
|
||||
default: auto
|
||||
form: form
|
||||
options:
|
||||
- value: auto
|
||||
label:
|
||||
en_US: auto
|
||||
zh_Hans: 自动检测
|
||||
- value: zh
|
||||
label:
|
||||
en_US: Chinese
|
||||
zh_Hans: 中文
|
||||
- value: en
|
||||
label:
|
||||
en_US: English
|
||||
zh_Hans: 英语
|
||||
- name: to
|
||||
type: select
|
||||
required: true
|
||||
label:
|
||||
en_US: destination language
|
||||
zh_Hans: 目标语言
|
||||
human_description:
|
||||
en_US: The destination language of the input text
|
||||
zh_Hans: 输入文本的目标语言
|
||||
default: en
|
||||
form: form
|
||||
options:
|
||||
- value: zh
|
||||
label:
|
||||
en_US: Chinese
|
||||
zh_Hans: 中文
|
||||
- value: en
|
||||
label:
|
||||
en_US: English
|
||||
zh_Hans: 英语
|
||||
- name: domain
|
||||
type: select
|
||||
required: true
|
||||
label:
|
||||
en_US: domain
|
||||
zh_Hans: 领域
|
||||
human_description:
|
||||
en_US: The domain of the input text
|
||||
zh_Hans: 输入文本的领域
|
||||
default: novel
|
||||
form: form
|
||||
options:
|
||||
- value: it
|
||||
label:
|
||||
en_US: it
|
||||
zh_Hans: 信息技术领域
|
||||
- value: finance
|
||||
label:
|
||||
en_US: finance
|
||||
zh_Hans: 金融财经领域
|
||||
- value: machinery
|
||||
label:
|
||||
en_US: machinery
|
||||
zh_Hans: 机械制造领域
|
||||
- value: senimed
|
||||
label:
|
||||
en_US: senimed
|
||||
zh_Hans: 生物医药领域
|
||||
- value: novel
|
||||
label:
|
||||
en_US: novel (only support Chinese to English translation)
|
||||
zh_Hans: 网络文学领域（仅支持中到英）
|
||||
- value: academic
|
||||
label:
|
||||
en_US: academic
|
||||
zh_Hans: 学术论文领域
|
||||
- value: aerospace
|
||||
label:
|
||||
en_US: aerospace
|
||||
zh_Hans: 航空航天领域
|
||||
- value: wiki
|
||||
label:
|
||||
en_US: wiki (only support Chinese to English translation)
|
||||
zh_Hans: 人文社科领域（仅支持中到英）
|
||||
- value: news
|
||||
label:
|
||||
en_US: news
|
||||
zh_Hans: 新闻咨询领域
|
||||
- value: law
|
||||
label:
|
||||
en_US: law
|
||||
zh_Hans: 法律法规领域
|
||||
- value: contract
|
||||
label:
|
||||
en_US: contract
|
||||
zh_Hans: 合同领域
|
||||
|
|
@ -0,0 +1,95 @@
|
|||
import random
|
||||
from typing import Any, Union
|
||||
|
||||
import requests
|
||||
|
||||
from core.tools.entities.tool_entities import ToolInvokeMessage
|
||||
from core.tools.provider.builtin.baidu_translate._baidu_translate_tool_base import BaiduTranslateToolBase
|
||||
from core.tools.tool.builtin_tool import BuiltinTool
|
||||
|
||||
|
||||
class BaiduLanguageTool(BuiltinTool, BaiduTranslateToolBase):
|
||||
def _invoke(
|
||||
self,
|
||||
user_id: str,
|
||||
tool_parameters: dict[str, Any],
|
||||
) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
|
||||
"""
|
||||
invoke tools
|
||||
"""
|
||||
BAIDU_LANGUAGE_URL = "https://fanyi-api.baidu.com/api/trans/vip/language"
|
||||
|
||||
appid = self.runtime.credentials.get("appid", "")
|
||||
if not appid:
|
||||
raise ValueError("invalid baidu translate appid")
|
||||
|
||||
secret = self.runtime.credentials.get("secret", "")
|
||||
if not secret:
|
||||
raise ValueError("invalid baidu translate secret")
|
||||
|
||||
q = tool_parameters.get("q", "")
|
||||
if not q:
|
||||
raise ValueError("Please input text to translate")
|
||||
|
||||
description_language = tool_parameters.get("description_language", "English")
|
||||
|
||||
salt = str(random.randint(32768, 16777215))
|
||||
sign = self._get_sign(appid, secret, salt, q)
|
||||
|
||||
headers = {"Content-Type": "application/x-www-form-urlencoded"}
|
||||
params = {
|
||||
"q": q,
|
||||
"appid": appid,
|
||||
"salt": salt,
|
||||
"sign": sign,
|
||||
}
|
||||
|
||||
try:
|
||||
response = requests.post(BAIDU_LANGUAGE_URL, params=params, headers=headers)
|
||||
result = response.json()
|
||||
if "error_code" not in result:
|
||||
raise ValueError("Translation service error, please check the network")
|
||||
|
||||
result_text = ""
|
||||
if result["error_code"] != 0:
|
||||
result_text = f'{result["error_code"]}: {result["error_msg"]}'
|
||||
else:
|
||||
result_text = result["data"]["src"]
|
||||
result_text = self.mapping_result(description_language, result_text)
|
||||
|
||||
return self.create_text_message(result_text)
|
||||
except requests.RequestException as e:
|
||||
raise ValueError(f"Translation service error: {e}")
|
||||
except Exception:
|
||||
raise ValueError("Translation service error, please check the network")
|
||||
|
||||
def mapping_result(self, description_language: str, result: str) -> str:
|
||||
"""
|
||||
mapping result
|
||||
"""
|
||||
mapping = {
|
||||
"English": {
|
||||
"zh": "Chinese",
|
||||
"en": "English",
|
||||
"jp": "Japanese",
|
||||
"kor": "Korean",
|
||||
"th": "Thai",
|
||||
"vie": "Vietnamese",
|
||||
"ru": "Russian",
|
||||
},
|
||||
"Chinese": {
|
||||
"zh": "中文",
|
||||
"en": "英文",
|
||||
"jp": "日文",
|
||||
"kor": "韩文",
|
||||
"th": "泰语",
|
||||
"vie": "越南语",
|
||||
"ru": "俄语",
|
||||
},
|
||||
}
|
||||
|
||||
language_mapping = mapping.get(description_language)
|
||||
if not language_mapping:
|
||||
return result
|
||||
|
||||
return language_mapping.get(result, result)
|
||||
|
|
@ -0,0 +1,43 @@
|
|||
identity:
|
||||
name: language
|
||||
author: Xiao Ley
|
||||
label:
|
||||
en_US: Baidu Language
|
||||
zh_Hans: 百度语种识别
|
||||
description:
|
||||
human:
|
||||
en_US: A tool for Baidu Language, support Chinese, English, Japanese, Korean, Thai, Vietnamese and Russian
|
||||
zh_Hans: 使用百度进行语种识别，支持的语种：中文、英语、日语、韩语、泰语、越南语和俄语
|
||||
llm: A tool for Baidu Language
|
||||
parameters:
|
||||
- name: q
|
||||
type: string
|
||||
required: true
|
||||
label:
|
||||
en_US: Text content
|
||||
zh_Hans: 文本内容
|
||||
human_description:
|
||||
en_US: Text content to be recognized
|
||||
zh_Hans: 需要识别语言的文本内容
|
||||
llm_description: Text content to be recognized
|
||||
form: llm
|
||||
- name: description_language
|
||||
type: select
|
||||
required: true
|
||||
label:
|
||||
en_US: Description language
|
||||
zh_Hans: 描述语言
|
||||
human_description:
|
||||
en_US: Describe the language used to identify the results
|
||||
zh_Hans: 描述识别结果所用的语言
|
||||
default: Chinese
|
||||
form: form
|
||||
options:
|
||||
- value: Chinese
|
||||
label:
|
||||
en_US: Chinese
|
||||
zh_Hans: 中文
|
||||
- value: English
|
||||
label:
|
||||
en_US: English
|
||||
zh_Hans: 英语
|
||||
|
|
@ -0,0 +1,67 @@
|
|||
import random
|
||||
from typing import Any, Union
|
||||
|
||||
import requests
|
||||
|
||||
from core.tools.entities.tool_entities import ToolInvokeMessage
|
||||
from core.tools.provider.builtin.baidu_translate._baidu_translate_tool_base import BaiduTranslateToolBase
|
||||
from core.tools.tool.builtin_tool import BuiltinTool
|
||||
|
||||
|
||||
class BaiduTranslateTool(BuiltinTool, BaiduTranslateToolBase):
|
||||
def _invoke(
|
||||
self,
|
||||
user_id: str,
|
||||
tool_parameters: dict[str, Any],
|
||||
) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
|
||||
"""
|
||||
invoke tools
|
||||
"""
|
||||
BAIDU_TRANSLATE_URL = "https://fanyi-api.baidu.com/api/trans/vip/translate"
|
||||
|
||||
appid = self.runtime.credentials.get("appid", "")
|
||||
if not appid:
|
||||
raise ValueError("invalid baidu translate appid")
|
||||
|
||||
secret = self.runtime.credentials.get("secret", "")
|
||||
if not secret:
|
||||
raise ValueError("invalid baidu translate secret")
|
||||
|
||||
q = tool_parameters.get("q", "")
|
||||
if not q:
|
||||
raise ValueError("Please input text to translate")
|
||||
|
||||
from_ = tool_parameters.get("from", "")
|
||||
if not from_:
|
||||
raise ValueError("Please select source language")
|
||||
|
||||
to = tool_parameters.get("to", "")
|
||||
if not to:
|
||||
raise ValueError("Please select destination language")
|
||||
|
||||
salt = str(random.randint(32768, 16777215))
|
||||
sign = self._get_sign(appid, secret, salt, q)
|
||||
|
||||
headers = {"Content-Type": "application/x-www-form-urlencoded"}
|
||||
params = {
|
||||
"q": q,
|
||||
"from": from_,
|
||||
"to": to,
|
||||
"appid": appid,
|
||||
"salt": salt,
|
||||
"sign": sign,
|
||||
}
|
||||
try:
|
||||
response = requests.post(BAIDU_TRANSLATE_URL, params=params, headers=headers)
|
||||
result = response.json()
|
||||
|
||||
if "trans_result" in result:
|
||||
result_text = result["trans_result"][0]["dst"]
|
||||
else:
|
||||
result_text = f'{result["error_code"]}: {result["error_msg"]}'
|
||||
|
||||
return self.create_text_message(str(result_text))
|
||||
except requests.RequestException as e:
|
||||
raise ValueError(f"Translation service error: {e}")
|
||||
except Exception:
|
||||
raise ValueError("Translation service error, please check the network")
|
||||
|
|
@ -0,0 +1,275 @@
|
|||
identity:
|
||||
name: translate
|
||||
author: Xiao Ley
|
||||
label:
|
||||
en_US: Translate
|
||||
zh_Hans: 百度翻译
|
||||
description:
|
||||
human:
|
||||
en_US: A tool for Baidu Translate
|
||||
zh_Hans: 百度翻译
|
||||
llm: A tool for Baidu Translate
|
||||
parameters:
|
||||
- name: q
|
||||
type: string
|
||||
required: true
|
||||
label:
|
||||
en_US: Text content
|
||||
zh_Hans: 文本内容
|
||||
human_description:
|
||||
en_US: Text content to be translated
|
||||
zh_Hans: 需要翻译的文本内容
|
||||
llm_description: Text content to be translated
|
||||
form: llm
|
||||
- name: from
|
||||
type: select
|
||||
required: true
|
||||
label:
|
||||
en_US: source language
|
||||
zh_Hans: 源语言
|
||||
human_description:
|
||||
en_US: The source language of the input text
|
||||
zh_Hans: 输入的文本的源语言
|
||||
default: auto
|
||||
form: form
|
||||
options:
|
||||
- value: auto
|
||||
label:
|
||||
en_US: auto
|
||||
zh_Hans: 自动检测
|
||||
- value: zh
|
||||
label:
|
||||
en_US: Chinese
|
||||
zh_Hans: 中文
|
||||
- value: en
|
||||
label:
|
||||
en_US: English
|
||||
zh_Hans: 英语
|
||||
- value: cht
|
||||
label:
|
||||
en_US: Traditional Chinese
|
||||
zh_Hans: 繁体中文
|
||||
- value: yue
|
||||
label:
|
||||
en_US: Yue
|
||||
zh_Hans: 粤语
|
||||
- value: wyw
|
||||
label:
|
||||
en_US: Wyw
|
||||
zh_Hans: 文言文
|
||||
- value: jp
|
||||
label:
|
||||
en_US: Japanese
|
||||
zh_Hans: 日语
|
||||
- value: kor
|
||||
label:
|
||||
en_US: Korean
|
||||
zh_Hans: 韩语
|
||||
- value: fra
|
||||
label:
|
||||
en_US: French
|
||||
zh_Hans: 法语
|
||||
- value: spa
|
||||
label:
|
||||
en_US: Spanish
|
||||
zh_Hans: 西班牙语
|
||||
- value: th
|
||||
label:
|
||||
en_US: Thai
|
||||
zh_Hans: 泰语
|
||||
- value: ara
|
||||
label:
|
||||
en_US: Arabic
|
||||
zh_Hans: 阿拉伯语
|
||||
- value: ru
|
||||
label:
|
||||
en_US: Russian
|
||||
zh_Hans: 俄语
|
||||
- value: pt
|
||||
label:
|
||||
en_US: Portuguese
|
||||
zh_Hans: 葡萄牙语
|
||||
- value: de
|
||||
label:
|
||||
en_US: German
|
||||
zh_Hans: 德语
|
||||
- value: it
|
||||
label:
|
||||
en_US: Italian
|
||||
zh_Hans: 意大利语
|
||||
- value: el
|
||||
label:
|
||||
en_US: Greek
|
||||
zh_Hans: 希腊语
|
||||
- value: nl
|
||||
label:
|
||||
en_US: Dutch
|
||||
zh_Hans: 荷兰语
|
||||
- value: pl
|
||||
label:
|
||||
en_US: Polish
|
||||
zh_Hans: 波兰语
|
||||
- value: bul
|
||||
label:
|
||||
en_US: Bulgarian
|
||||
zh_Hans: 保加利亚语
|
||||
- value: est
|
||||
label:
|
||||
en_US: Estonian
|
||||
zh_Hans: 爱沙尼亚语
|
||||
- value: dan
|
||||
label:
|
||||
en_US: Danish
|
||||
zh_Hans: 丹麦语
|
||||
- value: fin
|
||||
label:
|
||||
en_US: Finnish
|
||||
zh_Hans: 芬兰语
|
||||
- value: cs
|
||||
label:
|
||||
en_US: Czech
|
||||
zh_Hans: 捷克语
|
||||
- value: rom
|
||||
label:
|
||||
en_US: Romanian
|
||||
zh_Hans: 罗马尼亚语
|
||||
- value: slo
|
||||
label:
|
||||
en_US: Slovak
|
||||
zh_Hans: 斯洛文尼亚语
|
||||
- value: swe
|
||||
label:
|
||||
en_US: Swedish
|
||||
zh_Hans: 瑞典语
|
||||
- value: hu
|
||||
label:
|
||||
en_US: Hungarian
|
||||
zh_Hans: 匈牙利语
|
||||
- value: vie
|
||||
label:
|
||||
en_US: Vietnamese
|
||||
zh_Hans: 越南语
|
||||
- name: to
|
||||
type: select
|
||||
required: true
|
||||
label:
|
||||
en_US: destination language
|
||||
zh_Hans: 目标语言
|
||||
human_description:
|
||||
en_US: The destination language of the input text
|
||||
zh_Hans: 输入文本的目标语言
|
||||
default: en
|
||||
form: form
|
||||
options:
|
||||
- value: zh
|
||||
label:
|
||||
en_US: Chinese
|
||||
zh_Hans: 中文
|
||||
- value: en
|
||||
label:
|
||||
en_US: English
|
||||
zh_Hans: 英语
|
||||
- value: cht
|
||||
label:
|
||||
en_US: Traditional Chinese
|
||||
zh_Hans: 繁体中文
|
||||
- value: yue
|
||||
label:
|
||||
en_US: Yue
|
||||
zh_Hans: 粤语
|
||||
- value: wyw
|
||||
label:
|
||||
en_US: Wyw
|
||||
zh_Hans: 文言文
|
||||
- value: jp
|
||||
label:
|
||||
en_US: Japanese
|
||||
zh_Hans: 日语
|
||||
- value: kor
|
||||
label:
|
||||
en_US: Korean
|
||||
zh_Hans: 韩语
|
||||
- value: fra
|
||||
label:
|
||||
en_US: French
|
||||
zh_Hans: 法语
|
||||
- value: spa
|
||||
label:
|
||||
en_US: Spanish
|
||||
zh_Hans: 西班牙语
|
||||
- value: th
|
||||
label:
|
||||
en_US: Thai
|
||||
zh_Hans: 泰语
|
||||
- value: ara
|
||||
label:
|
||||
en_US: Arabic
|
||||
zh_Hans: 阿拉伯语
|
||||
- value: ru
|
||||
label:
|
||||
en_US: Russian
|
||||
zh_Hans: 俄语
|
||||
- value: pt
|
||||
label:
|
||||
en_US: Portuguese
|
||||
zh_Hans: 葡萄牙语
|
||||
- value: de
|
||||
label:
|
||||
en_US: German
|
||||
zh_Hans: 德语
|
||||
- value: it
|
||||
label:
|
||||
en_US: Italian
|
||||
zh_Hans: 意大利语
|
||||
- value: el
|
||||
label:
|
||||
en_US: Greek
|
||||
zh_Hans: 希腊语
|
||||
- value: nl
|
||||
label:
|
||||
en_US: Dutch
|
||||
zh_Hans: 荷兰语
|
||||
- value: pl
|
||||
label:
|
||||
en_US: Polish
|
||||
zh_Hans: 波兰语
|
||||
- value: bul
|
||||
label:
|
||||
en_US: Bulgarian
|
||||
zh_Hans: 保加利亚语
|
||||
- value: est
|
||||
label:
|
||||
en_US: Estonian
|
||||
zh_Hans: 爱沙尼亚语
|
||||
- value: dan
|
||||
label:
|
||||
en_US: Danish
|
||||
zh_Hans: 丹麦语
|
||||
- value: fin
|
||||
label:
|
||||
en_US: Finnish
|
||||
zh_Hans: 芬兰语
|
||||
- value: cs
|
||||
label:
|
||||
en_US: Czech
|
||||
zh_Hans: 捷克语
|
||||
- value: rom
|
||||
label:
|
||||
en_US: Romanian
|
||||
zh_Hans: 罗马尼亚语
|
||||
- value: slo
|
||||
label:
|
||||
en_US: Slovak
|
||||
zh_Hans: 斯洛文尼亚语
|
||||
- value: swe
|
||||
label:
|
||||
en_US: Swedish
|
||||
zh_Hans: 瑞典语
|
||||
- value: hu
|
||||
label:
|
||||
en_US: Hungarian
|
||||
zh_Hans: 匈牙利语
|
||||
- value: vie
|
||||
label:
|
||||
en_US: Vietnamese
|
||||
zh_Hans: 越南语
|
||||
|
|
@ -1 +0,0 @@
|
|||
VECTORIZER_ICON_PNG = "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" # noqa: E501
|
||||
|
|
@ -1,11 +1,12 @@
|
|||
from base64 import b64decode
|
||||
from typing import Any, Union
|
||||
|
||||
from httpx import post
|
||||
|
||||
from core.file.enums import FileType
|
||||
from core.file.file_manager import download
|
||||
from core.tools.entities.common_entities import I18nObject
|
||||
from core.tools.entities.tool_entities import ToolInvokeMessage, ToolParameter
|
||||
from core.tools.errors import ToolProviderCredentialValidationError
|
||||
from core.tools.provider.builtin.vectorizer.tools.test_data import VECTORIZER_ICON_PNG
|
||||
from core.tools.errors import ToolParameterValidationError
|
||||
from core.tools.tool.builtin_tool import BuiltinTool
|
||||
|
||||
|
||||
|
|
@ -16,30 +17,30 @@ class VectorizerTool(BuiltinTool):
|
|||
"""
|
||||
invoke tools
|
||||
"""
|
||||
api_key_name = self.runtime.credentials.get("api_key_name", None)
|
||||
api_key_value = self.runtime.credentials.get("api_key_value", None)
|
||||
api_key_name = self.runtime.credentials.get("api_key_name")
|
||||
api_key_value = self.runtime.credentials.get("api_key_value")
|
||||
mode = tool_parameters.get("mode", "test")
|
||||
if mode == "production":
|
||||
mode = "preview"
|
||||
|
||||
if not api_key_name or not api_key_value:
|
||||
raise ToolProviderCredentialValidationError("Please input api key name and value")
|
||||
|
||||
# image file for workflow mode
|
||||
image = tool_parameters.get("image")
|
||||
if image and image.type != FileType.IMAGE:
|
||||
raise ToolParameterValidationError("Not a valid image")
|
||||
# image_id for agent mode
|
||||
image_id = tool_parameters.get("image_id", "")
|
||||
if not image_id:
|
||||
return self.create_text_message("Please input image id")
|
||||
|
||||
if image_id.startswith("__test_"):
|
||||
image_binary = b64decode(VECTORIZER_ICON_PNG)
|
||||
else:
|
||||
if image_id:
|
||||
image_binary = self.get_variable_file(self.VariableKey.IMAGE)
|
||||
if not image_binary:
|
||||
return self.create_text_message("Image not found, please request user to generate image firstly.")
|
||||
elif image:
|
||||
image_binary = download(image)
|
||||
else:
|
||||
raise ToolParameterValidationError("Please provide either image or image_id")
|
||||
|
||||
response = post(
|
||||
"https://vectorizer.ai/api/v1/vectorize",
|
||||
data={"mode": mode},
|
||||
files={"image": image_binary},
|
||||
data={"mode": mode} if mode == "test" else {},
|
||||
auth=(api_key_name, api_key_value),
|
||||
timeout=30,
|
||||
)
|
||||
|
|
@ -59,11 +60,23 @@ class VectorizerTool(BuiltinTool):
|
|||
return [
|
||||
ToolParameter.get_simple_instance(
|
||||
name="image_id",
|
||||
llm_description=f"the image id that you want to vectorize, \
|
||||
and the image id should be specified in \
|
||||
llm_description=f"the image_id that you want to vectorize, \
|
||||
and the image_id should be specified in \
|
||||
{[i.name for i in self.list_default_image_variables()]}",
|
||||
type=ToolParameter.ToolParameterType.SELECT,
|
||||
required=True,
|
||||
required=False,
|
||||
options=[i.name for i in self.list_default_image_variables()],
|
||||
)
|
||||
),
|
||||
ToolParameter(
|
||||
name="image",
|
||||
label=I18nObject(en_US="image", zh_Hans="image"),
|
||||
human_description=I18nObject(
|
||||
en_US="The image to be converted.",
|
||||
zh_Hans="要转换的图片。",
|
||||
),
|
||||
type=ToolParameter.ToolParameterType.FILE,
|
||||
form=ToolParameter.ToolParameterForm.LLM,
|
||||
llm_description="you should not input this parameter. just input the image_id.",
|
||||
required=False,
|
||||
),
|
||||
]
|
||||
|
|
|
|||
|
|
@ -4,14 +4,21 @@ identity:
|
|||
label:
|
||||
en_US: Vectorizer.AI
|
||||
zh_Hans: Vectorizer.AI
|
||||
pt_BR: Vectorizer.AI
|
||||
description:
|
||||
human:
|
||||
en_US: Convert your PNG and JPG images to SVG vectors quickly and easily. Fully automatically. Using AI.
|
||||
zh_Hans: 一个将 PNG 和 JPG 图像快速轻松地转换为 SVG 矢量图的工具。
|
||||
pt_BR: Convert your PNG and JPG images to SVG vectors quickly and easily. Fully automatically. Using AI.
|
||||
llm: A tool for converting images to SVG vectors. you should input the image id as the input of this tool. the image id can be got from parameters.
|
||||
parameters:
|
||||
- name: image
|
||||
type: file
|
||||
label:
|
||||
en_US: image
|
||||
human_description:
|
||||
en_US: The image to be converted.
|
||||
zh_Hans: 要转换的图片。
|
||||
llm_description: you should not input this parameter. just input the image_id.
|
||||
form: llm
|
||||
- name: mode
|
||||
type: select
|
||||
required: true
|
||||
|
|
@ -20,19 +27,15 @@ parameters:
|
|||
label:
|
||||
en_US: production
|
||||
zh_Hans: 生产模式
|
||||
pt_BR: production
|
||||
- value: test
|
||||
label:
|
||||
en_US: test
|
||||
zh_Hans: 测试模式
|
||||
pt_BR: test
|
||||
default: test
|
||||
label:
|
||||
en_US: Mode
|
||||
zh_Hans: 模式
|
||||
pt_BR: Mode
|
||||
human_description:
|
||||
en_US: It is free to integrate with and test out the API in test mode, no subscription required.
|
||||
zh_Hans: 在测试模式下，可以免费测试API。
|
||||
pt_BR: It is free to integrate with and test out the API in test mode, no subscription required.
|
||||
form: form
|
||||
|
|
|
|||
|
|
@ -1,5 +1,7 @@
|
|||
from typing import Any
|
||||
|
||||
from core.file import File
|
||||
from core.file.enums import FileTransferMethod, FileType
|
||||
from core.tools.errors import ToolProviderCredentialValidationError
|
||||
from core.tools.provider.builtin.vectorizer.tools.vectorizer import VectorizerTool
|
||||
from core.tools.provider.builtin_tool_provider import BuiltinToolProviderController
|
||||
|
|
@ -7,6 +9,12 @@ from core.tools.provider.builtin_tool_provider import BuiltinToolProviderControl
|
|||
|
||||
class VectorizerProvider(BuiltinToolProviderController):
|
||||
def _validate_credentials(self, credentials: dict[str, Any]) -> None:
|
||||
test_img = File(
|
||||
tenant_id="__test_123",
|
||||
remote_url="https://cloud.dify.ai/logo/logo-site.png",
|
||||
type=FileType.IMAGE,
|
||||
transfer_method=FileTransferMethod.REMOTE_URL,
|
||||
)
|
||||
try:
|
||||
VectorizerTool().fork_tool_runtime(
|
||||
runtime={
|
||||
|
|
@ -14,7 +22,7 @@ class VectorizerProvider(BuiltinToolProviderController):
|
|||
}
|
||||
).invoke(
|
||||
user_id="",
|
||||
tool_parameters={"mode": "test", "image_id": "__test_123"},
|
||||
tool_parameters={"mode": "test", "image": test_img},
|
||||
)
|
||||
except Exception as e:
|
||||
raise ToolProviderCredentialValidationError(str(e))
|
||||
|
|
|
|||
|
|
@ -4,11 +4,9 @@ identity:
|
|||
label:
|
||||
en_US: Vectorizer.AI
|
||||
zh_Hans: Vectorizer.AI
|
||||
pt_BR: Vectorizer.AI
|
||||
description:
|
||||
en_US: Convert your PNG and JPG images to SVG vectors quickly and easily. Fully automatically. Using AI.
|
||||
zh_Hans: 一个将 PNG 和 JPG 图像快速轻松地转换为 SVG 矢量图的工具。
|
||||
pt_BR: Convert your PNG and JPG images to SVG vectors quickly and easily. Fully automatically. Using AI.
|
||||
icon: icon.png
|
||||
tags:
|
||||
- productivity
|
||||
|
|
@ -20,15 +18,12 @@ credentials_for_provider:
|
|||
label:
|
||||
en_US: Vectorizer.AI API Key name
|
||||
zh_Hans: Vectorizer.AI API Key name
|
||||
pt_BR: Vectorizer.AI API Key name
|
||||
placeholder:
|
||||
en_US: Please input your Vectorizer.AI ApiKey name
|
||||
zh_Hans: 请输入你的 Vectorizer.AI ApiKey name
|
||||
pt_BR: Please input your Vectorizer.AI ApiKey name
|
||||
help:
|
||||
en_US: Get your Vectorizer.AI API Key from Vectorizer.AI.
|
||||
zh_Hans: 从 Vectorizer.AI 获取您的 Vectorizer.AI API Key。
|
||||
pt_BR: Get your Vectorizer.AI API Key from Vectorizer.AI.
|
||||
url: https://vectorizer.ai/api
|
||||
api_key_value:
|
||||
type: secret-input
|
||||
|
|
@ -36,12 +31,9 @@ credentials_for_provider:
|
|||
label:
|
||||
en_US: Vectorizer.AI API Key
|
||||
zh_Hans: Vectorizer.AI API Key
|
||||
pt_BR: Vectorizer.AI API Key
|
||||
placeholder:
|
||||
en_US: Please input your Vectorizer.AI ApiKey
|
||||
zh_Hans: 请输入你的 Vectorizer.AI ApiKey
|
||||
pt_BR: Please input your Vectorizer.AI ApiKey
|
||||
help:
|
||||
en_US: Get your Vectorizer.AI API Key from Vectorizer.AI.
|
||||
zh_Hans: 从 Vectorizer.AI 获取您的 Vectorizer.AI API Key。
|
||||
pt_BR: Get your Vectorizer.AI API Key from Vectorizer.AI.
|
||||
|
|
|
|||
|
|
@ -242,11 +242,15 @@ class ToolManager:
|
|||
parameters = tool_entity.get_all_runtime_parameters()
|
||||
for parameter in parameters:
|
||||
# check file types
|
||||
if parameter.type in {
|
||||
ToolParameter.ToolParameterType.SYSTEM_FILES,
|
||||
ToolParameter.ToolParameterType.FILE,
|
||||
ToolParameter.ToolParameterType.FILES,
|
||||
}:
|
||||
if (
|
||||
parameter.type
|
||||
in {
|
||||
ToolParameter.ToolParameterType.SYSTEM_FILES,
|
||||
ToolParameter.ToolParameterType.FILE,
|
||||
ToolParameter.ToolParameterType.FILES,
|
||||
}
|
||||
and parameter.required
|
||||
):
|
||||
raise ValueError(f"file type parameter {parameter.name} not supported in agent")
|
||||
|
||||
if parameter.form == ToolParameter.ToolParameterForm.FORM:
|
||||
|
|
|
|||
|
|
@ -153,6 +153,7 @@ class AnswerStreamGeneratorRouter:
|
|||
NodeType.IF_ELSE,
|
||||
NodeType.QUESTION_CLASSIFIER,
|
||||
NodeType.ITERATION,
|
||||
NodeType.CONVERSATION_VARIABLE_ASSIGNER,
|
||||
}:
|
||||
answer_dependencies[answer_node_id].append(source_node_id)
|
||||
else:
|
||||
|
|
|
|||
|
|
@ -94,7 +94,7 @@ class Response:
|
|||
@property
|
||||
def is_file(self):
|
||||
content_type = self.content_type
|
||||
content_disposition = self.response.headers.get("Content-Disposition", "")
|
||||
content_disposition = self.response.headers.get("content-disposition", "")
|
||||
|
||||
return "attachment" in content_disposition or (
|
||||
not any(non_file in content_type for non_file in NON_FILE_CONTENT_TYPES)
|
||||
|
|
@ -103,7 +103,7 @@ class Response:
|
|||
|
||||
@property
|
||||
def content_type(self) -> str:
|
||||
return self.headers.get("Content-Type", "")
|
||||
return self.headers.get("content-type", "")
|
||||
|
||||
@property
|
||||
def text(self) -> str:
|
||||
|
|
|
|||
|
|
@ -33,7 +33,7 @@ class Executor:
|
|||
params: Mapping[str, str] | None
|
||||
content: str | bytes | None
|
||||
data: Mapping[str, Any] | None
|
||||
files: Mapping[str, bytes] | None
|
||||
files: Mapping[str, tuple[str | None, bytes, str]] | None
|
||||
json: Any
|
||||
headers: dict[str, str]
|
||||
auth: HttpRequestNodeAuthorization
|
||||
|
|
@ -141,7 +141,11 @@ class Executor:
|
|||
files = {k: self.variable_pool.get_file(selector) for k, selector in file_selectors.items()}
|
||||
files = {k: v for k, v in files.items() if v is not None}
|
||||
files = {k: variable.value for k, variable in files.items()}
|
||||
files = {k: file_manager.download(v) for k, v in files.items() if v.related_id is not None}
|
||||
files = {
|
||||
k: (v.filename, file_manager.download(v), v.mime_type or "application/octet-stream")
|
||||
for k, v in files.items()
|
||||
if v.related_id is not None
|
||||
}
|
||||
|
||||
self.data = form_data
|
||||
self.files = files
|
||||
|
|
|
|||
|
|
@ -142,10 +142,11 @@ class HttpRequestNode(BaseNode[HttpRequestNodeData]):
|
|||
Extract files from response
|
||||
"""
|
||||
files = []
|
||||
is_file = response.is_file
|
||||
content_type = response.content_type
|
||||
content = response.content
|
||||
|
||||
if content_type:
|
||||
if is_file and content_type:
|
||||
# extract filename from url
|
||||
filename = path.basename(url)
|
||||
# extract extension if possible
|
||||
|
|
|
|||
|
|
@ -327,7 +327,7 @@ class LLMNode(BaseNode[LLMNodeData]):
|
|||
if variable is None:
|
||||
raise ValueError(f"Variable {variable_selector.variable} not found")
|
||||
if isinstance(variable, NoneSegment):
|
||||
continue
|
||||
inputs[variable_selector.variable] = ""
|
||||
inputs[variable_selector.variable] = variable.to_object()
|
||||
|
||||
memory = node_data.memory
|
||||
|
|
|
|||
|
|
@ -1,8 +1,10 @@
|
|||
import logging
|
||||
import os
|
||||
import sys
|
||||
from datetime import datetime
|
||||
from logging.handlers import RotatingFileHandler
|
||||
|
||||
import pytz
|
||||
from flask import Flask
|
||||
|
||||
from configs import dify_config
|
||||
|
|
@ -30,16 +32,10 @@ def init_app(app: Flask):
|
|||
handlers=log_handlers,
|
||||
force=True,
|
||||
)
|
||||
|
||||
log_tz = dify_config.LOG_TZ
|
||||
if log_tz:
|
||||
from datetime import datetime
|
||||
|
||||
import pytz
|
||||
|
||||
timezone = pytz.timezone(log_tz)
|
||||
|
||||
def time_converter(seconds):
|
||||
return datetime.utcfromtimestamp(seconds).astimezone(timezone).timetuple()
|
||||
|
||||
for handler in logging.root.handlers:
|
||||
handler.formatter.converter = time_converter
|
||||
handler.formatter.converter = lambda seconds: (
|
||||
datetime.fromtimestamp(seconds, tz=pytz.UTC).astimezone(log_tz).timetuple()
|
||||
)
|
||||
|
|
|
|||
|
|
@ -1,4 +1,4 @@
|
|||
# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
|
||||
# This file is automatically @generated by Poetry 1.8.2 and should not be changed by hand.
|
||||
|
||||
[[package]]
|
||||
name = "aiohappyeyeballs"
|
||||
|
|
@ -932,6 +932,10 @@ files = [
|
|||
{file = "Brotli-1.1.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:a37b8f0391212d29b3a91a799c8e4a2855e0576911cdfb2515487e30e322253d"},
|
||||
{file = "Brotli-1.1.0-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:e84799f09591700a4154154cab9787452925578841a94321d5ee8fb9a9a328f0"},
|
||||
{file = "Brotli-1.1.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:f66b5337fa213f1da0d9000bc8dc0cb5b896b726eefd9c6046f699b169c41b9e"},
|
||||
{file = "Brotli-1.1.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:5dab0844f2cf82be357a0eb11a9087f70c5430b2c241493fc122bb6f2bb0917c"},
|
||||
{file = "Brotli-1.1.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:e4fe605b917c70283db7dfe5ada75e04561479075761a0b3866c081d035b01c1"},
|
||||
{file = "Brotli-1.1.0-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:1e9a65b5736232e7a7f91ff3d02277f11d339bf34099a56cdab6a8b3410a02b2"},
|
||||
{file = "Brotli-1.1.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:58d4b711689366d4a03ac7957ab8c28890415e267f9b6589969e74b6e42225ec"},
|
||||
{file = "Brotli-1.1.0-cp310-cp310-win32.whl", hash = "sha256:be36e3d172dc816333f33520154d708a2657ea63762ec16b62ece02ab5e4daf2"},
|
||||
{file = "Brotli-1.1.0-cp310-cp310-win_amd64.whl", hash = "sha256:0c6244521dda65ea562d5a69b9a26120769b7a9fb3db2fe9545935ed6735b128"},
|
||||
{file = "Brotli-1.1.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:a3daabb76a78f829cafc365531c972016e4aa8d5b4bf60660ad8ecee19df7ccc"},
|
||||
|
|
@ -944,8 +948,14 @@ files = [
|
|||
{file = "Brotli-1.1.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:19c116e796420b0cee3da1ccec3b764ed2952ccfcc298b55a10e5610ad7885f9"},
|
||||
{file = "Brotli-1.1.0-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:510b5b1bfbe20e1a7b3baf5fed9e9451873559a976c1a78eebaa3b86c57b4265"},
|
||||
{file = "Brotli-1.1.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:a1fd8a29719ccce974d523580987b7f8229aeace506952fa9ce1d53a033873c8"},
|
||||
{file = "Brotli-1.1.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:c247dd99d39e0338a604f8c2b3bc7061d5c2e9e2ac7ba9cc1be5a69cb6cd832f"},
|
||||
{file = "Brotli-1.1.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:1b2c248cd517c222d89e74669a4adfa5577e06ab68771a529060cf5a156e9757"},
|
||||
{file = "Brotli-1.1.0-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:2a24c50840d89ded6c9a8fdc7b6ed3692ed4e86f1c4a4a938e1e92def92933e0"},
|
||||
{file = "Brotli-1.1.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:f31859074d57b4639318523d6ffdca586ace54271a73ad23ad021acd807eb14b"},
|
||||
{file = "Brotli-1.1.0-cp311-cp311-win32.whl", hash = "sha256:39da8adedf6942d76dc3e46653e52df937a3c4d6d18fdc94a7c29d263b1f5b50"},
|
||||
{file = "Brotli-1.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:aac0411d20e345dc0920bdec5548e438e999ff68d77564d5e9463a7ca9d3e7b1"},
|
||||
{file = "Brotli-1.1.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:32d95b80260d79926f5fab3c41701dbb818fde1c9da590e77e571eefd14abe28"},
|
||||
{file = "Brotli-1.1.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:b760c65308ff1e462f65d69c12e4ae085cff3b332d894637f6273a12a482d09f"},
|
||||
{file = "Brotli-1.1.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:316cc9b17edf613ac76b1f1f305d2a748f1b976b033b049a6ecdfd5612c70409"},
|
||||
{file = "Brotli-1.1.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:caf9ee9a5775f3111642d33b86237b05808dafcd6268faa492250e9b78046eb2"},
|
||||
{file = "Brotli-1.1.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:70051525001750221daa10907c77830bc889cb6d865cc0b813d9db7fefc21451"},
|
||||
|
|
@ -956,8 +966,24 @@ files = [
|
|||
{file = "Brotli-1.1.0-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:4093c631e96fdd49e0377a9c167bfd75b6d0bad2ace734c6eb20b348bc3ea180"},
|
||||
{file = "Brotli-1.1.0-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:7e4c4629ddad63006efa0ef968c8e4751c5868ff0b1c5c40f76524e894c50248"},
|
||||
{file = "Brotli-1.1.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:861bf317735688269936f755fa136a99d1ed526883859f86e41a5d43c61d8966"},
|
||||
{file = "Brotli-1.1.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:87a3044c3a35055527ac75e419dfa9f4f3667a1e887ee80360589eb8c90aabb9"},
|
||||
{file = "Brotli-1.1.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:c5529b34c1c9d937168297f2c1fde7ebe9ebdd5e121297ff9c043bdb2ae3d6fb"},
|
||||
{file = "Brotli-1.1.0-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:ca63e1890ede90b2e4454f9a65135a4d387a4585ff8282bb72964fab893f2111"},
|
||||
{file = "Brotli-1.1.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:e79e6520141d792237c70bcd7a3b122d00f2613769ae0cb61c52e89fd3443839"},
|
||||
{file = "Brotli-1.1.0-cp312-cp312-win32.whl", hash = "sha256:5f4d5ea15c9382135076d2fb28dde923352fe02951e66935a9efaac8f10e81b0"},
|
||||
{file = "Brotli-1.1.0-cp312-cp312-win_amd64.whl", hash = "sha256:906bc3a79de8c4ae5b86d3d75a8b77e44404b0f4261714306e3ad248d8ab0951"},
|
||||
{file = "Brotli-1.1.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:8bf32b98b75c13ec7cf774164172683d6e7891088f6316e54425fde1efc276d5"},
|
||||
{file = "Brotli-1.1.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:7bc37c4d6b87fb1017ea28c9508b36bbcb0c3d18b4260fcdf08b200c74a6aee8"},
|
||||
{file = "Brotli-1.1.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3c0ef38c7a7014ffac184db9e04debe495d317cc9c6fb10071f7fefd93100a4f"},
|
||||
{file = "Brotli-1.1.0-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:91d7cc2a76b5567591d12c01f019dd7afce6ba8cba6571187e21e2fc418ae648"},
|
||||
{file = "Brotli-1.1.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a93dde851926f4f2678e704fadeb39e16c35d8baebd5252c9fd94ce8ce68c4a0"},
|
||||
{file = "Brotli-1.1.0-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f0db75f47be8b8abc8d9e31bc7aad0547ca26f24a54e6fd10231d623f183d089"},
|
||||
{file = "Brotli-1.1.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:6967ced6730aed543b8673008b5a391c3b1076d834ca438bbd70635c73775368"},
|
||||
{file = "Brotli-1.1.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:7eedaa5d036d9336c95915035fb57422054014ebdeb6f3b42eac809928e40d0c"},
|
||||
{file = "Brotli-1.1.0-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:d487f5432bf35b60ed625d7e1b448e2dc855422e87469e3f450aa5552b0eb284"},
|
||||
{file = "Brotli-1.1.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:832436e59afb93e1836081a20f324cb185836c617659b07b129141a8426973c7"},
|
||||
{file = "Brotli-1.1.0-cp313-cp313-win32.whl", hash = "sha256:43395e90523f9c23a3d5bdf004733246fba087f2948f87ab28015f12359ca6a0"},
|
||||
{file = "Brotli-1.1.0-cp313-cp313-win_amd64.whl", hash = "sha256:9011560a466d2eb3f5a6e4929cf4a09be405c64154e12df0dd72713f6500e32b"},
|
||||
{file = "Brotli-1.1.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:a090ca607cbb6a34b0391776f0cb48062081f5f60ddcce5d11838e67a01928d1"},
|
||||
{file = "Brotli-1.1.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2de9d02f5bda03d27ede52e8cfe7b865b066fa49258cbab568720aa5be80a47d"},
|
||||
{file = "Brotli-1.1.0-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2333e30a5e00fe0fe55903c8832e08ee9c3b1382aacf4db26664a16528d51b4b"},
|
||||
|
|
@ -967,6 +993,10 @@ files = [
|
|||
{file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:fd5f17ff8f14003595ab414e45fce13d073e0762394f957182e69035c9f3d7c2"},
|
||||
{file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_1_ppc64le.whl", hash = "sha256:069a121ac97412d1fe506da790b3e69f52254b9df4eb665cd42460c837193354"},
|
||||
{file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:e93dfc1a1165e385cc8239fab7c036fb2cd8093728cbd85097b284d7b99249a2"},
|
||||
{file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_2_aarch64.whl", hash = "sha256:aea440a510e14e818e67bfc4027880e2fb500c2ccb20ab21c7a7c8b5b4703d75"},
|
||||
{file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_2_i686.whl", hash = "sha256:6974f52a02321b36847cd19d1b8e381bf39939c21efd6ee2fc13a28b0d99348c"},
|
||||
{file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_2_ppc64le.whl", hash = "sha256:a7e53012d2853a07a4a79c00643832161a910674a893d296c9f1259859a289d2"},
|
||||
{file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_2_x86_64.whl", hash = "sha256:d7702622a8b40c49bffb46e1e3ba2e81268d5c04a34f460978c6b5517a34dd52"},
|
||||
{file = "Brotli-1.1.0-cp36-cp36m-win32.whl", hash = "sha256:a599669fd7c47233438a56936988a2478685e74854088ef5293802123b5b2460"},
|
||||
{file = "Brotli-1.1.0-cp36-cp36m-win_amd64.whl", hash = "sha256:d143fd47fad1db3d7c27a1b1d66162e855b5d50a89666af46e1679c496e8e579"},
|
||||
{file = "Brotli-1.1.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:11d00ed0a83fa22d29bc6b64ef636c4552ebafcef57154b4ddd132f5638fbd1c"},
|
||||
|
|
@ -978,6 +1008,10 @@ files = [
|
|||
{file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:919e32f147ae93a09fe064d77d5ebf4e35502a8df75c29fb05788528e330fe74"},
|
||||
{file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:23032ae55523cc7bccb4f6a0bf368cd25ad9bcdcc1990b64a647e7bbcce9cb5b"},
|
||||
{file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:224e57f6eac61cc449f498cc5f0e1725ba2071a3d4f48d5d9dffba42db196438"},
|
||||
{file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_2_aarch64.whl", hash = "sha256:cb1dac1770878ade83f2ccdf7d25e494f05c9165f5246b46a621cc849341dc01"},
|
||||
{file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_2_i686.whl", hash = "sha256:3ee8a80d67a4334482d9712b8e83ca6b1d9bc7e351931252ebef5d8f7335a547"},
|
||||
{file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_2_ppc64le.whl", hash = "sha256:5e55da2c8724191e5b557f8e18943b1b4839b8efc3ef60d65985bcf6f587dd38"},
|
||||
{file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_2_x86_64.whl", hash = "sha256:d342778ef319e1026af243ed0a07c97acf3bad33b9f29e7ae6a1f68fd083e90c"},
|
||||
{file = "Brotli-1.1.0-cp37-cp37m-win32.whl", hash = "sha256:587ca6d3cef6e4e868102672d3bd9dc9698c309ba56d41c2b9c85bbb903cdb95"},
|
||||
{file = "Brotli-1.1.0-cp37-cp37m-win_amd64.whl", hash = "sha256:2954c1c23f81c2eaf0b0717d9380bd348578a94161a65b3a2afc62c86467dd68"},
|
||||
{file = "Brotli-1.1.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:efa8b278894b14d6da122a72fefcebc28445f2d3f880ac59d46c90f4c13be9a3"},
|
||||
|
|
@ -990,6 +1024,10 @@ files = [
|
|||
{file = "Brotli-1.1.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:1ab4fbee0b2d9098c74f3057b2bc055a8bd92ccf02f65944a241b4349229185a"},
|
||||
{file = "Brotli-1.1.0-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:141bd4d93984070e097521ed07e2575b46f817d08f9fa42b16b9b5f27b5ac088"},
|
||||
{file = "Brotli-1.1.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:fce1473f3ccc4187f75b4690cfc922628aed4d3dd013d047f95a9b3919a86596"},
|
||||
{file = "Brotli-1.1.0-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:d2b35ca2c7f81d173d2fadc2f4f31e88cc5f7a39ae5b6db5513cf3383b0e0ec7"},
|
||||
{file = "Brotli-1.1.0-cp38-cp38-musllinux_1_2_i686.whl", hash = "sha256:af6fa6817889314555aede9a919612b23739395ce767fe7fcbea9a80bf140fe5"},
|
||||
{file = "Brotli-1.1.0-cp38-cp38-musllinux_1_2_ppc64le.whl", hash = "sha256:2feb1d960f760a575dbc5ab3b1c00504b24caaf6986e2dc2b01c09c87866a943"},
|
||||
{file = "Brotli-1.1.0-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:4410f84b33374409552ac9b6903507cdb31cd30d2501fc5ca13d18f73548444a"},
|
||||
{file = "Brotli-1.1.0-cp38-cp38-win32.whl", hash = "sha256:db85ecf4e609a48f4b29055f1e144231b90edc90af7481aa731ba2d059226b1b"},
|
||||
{file = "Brotli-1.1.0-cp38-cp38-win_amd64.whl", hash = "sha256:3d7954194c36e304e1523f55d7042c59dc53ec20dd4e9ea9d151f1b62b4415c0"},
|
||||
{file = "Brotli-1.1.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:5fb2ce4b8045c78ebbc7b8f3c15062e435d47e7393cc57c25115cfd49883747a"},
|
||||
|
|
@ -1002,6 +1040,10 @@ files = [
|
|||
{file = "Brotli-1.1.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:949f3b7c29912693cee0afcf09acd6ebc04c57af949d9bf77d6101ebb61e388c"},
|
||||
{file = "Brotli-1.1.0-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:89f4988c7203739d48c6f806f1e87a1d96e0806d44f0fba61dba81392c9e474d"},
|
||||
{file = "Brotli-1.1.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:de6551e370ef19f8de1807d0a9aa2cdfdce2e85ce88b122fe9f6b2b076837e59"},
|
||||
{file = "Brotli-1.1.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:0737ddb3068957cf1b054899b0883830bb1fec522ec76b1098f9b6e0f02d9419"},
|
||||
{file = "Brotli-1.1.0-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:4f3607b129417e111e30637af1b56f24f7a49e64763253bbc275c75fa887d4b2"},
|
||||
{file = "Brotli-1.1.0-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:6c6e0c425f22c1c719c42670d561ad682f7bfeeef918edea971a79ac5252437f"},
|
||||
{file = "Brotli-1.1.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:494994f807ba0b92092a163a0a283961369a65f6cbe01e8891132b7a320e61eb"},
|
||||
{file = "Brotli-1.1.0-cp39-cp39-win32.whl", hash = "sha256:f0d8a7a6b5983c2496e364b969f0e526647a06b075d034f3297dc66f3b360c64"},
|
||||
{file = "Brotli-1.1.0-cp39-cp39-win_amd64.whl", hash = "sha256:cdad5b9014d83ca68c25d2e9444e28e967ef16e80f6b436918c700c117a85467"},
|
||||
{file = "Brotli-1.1.0.tar.gz", hash = "sha256:81de08ac11bcb85841e440c13611c00b67d3bf82698314928d0b676362546724"},
|
||||
|
|
@ -1801,6 +1843,46 @@ requests = ">=2.8"
|
|||
six = "*"
|
||||
xmltodict = "*"
|
||||
|
||||
[[package]]
|
||||
name = "couchbase"
|
||||
version = "4.3.3"
|
||||
description = "Python Client for Couchbase"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
files = [
|
||||
{file = "couchbase-4.3.3-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:d8069e4f01332859d56cca597874645c914699162b3979d1b432f0dfc186b124"},
|
||||
{file = "couchbase-4.3.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:1caa6cfef49c785b35b1702102f718227f351df87bba2694b9334520c41e9eb5"},
|
||||
{file = "couchbase-4.3.3-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:f4a9a65c44935249fa078fb90a3c28ea71da9d2d5889fcd514b12d0538010ae0"},
|
||||
{file = "couchbase-4.3.3-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:4f144b8c482c18283d8e419b844630d41f3249b07d43d40b5e3535444e57d0fb"},
|
||||
{file = "couchbase-4.3.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:1c534fba6fdc7cf47eed9dee8a57d1e9eb867bf008574e321fa380a77cebf32f"},
|
||||
{file = "couchbase-4.3.3-cp310-cp310-win_amd64.whl", hash = "sha256:b841be06e0e4370b69ebef6bca3409c378186f7d6e964cd645ba18e97216c022"},
|
||||
{file = "couchbase-4.3.3-cp311-cp311-macosx_10_15_x86_64.whl", hash = "sha256:eee7a73b3acbdc78ae314fddf7f975b3c9e05df07df255f4dcc878939a2abae0"},
|
||||
{file = "couchbase-4.3.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:53417cafcf90ff4e2fd81ebba2a08b7ad56f17160d1c5019ad3b09c758aeb363"},
|
||||
{file = "couchbase-4.3.3-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:0cefd13bea8b0f150f1b9d27fd7614f971f77419b31817781d26ba315ed658bb"},
|
||||
{file = "couchbase-4.3.3-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:78fa1054d7740e2fe38fce0a2aab4e9a2d30263d894e0615ee5df297f02f59a3"},
|
||||
{file = "couchbase-4.3.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:eb093899cfad5a7472258a9b6a57775dbf23a6e0180241507ba89ce3ab241e41"},
|
||||
{file = "couchbase-4.3.3-cp311-cp311-win_amd64.whl", hash = "sha256:f7cfbdc699af5715f49365ffbb05a6a7366a534c0d7161edf270ad3e735a6c5d"},
|
||||
{file = "couchbase-4.3.3-cp312-cp312-macosx_10_15_x86_64.whl", hash = "sha256:58352cae9b8affdaa2ac012e0a03c8c2632ee6297a878232888b4e0360d0d5df"},
|
||||
{file = "couchbase-4.3.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:728e7e3b5e1682706cb9d63993d289226d02a25089527b8ecb4e3889dabc38cf"},
|
||||
{file = "couchbase-4.3.3-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:73014bf098cf14187a39cc13453e0d859c1d54568df28f69cc308a9a5f24feb2"},
|
||||
{file = "couchbase-4.3.3-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:a743375804068ae01b73c916bfca738764c8c12f381bb399ef04e784935856a1"},
|
||||
{file = "couchbase-4.3.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:394c122cfe02a76a99e7d5178e64129f6da49843225e78d8629abcab556c24af"},
|
||||
{file = "couchbase-4.3.3-cp312-cp312-win_amd64.whl", hash = "sha256:bf85d7a5cda548d9801614651206068b4445fa37972e62b14d7521a958198693"},
|
||||
{file = "couchbase-4.3.3-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:92d23c9cedd571631070791f2afee0e3d7d8c9ce1bf2ea6e9a4f2fdbc37a0f1e"},
|
||||
{file = "couchbase-4.3.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:38c42eb29a73cce2998ae5df45bd61b16dce9765d3bff968ec5cf6a622faa291"},
|
||||
{file = "couchbase-4.3.3-cp38-cp38-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:afed137bf0edc642d7b201b6ab7b1e7117bb4c8eac6b2f253cc6e106f334a2a1"},
|
||||
{file = "couchbase-4.3.3-cp38-cp38-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:954d991377d47883aaf903934c5d0f19577680a2abf80d3ce5bb9b3c80991fc7"},
|
||||
{file = "couchbase-4.3.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:d5552b9fa684630698dc98d6f3b1082540634c1b7ad5bf53b843b5da57b0169c"},
|
||||
{file = "couchbase-4.3.3-cp38-cp38-win_amd64.whl", hash = "sha256:f88f2b7e0c894f7237d9f3fb5c46abc44b8151a97b3ca8e75f57d23ebf59f9da"},
|
||||
{file = "couchbase-4.3.3-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:769e1e2367ea1d4de181fcd4b4e353e9abef97d15b581a6c5aea49ece3dc7d59"},
|
||||
{file = "couchbase-4.3.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:47f59a0b35ffce060583fd11f98f049f3b70701cf14aab9ac092594aca486aeb"},
|
||||
{file = "couchbase-4.3.3-cp39-cp39-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:440bb93d611827ba0ea2403c6f204fe931467a6cb5811f0e03bf1779204ef843"},
|
||||
{file = "couchbase-4.3.3-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:cdb4dde62e1d41c0b8707121ab68fa78b7a1508541bd48fc850be396f91bc8d9"},
|
||||
{file = "couchbase-4.3.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:7f8cf45f317b39cc19db5c67b565662f08d6c90305b3aa14e04bc22707258213"},
|
||||
{file = "couchbase-4.3.3-cp39-cp39-win_amd64.whl", hash = "sha256:c97d48ad486c8f201b4482d5594258f949369cb44792ed148d5159a3d12ae21b"},
|
||||
{file = "couchbase-4.3.3.tar.gz", hash = "sha256:27808500551564b39b46943cf3daab572694889c1eb638425d363edb48b20da7"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "coverage"
|
||||
version = "7.2.7"
|
||||
|
|
@ -6850,6 +6932,19 @@ files = [
|
|||
{file = "pyarrow-17.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:392bc9feabc647338e6c89267635e111d71edad5fcffba204425a7c8d13610d7"},
|
||||
{file = "pyarrow-17.0.0-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:af5ff82a04b2171415f1410cff7ebb79861afc5dae50be73ce06d6e870615204"},
|
||||
{file = "pyarrow-17.0.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:edca18eaca89cd6382dfbcff3dd2d87633433043650c07375d095cd3517561d8"},
|
||||
{file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7c7916bff914ac5d4a8fe25b7a25e432ff921e72f6f2b7547d1e325c1ad9d155"},
|
||||
{file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f553ca691b9e94b202ff741bdd40f6ccb70cdd5fbf65c187af132f1317de6145"},
|
||||
{file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:0cdb0e627c86c373205a2f94a510ac4376fdc523f8bb36beab2e7f204416163c"},
|
||||
{file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:d7d192305d9d8bc9082d10f361fc70a73590a4c65cf31c3e6926cd72b76bc35c"},
|
||||
{file = "pyarrow-17.0.0-cp38-cp38-win_amd64.whl", hash = "sha256:02dae06ce212d8b3244dd3e7d12d9c4d3046945a5933d28026598e9dbbda1fca"},
|
||||
{file = "pyarrow-17.0.0-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:13d7a460b412f31e4c0efa1148e1d29bdf18ad1411eb6757d38f8fbdcc8645fb"},
|
||||
{file = "pyarrow-17.0.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:9b564a51fbccfab5a04a80453e5ac6c9954a9c5ef2890d1bcf63741909c3f8df"},
|
||||
{file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:32503827abbc5aadedfa235f5ece8c4f8f8b0a3cf01066bc8d29de7539532687"},
|
||||
{file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a155acc7f154b9ffcc85497509bcd0d43efb80d6f733b0dc3bb14e281f131c8b"},
|
||||
{file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:dec8d129254d0188a49f8a1fc99e0560dc1b85f60af729f47de4046015f9b0a5"},
|
||||
{file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:a48ddf5c3c6a6c505904545c25a4ae13646ae1f8ba703c4df4a1bfe4f4006bda"},
|
||||
{file = "pyarrow-17.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:42bf93249a083aca230ba7e2786c5f673507fa97bbd9725a1e2754715151a204"},
|
||||
{file = "pyarrow-17.0.0.tar.gz", hash = "sha256:4beca9521ed2c0921c1023e68d097d0299b62c362639ea315572a58f3f50fd28"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
|
|
@ -7216,6 +7311,22 @@ files = [
|
|||
ed25519 = ["PyNaCl (>=1.4.0)"]
|
||||
rsa = ["cryptography"]
|
||||
|
||||
[[package]]
|
||||
name = "pyobvector"
|
||||
version = "0.1.6"
|
||||
description = "A python SDK for OceanBase Vector Store, based on SQLAlchemy, compatible with Milvus API."
|
||||
optional = false
|
||||
python-versions = "<4.0,>=3.9"
|
||||
files = [
|
||||
{file = "pyobvector-0.1.6-py3-none-any.whl", hash = "sha256:0d700e865a85b4716b9a03384189e49288cd9d5f3cef88aed4740bc82d5fd136"},
|
||||
{file = "pyobvector-0.1.6.tar.gz", hash = "sha256:05551addcac8c596992d5e38b480c83ca3481c6cfc6f56a1a1bddfb2e6ae037e"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
numpy = ">=1.26.0,<2.0.0"
|
||||
pymysql = ">=1.1.1,<2.0.0"
|
||||
sqlalchemy = ">=2.0.32,<3.0.0"
|
||||
|
||||
[[package]]
|
||||
name = "pyopenssl"
|
||||
version = "24.2.1"
|
||||
|
|
@ -8624,6 +8735,11 @@ files = [
|
|||
{file = "scikit_learn-1.5.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f60021ec1574e56632be2a36b946f8143bf4e5e6af4a06d85281adc22938e0dd"},
|
||||
{file = "scikit_learn-1.5.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:394397841449853c2290a32050382edaec3da89e35b3e03d6cc966aebc6a8ae6"},
|
||||
{file = "scikit_learn-1.5.2-cp312-cp312-win_amd64.whl", hash = "sha256:57cc1786cfd6bd118220a92ede80270132aa353647684efa385a74244a41e3b1"},
|
||||
{file = "scikit_learn-1.5.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:e9a702e2de732bbb20d3bad29ebd77fc05a6b427dc49964300340e4c9328b3f5"},
|
||||
{file = "scikit_learn-1.5.2-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:b0768ad641981f5d3a198430a1d31c3e044ed2e8a6f22166b4d546a5116d7908"},
|
||||
{file = "scikit_learn-1.5.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:178ddd0a5cb0044464fc1bfc4cca5b1833bfc7bb022d70b05db8530da4bb3dd3"},
|
||||
{file = "scikit_learn-1.5.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f7284ade780084d94505632241bf78c44ab3b6f1e8ccab3d2af58e0e950f9c12"},
|
||||
{file = "scikit_learn-1.5.2-cp313-cp313-win_amd64.whl", hash = "sha256:b7b0f9a0b1040830d38c39b91b3a44e1b643f4b36e36567b80b7c6bd2202a27f"},
|
||||
{file = "scikit_learn-1.5.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:757c7d514ddb00ae249832fe87100d9c73c6ea91423802872d9e74970a0e40b9"},
|
||||
{file = "scikit_learn-1.5.2-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:52788f48b5d8bca5c0736c175fa6bdaab2ef00a8f536cda698db61bd89c551c1"},
|
||||
{file = "scikit_learn-1.5.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:643964678f4b5fbdc95cbf8aec638acc7aa70f5f79ee2cdad1eec3df4ba6ead8"},
|
||||
|
|
@ -10866,4 +10982,4 @@ cffi = ["cffi (>=1.11)"]
|
|||
[metadata]
|
||||
lock-version = "2.0"
|
||||
python-versions = ">=3.10,<3.13"
|
||||
content-hash = "1b268122d3d4771ba219f0e983322e0454b7b8644dba35da38d7d950d489e1ba"
|
||||
content-hash = "ef927b98c33d704d680e08db0e5c7d9a4e05454c66fcd6a5f656a65eb08e886b"
|
||||
|
|
|
|||
|
|
@ -239,6 +239,7 @@ alibabacloud_gpdb20160503 = "~3.8.0"
|
|||
alibabacloud_tea_openapi = "~0.3.9"
|
||||
chromadb = "0.5.1"
|
||||
clickhouse-connect = "~0.7.16"
|
||||
couchbase = "~4.3.0"
|
||||
elasticsearch = "8.14.0"
|
||||
opensearch-py = "2.4.0"
|
||||
oracledb = "~2.2.1"
|
||||
|
|
@ -246,6 +247,7 @@ pgvecto-rs = { version = "~0.2.1", extras = ['sqlalchemy'] }
|
|||
pgvector = "0.2.5"
|
||||
pymilvus = "~2.4.4"
|
||||
pymochow = "1.3.1"
|
||||
pyobvector = "~0.1.6"
|
||||
qdrant-client = "1.7.3"
|
||||
tcvectordb = "1.3.2"
|
||||
tidb-vector = "0.0.9"
|
||||
|
|
|
|||
|
|
@ -27,3 +27,4 @@ env =
|
|||
XINFERENCE_GENERATION_MODEL_UID = generate
|
||||
XINFERENCE_RERANK_MODEL_UID = rerank
|
||||
XINFERENCE_SERVER_URL = http://a.abc.com:11451
|
||||
GITEE_AI_API_KEY = aaaaaaaaaaaaaaaaaaaa
|
||||
|
|
|
|||
|
|
@ -6,6 +6,8 @@ from typing import Any, Optional, Union
|
|||
import httpx
|
||||
import validators
|
||||
|
||||
from constants import HIDDEN_VALUE
|
||||
|
||||
# from tasks.external_document_indexing_task import external_document_indexing_task
|
||||
from core.helper import ssrf_proxy
|
||||
from extensions.ext_database import db
|
||||
|
|
@ -68,7 +70,7 @@ class ExternalDatasetService:
|
|||
|
||||
endpoint = f"{settings['endpoint']}/retrieval"
|
||||
api_key = settings["api_key"]
|
||||
if not validators.url(endpoint):
|
||||
if not validators.url(endpoint, simple_host=True):
|
||||
raise ValueError(f"invalid endpoint: {endpoint}")
|
||||
try:
|
||||
response = httpx.post(endpoint, headers={"Authorization": f"Bearer {api_key}"})
|
||||
|
|
@ -92,6 +94,8 @@ class ExternalDatasetService:
|
|||
).first()
|
||||
if external_knowledge_api is None:
|
||||
raise ValueError("api template not found")
|
||||
if args.get("settings") and args.get("settings").get("api_key") == HIDDEN_VALUE:
|
||||
args.get("settings")["api_key"] = external_knowledge_api.settings_dict.get("api_key")
|
||||
|
||||
external_knowledge_api.name = args.get("name")
|
||||
external_knowledge_api.description = args.get("description", "")
|
||||
|
|
|
|||
|
|
@ -83,3 +83,6 @@ VOLC_EMBEDDING_ENDPOINT_ID=
|
|||
|
||||
# 360 AI Credentials
|
||||
ZHINAO_API_KEY=
|
||||
|
||||
# Gitee AI Credentials
|
||||
GITEE_AI_API_KEY=
|
||||
|
|
|
|||
|
|
@ -0,0 +1,132 @@
|
|||
import os
|
||||
from collections.abc import Generator
|
||||
|
||||
import pytest
|
||||
|
||||
from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta
|
||||
from core.model_runtime.entities.message_entities import (
|
||||
AssistantPromptMessage,
|
||||
PromptMessageTool,
|
||||
SystemPromptMessage,
|
||||
UserPromptMessage,
|
||||
)
|
||||
from core.model_runtime.entities.model_entities import AIModelEntity
|
||||
from core.model_runtime.errors.validate import CredentialsValidateFailedError
|
||||
from core.model_runtime.model_providers.gitee_ai.llm.llm import GiteeAILargeLanguageModel
|
||||
|
||||
|
||||
def test_predefined_models():
|
||||
model = GiteeAILargeLanguageModel()
|
||||
model_schemas = model.predefined_models()
|
||||
|
||||
assert len(model_schemas) >= 1
|
||||
assert isinstance(model_schemas[0], AIModelEntity)
|
||||
|
||||
|
||||
def test_validate_credentials_for_chat_model():
|
||||
model = GiteeAILargeLanguageModel()
|
||||
|
||||
with pytest.raises(CredentialsValidateFailedError):
|
||||
# model name to gpt-3.5-turbo because of mocking
|
||||
model.validate_credentials(model="gpt-3.5-turbo", credentials={"api_key": "invalid_key"})
|
||||
|
||||
model.validate_credentials(
|
||||
model="Qwen2-7B-Instruct",
|
||||
credentials={"api_key": os.environ.get("GITEE_AI_API_KEY")},
|
||||
)
|
||||
|
||||
|
||||
def test_invoke_chat_model():
|
||||
model = GiteeAILargeLanguageModel()
|
||||
|
||||
result = model.invoke(
|
||||
model="Qwen2-7B-Instruct",
|
||||
credentials={"api_key": os.environ.get("GITEE_AI_API_KEY")},
|
||||
prompt_messages=[
|
||||
SystemPromptMessage(
|
||||
content="You are a helpful AI assistant.",
|
||||
),
|
||||
UserPromptMessage(content="Hello World!"),
|
||||
],
|
||||
model_parameters={
|
||||
"temperature": 0.0,
|
||||
"top_p": 1.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0,
|
||||
"max_tokens": 10,
|
||||
"stream": False,
|
||||
},
|
||||
stop=["How"],
|
||||
stream=False,
|
||||
user="foo",
|
||||
)
|
||||
|
||||
assert isinstance(result, LLMResult)
|
||||
assert len(result.message.content) > 0
|
||||
|
||||
|
||||
def test_invoke_stream_chat_model():
|
||||
model = GiteeAILargeLanguageModel()
|
||||
|
||||
result = model.invoke(
|
||||
model="Qwen2-7B-Instruct",
|
||||
credentials={"api_key": os.environ.get("GITEE_AI_API_KEY")},
|
||||
prompt_messages=[
|
||||
SystemPromptMessage(
|
||||
content="You are a helpful AI assistant.",
|
||||
),
|
||||
UserPromptMessage(content="Hello World!"),
|
||||
],
|
||||
model_parameters={"temperature": 0.0, "max_tokens": 100, "stream": False},
|
||||
stream=True,
|
||||
user="foo",
|
||||
)
|
||||
|
||||
assert isinstance(result, Generator)
|
||||
|
||||
for chunk in result:
|
||||
assert isinstance(chunk, LLMResultChunk)
|
||||
assert isinstance(chunk.delta, LLMResultChunkDelta)
|
||||
assert isinstance(chunk.delta.message, AssistantPromptMessage)
|
||||
assert len(chunk.delta.message.content) > 0 if chunk.delta.finish_reason is None else True
|
||||
if chunk.delta.finish_reason is not None:
|
||||
assert chunk.delta.usage is not None
|
||||
|
||||
|
||||
def test_get_num_tokens():
|
||||
model = GiteeAILargeLanguageModel()
|
||||
|
||||
num_tokens = model.get_num_tokens(
|
||||
model="Qwen2-7B-Instruct",
|
||||
credentials={"api_key": os.environ.get("GITEE_AI_API_KEY")},
|
||||
prompt_messages=[UserPromptMessage(content="Hello World!")],
|
||||
)
|
||||
|
||||
assert num_tokens == 10
|
||||
|
||||
num_tokens = model.get_num_tokens(
|
||||
model="Qwen2-7B-Instruct",
|
||||
credentials={"api_key": os.environ.get("GITEE_AI_API_KEY")},
|
||||
prompt_messages=[
|
||||
SystemPromptMessage(
|
||||
content="You are a helpful AI assistant.",
|
||||
),
|
||||
UserPromptMessage(content="Hello World!"),
|
||||
],
|
||||
tools=[
|
||||
PromptMessageTool(
|
||||
name="get_weather",
|
||||
description="Determine weather in my location",
|
||||
parameters={
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"location": {"type": "string", "description": "The city and state e.g. San Francisco, CA"},
|
||||
"unit": {"type": "string", "enum": ["c", "f"]},
|
||||
},
|
||||
"required": ["location"],
|
||||
},
|
||||
),
|
||||
],
|
||||
)
|
||||
|
||||
assert num_tokens == 77
|
||||
|
|
@ -0,0 +1,15 @@
|
|||
import os
|
||||
|
||||
import pytest
|
||||
|
||||
from core.model_runtime.errors.validate import CredentialsValidateFailedError
|
||||
from core.model_runtime.model_providers.gitee_ai.gitee_ai import GiteeAIProvider
|
||||
|
||||
|
||||
def test_validate_provider_credentials():
|
||||
provider = GiteeAIProvider()
|
||||
|
||||
with pytest.raises(CredentialsValidateFailedError):
|
||||
provider.validate_provider_credentials(credentials={"api_key": "invalid_key"})
|
||||
|
||||
provider.validate_provider_credentials(credentials={"api_key": os.environ.get("GITEE_AI_API_KEY")})
|
||||
|
|
@ -0,0 +1,47 @@
|
|||
import os
|
||||
|
||||
import pytest
|
||||
|
||||
from core.model_runtime.entities.rerank_entities import RerankResult
|
||||
from core.model_runtime.errors.validate import CredentialsValidateFailedError
|
||||
from core.model_runtime.model_providers.gitee_ai.rerank.rerank import GiteeAIRerankModel
|
||||
|
||||
|
||||
def test_validate_credentials():
|
||||
model = GiteeAIRerankModel()
|
||||
|
||||
with pytest.raises(CredentialsValidateFailedError):
|
||||
model.validate_credentials(
|
||||
model="bge-reranker-v2-m3",
|
||||
credentials={"api_key": "invalid_key"},
|
||||
)
|
||||
|
||||
model.validate_credentials(
|
||||
model="bge-reranker-v2-m3",
|
||||
credentials={
|
||||
"api_key": os.environ.get("GITEE_AI_API_KEY"),
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
def test_invoke_model():
|
||||
model = GiteeAIRerankModel()
|
||||
result = model.invoke(
|
||||
model="bge-reranker-v2-m3",
|
||||
credentials={
|
||||
"api_key": os.environ.get("GITEE_AI_API_KEY"),
|
||||
},
|
||||
query="What is the capital of the United States?",
|
||||
docs=[
|
||||
"Carson City is the capital city of the American state of Nevada. At the 2010 United States "
|
||||
"Census, Carson City had a population of 55,274.",
|
||||
"The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean that "
|
||||
"are a political division controlled by the United States. Its capital is Saipan.",
|
||||
],
|
||||
top_n=1,
|
||||
score_threshold=0.01,
|
||||
)
|
||||
|
||||
assert isinstance(result, RerankResult)
|
||||
assert len(result.docs) == 1
|
||||
assert result.docs[0].score >= 0.01
|
||||
|
|
@ -0,0 +1,45 @@
|
|||
import os
|
||||
|
||||
import pytest
|
||||
|
||||
from core.model_runtime.errors.validate import CredentialsValidateFailedError
|
||||
from core.model_runtime.model_providers.gitee_ai.speech2text.speech2text import GiteeAISpeech2TextModel
|
||||
|
||||
|
||||
def test_validate_credentials():
|
||||
model = GiteeAISpeech2TextModel()
|
||||
|
||||
with pytest.raises(CredentialsValidateFailedError):
|
||||
model.validate_credentials(
|
||||
model="whisper-base",
|
||||
credentials={"api_key": "invalid_key"},
|
||||
)
|
||||
|
||||
model.validate_credentials(
|
||||
model="whisper-base",
|
||||
credentials={"api_key": os.environ.get("GITEE_AI_API_KEY")},
|
||||
)
|
||||
|
||||
|
||||
def test_invoke_model():
|
||||
model = GiteeAISpeech2TextModel()
|
||||
|
||||
# Get the directory of the current file
|
||||
current_dir = os.path.dirname(os.path.abspath(__file__))
|
||||
|
||||
# Get assets directory
|
||||
assets_dir = os.path.join(os.path.dirname(current_dir), "assets")
|
||||
|
||||
# Construct the path to the audio file
|
||||
audio_file_path = os.path.join(assets_dir, "audio.mp3")
|
||||
|
||||
# Open the file and get the file object
|
||||
with open(audio_file_path, "rb") as audio_file:
|
||||
file = audio_file
|
||||
|
||||
result = model.invoke(
|
||||
model="whisper-base", credentials={"api_key": os.environ.get("GITEE_AI_API_KEY")}, file=file
|
||||
)
|
||||
|
||||
assert isinstance(result, str)
|
||||
assert result == "1 2 3 4 5 6 7 8 9 10"
|
||||
|
|
@ -0,0 +1,46 @@
|
|||
import os
|
||||
|
||||
import pytest
|
||||
|
||||
from core.model_runtime.entities.text_embedding_entities import TextEmbeddingResult
|
||||
from core.model_runtime.errors.validate import CredentialsValidateFailedError
|
||||
from core.model_runtime.model_providers.gitee_ai.text_embedding.text_embedding import GiteeAIEmbeddingModel
|
||||
|
||||
|
||||
def test_validate_credentials():
|
||||
model = GiteeAIEmbeddingModel()
|
||||
|
||||
with pytest.raises(CredentialsValidateFailedError):
|
||||
model.validate_credentials(model="bge-large-zh-v1.5", credentials={"api_key": "invalid_key"})
|
||||
|
||||
model.validate_credentials(model="bge-large-zh-v1.5", credentials={"api_key": os.environ.get("GITEE_AI_API_KEY")})
|
||||
|
||||
|
||||
def test_invoke_model():
|
||||
model = GiteeAIEmbeddingModel()
|
||||
|
||||
result = model.invoke(
|
||||
model="bge-large-zh-v1.5",
|
||||
credentials={
|
||||
"api_key": os.environ.get("GITEE_AI_API_KEY"),
|
||||
},
|
||||
texts=["hello", "world"],
|
||||
user="user",
|
||||
)
|
||||
|
||||
assert isinstance(result, TextEmbeddingResult)
|
||||
assert len(result.embeddings) == 2
|
||||
|
||||
|
||||
def test_get_num_tokens():
|
||||
model = GiteeAIEmbeddingModel()
|
||||
|
||||
num_tokens = model.get_num_tokens(
|
||||
model="bge-large-zh-v1.5",
|
||||
credentials={
|
||||
"api_key": os.environ.get("GITEE_AI_API_KEY"),
|
||||
},
|
||||
texts=["hello", "world"],
|
||||
)
|
||||
|
||||
assert num_tokens == 2
|
||||
|
|
@ -0,0 +1,23 @@
|
|||
import os
|
||||
|
||||
from core.model_runtime.model_providers.gitee_ai.tts.tts import GiteeAIText2SpeechModel
|
||||
|
||||
|
||||
def test_invoke_model():
|
||||
model = GiteeAIText2SpeechModel()
|
||||
|
||||
result = model.invoke(
|
||||
model="speecht5_tts",
|
||||
tenant_id="test",
|
||||
credentials={
|
||||
"api_key": os.environ.get("GITEE_AI_API_KEY"),
|
||||
},
|
||||
content_text="Hello, world!",
|
||||
voice="",
|
||||
)
|
||||
|
||||
content = b""
|
||||
for chunk in result:
|
||||
content += chunk
|
||||
|
||||
assert content != b""
|
||||
|
|
@ -0,0 +1,50 @@
|
|||
import subprocess
|
||||
import time
|
||||
|
||||
from core.rag.datasource.vdb.couchbase.couchbase_vector import CouchbaseConfig, CouchbaseVector
|
||||
from tests.integration_tests.vdb.test_vector_store import (
|
||||
AbstractVectorTest,
|
||||
get_example_text,
|
||||
setup_mock_redis,
|
||||
)
|
||||
|
||||
|
||||
def wait_for_healthy_container(service_name="couchbase-server", timeout=300):
|
||||
start_time = time.time()
|
||||
while time.time() - start_time < timeout:
|
||||
result = subprocess.run(
|
||||
["docker", "inspect", "--format", "{{.State.Health.Status}}", service_name], capture_output=True, text=True
|
||||
)
|
||||
if result.stdout.strip() == "healthy":
|
||||
print(f"{service_name} is healthy!")
|
||||
return True
|
||||
else:
|
||||
print(f"Waiting for {service_name} to be healthy...")
|
||||
time.sleep(10)
|
||||
raise TimeoutError(f"{service_name} did not become healthy in time")
|
||||
|
||||
|
||||
class CouchbaseTest(AbstractVectorTest):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.vector = CouchbaseVector(
|
||||
collection_name=self.collection_name,
|
||||
config=CouchbaseConfig(
|
||||
connection_string="couchbase://127.0.0.1",
|
||||
user="Administrator",
|
||||
password="password",
|
||||
bucket_name="Embeddings",
|
||||
scope_name="_default",
|
||||
),
|
||||
)
|
||||
|
||||
def search_by_vector(self):
|
||||
# brief sleep to ensure document is indexed
|
||||
time.sleep(5)
|
||||
hits_by_vector = self.vector.search_by_vector(query_vector=self.example_embedding)
|
||||
assert len(hits_by_vector) == 1
|
||||
|
||||
|
||||
def test_couchbase(setup_mock_redis):
|
||||
wait_for_healthy_container("couchbase-server", timeout=60)
|
||||
CouchbaseTest().run_all_tests()
|
||||
|
|
@ -0,0 +1,71 @@
|
|||
from unittest.mock import MagicMock, patch
|
||||
|
||||
import pytest
|
||||
|
||||
from core.rag.datasource.vdb.oceanbase.oceanbase_vector import (
|
||||
OceanBaseVector,
|
||||
OceanBaseVectorConfig,
|
||||
)
|
||||
from tests.integration_tests.vdb.__mock.tcvectordb import setup_tcvectordb_mock
|
||||
from tests.integration_tests.vdb.test_vector_store import (
|
||||
AbstractVectorTest,
|
||||
get_example_text,
|
||||
setup_mock_redis,
|
||||
)
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def oceanbase_vector():
|
||||
return OceanBaseVector(
|
||||
"dify_test_collection",
|
||||
config=OceanBaseVectorConfig(
|
||||
host="127.0.0.1",
|
||||
port="2881",
|
||||
user="root@test",
|
||||
database="test",
|
||||
password="test",
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
class OceanBaseVectorTest(AbstractVectorTest):
|
||||
def __init__(self, vector: OceanBaseVector):
|
||||
super().__init__()
|
||||
self.vector = vector
|
||||
|
||||
def search_by_vector(self):
|
||||
hits_by_vector = self.vector.search_by_vector(query_vector=self.example_embedding)
|
||||
assert len(hits_by_vector) == 0
|
||||
|
||||
def search_by_full_text(self):
|
||||
hits_by_full_text = self.vector.search_by_full_text(query=get_example_text())
|
||||
assert len(hits_by_full_text) == 0
|
||||
|
||||
def text_exists(self):
|
||||
exist = self.vector.text_exists(self.example_doc_id)
|
||||
assert exist == True
|
||||
|
||||
def get_ids_by_metadata_field(self):
|
||||
ids = self.vector.get_ids_by_metadata_field(key="document_id", value=self.example_doc_id)
|
||||
assert len(ids) == 0
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def setup_mock_oceanbase_client():
|
||||
with patch("core.rag.datasource.vdb.oceanbase.oceanbase_vector.ObVecClient", new_callable=MagicMock) as mock_client:
|
||||
yield mock_client
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def setup_mock_oceanbase_vector(oceanbase_vector):
|
||||
with patch.object(oceanbase_vector, "_client"):
|
||||
yield oceanbase_vector
|
||||
|
||||
|
||||
def test_oceanbase_vector(
|
||||
setup_mock_redis,
|
||||
setup_mock_oceanbase_client,
|
||||
setup_mock_oceanbase_vector,
|
||||
oceanbase_vector,
|
||||
):
|
||||
OceanBaseVectorTest(oceanbase_vector).run_all_tests()
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue