refactor(list_operator): replace ValueError with InvalidKeyError

- Improves error handling by using a more specific InvalidKeyError for invalid order keys.
- Enhances code readability and maintainability by distinguishing between error types.

.devcontainer/post_start_command.sh

@@ -1,3 +1,3 @@
 #!/bin/bash
 
-poetry install -C api
+cd api && poetry install

.github/workflows/api-tests.yml

@@ -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

.github/workflows/build-push.yml

@@ -49,7 +49,7 @@ jobs:
           echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
 
       - name: Login to Docker Hub
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           username: ${{ env.DOCKERHUB_USER }}
           password: ${{ env.DOCKERHUB_TOKEN }}
@@ -114,7 +114,7 @@ jobs:
           merge-multiple: true
 
       - name: Login to Docker Hub
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           username: ${{ env.DOCKERHUB_USER }}
           password: ${{ env.DOCKERHUB_TOKEN }}

.github/workflows/expose_service_ports.sh

@@ -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"

.gitignore

@@ -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/*
@@ -189,4 +191,4 @@ pyrightconfig.json
 api/.vscode
 
 .idea/
-.vscode
+.vscode

README.md

@@ -1,5 +1,9 @@
 ![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
 
+<p align="center">
+  📌 <a href="https://dify.ai/blog/introducing-dify-workflow-file-upload-a-demo-on-ai-podcast">Introducing Dify Workflow File Upload: Recreate Google NotebookLM Podcast</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">Self-hosting</a> ·
@@ -42,6 +46,56 @@
 </p>
 
 
+## Table of Content
+0. [Quick-Start🚀](https://github.com/langgenius/dify?tab=readme-ov-file#quick-start)
+
+1. [Intro📖](https://github.com/langgenius/dify?tab=readme-ov-file#intro)
+
+2. [How to use🔧](https://github.com/langgenius/dify?tab=readme-ov-file#using-dify)
+
+3. [Stay Ahead🏃](https://github.com/langgenius/dify?tab=readme-ov-file#staying-ahead)
+
+4. [Next Steps🏹](https://github.com/langgenius/dify?tab=readme-ov-file#next-steps)
+
+5. [Contributing💪](https://github.com/langgenius/dify?tab=readme-ov-file#contributing)
+
+6. [Community and Contact🏠](https://github.com/langgenius/dify?tab=readme-ov-file#community--contact)
+
+7. [Star-History📈](https://github.com/langgenius/dify?tab=readme-ov-file#star-history)
+
+8. [Security🔒](https://github.com/langgenius/dify?tab=readme-ov-file#security-disclosure)
+
+9. [License🤝](https://github.com/langgenius/dify?tab=readme-ov-file#license)
+
+> Make sure you read through this README before you start utilizing Dify😊
+
+
+## Quick start
+The quickest way to deploy Dify locally is to run our [docker-compose.yml](https://github.com/langgenius/dify/blob/main/docker/docker-compose.yaml). Follow the instructions to start in 5 minutes.
+
+> Before installing Dify, make sure your machine meets the following minimum system requirements:
+> 
+>- CPU >= 2 Core
+>- RAM >= 4 GiB
+>- Docker and Docker Compose Installed
+</br>
+
+Run the following command in your terminal to clone the whole repo.
+```bash
+git clone https://github.com/langgenius/dify.git
+```
+After cloning,run the following command one by one.
+```bash
+cd dify
+cd docker
+cp .env.example .env
+docker compose up -d
+```
+
+After running, you can access the Dify dashboard in your browser at [http://localhost/install](http://localhost/install) and start the initialization process. You will be asked to setup an admin account.
+For more info of quick setup, check [here](https://docs.dify.ai/getting-started/install-self-hosted/docker-compose)
+
+## Intro
 Dify is an open-source LLM app development platform. Its intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production. Here's a list of the core features:
 </br> </br>
 
@@ -75,73 +129,6 @@ Dify is an open-source LLM app development platform. Its intuitive interface com
   All of Dify's offerings come with corresponding APIs, so you could effortlessly integrate Dify into your own business logic.
 
 
-## Feature comparison
-<table style="width: 100%;">
-  <tr>
-    <th align="center">Feature</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">Programming Approach</td>
-    <td align="center">API + App-oriented</td>
-    <td align="center">Python Code</td>
-    <td align="center">App-oriented</td>
-    <td align="center">API-oriented</td>
-  </tr>
-  <tr>
-    <td align="center">Supported LLMs</td>
-    <td align="center">Rich Variety</td>
-    <td align="center">Rich Variety</td>
-    <td align="center">Rich Variety</td>
-    <td align="center">OpenAI-only</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">Agent</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">Observability</td>
-    <td align="center">✅</td>
-    <td align="center">✅</td>
-    <td align="center">❌</td>
-    <td align="center">❌</td>
-  </tr>
-  <tr>
-    <td align="center">Enterprise Features (SSO/Access control)</td>
-    <td align="center">✅</td>
-    <td align="center">❌</td>
-    <td align="center">❌</td>
-    <td align="center">❌</td>
-  </tr>
-  <tr>
-    <td align="center">Local Deployment</td>
-    <td align="center">✅</td>
-    <td align="center">✅</td>
-    <td align="center">✅</td>
-    <td align="center">❌</td>
-  </tr>
-</table>
-
 ## Using Dify
 
 - **Cloud </br>**
@@ -162,30 +149,21 @@ Star Dify on GitHub and be instantly notified of new releases.
 
 ![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4)
 
-
-
-## Quick start
-> Before installing Dify, make sure your machine meets the following minimum system requirements:
-> 
->- CPU >= 2 Core
->- RAM >= 4 GiB
-
-</br>
-
-The easiest way to start the Dify server is to run our [docker-compose.yml](docker/docker-compose.yaml) file. Before running the installation command, make sure that [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/install/) are installed on your machine:
-
-```bash
-cd docker
-cp .env.example .env
-docker compose up -d
-```
-
-After running, you can access the Dify dashboard in your browser at [http://localhost/install](http://localhost/install) and start the initialization process.
-
-> If you'd like to contribute to Dify or do additional development, refer to our [guide to deploying from source code](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code)
-
 ## Next steps
 
+Go to [quick-start](https://github.com/langgenius/dify?tab=readme-ov-file#quick-start) to setup your Dify or setup by source code.
+
+#### If you......
+If you forget your admin account, you can refer to this [guide](https://docs.dify.ai/getting-started/install-self-hosted/faqs#id-4.-how-to-reset-the-password-of-the-admin-account) to reset the password.
+
+> Use docker compose up without "-d" to enable logs printing out in your terminal. This might be useful if you have encountered unknow problems when using Dify.
+
+If you encountered system error and would like to acquire help in Github issues, make sure you always paste logs of the error in the request to accerate the conversation. Go to [Community & contact](https://github.com/langgenius/dify?tab=readme-ov-file#community--contact) for more information.
+
+> Please read the [Dify Documentation](https://docs.dify.ai/) for detailed how-to-use guidance. Most of the potential problems are explained in the doc.
+
+> If you'd like to contribute to Dify or make additional development, refer to our [guide to deploying from source code](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code)
+
 If you need to customize the configuration, please refer to the comments in our [.env.example](docker/.env.example) file and update the corresponding values in your `.env` file. Additionally, you might need to make adjustments to the `docker-compose.yaml` file itself, such as changing image versions, port mappings, or volume mounts, based on your specific deployment environment and requirements. After making any changes, please re-run `docker-compose up -d`. You can find the full list of available environment variables [here](https://docs.dify.ai/getting-started/install-self-hosted/environments).
 
 If you'd like to configure a highly-available setup, there are community-contributed [Helm Charts](https://helm.sh/) and YAML files which allow Dify to be deployed on Kubernetes.
@@ -224,6 +202,7 @@ At the same time, please consider supporting Dify by sharing it on social media
 * [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
 * [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
 * [X(Twitter)](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
+* Make sure a log, if possible, is attached to an error reported to maximize solution efficiency.
 
 ## Star history
 

README_PT.md

@@ -0,0 +1,241 @@
+![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+
+<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).
+
+![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)
+
+
+**3. IDE de Prompt**: 
+  Interface intuitiva para criação de prompts, comparação de desempenho de modelos e adição de recursos como conversão de texto para fala em um aplicativo baseado em chat. 
+
+**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.
+
+![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4)
+
+
+
+## Início rápido
+> Antes de instalar o Dify, certifique-se de que sua máquina atenda aos seguintes requisitos mínimos de sistema:
+> 
+>- CPU >= 2 Núcleos
+>- RAM >= 4 GiB
+
+</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
+
+[![Gráfico de Histórico de Estrelas](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](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.

api/.env.example

@@ -31,8 +31,17 @@ REDIS_HOST=localhost
 REDIS_PORT=6379
 REDIS_USERNAME=
 REDIS_PASSWORD=difyai123456
+REDIS_USE_SSL=false
 REDIS_DB=0
 
+# redis Sentinel configuration.
+REDIS_USE_SENTINEL=false
+REDIS_SENTINELS=
+REDIS_SENTINEL_SERVICE_NAME=
+REDIS_SENTINEL_USERNAME=
+REDIS_SENTINEL_PASSWORD=
+REDIS_SENTINEL_SOCKET_TIMEOUT=0.1
+
 # PostgreSQL database configuration
 DB_USERNAME=postgres
 DB_PASSWORD=difyai123456
@@ -111,7 +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
@@ -127,6 +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=
@@ -186,6 +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
@@ -233,6 +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

api/Dockerfile

@@ -55,7 +55,12 @@ RUN apt-get update \
     && echo "deb http://deb.debian.org/debian testing main" > /etc/apt/sources.list \
     && apt-get update \
     # For Security
-    && apt-get install -y --no-install-recommends zlib1g=1:1.3.dfsg+really1.3.1-1 expat=2.6.3-1 libldap-2.5-0=2.5.18+dfsg-3+b1 perl=5.40.0-6 libsqlite3-0=3.46.1-1 \
+    && apt-get install -y --no-install-recommends expat=2.6.3-2 libldap-2.5-0=2.5.18+dfsg-3+b1 perl=5.40.0-6 libsqlite3-0=3.46.1-1 \
+    && if [ "$(dpkg --print-architecture)" = "amd64" ]; then \
+        apt-get install -y --no-install-recommends zlib1g=1:1.3.dfsg+really1.3.1-1+b1; \
+    else \
+        apt-get install -y --no-install-recommends zlib1g=1:1.3.dfsg+really1.3.1-1; \
+    fi \
     # install a chinese font to support the use of tools like matplotlib
     && apt-get install -y fonts-noto-cjk \
     && apt-get autoremove -y \

api/commands.py

@@ -278,6 +278,8 @@ def migrate_knowledge_vector_database():
         VectorType.BAIDU,
         VectorType.VIKINGDB,
         VectorType.UPSTASH,
+        VectorType.COUCHBASE,
+        VectorType.OCEANBASE,
     }
     page = 1
     while True:

api/configs/feature/__init__.py

@@ -571,6 +571,11 @@ class DataSetConfig(BaseSettings):
         default=False,
     )
 
+    TIDB_SERVERLESS_NUMBER: PositiveInt = Field(
+        description="number of tidb serverless cluster",
+        default=500,
+    )
+
 
 class WorkspaceConfig(BaseSettings):
     """

api/configs/middleware/__init__.py

@@ -16,10 +16,13 @@ from configs.middleware.storage.supabase_storage_config import SupabaseStorageCo
 from configs.middleware.storage.tencent_cos_storage_config import TencentCloudCOSStorageConfig
 from configs.middleware.storage.volcengine_tos_storage_config import VolcengineTOSStorageConfig
 from configs.middleware.vdb.analyticdb_config import AnalyticdbConfig
+from configs.middleware.vdb.baidu_vector_config import BaiduVectorDBConfig
 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
@@ -27,6 +30,7 @@ from configs.middleware.vdb.pgvectors_config import PGVectoRSConfig
 from configs.middleware.vdb.qdrant_config import QdrantConfig
 from configs.middleware.vdb.relyt_config import RelytConfig
 from configs.middleware.vdb.tencent_vector_config import TencentVectorDBConfig
+from configs.middleware.vdb.tidb_on_qdrant_config import TidbOnQdrantConfig
 from configs.middleware.vdb.tidb_vector_config import TiDBVectorConfig
 from configs.middleware.vdb.upstash_config import UpstashConfig
 from configs.middleware.vdb.vikingdb_config import VikingDBConfig
@@ -54,6 +58,11 @@ class VectorStoreConfig(BaseSettings):
         default=None,
     )
 
+    VECTOR_STORE_WHITELIST_ENABLE: Optional[bool] = Field(
+        description="Enable whitelist for vector store.",
+        default=False,
+    )
+
 
 class KeywordStoreConfig(BaseSettings):
     KEYWORD_STORE: str = Field(
@@ -245,8 +254,12 @@ class MiddlewareConfig(
     TiDBVectorConfig,
     WeaviateConfig,
     ElasticsearchConfig,
+    CouchbaseConfig,
     InternalTestConfig,
     VikingDBConfig,
     UpstashConfig,
+    TidbOnQdrantConfig,
+    OceanBaseVectorConfig,
+    BaiduVectorDBConfig,
 ):
     pass

api/configs/middleware/vdb/couchbase_config.py

@@ -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,
+    )

api/configs/middleware/vdb/oceanbase_config.py

@@ -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,
+    )

api/configs/middleware/vdb/tidb_on_qdrant_config.py

@@ -0,0 +1,70 @@
+from typing import Optional
+
+from pydantic import Field, NonNegativeInt, PositiveInt
+from pydantic_settings import BaseSettings
+
+
+class TidbOnQdrantConfig(BaseSettings):
+    """
+    Tidb on Qdrant configs
+    """
+
+    TIDB_ON_QDRANT_URL: Optional[str] = Field(
+        description="Tidb on Qdrant url",
+        default=None,
+    )
+
+    TIDB_ON_QDRANT_API_KEY: Optional[str] = Field(
+        description="Tidb on Qdrant api key",
+        default=None,
+    )
+
+    TIDB_ON_QDRANT_CLIENT_TIMEOUT: NonNegativeInt = Field(
+        description="Tidb on Qdrant client timeout in seconds",
+        default=20,
+    )
+
+    TIDB_ON_QDRANT_GRPC_ENABLED: bool = Field(
+        description="whether enable grpc support for Tidb on Qdrant connection",
+        default=False,
+    )
+
+    TIDB_ON_QDRANT_GRPC_PORT: PositiveInt = Field(
+        description="Tidb on Qdrant grpc port",
+        default=6334,
+    )
+
+    TIDB_PUBLIC_KEY: Optional[str] = Field(
+        description="Tidb account public key",
+        default=None,
+    )
+
+    TIDB_PRIVATE_KEY: Optional[str] = Field(
+        description="Tidb account private key",
+        default=None,
+    )
+
+    TIDB_API_URL: Optional[str] = Field(
+        description="Tidb API url",
+        default=None,
+    )
+
+    TIDB_IAM_API_URL: Optional[str] = Field(
+        description="Tidb IAM API url",
+        default=None,
+    )
+
+    TIDB_REGION: Optional[str] = Field(
+        description="Tidb serverless region",
+        default="regions/aws-us-east-1",
+    )
+
+    TIDB_PROJECT_ID: Optional[str] = Field(
+        description="Tidb project id",
+        default=None,
+    )
+
+    TIDB_SPEND_LIMIT: Optional[int] = Field(
+        description="Tidb spend limit",
+        default=100,
+    )

api/configs/packaging/__init__.py

@@ -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(

api/controllers/common/errors.py

@@ -0,0 +1,6 @@
+from werkzeug.exceptions import HTTPException
+
+
+class FilenameNotExistsError(HTTPException):
+    code = 400
+    description = "The specified filename does not exist."

api/controllers/common/helpers.py

@@ -0,0 +1,58 @@
+import mimetypes
+import os
+import re
+import urllib.parse
+from uuid import uuid4
+
+import httpx
+from pydantic import BaseModel
+
+
+class FileInfo(BaseModel):
+    filename: str
+    extension: str
+    mimetype: str
+    size: int
+
+
+def guess_file_info_from_response(response: httpx.Response):
+    url = str(response.url)
+    # Try to extract filename from URL
+    parsed_url = urllib.parse.urlparse(url)
+    url_path = parsed_url.path
+    filename = os.path.basename(url_path)
+
+    # If filename couldn't be extracted, use Content-Disposition header
+    if not filename:
+        content_disposition = response.headers.get("Content-Disposition")
+        if content_disposition:
+            filename_match = re.search(r'filename="?(.+)"?', content_disposition)
+            if filename_match:
+                filename = filename_match.group(1)
+
+    # If still no filename, generate a unique one
+    if not filename:
+        unique_name = str(uuid4())
+        filename = f"{unique_name}"
+
+    # Guess MIME type from filename first, then URL
+    mimetype, _ = mimetypes.guess_type(filename)
+    if mimetype is None:
+        mimetype, _ = mimetypes.guess_type(url)
+    if mimetype is None:
+        # If guessing fails, use Content-Type from response headers
+        mimetype = response.headers.get("Content-Type", "application/octet-stream")
+
+    extension = os.path.splitext(filename)[1]
+
+    # Ensure filename has an extension
+    if not extension:
+        extension = mimetypes.guess_extension(mimetype) or ".bin"
+        filename = f"{filename}{extension}"
+
+    return FileInfo(
+        filename=filename,
+        extension=extension,
+        mimetype=mimetype,
+        size=int(response.headers.get("Content-Length", -1)),
+    )

api/controllers/console/__init__.py

@@ -2,9 +2,21 @@ from flask import Blueprint
 
 from libs.external_api import ExternalApi
 
+from .files import FileApi, FilePreviewApi, FileSupportTypeApi
+from .remote_files import RemoteFileInfoApi, RemoteFileUploadApi
+
 bp = Blueprint("console", __name__, url_prefix="/console/api")
 api = ExternalApi(bp)
 
+# File
+api.add_resource(FileApi, "/files/upload")
+api.add_resource(FilePreviewApi, "/files/<uuid:file_id>/preview")
+api.add_resource(FileSupportTypeApi, "/files/support-type")
+
+# Remote files
+api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")
+api.add_resource(RemoteFileUploadApi, "/remote-files/upload")
+
 # Import other controllers
 from . import admin, apikey, extension, feature, ping, setup, version
 
@@ -43,7 +55,6 @@ from .datasets import (
     datasets_document,
     datasets_segments,
     external,
-    file,
     hit_testing,
     website,
 )

api/controllers/console/apikey.py

@@ -10,8 +10,7 @@ from models.dataset import Dataset
 from models.model import ApiToken, App
 
 from . import api
-from .setup import setup_required
-from .wraps import account_initialization_required
+from .wraps import account_initialization_required, setup_required
 
 api_key_fields = {
     "id": fields.String,

api/controllers/console/app/advanced_prompt_template.py

@@ -1,8 +1,7 @@
 from flask_restful import Resource, reqparse
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from libs.login import login_required
 from services.advanced_prompt_template_service import AdvancedPromptTemplateService
 

api/controllers/console/app/agent.py

@@ -2,8 +2,7 @@ from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from libs.helper import uuid_value
 from libs.login import login_required
 from models.model import AppMode

api/controllers/console/app/annotation.py

@@ -6,8 +6,11 @@ from werkzeug.exceptions import Forbidden
 from controllers.console import api
 from controllers.console.app.error import NoFileUploadedError
 from controllers.console.datasets.error import TooManyFilesError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
 from extensions.ext_redis import redis_client
 from fields.annotation_fields import (
     annotation_fields,

api/controllers/console/app/app.py

@@ -6,8 +6,11 @@ from werkzeug.exceptions import BadRequest, Forbidden, abort
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
 from core.ops.ops_trace_manager import OpsTraceManager
 from fields.app_fields import (
     app_detail_fields,

api/controllers/console/app/audio.py

@@ -18,8 +18,7 @@ from controllers.console.app.error import (
     UnsupportedAudioTypeError,
 )
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError
 from libs.login import login_required

api/controllers/console/app/completion.py

@@ -15,8 +15,7 @@ from controllers.console.app.error import (
     ProviderQuotaExceededError,
 )
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom

api/controllers/console/app/conversation.py

@@ -10,8 +10,7 @@ from werkzeug.exceptions import Forbidden, NotFound
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.app.entities.app_invoke_entities import InvokeFrom
 from extensions.ext_database import db
 from fields.conversation_fields import (

api/controllers/console/app/conversation_variables.py

@@ -4,8 +4,7 @@ from sqlalchemy.orm import Session
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from extensions.ext_database import db
 from fields.conversation_variable_fields import paginated_conversation_variable_fields
 from libs.login import login_required

api/controllers/console/app/generator.py

@@ -10,8 +10,7 @@ from controllers.console.app.error import (
     ProviderNotInitializeError,
     ProviderQuotaExceededError,
 )
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.llm_generator.llm_generator import LLMGenerator
 from core.model_runtime.errors.invoke import InvokeError

api/controllers/console/app/message.py

@@ -14,8 +14,11 @@ from controllers.console.app.error import (
 )
 from controllers.console.app.wraps import get_app_model
 from controllers.console.explore.error import AppSuggestedQuestionsAfterAnswerDisabledError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError

api/controllers/console/app/model_config.py

@@ -6,8 +6,7 @@ from flask_restful import Resource
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.agent.entities import AgentToolEntity
 from core.tools.tool_manager import ToolManager
 from core.tools.utils.configuration import ToolParameterConfigurationManager

api/controllers/console/app/ops_trace.py

@@ -2,8 +2,7 @@ from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.app.error import TracingConfigCheckError, TracingConfigIsExist, TracingConfigNotExist
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from libs.login import login_required
 from services.ops_service import OpsService
 

api/controllers/console/app/site.py

@@ -7,8 +7,7 @@ from werkzeug.exceptions import Forbidden, NotFound
 from constants.languages import supported_language
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from extensions.ext_database import db
 from fields.app_fields import app_site_fields
 from libs.login import login_required

api/controllers/console/app/statistic.py

@@ -8,8 +8,7 @@ from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from extensions.ext_database import db
 from libs.helper import DatetimeString
 from libs.login import login_required

api/controllers/console/app/workflow.py

@@ -9,8 +9,7 @@ import services
 from controllers.console import api
 from controllers.console.app.error import ConversationCompletedError, DraftWorkflowNotExist, DraftWorkflowNotSync
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from factories import variable_factory

api/controllers/console/app/workflow_app_log.py

@@ -3,8 +3,7 @@ from flask_restful.inputs import int_range
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from fields.workflow_app_log_fields import workflow_app_log_pagination_fields
 from libs.login import login_required
 from models import App

api/controllers/console/app/workflow_run.py

@@ -3,8 +3,7 @@ from flask_restful.inputs import int_range
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from fields.workflow_run_fields import (
     advanced_chat_workflow_run_pagination_fields,
     workflow_run_detail_fields,

api/controllers/console/app/workflow_statistic.py

@@ -8,8 +8,7 @@ from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from extensions.ext_database import db
 from libs.helper import DatetimeString
 from libs.login import login_required

api/controllers/console/auth/data_source_bearer_auth.py

@@ -7,8 +7,7 @@ from controllers.console.auth.error import ApiKeyAuthFailedError
 from libs.login import login_required
 from services.auth.api_key_auth_service import ApiKeyAuthService
 
-from ..setup import setup_required
-from ..wraps import account_initialization_required
+from ..wraps import account_initialization_required, setup_required
 
 
 class ApiKeyAuthDataSource(Resource):

api/controllers/console/auth/data_source_oauth.py

@@ -11,8 +11,7 @@ from controllers.console import api
 from libs.login import login_required
 from libs.oauth_data_source import NotionOAuth
 
-from ..setup import setup_required
-from ..wraps import account_initialization_required
+from ..wraps import account_initialization_required, setup_required
 
 
 def get_oauth_providers():

api/controllers/console/auth/forgot_password.py

@@ -13,7 +13,7 @@ from controllers.console.auth.error import (
     PasswordMismatchError,
 )
 from controllers.console.error import EmailSendIpLimitError, NotAllowedRegister
-from controllers.console.setup import setup_required
+from controllers.console.wraps import setup_required
 from events.tenant_event import tenant_was_created
 from extensions.ext_database import db
 from libs.helper import email, extract_remote_ip

api/controllers/console/auth/login.py

@@ -20,7 +20,7 @@ from controllers.console.error import (
     NotAllowedCreateWorkspace,
     NotAllowedRegister,
 )
-from controllers.console.setup import setup_required
+from controllers.console.wraps import setup_required
 from events.tenant_event import tenant_was_created
 from libs.helper import email, extract_remote_ip
 from libs.password import valid_password

api/controllers/console/billing/billing.py

@@ -2,8 +2,7 @@ from flask_login import current_user
 from flask_restful import Resource, reqparse
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, only_edition_cloud
+from controllers.console.wraps import account_initialization_required, only_edition_cloud, setup_required
 from libs.login import login_required
 from services.billing_service import BillingService
 

api/controllers/console/datasets/data_source.py

@@ -7,8 +7,7 @@ from flask_restful import Resource, marshal_with, reqparse
 from werkzeug.exceptions import NotFound
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.indexing_runner import IndexingRunner
 from core.rag.extractor.entity.extract_setting import ExtractSetting
 from core.rag.extractor.notion_extractor import NotionExtractor

api/controllers/console/datasets/datasets.py

@@ -10,8 +10,7 @@ from controllers.console import api
 from controllers.console.apikey import api_key_fields, api_key_list
 from controllers.console.app.error import ProviderNotInitializeError
 from controllers.console.datasets.error import DatasetInUseError, DatasetNameDuplicateError, IndexingEstimateError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.indexing_runner import IndexingRunner
 from core.model_runtime.entities.model_entities import ModelType
@@ -102,6 +101,13 @@ class DatasetListApi(Resource):
             help="type is required. Name must be between 1 to 40 characters.",
             type=_validate_name,
         )
+        parser.add_argument(
+            "description",
+            type=str,
+            nullable=True,
+            required=False,
+            default="",
+        )
         parser.add_argument(
             "indexing_technique",
             type=str,
@@ -140,6 +146,7 @@ class DatasetListApi(Resource):
             dataset = DatasetService.create_empty_dataset(
                 tenant_id=current_user.current_tenant_id,
                 name=args["name"],
+                description=args["description"],
                 indexing_technique=args["indexing_technique"],
                 account=current_user,
                 permission=DatasetPermissionEnum.ONLY_ME,
@@ -620,6 +627,7 @@ class DatasetRetrievalSettingApi(Resource):
                 | VectorType.BAIDU
                 | VectorType.VIKINGDB
                 | VectorType.UPSTASH
+                | VectorType.OCEANBASE
             ):
                 return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
             case (
@@ -631,6 +639,8 @@ class DatasetRetrievalSettingApi(Resource):
                 | VectorType.ORACLE
                 | VectorType.ELASTICSEARCH
                 | VectorType.PGVECTOR
+                | VectorType.TIDB_ON_QDRANT
+                | VectorType.COUCHBASE
             ):
                 return {
                     "retrieval_method": [
@@ -659,6 +669,7 @@ class DatasetRetrievalSettingMockApi(Resource):
                 | VectorType.BAIDU
                 | VectorType.VIKINGDB
                 | VectorType.UPSTASH
+                | VectorType.OCEANBASE
             ):
                 return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
             case (
@@ -669,6 +680,7 @@ class DatasetRetrievalSettingMockApi(Resource):
                 | VectorType.MYSCALE
                 | VectorType.ORACLE
                 | VectorType.ELASTICSEARCH
+                | VectorType.COUCHBASE
                 | VectorType.PGVECTOR
             ):
                 return {

api/controllers/console/datasets/datasets_document.py

@@ -24,8 +24,11 @@ from controllers.console.datasets.error import (
     InvalidActionError,
     InvalidMetadataError,
 )
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
 from core.errors.error import (
     LLMBadRequestError,
     ModelCurrentlyNotSupportError,

api/controllers/console/datasets/datasets_segments.py

@@ -11,11 +11,11 @@ import services
 from controllers.console import api
 from controllers.console.app.error import ProviderNotInitializeError
 from controllers.console.datasets.error import InvalidActionError, NoFileUploadedError, TooManyFilesError
-from controllers.console.setup import setup_required
 from controllers.console.wraps import (
     account_initialization_required,
     cloud_edition_billing_knowledge_limit_check,
     cloud_edition_billing_resource_check,
+    setup_required,
 )
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.model_manager import ModelManager

api/controllers/console/datasets/external.py

@@ -6,8 +6,7 @@ from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 import services
 from controllers.console import api
 from controllers.console.datasets.error import DatasetNameDuplicateError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from fields.dataset_fields import dataset_detail_fields
 from libs.login import login_required
 from services.dataset_service import DatasetService

api/controllers/console/datasets/hit_testing.py

@@ -2,8 +2,7 @@ from flask_restful import Resource
 
 from controllers.console import api
 from controllers.console.datasets.hit_testing_base import DatasetsHitTestingBase
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from libs.login import login_required
 
 

api/controllers/console/datasets/website.py

@@ -2,8 +2,7 @@ from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.datasets.error import WebsiteCrawlError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from libs.login import login_required
 from services.website_service import WebsiteService
 

api/controllers/console/explore/parameter.py

@@ -25,6 +25,7 @@ class AppParameterApi(InstalledAppResource):
         "image_file_size_limit": fields.Integer,
         "video_file_size_limit": fields.Integer,
         "audio_file_size_limit": fields.Integer,
+        "file_size_limit": fields.Integer,
     }
 
     parameters_fields = {
@@ -90,6 +91,7 @@ class AppParameterApi(InstalledAppResource):
                 "image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT,
                 "video_file_size_limit": dify_config.UPLOAD_VIDEO_FILE_SIZE_LIMIT,
                 "audio_file_size_limit": dify_config.UPLOAD_AUDIO_FILE_SIZE_LIMIT,
+                "file_size_limit": dify_config.UPLOAD_FILE_SIZE_LIMIT,
             },
         }
 

api/controllers/console/extension.py

@@ -3,8 +3,7 @@ from flask_restful import Resource, marshal_with, reqparse
 
 from constants import HIDDEN_VALUE
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from fields.api_based_extension_fields import api_based_extension_fields
 from libs.login import login_required
 from models.api_based_extension import APIBasedExtension

api/controllers/console/feature.py

@@ -5,8 +5,7 @@ from libs.login import login_required
 from services.feature_service import FeatureService
 
 from . import api
-from .setup import setup_required
-from .wraps import account_initialization_required, cloud_utm_record
+from .wraps import account_initialization_required, cloud_utm_record, setup_required
 
 
 class FeatureApi(Resource):

api/controllers/console/files/__init__.py

@@ -1,25 +1,26 @@
-import urllib.parse
-
 from flask import request
 from flask_login import current_user
-from flask_restful import Resource, marshal_with, reqparse
+from flask_restful import Resource, marshal_with
 
 import services
 from configs import dify_config
 from constants import DOCUMENT_EXTENSIONS
-from controllers.console import api
-from controllers.console.datasets.error import (
+from controllers.common.errors import FilenameNotExistsError
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
+from fields.file_fields import file_fields, upload_config_fields
+from libs.login import login_required
+from services.file_service import FileService
+
+from .errors import (
     FileTooLargeError,
     NoFileUploadedError,
     TooManyFilesError,
     UnsupportedFileTypeError,
 )
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
-from core.helper import ssrf_proxy
-from fields.file_fields import file_fields, remote_file_info_fields, upload_config_fields
-from libs.login import login_required
-from services.file_service import FileService
 
 PREVIEW_WORDS_LIMIT = 3000
 
@@ -44,21 +45,29 @@ class FileApi(Resource):
     @marshal_with(file_fields)
     @cloud_edition_billing_resource_check("documents")
     def post(self):
-        # get file from request
         file = request.files["file"]
+        source = request.form.get("source")
 
-        parser = reqparse.RequestParser()
-        parser.add_argument("source", type=str, required=False, location="args")
-        source = parser.parse_args().get("source")
-
-        # check file
         if "file" not in request.files:
             raise NoFileUploadedError()
 
         if len(request.files) > 1:
             raise TooManyFilesError()
+
+        if not file.filename:
+            raise FilenameNotExistsError
+
+        if source not in ("datasets", None):
+            source = None
+
         try:
-            upload_file = FileService.upload_file(file=file, user=current_user, source=source)
+            upload_file = FileService.upload_file(
+                filename=file.filename,
+                content=file.read(),
+                mimetype=file.mimetype,
+                user=current_user,
+                source=source,
+            )
         except services.errors.file.FileTooLargeError as file_too_large_error:
             raise FileTooLargeError(file_too_large_error.description)
         except services.errors.file.UnsupportedFileTypeError:
@@ -83,23 +92,3 @@ class FileSupportTypeApi(Resource):
     @account_initialization_required
     def get(self):
         return {"allowed_extensions": DOCUMENT_EXTENSIONS}
-
-
-class RemoteFileInfoApi(Resource):
-    @marshal_with(remote_file_info_fields)
-    def get(self, url):
-        decoded_url = urllib.parse.unquote(url)
-        try:
-            response = ssrf_proxy.head(decoded_url)
-            return {
-                "file_type": response.headers.get("Content-Type", "application/octet-stream"),
-                "file_length": int(response.headers.get("Content-Length", 0)),
-            }
-        except Exception as e:
-            return {"error": str(e)}, 400
-
-
-api.add_resource(FileApi, "/files/upload")
-api.add_resource(FilePreviewApi, "/files/<uuid:file_id>/preview")
-api.add_resource(FileSupportTypeApi, "/files/support-type")
-api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")

api/controllers/console/files/errors.py

@@ -0,0 +1,25 @@
+from libs.exception import BaseHTTPException
+
+
+class FileTooLargeError(BaseHTTPException):
+    error_code = "file_too_large"
+    description = "File size exceeded. {message}"
+    code = 413
+
+
+class UnsupportedFileTypeError(BaseHTTPException):
+    error_code = "unsupported_file_type"
+    description = "File type not allowed."
+    code = 415
+
+
+class TooManyFilesError(BaseHTTPException):
+    error_code = "too_many_files"
+    description = "Only one file is allowed."
+    code = 400
+
+
+class NoFileUploadedError(BaseHTTPException):
+    error_code = "no_file_uploaded"
+    description = "Please upload your file."
+    code = 400

api/controllers/console/remote_files.py

@@ -0,0 +1,71 @@
+import urllib.parse
+from typing import cast
+
+from flask_login import current_user
+from flask_restful import Resource, marshal_with, reqparse
+
+from controllers.common import helpers
+from core.file import helpers as file_helpers
+from core.helper import ssrf_proxy
+from fields.file_fields import file_fields_with_signed_url, remote_file_info_fields
+from models.account import Account
+from services.file_service import FileService
+
+
+class RemoteFileInfoApi(Resource):
+    @marshal_with(remote_file_info_fields)
+    def get(self, url):
+        decoded_url = urllib.parse.unquote(url)
+        try:
+            response = ssrf_proxy.head(decoded_url)
+            return {
+                "file_type": response.headers.get("Content-Type", "application/octet-stream"),
+                "file_length": int(response.headers.get("Content-Length", 0)),
+            }
+        except Exception as e:
+            return {"error": str(e)}, 400
+
+
+class RemoteFileUploadApi(Resource):
+    @marshal_with(file_fields_with_signed_url)
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("url", type=str, required=True, help="URL is required")
+        args = parser.parse_args()
+
+        url = args["url"]
+
+        response = ssrf_proxy.head(url)
+        response.raise_for_status()
+
+        file_info = helpers.guess_file_info_from_response(response)
+
+        if not FileService.is_file_size_within_limit(extension=file_info.extension, file_size=file_info.size):
+            return {"error": "File size exceeded"}, 400
+
+        response = ssrf_proxy.get(url)
+        response.raise_for_status()
+        content = response.content
+
+        try:
+            user = cast(Account, current_user)
+            upload_file = FileService.upload_file(
+                filename=file_info.filename,
+                content=content,
+                mimetype=file_info.mimetype,
+                user=user,
+                source_url=url,
+            )
+        except Exception as e:
+            return {"error": str(e)}, 400
+
+        return {
+            "id": upload_file.id,
+            "name": upload_file.name,
+            "size": upload_file.size,
+            "extension": upload_file.extension,
+            "url": file_helpers.get_signed_file_url(upload_file_id=upload_file.id),
+            "mime_type": upload_file.mime_type,
+            "created_by": upload_file.created_by,
+            "created_at": upload_file.created_at,
+        }, 201

api/controllers/console/setup.py

@@ -1,5 +1,3 @@
-from functools import wraps
-
 from flask import request
 from flask_restful import Resource, reqparse
 
@@ -10,7 +8,7 @@ from models.model import DifySetup
 from services.account_service import RegisterService, TenantService
 
 from . import api
-from .error import AlreadySetupError, NotInitValidateError, NotSetupError
+from .error import AlreadySetupError, NotInitValidateError
 from .init_validate import get_init_validate_status
 from .wraps import only_edition_self_hosted
 
@@ -52,26 +50,10 @@ class SetupApi(Resource):
         return {"result": "success"}, 201
 
 
-def setup_required(view):
-    @wraps(view)
-    def decorated(*args, **kwargs):
-        # check setup
-        if not get_init_validate_status():
-            raise NotInitValidateError()
-
-        elif not get_setup_status():
-            raise NotSetupError()
-
-        return view(*args, **kwargs)
-
-    return decorated
-
-
 def get_setup_status():
     if dify_config.EDITION == "SELF_HOSTED":
         return DifySetup.query.first()
-    else:
-        return True
+    return True
 
 
 api.add_resource(SetupApi, "/setup")

api/controllers/console/tag/tags.py

@@ -4,8 +4,7 @@ from flask_restful import Resource, marshal_with, reqparse
 from werkzeug.exceptions import Forbidden
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from fields.tag_fields import tag_fields
 from libs.login import login_required
 from models.model import Tag

api/controllers/console/version.py

@@ -3,6 +3,7 @@ import logging
 
 import requests
 from flask_restful import Resource, reqparse
+from packaging import version
 
 from configs import dify_config
 
@@ -47,43 +48,15 @@ class VersionApi(Resource):
 
 
 def _has_new_version(*, latest_version: str, current_version: str) -> bool:
-    def parse_version(version: str) -> tuple:
-        # Split version into parts and pre-release suffix if any
-        parts = version.split("-")
-        version_parts = parts[0].split(".")
-        pre_release = parts[1] if len(parts) > 1 else None
+    try:
+        latest = version.parse(latest_version)
+        current = version.parse(current_version)
 
-        # Validate version format
-        if len(version_parts) != 3:
-            raise ValueError(f"Invalid version format: {version}")
-
-        try:
-            # Convert version parts to integers
-            major, minor, patch = map(int, version_parts)
-            return (major, minor, patch, pre_release)
-        except ValueError:
-            raise ValueError(f"Invalid version format: {version}")
-
-    latest = parse_version(latest_version)
-    current = parse_version(current_version)
-
-    # Compare major, minor, and patch versions
-    for latest_part, current_part in zip(latest[:3], current[:3]):
-        if latest_part > current_part:
-            return True
-        elif latest_part < current_part:
-            return False
-
-    # If versions are equal, check pre-release suffixes
-    if latest[3] is None and current[3] is not None:
-        return True
-    elif latest[3] is not None and current[3] is None:
+        # Compare versions
+        return latest > current
+    except version.InvalidVersion:
+        logging.warning(f"Invalid version format: latest={latest_version}, current={current_version}")
         return False
-    elif latest[3] is not None and current[3] is not None:
-        # Simple string comparison for pre-release versions
-        return latest[3] > current[3]
-
-    return False
 
 
 api.add_resource(VersionApi, "/version")

api/controllers/console/workspace/account.py

@@ -8,14 +8,13 @@ from flask_restful import Resource, fields, marshal_with, reqparse
 from configs import dify_config
 from constants.languages import supported_language
 from controllers.console import api
-from controllers.console.setup import setup_required
 from controllers.console.workspace.error import (
     AccountAlreadyInitedError,
     CurrentPasswordIncorrectError,
     InvalidInvitationCodeError,
     RepeatPasswordNotMatchError,
 )
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from extensions.ext_database import db
 from fields.member_fields import account_fields
 from libs.helper import TimestampField, timezone

api/controllers/console/workspace/load_balancing_config.py

@@ -2,8 +2,7 @@ from flask_restful import Resource, reqparse
 from werkzeug.exceptions import Forbidden
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.model_runtime.entities.model_entities import ModelType
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
 from libs.login import current_user, login_required

api/controllers/console/workspace/members.py

@@ -4,8 +4,11 @@ from flask_restful import Resource, abort, marshal_with, reqparse
 import services
 from configs import dify_config
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
 from extensions.ext_database import db
 from fields.member_fields import account_with_role_list_fields
 from libs.login import login_required

api/controllers/console/workspace/model_providers.py

@@ -6,8 +6,7 @@ from flask_restful import Resource, reqparse
 from werkzeug.exceptions import Forbidden
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.model_runtime.entities.model_entities import ModelType
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
 from core.model_runtime.utils.encoders import jsonable_encoder

api/controllers/console/workspace/models.py

@@ -5,8 +5,7 @@ from flask_restful import Resource, reqparse
 from werkzeug.exceptions import Forbidden
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.model_runtime.entities.model_entities import ModelType
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
 from core.model_runtime.utils.encoders import jsonable_encoder

api/controllers/console/workspace/tool_providers.py

@@ -7,8 +7,7 @@ from werkzeug.exceptions import Forbidden
 
 from configs import dify_config
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.model_runtime.utils.encoders import jsonable_encoder
 from libs.helper import alphanumeric, uuid_value
 from libs.login import login_required

api/controllers/console/workspace/workspace.py

@@ -6,6 +6,7 @@ from flask_restful import Resource, fields, inputs, marshal, marshal_with, reqpa
 from werkzeug.exceptions import Unauthorized
 
 import services
+from controllers.common.errors import FilenameNotExistsError
 from controllers.console import api
 from controllers.console.admin import admin_required
 from controllers.console.datasets.error import (
@@ -15,8 +16,11 @@ from controllers.console.datasets.error import (
     UnsupportedFileTypeError,
 )
 from controllers.console.error import AccountNotLinkTenantError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
 from extensions.ext_database import db
 from libs.helper import TimestampField
 from libs.login import login_required
@@ -193,12 +197,20 @@ class WebappLogoWorkspaceApi(Resource):
         if len(request.files) > 1:
             raise TooManyFilesError()
 
+        if not file.filename:
+            raise FilenameNotExistsError
+
         extension = file.filename.split(".")[-1]
         if extension.lower() not in {"svg", "png"}:
             raise UnsupportedFileTypeError()
 
         try:
-            upload_file = FileService.upload_file(file=file, user=current_user)
+            upload_file = FileService.upload_file(
+                filename=file.filename,
+                content=file.read(),
+                mimetype=file.mimetype,
+                user=current_user,
+            )
 
         except services.errors.file.FileTooLargeError as file_too_large_error:
             raise FileTooLargeError(file_too_large_error.description)

api/controllers/console/wraps.py

@@ -1,4 +1,5 @@
 import json
+import os
 from functools import wraps
 
 from flask import abort, request
@@ -6,9 +7,12 @@ from flask_login import current_user
 
 from configs import dify_config
 from controllers.console.workspace.error import AccountNotInitializedError
+from models.model import DifySetup
 from services.feature_service import FeatureService
 from services.operation_service import OperationService
 
+from .error import NotInitValidateError, NotSetupError
+
 
 def account_initialization_required(view):
     @wraps(view)
@@ -124,3 +128,17 @@ def cloud_utm_record(view):
         return view(*args, **kwargs)
 
     return decorated
+
+
+def setup_required(view):
+    @wraps(view)
+    def decorated(*args, **kwargs):
+        # check setup
+        if dify_config.EDITION == "SELF_HOSTED" and os.environ.get("INIT_PASSWORD") and not DifySetup.query.first():
+            raise NotInitValidateError()
+        elif dify_config.EDITION == "SELF_HOSTED" and not DifySetup.query.first():
+            raise NotSetupError()
+
+        return view(*args, **kwargs)
+
+    return decorated

api/controllers/inner_api/workspace/workspace.py

@@ -1,6 +1,6 @@
 from flask_restful import Resource, reqparse
 
-from controllers.console.setup import setup_required
+from controllers.console.wraps import setup_required
 from controllers.inner_api import api
 from controllers.inner_api.wraps import inner_api_only
 from events.tenant_event import tenant_was_created
@@ -21,7 +21,7 @@ class EnterpriseWorkspace(Resource):
         if account is None:
             return {"message": "owner account not found."}, 404
 
-        tenant = TenantService.create_tenant(args["name"])
+        tenant = TenantService.create_tenant(args["name"], is_from_dashboard=True)
         TenantService.create_tenant_member(tenant, account, role="owner")
 
         tenant_was_created.send(tenant)

api/controllers/service_api/app/app.py

@@ -22,9 +22,10 @@ class AppParameterApi(Resource):
     }
 
     system_parameters_fields = {
-        "image_file_size_limit": fields.String,
+        "image_file_size_limit": fields.Integer,
         "video_file_size_limit": fields.Integer,
         "audio_file_size_limit": fields.Integer,
+        "file_size_limit": fields.Integer,
     }
 
     parameters_fields = {
@@ -89,6 +90,7 @@ class AppParameterApi(Resource):
                 "image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT,
                 "video_file_size_limit": dify_config.UPLOAD_VIDEO_FILE_SIZE_LIMIT,
                 "audio_file_size_limit": dify_config.UPLOAD_AUDIO_FILE_SIZE_LIMIT,
+                "file_size_limit": dify_config.UPLOAD_FILE_SIZE_LIMIT,
             },
         }
 

api/controllers/service_api/app/file.py

@@ -2,6 +2,7 @@ from flask import request
 from flask_restful import Resource, marshal_with
 
 import services
+from controllers.common.errors import FilenameNotExistsError
 from controllers.service_api import api
 from controllers.service_api.app.error import (
     FileTooLargeError,
@@ -31,8 +32,17 @@ class FileApi(Resource):
         if len(request.files) > 1:
             raise TooManyFilesError()
 
+        if not file.filename:
+            raise FilenameNotExistsError
+
         try:
-            upload_file = FileService.upload_file(file, end_user)
+            upload_file = FileService.upload_file(
+                filename=file.filename,
+                content=file.read(),
+                mimetype=file.mimetype,
+                user=end_user,
+                source="datasets",
+            )
         except services.errors.file.FileTooLargeError as file_too_large_error:
             raise FileTooLargeError(file_too_large_error.description)
         except services.errors.file.UnsupportedFileTypeError:

api/controllers/service_api/dataset/dataset.py

@@ -66,6 +66,13 @@ class DatasetListApi(DatasetApiResource):
             help="type is required. Name must be between 1 to 40 characters.",
             type=_validate_name,
         )
+        parser.add_argument(
+            "description",
+            type=str,
+            nullable=True,
+            required=False,
+            default="",
+        )
         parser.add_argument(
             "indexing_technique",
             type=str,
@@ -108,6 +115,7 @@ class DatasetListApi(DatasetApiResource):
             dataset = DatasetService.create_empty_dataset(
                 tenant_id=tenant_id,
                 name=args["name"],
+                description=args["description"],
                 indexing_technique=args["indexing_technique"],
                 account=current_user,
                 permission=args["permission"],

api/controllers/service_api/dataset/document.py

@@ -6,6 +6,7 @@ from sqlalchemy import desc
 from werkzeug.exceptions import NotFound
 
 import services.dataset_service
+from controllers.common.errors import FilenameNotExistsError
 from controllers.service_api import api
 from controllers.service_api.app.error import ProviderNotInitializeError
 from controllers.service_api.dataset.error import (
@@ -55,7 +56,12 @@ class DocumentAddByTextApi(DatasetApiResource):
         if not dataset.indexing_technique and not args["indexing_technique"]:
             raise ValueError("indexing_technique is required.")
 
-        upload_file = FileService.upload_text(args.get("text"), args.get("name"))
+        text = args.get("text")
+        name = args.get("name")
+        if text is None or name is None:
+            raise ValueError("Both 'text' and 'name' must be non-null values.")
+
+        upload_file = FileService.upload_text(text=str(text), text_name=str(name))
         data_source = {
             "type": "upload_file",
             "info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
@@ -104,7 +110,11 @@ class DocumentUpdateByTextApi(DatasetApiResource):
             raise ValueError("Dataset is not exist.")
 
         if args["text"]:
-            upload_file = FileService.upload_text(args.get("text"), args.get("name"))
+            text = args.get("text")
+            name = args.get("name")
+            if text is None or name is None:
+                raise ValueError("Both text and name must be strings.")
+            upload_file = FileService.upload_text(text=str(text), text_name=str(name))
             data_source = {
                 "type": "upload_file",
                 "info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
@@ -163,7 +173,16 @@ class DocumentAddByFileApi(DatasetApiResource):
         if len(request.files) > 1:
             raise TooManyFilesError()
 
-        upload_file = FileService.upload_file(file, current_user)
+        if not file.filename:
+            raise FilenameNotExistsError
+
+        upload_file = FileService.upload_file(
+            filename=file.filename,
+            content=file.read(),
+            mimetype=file.mimetype,
+            user=current_user,
+            source="datasets",
+        )
         data_source = {"type": "upload_file", "info_list": {"file_info_list": {"file_ids": [upload_file.id]}}}
         args["data_source"] = data_source
         # validate args
@@ -212,7 +231,16 @@ class DocumentUpdateByFileApi(DatasetApiResource):
             if len(request.files) > 1:
                 raise TooManyFilesError()
 
-            upload_file = FileService.upload_file(file, current_user)
+            if not file.filename:
+                raise FilenameNotExistsError
+
+            upload_file = FileService.upload_file(
+                filename=file.filename,
+                content=file.read(),
+                mimetype=file.mimetype,
+                user=current_user,
+                source="datasets",
+            )
             data_source = {"type": "upload_file", "info_list": {"file_info_list": {"file_ids": [upload_file.id]}}}
             args["data_source"] = data_source
         # validate args
@@ -230,7 +258,7 @@ 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
 
 
@@ -331,10 +359,26 @@ class DocumentIndexingStatusApi(DatasetApiResource):
         return data
 
 
-api.add_resource(DocumentAddByTextApi, "/datasets/<uuid:dataset_id>/document/create_by_text")
-api.add_resource(DocumentAddByFileApi, "/datasets/<uuid:dataset_id>/document/create_by_file")
-api.add_resource(DocumentUpdateByTextApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_text")
-api.add_resource(DocumentUpdateByFileApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_file")
+api.add_resource(
+    DocumentAddByTextApi,
+    "/datasets/<uuid:dataset_id>/document/create_by_text",
+    "/datasets/<uuid:dataset_id>/document/create-by-text",
+)
+api.add_resource(
+    DocumentAddByFileApi,
+    "/datasets/<uuid:dataset_id>/document/create_by_file",
+    "/datasets/<uuid:dataset_id>/document/create-by-file",
+)
+api.add_resource(
+    DocumentUpdateByTextApi,
+    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_text",
+    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update-by-text",
+)
+api.add_resource(
+    DocumentUpdateByFileApi,
+    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_file",
+    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update-by-file",
+)
 api.add_resource(DocumentDeleteApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>")
 api.add_resource(DocumentListApi, "/datasets/<uuid:dataset_id>/documents")
 api.add_resource(DocumentIndexingStatusApi, "/datasets/<uuid:dataset_id>/documents/<string:batch>/indexing-status")

api/controllers/service_api/dataset/hit_testing.py

@@ -14,4 +14,4 @@ class HitTestingApi(DatasetApiResource, DatasetsHitTestingBase):
         return self.perform_hit_testing(dataset, args)
 
 
-api.add_resource(HitTestingApi, "/datasets/<uuid:dataset_id>/hit-testing")
+api.add_resource(HitTestingApi, "/datasets/<uuid:dataset_id>/hit-testing", "/datasets/<uuid:dataset_id>/retrieve")

api/controllers/web/__init__.py

@@ -2,8 +2,17 @@ from flask import Blueprint
 
 from libs.external_api import ExternalApi
 
+from .files import FileApi
+from .remote_files import RemoteFileInfoApi, RemoteFileUploadApi
+
 bp = Blueprint("web", __name__, url_prefix="/api")
 api = ExternalApi(bp)
 
+# Files
+api.add_resource(FileApi, "/files/upload")
 
-from . import app, audio, completion, conversation, feature, file, message, passport, saved_message, site, workflow
+# Remote files
+api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")
+api.add_resource(RemoteFileUploadApi, "/remote-files/upload")
+
+from . import app, audio, completion, conversation, feature, message, passport, saved_message, site, workflow

api/controllers/web/app.py

@@ -25,6 +25,7 @@ class AppParameterApi(WebApiResource):
         "image_file_size_limit": fields.Integer,
         "video_file_size_limit": fields.Integer,
         "audio_file_size_limit": fields.Integer,
+        "file_size_limit": fields.Integer,
     }
 
     parameters_fields = {
@@ -88,6 +89,7 @@ class AppParameterApi(WebApiResource):
                 "image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT,
                 "video_file_size_limit": dify_config.UPLOAD_VIDEO_FILE_SIZE_LIMIT,
                 "audio_file_size_limit": dify_config.UPLOAD_AUDIO_FILE_SIZE_LIMIT,
+                "file_size_limit": dify_config.UPLOAD_FILE_SIZE_LIMIT,
             },
         }
 

api/controllers/web/file.py

@@ -1,56 +0,0 @@
-import urllib.parse
-
-from flask import request
-from flask_restful import marshal_with, reqparse
-
-import services
-from controllers.web import api
-from controllers.web.error import FileTooLargeError, NoFileUploadedError, TooManyFilesError, UnsupportedFileTypeError
-from controllers.web.wraps import WebApiResource
-from core.helper import ssrf_proxy
-from fields.file_fields import file_fields, remote_file_info_fields
-from services.file_service import FileService
-
-
-class FileApi(WebApiResource):
-    @marshal_with(file_fields)
-    def post(self, app_model, end_user):
-        # get file from request
-        file = request.files["file"]
-
-        parser = reqparse.RequestParser()
-        parser.add_argument("source", type=str, required=False, location="args")
-        source = parser.parse_args().get("source")
-
-        # check file
-        if "file" not in request.files:
-            raise NoFileUploadedError()
-
-        if len(request.files) > 1:
-            raise TooManyFilesError()
-        try:
-            upload_file = FileService.upload_file(file=file, user=end_user, source=source)
-        except services.errors.file.FileTooLargeError as file_too_large_error:
-            raise FileTooLargeError(file_too_large_error.description)
-        except services.errors.file.UnsupportedFileTypeError:
-            raise UnsupportedFileTypeError()
-
-        return upload_file, 201
-
-
-class RemoteFileInfoApi(WebApiResource):
-    @marshal_with(remote_file_info_fields)
-    def get(self, url):
-        decoded_url = urllib.parse.unquote(url)
-        try:
-            response = ssrf_proxy.head(decoded_url)
-            return {
-                "file_type": response.headers.get("Content-Type", "application/octet-stream"),
-                "file_length": int(response.headers.get("Content-Length", -1)),
-            }
-        except Exception as e:
-            return {"error": str(e)}, 400
-
-
-api.add_resource(FileApi, "/files/upload")
-api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")

api/controllers/web/files.py

@@ -0,0 +1,43 @@
+from flask import request
+from flask_restful import marshal_with
+
+import services
+from controllers.common.errors import FilenameNotExistsError
+from controllers.web.error import FileTooLargeError, NoFileUploadedError, TooManyFilesError, UnsupportedFileTypeError
+from controllers.web.wraps import WebApiResource
+from fields.file_fields import file_fields
+from services.file_service import FileService
+
+
+class FileApi(WebApiResource):
+    @marshal_with(file_fields)
+    def post(self, app_model, end_user):
+        file = request.files["file"]
+        source = request.form.get("source")
+
+        if "file" not in request.files:
+            raise NoFileUploadedError()
+
+        if len(request.files) > 1:
+            raise TooManyFilesError()
+
+        if not file.filename:
+            raise FilenameNotExistsError
+
+        if source not in ("datasets", None):
+            source = None
+
+        try:
+            upload_file = FileService.upload_file(
+                filename=file.filename,
+                content=file.read(),
+                mimetype=file.mimetype,
+                user=end_user,
+                source=source,
+            )
+        except services.errors.file.FileTooLargeError as file_too_large_error:
+            raise FileTooLargeError(file_too_large_error.description)
+        except services.errors.file.UnsupportedFileTypeError:
+            raise UnsupportedFileTypeError()
+
+        return upload_file, 201

api/controllers/web/remote_files.py

@@ -0,0 +1,68 @@
+import urllib.parse
+
+from flask_restful import marshal_with, reqparse
+
+from controllers.common import helpers
+from controllers.web.wraps import WebApiResource
+from core.file import helpers as file_helpers
+from core.helper import ssrf_proxy
+from fields.file_fields import file_fields_with_signed_url, remote_file_info_fields
+from services.file_service import FileService
+
+
+class RemoteFileInfoApi(WebApiResource):
+    @marshal_with(remote_file_info_fields)
+    def get(self, url):
+        decoded_url = urllib.parse.unquote(url)
+        try:
+            response = ssrf_proxy.head(decoded_url)
+            return {
+                "file_type": response.headers.get("Content-Type", "application/octet-stream"),
+                "file_length": int(response.headers.get("Content-Length", -1)),
+            }
+        except Exception as e:
+            return {"error": str(e)}, 400
+
+
+class RemoteFileUploadApi(WebApiResource):
+    @marshal_with(file_fields_with_signed_url)
+    def post(self, app_model, end_user):  # Add app_model and end_user parameters
+        parser = reqparse.RequestParser()
+        parser.add_argument("url", type=str, required=True, help="URL is required")
+        args = parser.parse_args()
+
+        url = args["url"]
+
+        response = ssrf_proxy.head(url)
+        response.raise_for_status()
+
+        file_info = helpers.guess_file_info_from_response(response)
+
+        if not FileService.is_file_size_within_limit(extension=file_info.extension, file_size=file_info.size):
+            return {"error": "File size exceeded"}, 400
+
+        response = ssrf_proxy.get(url)
+        response.raise_for_status()
+        content = response.content
+
+        try:
+            upload_file = FileService.upload_file(
+                filename=file_info.filename,
+                content=content,
+                mimetype=file_info.mimetype,
+                user=end_user,  # Use end_user instead of current_user
+                source_url=url,
+            )
+        except Exception as e:
+            return {"error": str(e)}, 400
+
+        return {
+            "id": upload_file.id,
+            "name": upload_file.name,
+            "size": upload_file.size,
+            "extension": upload_file.extension,
+            "url": file_helpers.get_signed_file_url(upload_file_id=upload_file.id),
+            "mime_type": upload_file.mime_type,
+            "created_by": upload_file.created_by,
+            "created_at": upload_file.created_at,
+        }, 201

api/core/agent/base_agent_runner.py

@@ -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]

api/core/app/apps/base_app_generator.py

@@ -76,6 +76,7 @@ class BaseAppGenerator:
 
     def _validate_input(self, *, inputs: Mapping[str, Any], var: "VariableEntity"):
         user_input_value = inputs.get(var.variable)
+
         if not user_input_value:
             if var.required:
                 raise ValueError(f"{var.variable} is required in input form")
@@ -88,6 +89,7 @@ class BaseAppGenerator:
             VariableEntityType.PARAGRAPH,
         } and not isinstance(user_input_value, str):
             raise ValueError(f"(type '{var.type}') {var.variable} in input form must be a string")
+
         if var.type == VariableEntityType.NUMBER and isinstance(user_input_value, str):
             # may raise ValueError if user_input_value is not a valid number
             try:
@@ -97,25 +99,30 @@ class BaseAppGenerator:
                     return int(user_input_value)
             except ValueError:
                 raise ValueError(f"{var.variable} in input form must be a valid number")
-        if var.type == VariableEntityType.SELECT:
-            options = var.options
-            if user_input_value not in options:
-                raise ValueError(f"{var.variable} in input form must be one of the following: {options}")
-        elif var.type in {VariableEntityType.TEXT_INPUT, VariableEntityType.PARAGRAPH}:
-            if var.max_length and len(user_input_value) > var.max_length:
-                raise ValueError(f"{var.variable} in input form must be less than {var.max_length} characters")
-        elif var.type == VariableEntityType.FILE:
-            if not isinstance(user_input_value, dict) and not isinstance(user_input_value, File):
-                raise ValueError(f"{var.variable} in input form must be a file")
-        elif var.type == VariableEntityType.FILE_LIST:
-            if not (
-                isinstance(user_input_value, list)
-                and (
-                    all(isinstance(item, dict) for item in user_input_value)
-                    or all(isinstance(item, File) for item in user_input_value)
-                )
-            ):
-                raise ValueError(f"{var.variable} in input form must be a list of files")
+
+        match var.type:
+            case VariableEntityType.SELECT:
+                if user_input_value not in var.options:
+                    raise ValueError(f"{var.variable} in input form must be one of the following: {var.options}")
+            case VariableEntityType.TEXT_INPUT | VariableEntityType.PARAGRAPH:
+                if var.max_length and len(user_input_value) > var.max_length:
+                    raise ValueError(f"{var.variable} in input form must be less than {var.max_length} characters")
+            case VariableEntityType.FILE:
+                if not isinstance(user_input_value, dict) and not isinstance(user_input_value, File):
+                    raise ValueError(f"{var.variable} in input form must be a file")
+            case VariableEntityType.FILE_LIST:
+                # if number of files exceeds the limit, raise ValueError
+                if not (
+                    isinstance(user_input_value, list)
+                    and (
+                        all(isinstance(item, dict) for item in user_input_value)
+                        or all(isinstance(item, File) for item in user_input_value)
+                    )
+                ):
+                    raise ValueError(f"{var.variable} in input form must be a list of files")
+
+                if var.max_length and len(user_input_value) > var.max_length:
+                    raise ValueError(f"{var.variable} in input form must be less than {var.max_length} files")
 
         return user_input_value
 

api/core/file/file_manager.py

@@ -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, /):

api/core/indexing_runner.py

@@ -17,6 +17,7 @@ from core.errors.error import ProviderTokenNotInitError
 from core.llm_generator.llm_generator import LLMGenerator
 from core.model_manager import ModelInstance, ModelManager
 from core.model_runtime.entities.model_entities import ModelType
+from core.rag.cleaner.clean_processor import CleanProcessor
 from core.rag.datasource.keyword.keyword_factory import Keyword
 from core.rag.docstore.dataset_docstore import DatasetDocumentStore
 from core.rag.extractor.entity.extract_setting import ExtractSetting
@@ -597,26 +598,9 @@ class IndexingRunner:
             rules = DatasetProcessRule.AUTOMATIC_RULES
         else:
             rules = json.loads(processing_rule.rules) if processing_rule.rules else {}
+        document_text = CleanProcessor.clean(text, rules)
 
-        if "pre_processing_rules" in rules:
-            pre_processing_rules = rules["pre_processing_rules"]
-            for pre_processing_rule in pre_processing_rules:
-                if pre_processing_rule["id"] == "remove_extra_spaces" and pre_processing_rule["enabled"] is True:
-                    # Remove extra spaces
-                    pattern = r"\n{3,}"
-                    text = re.sub(pattern, "\n\n", text)
-                    pattern = r"[\t\f\r\x20\u00a0\u1680\u180e\u2000-\u200a\u202f\u205f\u3000]{2,}"
-                    text = re.sub(pattern, " ", text)
-                elif pre_processing_rule["id"] == "remove_urls_emails" and pre_processing_rule["enabled"] is True:
-                    # Remove email
-                    pattern = r"([a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+)"
-                    text = re.sub(pattern, "", text)
-
-                    # Remove URL
-                    pattern = r"https?://[^\s]+"
-                    text = re.sub(pattern, "", text)
-
-        return text
+        return document_text
 
     @staticmethod
     def format_split_text(text):

api/core/model_runtime/model_providers/azure_openai/_constant.py

@@ -37,6 +37,17 @@ def _get_max_tokens(default: int, min_val: int, max_val: int) -> ParameterRule:
     return rule
 
 
+def _get_o1_max_tokens(default: int, min_val: int, max_val: int) -> ParameterRule:
+    rule = ParameterRule(
+        name="max_completion_tokens",
+        **PARAMETER_RULE_TEMPLATE[DefaultParameterName.MAX_TOKENS],
+    )
+    rule.default = default
+    rule.min = min_val
+    rule.max = max_val
+    return rule
+
+
 class AzureBaseModel(BaseModel):
     base_model_name: str
     entity: AIModelEntity
@@ -1098,14 +1109,6 @@ LLM_BASE_MODELS = [
                 ModelPropertyKey.CONTEXT_SIZE: 128000,
             },
             parameter_rules=[
-                ParameterRule(
-                    name="temperature",
-                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TEMPERATURE],
-                ),
-                ParameterRule(
-                    name="top_p",
-                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TOP_P],
-                ),
                 ParameterRule(
                     name="response_format",
                     label=I18nObject(zh_Hans="回复格式", en_US="response_format"),
@@ -1116,7 +1119,7 @@ LLM_BASE_MODELS = [
                     required=False,
                     options=["text", "json_object"],
                 ),
-                _get_max_tokens(default=512, min_val=1, max_val=32768),
+                _get_o1_max_tokens(default=512, min_val=1, max_val=32768),
             ],
             pricing=PriceConfig(
                 input=15.00,
@@ -1143,14 +1146,6 @@ LLM_BASE_MODELS = [
                 ModelPropertyKey.CONTEXT_SIZE: 128000,
             },
             parameter_rules=[
-                ParameterRule(
-                    name="temperature",
-                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TEMPERATURE],
-                ),
-                ParameterRule(
-                    name="top_p",
-                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TOP_P],
-                ),
                 ParameterRule(
                     name="response_format",
                     label=I18nObject(zh_Hans="回复格式", en_US="response_format"),
@@ -1161,7 +1156,7 @@ LLM_BASE_MODELS = [
                     required=False,
                     options=["text", "json_object"],
                 ),
-                _get_max_tokens(default=512, min_val=1, max_val=65536),
+                _get_o1_max_tokens(default=512, min_val=1, max_val=65536),
             ],
             pricing=PriceConfig(
                 input=3.00,

api/core/model_runtime/model_providers/azure_openai/azure_openai.yaml

@@ -53,6 +53,9 @@ model_credential_schema:
       type: select
       required: true
       options:
+        - label:
+            en_US: 2024-10-01-preview
+          value: 2024-10-01-preview
         - label:
             en_US: 2024-09-01-preview
           value: 2024-09-01-preview

api/core/model_runtime/model_providers/azure_openai/llm/llm.py

@@ -45,9 +45,7 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
         stream: bool = True,
         user: Optional[str] = None,
     ) -> Union[LLMResult, Generator]:
-        base_model_name = credentials.get("base_model_name")
-        if not base_model_name:
-            raise ValueError("Base Model Name is required")
+        base_model_name = self._get_base_model_name(credentials)
         ai_model_entity = self._get_ai_model_entity(base_model_name=base_model_name, model=model)
 
         if ai_model_entity and ai_model_entity.entity.model_properties.get(ModelPropertyKey.MODE) == LLMMode.CHAT.value:
@@ -81,9 +79,7 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
         prompt_messages: list[PromptMessage],
         tools: Optional[list[PromptMessageTool]] = None,
     ) -> int:
-        base_model_name = credentials.get("base_model_name")
-        if not base_model_name:
-            raise ValueError("Base Model Name is required")
+        base_model_name = self._get_base_model_name(credentials)
         model_entity = self._get_ai_model_entity(base_model_name=base_model_name, model=model)
         if not model_entity:
             raise ValueError(f"Base Model Name {base_model_name} is invalid")
@@ -108,9 +104,7 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
         if "base_model_name" not in credentials:
             raise CredentialsValidateFailedError("Base Model Name is required")
 
-        base_model_name = credentials.get("base_model_name")
-        if not base_model_name:
-            raise CredentialsValidateFailedError("Base Model Name is required")
+        base_model_name = self._get_base_model_name(credentials)
         ai_model_entity = self._get_ai_model_entity(base_model_name=base_model_name, model=model)
 
         if not ai_model_entity:
@@ -149,9 +143,7 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
             raise CredentialsValidateFailedError(str(ex))
 
     def get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
-        base_model_name = credentials.get("base_model_name")
-        if not base_model_name:
-            raise ValueError("Base Model Name is required")
+        base_model_name = self._get_base_model_name(credentials)
         ai_model_entity = self._get_ai_model_entity(base_model_name=base_model_name, model=model)
         return ai_model_entity.entity if ai_model_entity else None
 
@@ -308,11 +300,6 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
 
         if tools:
             extra_model_kwargs["tools"] = [helper.dump_model(PromptMessageFunction(function=tool)) for tool in tools]
-            # extra_model_kwargs['functions'] = [{
-            #     "name": tool.name,
-            #     "description": tool.description,
-            #     "parameters": tool.parameters
-            # } for tool in tools]
 
         if stop:
             extra_model_kwargs["stop"] = stop
@@ -769,3 +756,9 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
                 ai_model_entity_copy.entity.label.en_US = model
                 ai_model_entity_copy.entity.label.zh_Hans = model
                 return ai_model_entity_copy
+
+    def _get_base_model_name(self, credentials: dict) -> str:
+        base_model_name = credentials.get("base_model_name")
+        if not base_model_name:
+            raise ValueError("Base Model Name is required")
+        return base_model_name

api/core/model_runtime/model_providers/gitee_ai/_assets/Gitee-AI-Logo.svg

@@ -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>

api/core/model_runtime/model_providers/gitee_ai/_common.py

@@ -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,
+            ],
+        }

api/core/model_runtime/model_providers/gitee_ai/gitee_ai.py

@@ -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

api/core/model_runtime/model_providers/gitee_ai/gitee_ai.yaml

@@ -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

api/core/model_runtime/model_providers/gitee_ai/llm/Qwen2-72B-Instruct.yaml

@@ -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。"

api/core/model_runtime/model_providers/gitee_ai/llm/Qwen2-7B-Instruct.yaml

@@ -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。"

api/core/model_runtime/model_providers/gitee_ai/llm/Yi-1.5-34B-Chat.yaml

@@ -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。"

api/core/model_runtime/model_providers/gitee_ai/llm/_position.yaml

@@ -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

api/core/model_runtime/model_providers/gitee_ai/llm/codegeex4-all-9b.yaml

@@ -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。"

api/core/model_runtime/model_providers/gitee_ai/llm/deepseek-coder-33B-instruct-chat.yaml

@@ -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。"

api/core/model_runtime/model_providers/gitee_ai/llm/deepseek-coder-33B-instruct-completions.yaml

@@ -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。"

api/core/model_runtime/model_providers/gitee_ai/llm/glm-4-9b-chat.yaml

@@ -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。"

api/core/model_runtime/model_providers/gitee_ai/llm/llm.py

@@ -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