chore: update version to 0.10.2 in packaging and docker configurations (#9924)

Co-authored-by: crazywoola <427733928@qq.com>

.github/workflows/api-tests.yml

@@ -27,19 +27,18 @@ jobs:
       - name: Checkout code
         uses: actions/checkout@v4
 
-      - name: Install Poetry
-        uses: abatilo/actions-poetry@v3
-
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          cache: 'poetry'
           cache-dependency-path: |
             api/pyproject.toml
             api/poetry.lock
 
-      - name: Poetry check
+      - name: Install Poetry
+        uses: abatilo/actions-poetry@v3
+
+      - name: Check Poetry lockfile
         run: |
           poetry check -C api --lock
           poetry show -C api
@@ -47,6 +46,9 @@ jobs:
       - name: Install dependencies
         run: poetry install -C api --with dev
 
+      - name: Check dependencies in pyproject.toml
+        run: poetry run -C api bash dev/pytest/pytest_artifacts.sh
+
       - name: Run Unit tests
         run: poetry run -C api bash dev/pytest/pytest_unit_tests.sh
 

.github/workflows/build-push.yml

@@ -125,7 +125,7 @@ jobs:
         with:
           images: ${{ env[matrix.image_name_env] }}
           tags: |
-            type=raw,value=latest,enable=${{ startsWith(github.ref, 'refs/tags/') }}
+            type=raw,value=latest,enable=${{ startsWith(github.ref, 'refs/tags/') && !contains(github.ref, '-') }}
             type=ref,event=branch
             type=sha,enable=true,priority=100,prefix=,suffix=,format=long
             type=raw,value=${{ github.ref_name }},enable=${{ startsWith(github.ref, 'refs/tags/') }}

.github/workflows/db-migration-test.yml

@@ -23,18 +23,17 @@ jobs:
       - name: Checkout code
         uses: actions/checkout@v4
 
-      - name: Install Poetry
-        uses: abatilo/actions-poetry@v3
-
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          cache: 'poetry'
           cache-dependency-path: |
             api/pyproject.toml
             api/poetry.lock
 
+      - name: Install Poetry
+        uses: abatilo/actions-poetry@v3
+
       - name: Install dependencies
         run: poetry install -C api
 

.github/workflows/style.yml

@@ -24,15 +24,16 @@ jobs:
         with:
           files: api/**
 
-      - name: Install Poetry
-        uses: abatilo/actions-poetry@v3
-
       - name: Set up Python
         uses: actions/setup-python@v5
         if: steps.changed-files.outputs.any_changed == 'true'
         with:
           python-version: '3.10'
 
+      - name: Install Poetry
+        if: steps.changed-files.outputs.any_changed == 'true'
+        uses: abatilo/actions-poetry@v3
+
       - name: Python dependencies
         if: steps.changed-files.outputs.any_changed == 'true'
         run: poetry install -C api --only lint

.gitignore

@@ -175,6 +175,8 @@ docker/volumes/pgvector/data/*
 docker/volumes/pgvecto_rs/data/*
 
 docker/nginx/conf.d/default.conf
+docker/nginx/ssl/*
+!docker/nginx/ssl/.gitkeep
 docker/middleware.env
 
 sdks/python-client/build

LICENSE

@@ -6,8 +6,9 @@ Dify is licensed under the Apache License 2.0, with the following additional con
 
 a. Multi-tenant service: Unless explicitly authorized by Dify in writing, you may not use the Dify source code to operate a multi-tenant environment. 
     - Tenant Definition: Within the context of Dify, one tenant corresponds to one workspace. The workspace provides a separated area for each tenant's data and configurations.
-
-b. LOGO and copyright information: In the process of using Dify's frontend components, you may not remove or modify the LOGO or copyright information in the Dify console or applications. This restriction is inapplicable to uses of Dify that do not involve its frontend components.
+    
+b. LOGO and copyright information: In the process of using Dify's frontend, you may not remove or modify the LOGO or copyright information in the Dify console or applications. This restriction is inapplicable to uses of Dify that do not involve its frontend.
+    - Frontend Definition: For the purposes of this license, the "frontend" of Dify includes all components located in the `web/` directory when running Dify from the raw source code, or the "web" image when running Dify with Docker.
 
 Please contact business@dify.ai by email to inquire about licensing matters.
 

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> ·
@@ -17,7 +21,7 @@
             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 Twitter"></a>
+            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">
@@ -168,7 +172,7 @@ Star Dify on GitHub and be instantly notified of new releases.
 > Before installing Dify, make sure your machine meets the following minimum system requirements:
 > 
 >- CPU >= 2 Core
->- RAM >= 4GB
+>- RAM >= 4 GiB
 
 </br>
 
@@ -196,10 +200,14 @@ If you'd like to configure a highly-available setup, there are community-contrib
 
 #### Using Terraform for Deployment
 
+Deploy Dify to Cloud Platform with a single click using [terraform](https://www.terraform.io/)
+
 ##### Azure Global
-Deploy Dify to Azure with a single click using [terraform](https://www.terraform.io/).
 - [Azure Terraform by @nikawang](https://github.com/nikawang/dify-azure-terraform)
 
+##### Google Cloud
+- [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
+
 ## Contributing
 
 For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
@@ -219,7 +227,7 @@ At the same time, please consider supporting Dify by sharing it on social media
 * [Github Discussion](https://github.com/langgenius/dify/discussions). Best for: sharing feedback and asking questions.
 * [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
 * [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
-* [Twitter](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
+* [X(Twitter)](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
 
 ## Star history
 

README_AR.md

@@ -17,7 +17,7 @@
             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 Twitter"></a>
+            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">
@@ -179,10 +179,13 @@ docker compose up -d
 
 #### استخدام Terraform للتوزيع
 
+انشر Dify إلى منصة السحابة بنقرة واحدة باستخدام [terraform](https://www.terraform.io/)
+
 ##### Azure Global
-استخدم [terraform](https://www.terraform.io/) لنشر Dify على Azure بنقرة واحدة.
 - [Azure Terraform بواسطة @nikawang](https://github.com/nikawang/dify-azure-terraform)
 
+##### Google Cloud
+- [Google Cloud Terraform بواسطة @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
 ## المساهمة
 

README_CN.md

@@ -17,7 +17,7 @@
             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 Twitter"></a>
+            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">
@@ -154,7 +154,7 @@ Dify 是一个开源的 LLM 应用开发平台。其直观的界面结合了 AI
 我们提供[ Dify 云服务](https://dify.ai)，任何人都可以零设置尝试。它提供了自部署版本的所有功能，并在沙盒计划中包含 200 次免费的 GPT-4 调用。
 
 - **自托管 Dify 社区版</br>**
-使用这个[入门指南](#quick-start)快速在您的环境中运行 Dify。
+使用这个[入门指南](#快速启动)快速在您的环境中运行 Dify。
 使用我们的[文档](https://docs.dify.ai)进行进一步的参考和更深入的说明。
 
 - **面向企业/组织的 Dify</br>**
@@ -174,7 +174,7 @@ Dify 是一个开源的 LLM 应用开发平台。其直观的界面结合了 AI
 在安装 Dify 之前，请确保您的机器满足以下最低系统要求：
 
 - CPU >= 2 Core
-- RAM >= 4GB
+- RAM >= 4 GiB
 
 ### 快速启动
 
@@ -202,10 +202,14 @@ docker compose up -d
 
 #### 使用 Terraform 部署
 
+使用 [terraform](https://www.terraform.io/) 一键将 Dify 部署到云平台
+
 ##### Azure Global
-使用 [terraform](https://www.terraform.io/) 一键部署 Dify 到 Azure。
 - [Azure Terraform by @nikawang](https://github.com/nikawang/dify-azure-terraform)
 
+##### Google Cloud
+- [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
+
 ## Star History
 
 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
@@ -232,7 +236,7 @@ docker compose up -d
 - [GitHub Issues](https://github.com/langgenius/dify/issues)。👉：使用 Dify.AI 时遇到的错误和问题，请参阅[贡献指南](CONTRIBUTING.md)。
 - [电子邮件支持](mailto:hello@dify.ai?subject=[GitHub]Questions%20About%20Dify)。👉：关于使用 Dify.AI 的问题。
 - [Discord](https://discord.gg/FngNHpbcY7)。👉：分享您的应用程序并与社区交流。
-- [Twitter](https://twitter.com/dify_ai)。👉：分享您的应用程序并与社区交流。
+- [X(Twitter)](https://twitter.com/dify_ai)。👉：分享您的应用程序并与社区交流。
 - [商业许可](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)。👉：有关商业用途许可 Dify.AI 的商业咨询。
  - [微信]() 👉：扫描下方二维码，添加微信好友，备注 Dify，我们将邀请您加入 Dify 社区。  
 <img src="./images/wechat.png" alt="wechat" width="100"/>

README_ES.md

@@ -17,7 +17,7 @@
             alt="chat en 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="seguir en Twitter"></a>
+            alt="seguir en X(Twitter)"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Descargas de Docker" 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">
@@ -204,10 +204,13 @@ Si desea configurar una configuración de alta disponibilidad, la comunidad prop
 
 #### Uso de Terraform para el despliegue
 
+Despliega Dify en una plataforma en la nube con un solo clic utilizando [terraform](https://www.terraform.io/)
+
 ##### Azure Global
-Utiliza [terraform](https://www.terraform.io/) para desplegar Dify en Azure con un solo clic.
 - [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)
 
 ## Contribuir
 
@@ -228,7 +231,7 @@ Al mismo tiempo, considera apoyar a Dify compartiéndolo en redes sociales y en
 * [Discusión en GitHub](https://github.com/langgenius/dify/discussions). Lo mejor para: compartir comentarios y hacer preguntas.
 * [Reporte de problemas en GitHub](https://github.com/langgenius/dify/issues). Lo mejor para: errores que encuentres usando Dify.AI y propuestas de características. Consulta nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
 * [Discord](https://discord.gg/FngNHpbcY7). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad.
-* [Twitter](https://twitter.com/dify_ai). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad.
+* [X(Twitter)](https://twitter.com/dify_ai). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad.
 
 ## Historial de Estrellas
 

README_FR.md

@@ -17,7 +17,7 @@
             alt="chat sur 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="suivre sur Twitter"></a>
+            alt="suivre sur X(Twitter)"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Tirages Docker" 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">
@@ -202,10 +202,13 @@ Si vous souhaitez configurer une configuration haute disponibilité, la communau
 
 #### Utilisation de Terraform pour le déploiement
 
+Déployez Dify sur une plateforme cloud en un clic en utilisant [terraform](https://www.terraform.io/)
+
 ##### Azure Global
-Utilisez [terraform](https://www.terraform.io/) pour déployer Dify sur Azure en un clic.
 - [Azure Terraform par @nikawang](https://github.com/nikawang/dify-azure-terraform)
 
+##### Google Cloud
+- [Google Cloud Terraform par @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
 ## Contribuer
 
@@ -226,7 +229,7 @@ Dans le même temps, veuillez envisager de soutenir Dify en le partageant sur le
 * [Discussion GitHub](https://github.com/langgenius/dify/discussions). Meilleur pour: partager des commentaires et poser des questions.
 * [Problèmes GitHub](https://github.com/langgenius/dify/issues). Meilleur pour: les bogues que vous rencontrez en utilisant Dify.AI et les propositions de fonctionnalités. Consultez notre [Guide de contribution](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
 * [Discord](https://discord.gg/FngNHpbcY7). Meilleur pour: partager vos applications et passer du temps avec la communauté.
-* [Twitter](https://twitter.com/dify_ai). Meilleur pour: partager vos applications et passer du temps avec la communauté.
+* [X(Twitter)](https://twitter.com/dify_ai). Meilleur pour: partager vos applications et passer du temps avec la communauté.
 
 ## Historique des étoiles
 

README_JA.md

@@ -17,7 +17,7 @@
             alt="Discordでチャット"></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="Twitterでフォロー"></a>
+            alt="X(Twitter)でフォロー"></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">
@@ -68,7 +68,7 @@ DifyはオープンソースのLLMアプリケーション開発プラットフ
   プロンプトの作成、モデルパフォーマンスの比較が行え、チャットベースのアプリに音声合成などの機能も追加できます。
 
 **4. RAGパイプライン**: 
-  ドキュメントの取り込みから検索までをカバーする広範なRAG機能ができます。ほかにもPDF、PPT、その他の一般的なドキュメントフォーマットからのテキスト抽出のサーポイントも提供します。
+  ドキュメントの取り込みから検索までをカバーする広範なRAG機能ができます。ほかにもPDF、PPT、その他の一般的なドキュメントフォーマットからのテキスト抽出のサポートも提供します。
 
 **5. エージェント機能**: 
   LLM Function CallingやReActに基づくエージェントの定義が可能で、AIエージェント用のプリビルトまたはカスタムツールを追加できます。Difyには、Google検索、DALL·E、Stable Diffusion、WolframAlphaなどのAIエージェント用の50以上の組み込みツールが提供します。
@@ -201,10 +201,13 @@ docker compose up -d
 
 #### Terraformを使用したデプロイ
 
-##### Azure Global
-[terraform](https://www.terraform.io/) を使用して、AzureにDifyをワンクリックでデプロイします。
-- [nikawangのAzure Terraform](https://github.com/nikawang/dify-azure-terraform)
+[terraform](https://www.terraform.io/) を使用して、ワンクリックでDifyをクラウドプラットフォームにデプロイします
 
+##### Azure Global
+- [@nikawangによるAzure Terraform](https://github.com/nikawang/dify-azure-terraform)
+
+##### Google Cloud
+- [@sotazumによるGoogle Cloud Terraform](https://github.com/DeNA/dify-google-cloud-terraform)
 
 ## 貢献
 
@@ -225,7 +228,7 @@ docker compose up -d
 * [Github Discussion](https://github.com/langgenius/dify/discussions). 主に: フィードバックの共有や質問。
 * [GitHub Issues](https://github.com/langgenius/dify/issues). 主に: Dify.AIを使用する際に発生するエラーや問題については、[貢献ガイド](CONTRIBUTING_JA.md)を参照してください
 * [Discord](https://discord.gg/FngNHpbcY7). 主に: アプリケーションの共有やコミュニティとの交流。
-* [Twitter](https://twitter.com/dify_ai). 主に: アプリケーションの共有やコミュニティとの交流。
+* [X(Twitter)](https://twitter.com/dify_ai). 主に: アプリケーションの共有やコミュニティとの交流。
 
 
 

README_KL.md

@@ -17,7 +17,7 @@
             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 Twitter"></a>
+            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">
@@ -202,10 +202,13 @@ If you'd like to configure a highly-available setup, there are community-contrib
 
 #### Terraform atorlugu pilersitsineq
 
-##### Azure Global
-Atoruk [terraform](https://www.terraform.io/) Dify-mik Azure-mut ataatsikkut ikkussuilluarlugu.
-- [Azure Terraform atorlugu @nikawang](https://github.com/nikawang/dify-azure-terraform)
+wa'logh nIqHom neH ghun deployment toy'wI' [terraform](https://www.terraform.io/) lo'laH.
 
+##### Azure Global
+- [Azure Terraform mung @nikawang](https://github.com/nikawang/dify-azure-terraform)
+
+##### Google Cloud
+- [Google Cloud Terraform qachlot @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
 ## Contributing
 
@@ -228,7 +231,7 @@ At the same time, please consider supporting Dify by sharing it on social media
 ). Best for: sharing feedback and asking questions.
 * [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
 * [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
-* [Twitter](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
+* [X(Twitter)](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
 
 ## Star History
 

README_KR.md

@@ -17,7 +17,7 @@
             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 Twitter"></a>
+            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">
@@ -39,7 +39,6 @@
   <a href="./README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
   <a href="./README_TR.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
   <a href="./README_VI.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
-
 </p>
 
 
@@ -195,10 +194,14 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했
 
 #### Terraform을 사용한 배포
 
+[terraform](https://www.terraform.io/)을 사용하여 단 한 번의 클릭으로 Dify를 클라우드 플랫폼에 배포하십시오
+
 ##### Azure Global
-[terraform](https://www.terraform.io/)을 사용하여 Azure에 Dify를 원클릭으로 배포하세요.
 - [nikawang의 Azure Terraform](https://github.com/nikawang/dify-azure-terraform)
 
+##### Google Cloud
+- [sotazum의 Google Cloud Terraform](https://github.com/DeNA/dify-google-cloud-terraform)
+
 ## 기여
 
 코드에 기여하고 싶은 분들은 [기여 가이드](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)를 참조하세요.

README_TR.md

@@ -17,7 +17,7 @@
             alt="Discord'da sohbet et"></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="Twitter'da takip et"></a>
+            alt="X(Twitter)'da takip et"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Docker Çekmeleri" 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">
@@ -200,9 +200,13 @@ Yüksek kullanılabilirliğe sahip bir kurulum yapılandırmak isterseniz, Dify'
 
 #### Dağıtım için Terraform Kullanımı
 
+Dify'ı bulut platformuna tek tıklamayla dağıtın [terraform](https://www.terraform.io/) kullanarak
+
 ##### Azure Global
-[Terraform](https://www.terraform.io/) kullanarak Dify'ı Azure'a tek tıklamayla dağıtın.
-- [@nikawang tarafından Azure Terraform](https://github.com/nikawang/dify-azure-terraform)
+- [Azure Terraform tarafından @nikawang](https://github.com/nikawang/dify-azure-terraform)
+
+##### Google Cloud
+- [Google Cloud Terraform tarafından @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
 ## Katkıda Bulunma
 
@@ -222,7 +226,7 @@ Aynı zamanda, lütfen Dify'ı sosyal medyada, etkinliklerde ve konferanslarda p
 * [Github Tartışmaları](https://github.com/langgenius/dify/discussions). En uygun: geri bildirim paylaşmak ve soru sormak için.
 * [GitHub Sorunları](https://github.com/langgenius/dify/issues). En uygun: Dify.AI kullanırken karşılaştığınız hatalar ve özellik önerileri için. [Katkı Kılavuzumuza](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) bakın.
 * [Discord](https://discord.gg/FngNHpbcY7). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.
-* [Twitter](https://twitter.com/dify_ai). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.
+* [X(Twitter)](https://twitter.com/dify_ai). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.
 
 ## Star history
 

README_VI.md

@@ -17,7 +17,7 @@
             alt="chat trên 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="theo dõi trên Twitter"></a>
+            alt="theo dõi trên 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">
@@ -196,10 +196,14 @@ Nếu bạn muốn cấu hình một cài đặt có độ sẵn sàng cao, có
 
 #### Sử dụng Terraform để Triển khai
 
+Triển khai Dify lên nền tảng đám mây với một cú nhấp chuột bằng cách sử dụng [terraform](https://www.terraform.io/)
+
 ##### Azure Global
-Triển khai Dify lên Azure chỉ với một cú nhấp chuột bằng cách sử dụng [terraform](https://www.terraform.io/).
 - [Azure Terraform bởi @nikawang](https://github.com/nikawang/dify-azure-terraform)
 
+##### Google Cloud
+- [Google Cloud Terraform bởi @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
+
 ## Đóng góp
 
 Đối với những người muốn đóng góp mã, xem [Hướng dẫn Đóng góp](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) của chúng tôi. 
@@ -219,7 +223,7 @@ Triển khai Dify lên Azure chỉ với một cú nhấp chuột bằng cách s
 * [Thảo luận GitHub](https://github.com/langgenius/dify/discussions). Tốt nhất cho: chia sẻ phản hồi và đặt câu hỏi.
 * [Vấn đề GitHub](https://github.com/langgenius/dify/issues). Tốt nhất cho: lỗi bạn gặp phải khi sử dụng Dify.AI và đề xuất tính năng. Xem [Hướng dẫn Đóng góp](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) của chúng tôi.
 * [Discord](https://discord.gg/FngNHpbcY7). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng.
-* [Twitter](https://twitter.com/dify_ai). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng.
+* [X(Twitter)](https://twitter.com/dify_ai). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng.
 
 ## Lịch sử Yêu thích
 

api/.env.example

@@ -20,6 +20,9 @@ FILES_URL=http://127.0.0.1:5001
 # The time in seconds after the signature is rejected
 FILES_ACCESS_TIMEOUT=300
 
+# Access token expiration time in minutes
+ACCESS_TOKEN_EXPIRE_MINUTES=60
+
 # celery configuration
 CELERY_BROKER_URL=redis://:difyai123456@localhost:6379/1
 
@@ -28,8 +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
@@ -39,7 +51,7 @@ DB_DATABASE=dify
 
 # Storage configuration
 # use for store upload files, private keys...
-# storage type: local, s3, azure-blob, google-storage, tencent-cos, huawei-obs, volcengine-tos
+# storage type: local, s3, aliyun-oss, azure-blob, baidu-obs, google-storage, huawei-obs, oci-storage, tencent-cos, volcengine-tos, supabase
 STORAGE_TYPE=local
 STORAGE_LOCAL_PATH=storage
 S3_USE_AWS_MANAGED_IAM=false
@@ -79,6 +91,12 @@ HUAWEI_OBS_SECRET_KEY=your-secret-key
 HUAWEI_OBS_ACCESS_KEY=your-access-key
 HUAWEI_OBS_SERVER=your-server-url
 
+# Baidu OBS Storage Configuration
+BAIDU_OBS_BUCKET_NAME=your-bucket-name
+BAIDU_OBS_SECRET_KEY=your-secret-key
+BAIDU_OBS_ACCESS_KEY=your-access-key
+BAIDU_OBS_ENDPOINT=your-server-url
+
 # OCI Storage configuration
 OCI_ENDPOINT=your-endpoint
 OCI_BUCKET_NAME=your-bucket-name
@@ -93,11 +111,16 @@ VOLCENGINE_TOS_ACCESS_KEY=your-access-key
 VOLCENGINE_TOS_SECRET_KEY=your-secret-key
 VOLCENGINE_TOS_REGION=your-region
 
+# Supabase Storage Configuration
+SUPABASE_BUCKET_NAME=your-bucket-name
+SUPABASE_API_KEY=your-access-key
+SUPABASE_URL=your-server-url
+
 # CORS configuration
 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
+# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, vikingdb, upstash
 VECTOR_STORE=weaviate
 
 # Weaviate configuration
@@ -197,14 +220,39 @@ OPENSEARCH_USER=admin
 OPENSEARCH_PASSWORD=admin
 OPENSEARCH_SECURE=true
 
+# Baidu configuration
+BAIDU_VECTOR_DB_ENDPOINT=http://127.0.0.1:5287
+BAIDU_VECTOR_DB_CONNECTION_TIMEOUT_MS=30000
+BAIDU_VECTOR_DB_ACCOUNT=root
+BAIDU_VECTOR_DB_API_KEY=dify
+BAIDU_VECTOR_DB_DATABASE=dify
+BAIDU_VECTOR_DB_SHARD=1
+BAIDU_VECTOR_DB_REPLICAS=3
+
+# Upstash configuration
+UPSTASH_VECTOR_URL=your-server-url
+UPSTASH_VECTOR_TOKEN=your-access-token
+
+# ViKingDB configuration
+VIKINGDB_ACCESS_KEY=your-ak
+VIKINGDB_SECRET_KEY=your-sk
+VIKINGDB_REGION=cn-shanghai
+VIKINGDB_HOST=api-vikingdb.xxx.volces.com
+VIKINGDB_SCHEMA=http
+VIKINGDB_CONNECTION_TIMEOUT=30
+VIKINGDB_SOCKET_TIMEOUT=30
+
 # Upload configuration
 UPLOAD_FILE_SIZE_LIMIT=15
 UPLOAD_FILE_BATCH_LIMIT=5
 UPLOAD_IMAGE_FILE_SIZE_LIMIT=10
+UPLOAD_VIDEO_FILE_SIZE_LIMIT=100
+UPLOAD_AUDIO_FILE_SIZE_LIMIT=50
 
 # Model Configuration
 MULTIMODAL_SEND_IMAGE_FORMAT=base64
 PROMPT_GENERATION_MAX_TOKENS=512
+CODE_GENERATION_MAX_TOKENS=1024
 
 # Mail configuration, support: resend, smtp
 MAIL_TYPE=
@@ -265,8 +313,15 @@ HTTP_REQUEST_MAX_WRITE_TIMEOUT=600
 HTTP_REQUEST_NODE_MAX_BINARY_SIZE=10485760
 HTTP_REQUEST_NODE_MAX_TEXT_SIZE=1048576
 
+# Respect X-* headers to redirect clients
+RESPECT_XFORWARD_HEADERS_ENABLED=false
+
 # Log file path
 LOG_FILE=
+# Log file max size, the unit is MB
+LOG_FILE_MAX_SIZE=20
+# Log file max backup count
+LOG_FILE_BACKUP_COUNT=5
 
 # Indexing configuration
 INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=1000
@@ -275,6 +330,7 @@ INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=1000
 WORKFLOW_MAX_EXECUTION_STEPS=500
 WORKFLOW_MAX_EXECUTION_TIME=1200
 WORKFLOW_CALL_MAX_DEPTH=5
+MAX_VARIABLE_SIZE=204800
 
 # App configuration
 APP_MAX_EXECUTION_TIME=1200
@@ -292,3 +348,6 @@ POSITION_TOOL_EXCLUDES=
 POSITION_PROVIDER_PINS=
 POSITION_PROVIDER_INCLUDES=
 POSITION_PROVIDER_EXCLUDES=
+
+# Reset password token expiry minutes
+RESET_PASSWORD_TOKEN_EXPIRY_MINUTES=5

api/.vscode/launch.json.example

@@ -1,8 +1,15 @@
 {
     "version": "0.2.0",
+    "compounds": [
+        {
+            "name": "Launch Flask and Celery",
+            "configurations": ["Python: Flask", "Python: Celery"]
+        }
+    ],
     "configurations": [
         {
             "name": "Python: Flask",
+            "consoleName": "Flask",
             "type": "debugpy",
             "request": "launch",
             "python": "${workspaceFolder}/.venv/bin/python",
@@ -17,12 +24,12 @@
             },
             "args": [
                 "run",
-                "--host=0.0.0.0",
                 "--port=5001"
             ]
         },
         {
             "name": "Python: Celery",
+            "consoleName": "Celery",
             "type": "debugpy",
             "request": "launch",
             "python": "${workspaceFolder}/.venv/bin/python",
@@ -45,10 +52,10 @@
                 "-c",
                 "1",
                 "--loglevel",
-                "info",
+                "DEBUG",
                 "-Q",
                 "dataset,generation,mail,ops_trace,app_deletion"
             ]
-        },
+        }
     ]
-}
+}

api/Dockerfile

@@ -55,7 +55,9 @@ 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 perl=5.38.2-5 libsqlite3-0=3.46.0-1 \
+    && 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 \
+    # install a chinese font to support the use of tools like matplotlib
+    && apt-get install -y fonts-noto-cjk \
     && apt-get autoremove -y \
     && rm -rf /var/lib/apt/lists/*
 

api/README.md

@@ -85,3 +85,4 @@
    cd ../
    poetry run -C api bash dev/pytest/pytest_all_tests.sh
    ```
+

api/app.py

@@ -1,5 +1,7 @@
 import os
 
+from configs import dify_config
+
 if os.environ.get("DEBUG", "false").lower() != "true":
     from gevent import monkey
 
@@ -10,43 +12,20 @@ if os.environ.get("DEBUG", "false").lower() != "true":
     grpc.experimental.gevent.init_gevent()
 
 import json
-import logging
-import sys
 import threading
 import time
 import warnings
-from logging.handlers import RotatingFileHandler
 
-from flask import Flask, Response, request
-from flask_cors import CORS
-from werkzeug.exceptions import Unauthorized
+from flask import Response
 
-import contexts
-from commands import register_commands
-from configs import dify_config
+from app_factory import create_app
 
 # DO NOT REMOVE BELOW
-from events import event_handlers
-from extensions import (
-    ext_celery,
-    ext_code_based_extension,
-    ext_compress,
-    ext_database,
-    ext_hosting_provider,
-    ext_login,
-    ext_mail,
-    ext_migrate,
-    ext_redis,
-    ext_sentry,
-    ext_storage,
-)
+from events import event_handlers  # noqa: F401
 from extensions.ext_database import db
-from extensions.ext_login import login_manager
-from libs.passport import PassportService
 
 # TODO: Find a way to avoid importing models here
-from models import account, dataset, model, source, task, tool, tools, web
-from services.account_service import AccountService
+from models import account, dataset, model, source, task, tool, tools, web  # noqa: F401
 
 # DO NOT REMOVE ABOVE
 
@@ -59,192 +38,11 @@ if hasattr(time, "tzset"):
     time.tzset()
 
 
-class DifyApp(Flask):
-    pass
-
-
-# -------------
-# Configuration
-# -------------
-
-
-config_type = os.getenv("EDITION", default="SELF_HOSTED")  # ce edition first
-
-
-# ----------------------------
-# Application Factory Function
-# ----------------------------
-
-
-def create_flask_app_with_configs() -> Flask:
-    """
-    create a raw flask app
-    with configs loaded from .env file
-    """
-    dify_app = DifyApp(__name__)
-    dify_app.config.from_mapping(dify_config.model_dump())
-
-    # populate configs into system environment variables
-    for key, value in dify_app.config.items():
-        if isinstance(value, str):
-            os.environ[key] = value
-        elif isinstance(value, int | float | bool):
-            os.environ[key] = str(value)
-        elif value is None:
-            os.environ[key] = ""
-
-    return dify_app
-
-
-def create_app() -> Flask:
-    app = create_flask_app_with_configs()
-
-    app.secret_key = app.config["SECRET_KEY"]
-
-    log_handlers = None
-    log_file = app.config.get("LOG_FILE")
-    if log_file:
-        log_dir = os.path.dirname(log_file)
-        os.makedirs(log_dir, exist_ok=True)
-        log_handlers = [
-            RotatingFileHandler(
-                filename=log_file,
-                maxBytes=1024 * 1024 * 1024,
-                backupCount=5,
-            ),
-            logging.StreamHandler(sys.stdout),
-        ]
-
-    logging.basicConfig(
-        level=app.config.get("LOG_LEVEL"),
-        format=app.config.get("LOG_FORMAT"),
-        datefmt=app.config.get("LOG_DATEFORMAT"),
-        handlers=log_handlers,
-        force=True,
-    )
-    log_tz = app.config.get("LOG_TZ")
-    if log_tz:
-        from datetime import datetime
-
-        import pytz
-
-        timezone = pytz.timezone(log_tz)
-
-        def time_converter(seconds):
-            return datetime.utcfromtimestamp(seconds).astimezone(timezone).timetuple()
-
-        for handler in logging.root.handlers:
-            handler.formatter.converter = time_converter
-    initialize_extensions(app)
-    register_blueprints(app)
-    register_commands(app)
-
-    return app
-
-
-def initialize_extensions(app):
-    # Since the application instance is now created, pass it to each Flask
-    # extension instance to bind it to the Flask application instance (app)
-    ext_compress.init_app(app)
-    ext_code_based_extension.init()
-    ext_database.init_app(app)
-    ext_migrate.init(app, db)
-    ext_redis.init_app(app)
-    ext_storage.init_app(app)
-    ext_celery.init_app(app)
-    ext_login.init_app(app)
-    ext_mail.init_app(app)
-    ext_hosting_provider.init_app(app)
-    ext_sentry.init_app(app)
-
-
-# Flask-Login configuration
-@login_manager.request_loader
-def load_user_from_request(request_from_flask_login):
-    """Load user based on the request."""
-    if request.blueprint not in {"console", "inner_api"}:
-        return None
-    # Check if the user_id contains a dot, indicating the old format
-    auth_header = request.headers.get("Authorization", "")
-    if not auth_header:
-        auth_token = request.args.get("_token")
-        if not auth_token:
-            raise Unauthorized("Invalid Authorization token.")
-    else:
-        if " " not in auth_header:
-            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
-        auth_scheme, auth_token = auth_header.split(None, 1)
-        auth_scheme = auth_scheme.lower()
-        if auth_scheme != "bearer":
-            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
-
-    decoded = PassportService().verify(auth_token)
-    user_id = decoded.get("user_id")
-
-    account = AccountService.load_logged_in_account(account_id=user_id, token=auth_token)
-    if account:
-        contexts.tenant_id.set(account.current_tenant_id)
-    return account
-
-
-@login_manager.unauthorized_handler
-def unauthorized_handler():
-    """Handle unauthorized requests."""
-    return Response(
-        json.dumps({"code": "unauthorized", "message": "Unauthorized."}),
-        status=401,
-        content_type="application/json",
-    )
-
-
-# register blueprint routers
-def register_blueprints(app):
-    from controllers.console import bp as console_app_bp
-    from controllers.files import bp as files_bp
-    from controllers.inner_api import bp as inner_api_bp
-    from controllers.service_api import bp as service_api_bp
-    from controllers.web import bp as web_bp
-
-    CORS(
-        service_api_bp,
-        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-    )
-    app.register_blueprint(service_api_bp)
-
-    CORS(
-        web_bp,
-        resources={r"/*": {"origins": app.config["WEB_API_CORS_ALLOW_ORIGINS"]}},
-        supports_credentials=True,
-        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-        expose_headers=["X-Version", "X-Env"],
-    )
-
-    app.register_blueprint(web_bp)
-
-    CORS(
-        console_app_bp,
-        resources={r"/*": {"origins": app.config["CONSOLE_CORS_ALLOW_ORIGINS"]}},
-        supports_credentials=True,
-        allow_headers=["Content-Type", "Authorization"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-        expose_headers=["X-Version", "X-Env"],
-    )
-
-    app.register_blueprint(console_app_bp)
-
-    CORS(files_bp, allow_headers=["Content-Type"], methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"])
-    app.register_blueprint(files_bp)
-
-    app.register_blueprint(inner_api_bp)
-
-
 # create app
 app = create_app()
 celery = app.extensions["celery"]
 
-if app.config.get("TESTING"):
+if dify_config.TESTING:
     print("App is running in TESTING mode")
 
 
@@ -252,15 +50,15 @@ if app.config.get("TESTING"):
 def after_request(response):
     """Add Version headers to the response."""
     response.set_cookie("remember_token", "", expires=0)
-    response.headers.add("X-Version", app.config["CURRENT_VERSION"])
-    response.headers.add("X-Env", app.config["DEPLOY_ENV"])
+    response.headers.add("X-Version", dify_config.CURRENT_VERSION)
+    response.headers.add("X-Env", dify_config.DEPLOY_ENV)
     return response
 
 
 @app.route("/health")
 def health():
     return Response(
-        json.dumps({"pid": os.getpid(), "status": "ok", "version": app.config["CURRENT_VERSION"]}),
+        json.dumps({"pid": os.getpid(), "status": "ok", "version": dify_config.CURRENT_VERSION}),
         status=200,
         content_type="application/json",
     )

api/app_factory.py

@@ -0,0 +1,176 @@
+import os
+
+if os.environ.get("DEBUG", "false").lower() != "true":
+    from gevent import monkey
+
+    monkey.patch_all()
+
+    import grpc.experimental.gevent
+
+    grpc.experimental.gevent.init_gevent()
+
+import json
+
+from flask import Flask, Response, request
+from flask_cors import CORS
+from werkzeug.exceptions import Unauthorized
+
+import contexts
+from commands import register_commands
+from configs import dify_config
+from extensions import (
+    ext_celery,
+    ext_code_based_extension,
+    ext_compress,
+    ext_database,
+    ext_hosting_provider,
+    ext_logging,
+    ext_login,
+    ext_mail,
+    ext_migrate,
+    ext_proxy_fix,
+    ext_redis,
+    ext_sentry,
+    ext_storage,
+)
+from extensions.ext_database import db
+from extensions.ext_login import login_manager
+from libs.passport import PassportService
+from services.account_service import AccountService
+
+
+class DifyApp(Flask):
+    pass
+
+
+# ----------------------------
+# Application Factory Function
+# ----------------------------
+def create_flask_app_with_configs() -> Flask:
+    """
+    create a raw flask app
+    with configs loaded from .env file
+    """
+    dify_app = DifyApp(__name__)
+    dify_app.config.from_mapping(dify_config.model_dump())
+
+    # populate configs into system environment variables
+    for key, value in dify_app.config.items():
+        if isinstance(value, str):
+            os.environ[key] = value
+        elif isinstance(value, int | float | bool):
+            os.environ[key] = str(value)
+        elif value is None:
+            os.environ[key] = ""
+
+    return dify_app
+
+
+def create_app() -> Flask:
+    app = create_flask_app_with_configs()
+    app.secret_key = dify_config.SECRET_KEY
+    initialize_extensions(app)
+    register_blueprints(app)
+    register_commands(app)
+
+    return app
+
+
+def initialize_extensions(app):
+    # Since the application instance is now created, pass it to each Flask
+    # extension instance to bind it to the Flask application instance (app)
+    ext_logging.init_app(app)
+    ext_compress.init_app(app)
+    ext_code_based_extension.init()
+    ext_database.init_app(app)
+    ext_migrate.init(app, db)
+    ext_redis.init_app(app)
+    ext_storage.init_app(app)
+    ext_celery.init_app(app)
+    ext_login.init_app(app)
+    ext_mail.init_app(app)
+    ext_hosting_provider.init_app(app)
+    ext_sentry.init_app(app)
+    ext_proxy_fix.init_app(app)
+
+
+# Flask-Login configuration
+@login_manager.request_loader
+def load_user_from_request(request_from_flask_login):
+    """Load user based on the request."""
+    if request.blueprint not in {"console", "inner_api"}:
+        return None
+    # Check if the user_id contains a dot, indicating the old format
+    auth_header = request.headers.get("Authorization", "")
+    if not auth_header:
+        auth_token = request.args.get("_token")
+        if not auth_token:
+            raise Unauthorized("Invalid Authorization token.")
+    else:
+        if " " not in auth_header:
+            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
+        auth_scheme, auth_token = auth_header.split(None, 1)
+        auth_scheme = auth_scheme.lower()
+        if auth_scheme != "bearer":
+            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
+
+    decoded = PassportService().verify(auth_token)
+    user_id = decoded.get("user_id")
+
+    logged_in_account = AccountService.load_logged_in_account(account_id=user_id)
+    if logged_in_account:
+        contexts.tenant_id.set(logged_in_account.current_tenant_id)
+    return logged_in_account
+
+
+@login_manager.unauthorized_handler
+def unauthorized_handler():
+    """Handle unauthorized requests."""
+    return Response(
+        json.dumps({"code": "unauthorized", "message": "Unauthorized."}),
+        status=401,
+        content_type="application/json",
+    )
+
+
+# register blueprint routers
+def register_blueprints(app):
+    from controllers.console import bp as console_app_bp
+    from controllers.files import bp as files_bp
+    from controllers.inner_api import bp as inner_api_bp
+    from controllers.service_api import bp as service_api_bp
+    from controllers.web import bp as web_bp
+
+    CORS(
+        service_api_bp,
+        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
+        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
+    )
+    app.register_blueprint(service_api_bp)
+
+    CORS(
+        web_bp,
+        resources={r"/*": {"origins": dify_config.WEB_API_CORS_ALLOW_ORIGINS}},
+        supports_credentials=True,
+        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
+        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
+        expose_headers=["X-Version", "X-Env"],
+    )
+
+    app.register_blueprint(web_bp)
+
+    CORS(
+        console_app_bp,
+        resources={r"/*": {"origins": dify_config.CONSOLE_CORS_ALLOW_ORIGINS}},
+        supports_credentials=True,
+        allow_headers=["Content-Type", "Authorization"],
+        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
+        expose_headers=["X-Version", "X-Env"],
+    )
+
+    app.register_blueprint(console_app_bp)
+
+    CORS(files_bp, allow_headers=["Content-Type"], methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"])
+    app.register_blueprint(files_bp)
+
+    app.register_blueprint(inner_api_bp)

api/commands.py

@@ -19,7 +19,7 @@ from extensions.ext_redis import redis_client
 from libs.helper import email as email_validate
 from libs.password import hash_password, password_pattern, valid_password
 from libs.rsa import generate_key_pair
-from models.account import Tenant
+from models import Tenant
 from models.dataset import Dataset, DatasetCollectionBinding, DocumentSegment
 from models.dataset import Document as DatasetDocument
 from models.model import Account, App, AppAnnotationSetting, AppMode, Conversation, MessageAnnotation
@@ -259,6 +259,26 @@ def migrate_knowledge_vector_database():
     skipped_count = 0
     total_count = 0
     vector_type = dify_config.VECTOR_STORE
+    upper_colletion_vector_types = {
+        VectorType.MILVUS,
+        VectorType.PGVECTOR,
+        VectorType.RELYT,
+        VectorType.WEAVIATE,
+        VectorType.ORACLE,
+        VectorType.ELASTICSEARCH,
+    }
+    lower_colletion_vector_types = {
+        VectorType.ANALYTICDB,
+        VectorType.CHROMA,
+        VectorType.MYSCALE,
+        VectorType.PGVECTO_RS,
+        VectorType.TIDB_VECTOR,
+        VectorType.OPENSEARCH,
+        VectorType.TENCENT,
+        VectorType.BAIDU,
+        VectorType.VIKINGDB,
+        VectorType.UPSTASH,
+    }
     page = 1
     while True:
         try:
@@ -284,11 +304,9 @@ def migrate_knowledge_vector_database():
                         skipped_count = skipped_count + 1
                         continue
                 collection_name = ""
-                if vector_type == VectorType.WEAVIATE:
-                    dataset_id = dataset.id
+                dataset_id = dataset.id
+                if vector_type in upper_colletion_vector_types:
                     collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.WEAVIATE, "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
                 elif vector_type == VectorType.QDRANT:
                     if dataset.collection_binding_id:
                         dataset_collection_binding = (
@@ -301,55 +319,15 @@ def migrate_knowledge_vector_database():
                         else:
                             raise ValueError("Dataset Collection Binding not found")
                     else:
-                        dataset_id = dataset.id
                         collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.QDRANT, "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
 
-                elif vector_type == VectorType.MILVUS:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.MILVUS, "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.RELYT:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": "relyt", "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.TENCENT:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.TENCENT, "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.PGVECTOR:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.PGVECTOR, "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.OPENSEARCH:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {
-                        "type": VectorType.OPENSEARCH,
-                        "vector_store": {"class_prefix": collection_name},
-                    }
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.ANALYTICDB:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {
-                        "type": VectorType.ANALYTICDB,
-                        "vector_store": {"class_prefix": collection_name},
-                    }
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.ELASTICSEARCH:
-                    dataset_id = dataset.id
-                    index_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": "elasticsearch", "vector_store": {"class_prefix": index_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
+                elif vector_type in lower_colletion_vector_types:
+                    collection_name = Dataset.gen_collection_name_by_id(dataset_id).lower()
                 else:
                     raise ValueError(f"Vector store {vector_type} is not supported.")
 
+                index_struct_dict = {"type": vector_type, "vector_store": {"class_prefix": collection_name}}
+                dataset.index_struct = json.dumps(index_struct_dict)
                 vector = Vector(dataset)
                 click.echo(f"Migrating dataset {dataset.id}.")
 
@@ -449,14 +427,14 @@ def convert_to_agent_apps():
         # fetch first 1000 apps
         sql_query = """SELECT a.id AS id FROM apps a
             INNER JOIN app_model_configs am ON a.app_model_config_id=am.id
-            WHERE a.mode = 'chat' 
-            AND am.agent_mode is not null 
+            WHERE a.mode = 'chat'
+            AND am.agent_mode is not null
             AND (
-				am.agent_mode like '%"strategy": "function_call"%' 
+				am.agent_mode like '%"strategy": "function_call"%'
                 OR am.agent_mode  like '%"strategy": "react"%'
-			) 
+			)
             AND (
-				am.agent_mode like '{"enabled": true%' 
+				am.agent_mode like '{"enabled": true%'
                 OR am.agent_mode like '{"max_iteration": %'
 			) ORDER BY a.created_at DESC LIMIT 1000
         """

api/configs/feature/__init__.py

@@ -1,6 +1,15 @@
-from typing import Annotated, Optional
+from typing import Annotated, Literal, Optional
 
-from pydantic import AliasChoices, Field, HttpUrl, NegativeInt, NonNegativeInt, PositiveInt, computed_field
+from pydantic import (
+    AliasChoices,
+    Field,
+    HttpUrl,
+    NegativeInt,
+    NonNegativeInt,
+    PositiveFloat,
+    PositiveInt,
+    computed_field,
+)
 from pydantic_settings import BaseSettings
 
 from configs.feature.hosted_service import HostedServiceConfig
@@ -11,16 +20,31 @@ class SecurityConfig(BaseSettings):
     Security-related configurations for the application
     """
 
-    SECRET_KEY: Optional[str] = Field(
+    SECRET_KEY: str = Field(
         description="Secret key for secure session cookie signing."
         "Make sure you are changing this key for your deployment with a strong key."
         "Generate a strong key using `openssl rand -base64 42` or set via the `SECRET_KEY` environment variable.",
-        default=None,
+        default="",
     )
 
-    RESET_PASSWORD_TOKEN_EXPIRY_HOURS: PositiveInt = Field(
-        description="Duration in hours for which a password reset token remains valid",
-        default=24,
+    RESET_PASSWORD_TOKEN_EXPIRY_MINUTES: PositiveInt = Field(
+        description="Duration in minutes for which a password reset token remains valid",
+        default=5,
+    )
+
+    LOGIN_DISABLED: bool = Field(
+        description="Whether to disable login checks",
+        default=False,
+    )
+
+    ADMIN_API_KEY_ENABLE: bool = Field(
+        description="Whether to enable admin api key for authentication",
+        default=False,
+    )
+
+    ADMIN_API_KEY: Optional[str] = Field(
+        description="admin api key for authentication",
+        default=None,
     )
 
 
@@ -177,6 +201,16 @@ class FileUploadConfig(BaseSettings):
         default=10,
     )
 
+    UPLOAD_VIDEO_FILE_SIZE_LIMIT: NonNegativeInt = Field(
+        description="video file size limit in Megabytes for uploading files",
+        default=100,
+    )
+
+    UPLOAD_AUDIO_FILE_SIZE_LIMIT: NonNegativeInt = Field(
+        description="audio file size limit in Megabytes for uploading files",
+        default=50,
+    )
+
     BATCH_UPLOAD_LIMIT: NonNegativeInt = Field(
         description="Maximum number of files allowed in a batch upload operation",
         default=20,
@@ -247,6 +281,12 @@ class HttpConfig(BaseSettings):
         default=None,
     )
 
+    RESPECT_XFORWARD_HEADERS_ENABLED: bool = Field(
+        description="Enable or disable the X-Forwarded-For Proxy Fix middleware from Werkzeug"
+        " to respect X-* headers to redirect clients",
+        default=False,
+    )
+
 
 class InnerAPIConfig(BaseSettings):
     """
@@ -279,6 +319,16 @@ class LoggingConfig(BaseSettings):
         default=None,
     )
 
+    LOG_FILE_MAX_SIZE: PositiveInt = Field(
+        description="Maximum file size for file rotation retention, the unit is megabytes (MB)",
+        default=20,
+    )
+
+    LOG_FILE_BACKUP_COUNT: PositiveInt = Field(
+        description="Maximum file backup count file rotation retention",
+        default=5,
+    )
+
     LOG_FORMAT: str = Field(
         description="Format string for log messages",
         default="%(asctime)s.%(msecs)03d %(levelname)s [%(threadName)s] [%(filename)s:%(lineno)d] - %(message)s",
@@ -349,14 +399,14 @@ class WorkflowConfig(BaseSettings):
     )
 
     MAX_VARIABLE_SIZE: PositiveInt = Field(
-        description="Maximum size in bytes for a single variable in workflows. Default to 5KB.",
-        default=5 * 1024,
+        description="Maximum size in bytes for a single variable in workflows. Default to 200 KB.",
+        default=200 * 1024,
     )
 
 
-class OAuthConfig(BaseSettings):
+class AuthConfig(BaseSettings):
     """
-    Configuration for OAuth authentication
+    Configuration for authentication and OAuth
     """
 
     OAUTH_REDIRECT_PATH: str = Field(
@@ -365,7 +415,7 @@ class OAuthConfig(BaseSettings):
     )
 
     GITHUB_CLIENT_ID: Optional[str] = Field(
-        description="GitHub OAuth client secret",
+        description="GitHub OAuth client ID",
         default=None,
     )
 
@@ -384,6 +434,11 @@ class OAuthConfig(BaseSettings):
         default=None,
     )
 
+    ACCESS_TOKEN_EXPIRE_MINUTES: PositiveInt = Field(
+        description="Expiration time for access tokens in minutes",
+        default=60,
+    )
+
 
 class ModerationConfig(BaseSettings):
     """
@@ -462,12 +517,18 @@ class MailConfig(BaseSettings):
         default=False,
     )
 
+    EMAIL_SEND_IP_LIMIT_PER_MINUTE: PositiveInt = Field(
+        description="Maximum number of emails allowed to be sent from the same IP address in a minute",
+        default=50,
+    )
+
 
 class RagEtlConfig(BaseSettings):
     """
     Configuration for RAG ETL processes
     """
 
+    # TODO: This config is not only for rag etl, it is also for file upload, we should move it to file upload config
     ETL_TYPE: str = Field(
         description="RAG ETL type ('dify' or 'Unstructured'), default to 'dify'",
         default="dify",
@@ -495,16 +556,26 @@ class DataSetConfig(BaseSettings):
     Configuration for dataset management
     """
 
-    CLEAN_DAY_SETTING: PositiveInt = Field(
-        description="Interval in days for dataset cleanup operations",
+    PLAN_SANDBOX_CLEAN_DAY_SETTING: PositiveInt = Field(
+        description="Interval in days for dataset cleanup operations - plan: sandbox",
         default=30,
     )
 
+    PLAN_PRO_CLEAN_DAY_SETTING: PositiveInt = Field(
+        description="Interval in days for dataset cleanup operations - plan: pro and team",
+        default=7,
+    )
+
     DATASET_OPERATOR_ENABLED: bool = Field(
         description="Enable or disable dataset operator functionality",
         default=False,
     )
 
+    TIDB_SERVERLESS_NUMBER: PositiveInt = Field(
+        description="number of tidb serverless cluster",
+        default=500,
+    )
+
 
 class WorkspaceConfig(BaseSettings):
     """
@@ -529,7 +600,7 @@ class IndexingConfig(BaseSettings):
 
 
 class ImageFormatConfig(BaseSettings):
-    MULTIMODAL_SEND_IMAGE_FORMAT: str = Field(
+    MULTIMODAL_SEND_IMAGE_FORMAT: Literal["base64", "url"] = Field(
         description="Format for sending images in multimodal contexts ('base64' or 'url'), default is base64",
         default="base64",
     )
@@ -598,9 +669,37 @@ class PositionConfig(BaseSettings):
         return {item.strip() for item in self.POSITION_TOOL_EXCLUDES.split(",") if item.strip() != ""}
 
 
+class LoginConfig(BaseSettings):
+    ENABLE_EMAIL_CODE_LOGIN: bool = Field(
+        description="whether to enable email code login",
+        default=False,
+    )
+    ENABLE_EMAIL_PASSWORD_LOGIN: bool = Field(
+        description="whether to enable email password login",
+        default=True,
+    )
+    ENABLE_SOCIAL_OAUTH_LOGIN: bool = Field(
+        description="whether to enable github/google oauth login",
+        default=False,
+    )
+    EMAIL_CODE_LOGIN_TOKEN_EXPIRY_MINUTES: PositiveInt = Field(
+        description="expiry time in minutes for email code login token",
+        default=5,
+    )
+    ALLOW_REGISTER: bool = Field(
+        description="whether to enable register",
+        default=False,
+    )
+    ALLOW_CREATE_WORKSPACE: bool = Field(
+        description="whether to enable create workspace",
+        default=False,
+    )
+
+
 class FeatureConfig(
     # place the configs in alphabet order
     AppExecutionConfig,
+    AuthConfig,  # Changed from OAuthConfig to AuthConfig
     BillingConfig,
     CodeExecutionSandboxConfig,
     DataSetConfig,
@@ -615,14 +714,14 @@ class FeatureConfig(
     MailConfig,
     ModelLoadBalanceConfig,
     ModerationConfig,
-    OAuthConfig,
+    PositionConfig,
     RagEtlConfig,
     SecurityConfig,
     ToolConfig,
     UpdateConfig,
     WorkflowConfig,
     WorkspaceConfig,
-    PositionConfig,
+    LoginConfig,
     # hosted services config
     HostedServiceConfig,
     CeleryBeatConfig,

api/configs/middleware/__init__.py

@@ -5,13 +5,14 @@ from pydantic import Field, NonNegativeInt, PositiveFloat, PositiveInt, computed
 from pydantic_settings import BaseSettings
 
 from configs.middleware.cache.redis_config import RedisConfig
-from configs.middleware.external.bedrock_config import BedrockConfig
 from configs.middleware.storage.aliyun_oss_storage_config import AliyunOSSStorageConfig
 from configs.middleware.storage.amazon_s3_storage_config import S3StorageConfig
 from configs.middleware.storage.azure_blob_storage_config import AzureBlobStorageConfig
+from configs.middleware.storage.baidu_obs_storage_config import BaiduOBSStorageConfig
 from configs.middleware.storage.google_cloud_storage_config import GoogleCloudStorageConfig
 from configs.middleware.storage.huawei_obs_storage_config import HuaweiCloudOBSStorageConfig
 from configs.middleware.storage.oci_storage_config import OCIStorageConfig
+from configs.middleware.storage.supabase_storage_config import SupabaseStorageConfig
 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
@@ -26,14 +27,18 @@ 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
 from configs.middleware.vdb.weaviate_config import WeaviateConfig
 
 
 class StorageConfig(BaseSettings):
     STORAGE_TYPE: str = Field(
         description="Type of storage to use."
-        " Options: 'local', 's3', 'azure-blob', 'aliyun-oss', 'google-storage'. Default is 'local'.",
+        " Options: 'local', 's3', 'aliyun-oss', 'azure-blob', 'baidu-obs', 'google-storage', 'huawei-obs', "
+        "'oci-storage', 'tencent-cos', 'volcengine-tos', 'supabase'. Default is 'local'.",
         default="local",
     )
 
@@ -50,6 +55,11 @@ 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(
@@ -191,6 +201,22 @@ class CeleryConfig(DatabaseConfig):
         return self.CELERY_BROKER_URL.startswith("rediss://") if self.CELERY_BROKER_URL else False
 
 
+class InternalTestConfig(BaseSettings):
+    """
+    Configuration settings for Internal Test
+    """
+
+    AWS_SECRET_ACCESS_KEY: Optional[str] = Field(
+        description="Internal test AWS secret access key",
+        default=None,
+    )
+
+    AWS_ACCESS_KEY_ID: Optional[str] = Field(
+        description="Internal test AWS access key ID",
+        default=None,
+    )
+
+
 class MiddlewareConfig(
     # place the configs in alphabet order
     CeleryConfig,
@@ -201,12 +227,14 @@ class MiddlewareConfig(
     StorageConfig,
     AliyunOSSStorageConfig,
     AzureBlobStorageConfig,
+    BaiduOBSStorageConfig,
     GoogleCloudStorageConfig,
-    TencentCloudCOSStorageConfig,
     HuaweiCloudOBSStorageConfig,
-    VolcengineTOSStorageConfig,
-    S3StorageConfig,
     OCIStorageConfig,
+    S3StorageConfig,
+    SupabaseStorageConfig,
+    TencentCloudCOSStorageConfig,
+    VolcengineTOSStorageConfig,
     # configs of vdb and vdb providers
     VectorStoreConfig,
     AnalyticdbConfig,
@@ -223,6 +251,9 @@ class MiddlewareConfig(
     TiDBVectorConfig,
     WeaviateConfig,
     ElasticsearchConfig,
-    BedrockConfig,
+    InternalTestConfig,
+    VikingDBConfig,
+    UpstashConfig,
+    TidbOnQdrantConfig,
 ):
     pass

api/configs/middleware/external/bedrock_config.py

@@ -1,20 +0,0 @@
-from typing import Optional
-
-from pydantic import Field
-from pydantic_settings import BaseSettings
-
-
-class BedrockConfig(BaseSettings):
-    """
-    bedrock configs
-    """
-
-    AWS_SECRET_ACCESS_KEY: Optional[str] = Field(
-        description="AWS secret access key",
-        default=None,
-    )
-
-    AWS_ACCESS_KEY_ID: Optional[str] = Field(
-        description="AWS secret access id",
-        default=None,
-    )

api/configs/middleware/storage/baidu_obs_storage_config.py

@@ -0,0 +1,29 @@
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+
+class BaiduOBSStorageConfig(BaseModel):
+    """
+    Configuration settings for Baidu Object Storage Service (OBS)
+    """
+
+    BAIDU_OBS_BUCKET_NAME: Optional[str] = Field(
+        description="Name of the Baidu OBS bucket to store and retrieve objects (e.g., 'my-obs-bucket')",
+        default=None,
+    )
+
+    BAIDU_OBS_ACCESS_KEY: Optional[str] = Field(
+        description="Access Key ID for authenticating with Baidu OBS",
+        default=None,
+    )
+
+    BAIDU_OBS_SECRET_KEY: Optional[str] = Field(
+        description="Secret Access Key for authenticating with Baidu OBS",
+        default=None,
+    )
+
+    BAIDU_OBS_ENDPOINT: Optional[str] = Field(
+        description="URL of the Baidu OSS endpoint for your chosen region (e.g., 'https://.bj.bcebos.com')",
+        default=None,
+    )

api/configs/middleware/storage/supabase_storage_config.py

@@ -0,0 +1,24 @@
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+
+class SupabaseStorageConfig(BaseModel):
+    """
+    Configuration settings for Supabase Object Storage Service
+    """
+
+    SUPABASE_BUCKET_NAME: Optional[str] = Field(
+        description="Name of the Supabase bucket to store and retrieve objects (e.g., 'dify-bucket')",
+        default=None,
+    )
+
+    SUPABASE_API_KEY: Optional[str] = Field(
+        description="API KEY for authenticating with Supabase",
+        default=None,
+    )
+
+    SUPABASE_URL: Optional[str] = Field(
+        description="URL of the Supabase",
+        default=None,
+    )

api/configs/middleware/vdb/baidu_vector_config.py

@@ -0,0 +1,45 @@
+from typing import Optional
+
+from pydantic import Field, NonNegativeInt, PositiveInt
+from pydantic_settings import BaseSettings
+
+
+class BaiduVectorDBConfig(BaseSettings):
+    """
+    Configuration settings for Baidu Vector Database
+    """
+
+    BAIDU_VECTOR_DB_ENDPOINT: Optional[str] = Field(
+        description="URL of the Baidu Vector Database service (e.g., 'http://vdb.bj.baidubce.com')",
+        default=None,
+    )
+
+    BAIDU_VECTOR_DB_CONNECTION_TIMEOUT_MS: PositiveInt = Field(
+        description="Timeout in milliseconds for Baidu Vector Database operations (default is 30000 milliseconds)",
+        default=30000,
+    )
+
+    BAIDU_VECTOR_DB_ACCOUNT: Optional[str] = Field(
+        description="Account for authenticating with the Baidu Vector Database",
+        default=None,
+    )
+
+    BAIDU_VECTOR_DB_API_KEY: Optional[str] = Field(
+        description="API key for authenticating with the Baidu Vector Database service",
+        default=None,
+    )
+
+    BAIDU_VECTOR_DB_DATABASE: Optional[str] = Field(
+        description="Name of the specific Baidu Vector Database to connect to",
+        default=None,
+    )
+
+    BAIDU_VECTOR_DB_SHARD: PositiveInt = Field(
+        description="Number of shards for the Baidu Vector Database (default is 1)",
+        default=1,
+    )
+
+    BAIDU_VECTOR_DB_REPLICAS: NonNegativeInt = Field(
+        description="Number of replicas for the Baidu Vector Database (default is 3)",
+        default=3,
+    )

api/configs/middleware/vdb/oracle_config.py

@@ -14,7 +14,7 @@ class OracleConfig(BaseSettings):
         default=None,
     )
 
-    ORACLE_PORT: Optional[PositiveInt] = Field(
+    ORACLE_PORT: PositiveInt = Field(
         description="Port number on which the Oracle database server is listening (default is 1521)",
         default=1521,
     )

api/configs/middleware/vdb/pgvector_config.py

@@ -14,7 +14,7 @@ class PGVectorConfig(BaseSettings):
         default=None,
     )
 
-    PGVECTOR_PORT: Optional[PositiveInt] = Field(
+    PGVECTOR_PORT: PositiveInt = Field(
         description="Port number on which the PostgreSQL server is listening (default is 5433)",
         default=5433,
     )

api/configs/middleware/vdb/pgvectors_config.py

@@ -14,7 +14,7 @@ class PGVectoRSConfig(BaseSettings):
         default=None,
     )
 
-    PGVECTO_RS_PORT: Optional[PositiveInt] = Field(
+    PGVECTO_RS_PORT: PositiveInt = Field(
         description="Port number on which the PostgreSQL server with PGVecto.RS is listening (default is 5431)",
         default=5431,
     )

api/configs/middleware/vdb/tidb_on_qdrant_config.py

@@ -0,0 +1,65 @@
+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,
+    )

api/configs/middleware/vdb/upstash_config.py

@@ -0,0 +1,20 @@
+from typing import Optional
+
+from pydantic import Field
+from pydantic_settings import BaseSettings
+
+
+class UpstashConfig(BaseSettings):
+    """
+    Configuration settings for Upstash vector database
+    """
+
+    UPSTASH_VECTOR_URL: Optional[str] = Field(
+        description="URL of the upstash server (e.g., 'https://vector.upstash.io')",
+        default=None,
+    )
+
+    UPSTASH_VECTOR_TOKEN: Optional[str] = Field(
+        description="Token for authenticating with the upstash server",
+        default=None,
+    )

api/configs/middleware/vdb/vikingdb_config.py

@@ -0,0 +1,49 @@
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+
+class VikingDBConfig(BaseModel):
+    """
+    Configuration for connecting to Volcengine VikingDB.
+    Refer to the following documentation for details on obtaining credentials:
+    https://www.volcengine.com/docs/6291/65568
+    """
+
+    VIKINGDB_ACCESS_KEY: Optional[str] = Field(
+        description="The Access Key provided by Volcengine VikingDB for API authentication."
+        "Refer to the following documentation for details on obtaining credentials:"
+        "https://www.volcengine.com/docs/6291/65568",
+        default=None,
+    )
+
+    VIKINGDB_SECRET_KEY: Optional[str] = Field(
+        description="The Secret Key provided by Volcengine VikingDB for API authentication.",
+        default=None,
+    )
+
+    VIKINGDB_REGION: str = Field(
+        description="The region of the Volcengine VikingDB service.(e.g., 'cn-shanghai', 'cn-beijing').",
+        default="cn-shanghai",
+    )
+
+    VIKINGDB_HOST: str = Field(
+        description="The host of the Volcengine VikingDB service.(e.g., 'api-vikingdb.volces.com', \
+            'api-vikingdb.mlp.cn-shanghai.volces.com')",
+        default="api-vikingdb.mlp.cn-shanghai.volces.com",
+    )
+
+    VIKINGDB_SCHEME: str = Field(
+        description="The scheme of the Volcengine VikingDB service.(e.g., 'http', 'https').",
+        default="http",
+    )
+
+    VIKINGDB_CONNECTION_TIMEOUT: int = Field(
+        description="The connection timeout of the Volcengine VikingDB service.",
+        default=30,
+    )
+
+    VIKINGDB_SOCKET_TIMEOUT: int = Field(
+        description="The socket timeout of the Volcengine VikingDB service.",
+        default=30,
+    )

api/configs/packaging/__init__.py

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
 
     CURRENT_VERSION: str = Field(
         description="Dify version",
-        default="0.8.3",
+        default="0.10.2",
     )
 
     COMMIT_SHA: str = Field(

api/constants/__init__.py

@@ -1,2 +1,24 @@
+from configs import dify_config
+
 HIDDEN_VALUE = "[__HIDDEN__]"
 UUID_NIL = "00000000-0000-0000-0000-000000000000"
+
+IMAGE_EXTENSIONS = ["jpg", "jpeg", "png", "webp", "gif", "svg"]
+IMAGE_EXTENSIONS.extend([ext.upper() for ext in IMAGE_EXTENSIONS])
+
+VIDEO_EXTENSIONS = ["mp4", "mov", "mpeg", "mpga"]
+VIDEO_EXTENSIONS.extend([ext.upper() for ext in VIDEO_EXTENSIONS])
+
+AUDIO_EXTENSIONS = ["mp3", "m4a", "wav", "webm", "amr"]
+AUDIO_EXTENSIONS.extend([ext.upper() for ext in AUDIO_EXTENSIONS])
+
+
+if dify_config.ETL_TYPE == "Unstructured":
+    DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "pdf", "html", "htm", "xlsx", "xls"]
+    DOCUMENT_EXTENSIONS.extend(("docx", "csv", "eml", "msg", "pptx", "xml", "epub"))
+    if dify_config.UNSTRUCTURED_API_URL:
+        DOCUMENT_EXTENSIONS.append("ppt")
+    DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])
+else:
+    DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "pdf", "html", "htm", "xlsx", "xls", "docx", "csv"]
+    DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])

api/contexts/__init__.py

@@ -1,7 +1,9 @@
 from contextvars import ContextVar
+from typing import TYPE_CHECKING
 
-from core.workflow.entities.variable_pool import VariablePool
+if TYPE_CHECKING:
+    from core.workflow.entities.variable_pool import VariablePool
 
 tenant_id: ContextVar[str] = ContextVar("tenant_id")
 
-workflow_variable_pool: ContextVar[VariablePool] = ContextVar("workflow_variable_pool")
+workflow_variable_pool: ContextVar["VariablePool"] = ContextVar("workflow_variable_pool")

api/controllers/console/__init__.py

@@ -45,7 +45,6 @@ from .datasets import (
     external,
     file,
     hit_testing,
-    test_external,
     website,
 )
 

api/controllers/console/admin.py

@@ -1,10 +1,10 @@
-import os
 from functools import wraps
 
 from flask import request
 from flask_restful import Resource, reqparse
 from werkzeug.exceptions import NotFound, Unauthorized
 
+from configs import dify_config
 from constants.languages import supported_language
 from controllers.console import api
 from controllers.console.wraps import only_edition_cloud
@@ -15,7 +15,7 @@ from models.model import App, InstalledApp, RecommendedApp
 def admin_required(view):
     @wraps(view)
     def decorated(*args, **kwargs):
-        if not os.getenv("ADMIN_API_KEY"):
+        if not dify_config.ADMIN_API_KEY:
             raise Unauthorized("API key is invalid.")
 
         auth_header = request.headers.get("Authorization")
@@ -31,7 +31,7 @@ def admin_required(view):
         if auth_scheme != "bearer":
             raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
 
-        if os.getenv("ADMIN_API_KEY") != auth_token:
+        if dify_config.ADMIN_API_KEY != auth_token:
             raise Unauthorized("API key is invalid.")
 
         return view(*args, **kwargs)

api/controllers/console/app/conversation.py

@@ -22,7 +22,8 @@ from fields.conversation_fields import (
 )
 from libs.helper import DatetimeString
 from libs.login import login_required
-from models.model import AppMode, Conversation, EndUser, Message, MessageAnnotation
+from models import Conversation, EndUser, Message, MessageAnnotation
+from models.model import AppMode
 
 
 class CompletionConversationApi(Resource):
@@ -188,6 +189,7 @@ class ChatConversationApi(Resource):
                         subquery.c.from_end_user_session_id.ilike(keyword_filter),
                     ),
                 )
+                .group_by(Conversation.id)
             )
 
         account = current_user

api/controllers/console/app/generator.py

@@ -52,4 +52,39 @@ class RuleGenerateApi(Resource):
         return rules
 
 
+class RuleCodeGenerateApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("instruction", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("model_config", type=dict, required=True, nullable=False, location="json")
+        parser.add_argument("no_variable", type=bool, required=True, default=False, location="json")
+        parser.add_argument("code_language", type=str, required=False, default="javascript", location="json")
+        args = parser.parse_args()
+
+        account = current_user
+        CODE_GENERATION_MAX_TOKENS = int(os.getenv("CODE_GENERATION_MAX_TOKENS", "1024"))
+        try:
+            code_result = LLMGenerator.generate_code(
+                tenant_id=account.current_tenant_id,
+                instruction=args["instruction"],
+                model_config=args["model_config"],
+                code_language=args["code_language"],
+                max_tokens=CODE_GENERATION_MAX_TOKENS,
+            )
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        except QuotaExceededError:
+            raise ProviderQuotaExceededError()
+        except ModelCurrentlyNotSupportError:
+            raise ProviderModelCurrentlyNotSupportError()
+        except InvokeError as e:
+            raise CompletionRequestError(e.description)
+
+        return code_result
+
+
 api.add_resource(RuleGenerateApi, "/rule-generate")
+api.add_resource(RuleCodeGenerateApi, "/rule-code-generate")

api/controllers/console/app/message.py

@@ -105,6 +105,8 @@ class ChatMessageListApi(Resource):
             if rest_count > 0:
                 has_more = True
 
+        history_messages = list(reversed(history_messages))
+
         return InfiniteScrollPagination(data=history_messages, limit=args["limit"], has_more=has_more)
 
 

api/controllers/console/app/site.py

@@ -12,7 +12,7 @@ from controllers.console.wraps import account_initialization_required
 from extensions.ext_database import db
 from fields.app_fields import app_site_fields
 from libs.login import login_required
-from models.model import Site
+from models import Site
 
 
 def parse_app_site_args():

api/controllers/console/app/workflow.py

@@ -13,14 +13,14 @@ from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
-from core.app.segments import factory
-from core.errors.error import AppInvokeQuotaExceededError
+from factories import variable_factory
 from fields.workflow_fields import workflow_fields
 from fields.workflow_run_fields import workflow_run_node_execution_fields
 from libs import helper
 from libs.helper import TimestampField, uuid_value
 from libs.login import current_user, login_required
-from models.model import App, AppMode
+from models import App
+from models.model import AppMode
 from services.app_dsl_service import AppDslService
 from services.app_generate_service import AppGenerateService
 from services.errors.app import WorkflowHashNotEqualError
@@ -101,9 +101,13 @@ class DraftWorkflowApi(Resource):
 
         try:
             environment_variables_list = args.get("environment_variables") or []
-            environment_variables = [factory.build_variable_from_mapping(obj) for obj in environment_variables_list]
+            environment_variables = [
+                variable_factory.build_variable_from_mapping(obj) for obj in environment_variables_list
+            ]
             conversation_variables_list = args.get("conversation_variables") or []
-            conversation_variables = [factory.build_variable_from_mapping(obj) for obj in conversation_variables_list]
+            conversation_variables = [
+                variable_factory.build_variable_from_mapping(obj) for obj in conversation_variables_list
+            ]
             workflow = workflow_service.sync_draft_workflow(
                 app_model=app_model,
                 graph=args["graph"],
@@ -273,17 +277,15 @@ class DraftWorkflowRunApi(Resource):
         parser.add_argument("files", type=list, required=False, location="json")
         args = parser.parse_args()
 
-        try:
-            response = AppGenerateService.generate(
-                app_model=app_model, user=current_user, args=args, invoke_from=InvokeFrom.DEBUGGER, streaming=True
-            )
+        response = AppGenerateService.generate(
+            app_model=app_model,
+            user=current_user,
+            args=args,
+            invoke_from=InvokeFrom.DEBUGGER,
+            streaming=True,
+        )
 
-            return helper.compact_generate_response(response)
-        except (ValueError, AppInvokeQuotaExceededError) as e:
-            raise e
-        except Exception as e:
-            logging.exception("internal server error.")
-            raise InternalServerError()
+        return helper.compact_generate_response(response)
 
 
 class WorkflowTaskStopApi(Resource):

api/controllers/console/app/workflow_app_log.py

@@ -7,7 +7,8 @@ from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
 from fields.workflow_app_log_fields import workflow_app_log_pagination_fields
 from libs.login import login_required
-from models.model import App, AppMode
+from models import App
+from models.model import AppMode
 from services.workflow_app_service import WorkflowAppService
 
 

api/controllers/console/app/workflow_run.py

@@ -13,7 +13,8 @@ from fields.workflow_run_fields import (
 )
 from libs.helper import uuid_value
 from libs.login import login_required
-from models.model import App, AppMode
+from models import App
+from models.model import AppMode
 from services.workflow_run_service import WorkflowRunService
 
 

api/controllers/console/app/workflow_statistic.py

@@ -13,8 +13,8 @@ from controllers.console.wraps import account_initialization_required
 from extensions.ext_database import db
 from libs.helper import DatetimeString
 from libs.login import login_required
+from models.enums import WorkflowRunTriggeredFrom
 from models.model import AppMode
-from models.workflow import WorkflowRunTriggeredFrom
 
 
 class WorkflowDailyRunsStatistic(Resource):

api/controllers/console/app/wraps.py

@@ -5,7 +5,8 @@ from typing import Optional, Union
 from controllers.console.app.error import AppNotFoundError
 from extensions.ext_database import db
 from libs.login import current_user
-from models.model import App, AppMode
+from models import App
+from models.model import AppMode
 
 
 def get_app_model(view: Optional[Callable] = None, *, mode: Union[AppMode, list[AppMode]] = None):

api/controllers/console/auth/activate.py

@@ -1,17 +1,15 @@
-import base64
 import datetime
-import secrets
 
+from flask import request
 from flask_restful import Resource, reqparse
 
 from constants.languages import supported_language
 from controllers.console import api
 from controllers.console.error import AlreadyActivateError
 from extensions.ext_database import db
-from libs.helper import StrLen, email, timezone
-from libs.password import hash_password, valid_password
-from models.account import AccountStatus
-from services.account_service import RegisterService
+from libs.helper import StrLen, email, extract_remote_ip, timezone
+from models.account import AccountStatus, Tenant
+from services.account_service import AccountService, RegisterService
 
 
 class ActivateCheckApi(Resource):
@@ -27,8 +25,18 @@ class ActivateCheckApi(Resource):
         token = args["token"]
 
         invitation = RegisterService.get_invitation_if_token_valid(workspaceId, reg_email, token)
-
-        return {"is_valid": invitation is not None, "workspace_name": invitation["tenant"].name if invitation else None}
+        if invitation:
+            data = invitation.get("data", {})
+            tenant: Tenant = invitation.get("tenant", None)
+            workspace_name = tenant.name if tenant else None
+            workspace_id = tenant.id if tenant else None
+            invitee_email = data.get("email") if data else None
+            return {
+                "is_valid": invitation is not None,
+                "data": {"workspace_name": workspace_name, "workspace_id": workspace_id, "email": invitee_email},
+            }
+        else:
+            return {"is_valid": False}
 
 
 class ActivateApi(Resource):
@@ -38,7 +46,6 @@ class ActivateApi(Resource):
         parser.add_argument("email", type=email, required=False, nullable=True, location="json")
         parser.add_argument("token", type=str, required=True, nullable=False, location="json")
         parser.add_argument("name", type=StrLen(30), required=True, nullable=False, location="json")
-        parser.add_argument("password", type=valid_password, required=True, nullable=False, location="json")
         parser.add_argument(
             "interface_language", type=supported_language, required=True, nullable=False, location="json"
         )
@@ -54,15 +61,6 @@ class ActivateApi(Resource):
         account = invitation["account"]
         account.name = args["name"]
 
-        # generate password salt
-        salt = secrets.token_bytes(16)
-        base64_salt = base64.b64encode(salt).decode()
-
-        # encrypt password with salt
-        password_hashed = hash_password(args["password"], salt)
-        base64_password_hashed = base64.b64encode(password_hashed).decode()
-        account.password = base64_password_hashed
-        account.password_salt = base64_salt
         account.interface_language = args["interface_language"]
         account.timezone = args["timezone"]
         account.interface_theme = "light"
@@ -70,7 +68,9 @@ class ActivateApi(Resource):
         account.initialized_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
         db.session.commit()
 
-        return {"result": "success"}
+        token_pair = AccountService.login(account, ip_address=extract_remote_ip(request))
+
+        return {"result": "success", "data": token_pair.model_dump()}
 
 
 api.add_resource(ActivateCheckApi, "/activate/check")

api/controllers/console/auth/error.py

@@ -27,5 +27,29 @@ class InvalidTokenError(BaseHTTPException):
 
 class PasswordResetRateLimitExceededError(BaseHTTPException):
     error_code = "password_reset_rate_limit_exceeded"
-    description = "Password reset rate limit exceeded. Try again later."
+    description = "Too many password reset emails have been sent. Please try again in 1 minutes."
+    code = 429
+
+
+class EmailCodeError(BaseHTTPException):
+    error_code = "email_code_error"
+    description = "Email code is invalid or expired."
+    code = 400
+
+
+class EmailOrPasswordMismatchError(BaseHTTPException):
+    error_code = "email_or_password_mismatch"
+    description = "The email or password is mismatched."
+    code = 400
+
+
+class EmailPasswordLoginLimitError(BaseHTTPException):
+    error_code = "email_code_login_limit"
+    description = "Too many incorrect password attempts. Please try again later."
+    code = 429
+
+
+class EmailCodeLoginRateLimitExceededError(BaseHTTPException):
+    error_code = "email_code_login_rate_limit_exceeded"
+    description = "Too many login emails have been sent. Please try again in 5 minutes."
     code = 429

api/controllers/console/auth/forgot_password.py

@@ -1,65 +1,82 @@
 import base64
-import logging
 import secrets
 
+from flask import request
 from flask_restful import Resource, reqparse
 
+from constants.languages import languages
 from controllers.console import api
 from controllers.console.auth.error import (
+    EmailCodeError,
     InvalidEmailError,
     InvalidTokenError,
     PasswordMismatchError,
-    PasswordResetRateLimitExceededError,
 )
+from controllers.console.error import EmailSendIpLimitError, NotAllowedRegister
 from controllers.console.setup import setup_required
+from events.tenant_event import tenant_was_created
 from extensions.ext_database import db
-from libs.helper import email as email_validate
+from libs.helper import email, extract_remote_ip
 from libs.password import hash_password, valid_password
 from models.account import Account
-from services.account_service import AccountService
-from services.errors.account import RateLimitExceededError
+from services.account_service import AccountService, TenantService
+from services.errors.workspace import WorkSpaceNotAllowedCreateError
+from services.feature_service import FeatureService
 
 
 class ForgotPasswordSendEmailApi(Resource):
     @setup_required
     def post(self):
         parser = reqparse.RequestParser()
-        parser.add_argument("email", type=str, required=True, location="json")
+        parser.add_argument("email", type=email, required=True, location="json")
+        parser.add_argument("language", type=str, required=False, location="json")
         args = parser.parse_args()
 
-        email = args["email"]
+        ip_address = extract_remote_ip(request)
+        if AccountService.is_email_send_ip_limit(ip_address):
+            raise EmailSendIpLimitError()
 
-        if not email_validate(email):
-            raise InvalidEmailError()
-
-        account = Account.query.filter_by(email=email).first()
-
-        if account:
-            try:
-                AccountService.send_reset_password_email(account=account)
-            except RateLimitExceededError:
-                logging.warning(f"Rate limit exceeded for email: {account.email}")
-                raise PasswordResetRateLimitExceededError()
+        if args["language"] is not None and args["language"] == "zh-Hans":
+            language = "zh-Hans"
         else:
-            # Return success to avoid revealing email registration status
-            logging.warning(f"Attempt to reset password for unregistered email: {email}")
+            language = "en-US"
 
-        return {"result": "success"}
+        account = Account.query.filter_by(email=args["email"]).first()
+        token = None
+        if account is None:
+            if FeatureService.get_system_features().is_allow_register:
+                token = AccountService.send_reset_password_email(email=args["email"], language=language)
+                return {"result": "fail", "data": token, "code": "account_not_found"}
+            else:
+                raise NotAllowedRegister()
+        else:
+            token = AccountService.send_reset_password_email(account=account, email=args["email"], language=language)
+
+        return {"result": "success", "data": token}
 
 
 class ForgotPasswordCheckApi(Resource):
     @setup_required
     def post(self):
         parser = reqparse.RequestParser()
+        parser.add_argument("email", type=str, required=True, location="json")
+        parser.add_argument("code", type=str, required=True, location="json")
         parser.add_argument("token", type=str, required=True, nullable=False, location="json")
         args = parser.parse_args()
-        token = args["token"]
 
-        reset_data = AccountService.get_reset_password_data(token)
+        user_email = args["email"]
 
-        if reset_data is None:
-            return {"is_valid": False, "email": None}
-        return {"is_valid": True, "email": reset_data.get("email")}
+        token_data = AccountService.get_reset_password_data(args["token"])
+        if token_data is None:
+            raise InvalidTokenError()
+
+        if user_email != token_data.get("email"):
+            raise InvalidEmailError()
+
+        if args["code"] != token_data.get("code"):
+            raise EmailCodeError()
+
+        return {"is_valid": True, "email": token_data.get("email")}
 
 
 class ForgotPasswordResetApi(Resource):
@@ -92,9 +109,26 @@ class ForgotPasswordResetApi(Resource):
         base64_password_hashed = base64.b64encode(password_hashed).decode()
 
         account = Account.query.filter_by(email=reset_data.get("email")).first()
-        account.password = base64_password_hashed
-        account.password_salt = base64_salt
-        db.session.commit()
+        if account:
+            account.password = base64_password_hashed
+            account.password_salt = base64_salt
+            db.session.commit()
+            tenant = TenantService.get_join_tenants(account)
+            if not tenant and not FeatureService.get_system_features().is_allow_create_workspace:
+                tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
+                TenantService.create_tenant_member(tenant, account, role="owner")
+                account.current_tenant = tenant
+                tenant_was_created.send(tenant)
+        else:
+            try:
+                account = AccountService.create_account_and_tenant(
+                    email=reset_data.get("email"),
+                    name=reset_data.get("email"),
+                    password=password_confirm,
+                    interface_language=languages[0],
+                )
+            except WorkSpaceNotAllowedCreateError:
+                pass
 
         return {"result": "success"}
 

api/controllers/console/auth/login.py

@@ -5,12 +5,29 @@ from flask import request
 from flask_restful import Resource, reqparse
 
 import services
+from constants.languages import languages
 from controllers.console import api
+from controllers.console.auth.error import (
+    EmailCodeError,
+    EmailOrPasswordMismatchError,
+    EmailPasswordLoginLimitError,
+    InvalidEmailError,
+    InvalidTokenError,
+)
+from controllers.console.error import (
+    AccountBannedError,
+    EmailSendIpLimitError,
+    NotAllowedCreateWorkspace,
+    NotAllowedRegister,
+)
 from controllers.console.setup import setup_required
-from libs.helper import email, get_remote_ip
+from events.tenant_event import tenant_was_created
+from libs.helper import email, extract_remote_ip
 from libs.password import valid_password
 from models.account import Account
-from services.account_service import AccountService, TenantService
+from services.account_service import AccountService, RegisterService, TenantService
+from services.errors.workspace import WorkSpaceNotAllowedCreateError
+from services.feature_service import FeatureService
 
 
 class LoginApi(Resource):
@@ -23,15 +40,43 @@ class LoginApi(Resource):
         parser.add_argument("email", type=email, required=True, location="json")
         parser.add_argument("password", type=valid_password, required=True, location="json")
         parser.add_argument("remember_me", type=bool, required=False, default=False, location="json")
+        parser.add_argument("invite_token", type=str, required=False, default=None, location="json")
+        parser.add_argument("language", type=str, required=False, default="en-US", location="json")
         args = parser.parse_args()
 
-        # todo: Verify the recaptcha
+        is_login_error_rate_limit = AccountService.is_login_error_rate_limit(args["email"])
+        if is_login_error_rate_limit:
+            raise EmailPasswordLoginLimitError()
+
+        invitation = args["invite_token"]
+        if invitation:
+            invitation = RegisterService.get_invitation_if_token_valid(None, args["email"], invitation)
+
+        if args["language"] is not None and args["language"] == "zh-Hans":
+            language = "zh-Hans"
+        else:
+            language = "en-US"
 
         try:
-            account = AccountService.authenticate(args["email"], args["password"])
-        except services.errors.account.AccountLoginError as e:
-            return {"code": "unauthorized", "message": str(e)}, 401
-
+            if invitation:
+                data = invitation.get("data", {})
+                invitee_email = data.get("email") if data else None
+                if invitee_email != args["email"]:
+                    raise InvalidEmailError()
+                account = AccountService.authenticate(args["email"], args["password"], args["invite_token"])
+            else:
+                account = AccountService.authenticate(args["email"], args["password"])
+        except services.errors.account.AccountLoginError:
+            raise AccountBannedError()
+        except services.errors.account.AccountPasswordError:
+            AccountService.add_login_error_rate_limit(args["email"])
+            raise EmailOrPasswordMismatchError()
+        except services.errors.account.AccountNotFoundError:
+            if FeatureService.get_system_features().is_allow_register:
+                token = AccountService.send_reset_password_email(email=args["email"], language=language)
+                return {"result": "fail", "data": token, "code": "account_not_found"}
+            else:
+                raise NotAllowedRegister()
         # SELF_HOSTED only have one workspace
         tenants = TenantService.get_join_tenants(account)
         if len(tenants) == 0:
@@ -40,71 +85,138 @@ class LoginApi(Resource):
                 "data": "workspace not found, please contact system admin to invite you to join in a workspace",
             }
 
-        token = AccountService.login(account, ip_address=get_remote_ip(request))
-
-        return {"result": "success", "data": token}
+        token_pair = AccountService.login(account=account, ip_address=extract_remote_ip(request))
+        AccountService.reset_login_error_rate_limit(args["email"])
+        return {"result": "success", "data": token_pair.model_dump()}
 
 
 class LogoutApi(Resource):
     @setup_required
     def get(self):
         account = cast(Account, flask_login.current_user)
-        token = request.headers.get("Authorization", "").split(" ")[1]
-        AccountService.logout(account=account, token=token)
+        if isinstance(account, flask_login.AnonymousUserMixin):
+            return {"result": "success"}
+        AccountService.logout(account=account)
         flask_login.logout_user()
         return {"result": "success"}
 
 
-class ResetPasswordApi(Resource):
+class ResetPasswordSendEmailApi(Resource):
     @setup_required
-    def get(self):
-        # parser = reqparse.RequestParser()
-        # parser.add_argument('email', type=email, required=True, location='json')
-        # args = parser.parse_args()
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("email", type=email, required=True, location="json")
+        parser.add_argument("language", type=str, required=False, location="json")
+        args = parser.parse_args()
 
-        # import mailchimp_transactional as MailchimpTransactional
-        # from mailchimp_transactional.api_client import ApiClientError
+        if args["language"] is not None and args["language"] == "zh-Hans":
+            language = "zh-Hans"
+        else:
+            language = "en-US"
 
-        # account = {'email': args['email']}
-        # account = AccountService.get_by_email(args['email'])
-        # if account is None:
-        #     raise ValueError('Email not found')
-        # new_password = AccountService.generate_password()
-        # AccountService.update_password(account, new_password)
+        account = AccountService.get_user_through_email(args["email"])
+        if account is None:
+            if FeatureService.get_system_features().is_allow_register:
+                token = AccountService.send_reset_password_email(email=args["email"], language=language)
+            else:
+                raise NotAllowedRegister()
+        else:
+            token = AccountService.send_reset_password_email(account=account, language=language)
 
-        # todo: Send email
-        # MAILCHIMP_API_KEY = dify_config.MAILCHIMP_TRANSACTIONAL_API_KEY
-        # mailchimp = MailchimpTransactional(MAILCHIMP_API_KEY)
+        return {"result": "success", "data": token}
 
-        # message = {
-        #     'from_email': 'noreply@example.com',
-        #     'to': [{'email': account['email']}],
-        #     'subject': 'Reset your Dify password',
-        #     'html': """
-        #         <p>Dear User,</p>
-        #         <p>The Dify team has generated a new password for you, details as follows:</p>
-        #         <p><strong>{new_password}</strong></p>
-        #         <p>Please change your password to log in as soon as possible.</p>
-        #         <p>Regards,</p>
-        #         <p>The Dify Team</p>
-        #     """
-        # }
 
-        # response = mailchimp.messages.send({
-        #     'message': message,
-        #     # required for transactional email
-        #     ' settings': {
-        #         'sandbox_mode': dify_config.MAILCHIMP_SANDBOX_MODE,
-        #     },
-        # })
+class EmailCodeLoginSendEmailApi(Resource):
+    @setup_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("email", type=email, required=True, location="json")
+        parser.add_argument("language", type=str, required=False, location="json")
+        args = parser.parse_args()
 
-        # Check if MSG was sent
-        # if response.status_code != 200:
-        #     # handle error
-        #     pass
+        ip_address = extract_remote_ip(request)
+        if AccountService.is_email_send_ip_limit(ip_address):
+            raise EmailSendIpLimitError()
 
-        return {"result": "success"}
+        if args["language"] is not None and args["language"] == "zh-Hans":
+            language = "zh-Hans"
+        else:
+            language = "en-US"
+
+        account = AccountService.get_user_through_email(args["email"])
+        if account is None:
+            if FeatureService.get_system_features().is_allow_register:
+                token = AccountService.send_email_code_login_email(email=args["email"], language=language)
+            else:
+                raise NotAllowedRegister()
+        else:
+            token = AccountService.send_email_code_login_email(account=account, language=language)
+
+        return {"result": "success", "data": token}
+
+
+class EmailCodeLoginApi(Resource):
+    @setup_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("email", type=str, required=True, location="json")
+        parser.add_argument("code", type=str, required=True, location="json")
+        parser.add_argument("token", type=str, required=True, location="json")
+        args = parser.parse_args()
+
+        user_email = args["email"]
+
+        token_data = AccountService.get_email_code_login_data(args["token"])
+        if token_data is None:
+            raise InvalidTokenError()
+
+        if token_data["email"] != args["email"]:
+            raise InvalidEmailError()
+
+        if token_data["code"] != args["code"]:
+            raise EmailCodeError()
+
+        AccountService.revoke_email_code_login_token(args["token"])
+        account = AccountService.get_user_through_email(user_email)
+        if account:
+            tenant = TenantService.get_join_tenants(account)
+            if not tenant:
+                if not FeatureService.get_system_features().is_allow_create_workspace:
+                    raise NotAllowedCreateWorkspace()
+                else:
+                    tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
+                    TenantService.create_tenant_member(tenant, account, role="owner")
+                    account.current_tenant = tenant
+                    tenant_was_created.send(tenant)
+
+        if account is None:
+            try:
+                account = AccountService.create_account_and_tenant(
+                    email=user_email, name=user_email, interface_language=languages[0]
+                )
+            except WorkSpaceNotAllowedCreateError:
+                return NotAllowedCreateWorkspace()
+        token_pair = AccountService.login(account, ip_address=extract_remote_ip(request))
+        AccountService.reset_login_error_rate_limit(args["email"])
+        return {"result": "success", "data": token_pair.model_dump()}
+
+
+class RefreshTokenApi(Resource):
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("refresh_token", type=str, required=True, location="json")
+        args = parser.parse_args()
+
+        try:
+            new_token_pair = AccountService.refresh_token(args["refresh_token"])
+            return {"result": "success", "data": new_token_pair.model_dump()}
+        except Exception as e:
+            return {"result": "fail", "data": str(e)}, 401
 
 
 api.add_resource(LoginApi, "/login")
 api.add_resource(LogoutApi, "/logout")
+api.add_resource(EmailCodeLoginSendEmailApi, "/email-code-login")
+api.add_resource(EmailCodeLoginApi, "/email-code-login/validity")
+api.add_resource(ResetPasswordSendEmailApi, "/reset-password")
+api.add_resource(RefreshTokenApi, "/refresh-token")

api/controllers/console/auth/oauth.py

@@ -5,14 +5,20 @@ from typing import Optional
 import requests
 from flask import current_app, redirect, request
 from flask_restful import Resource
+from werkzeug.exceptions import Unauthorized
 
 from configs import dify_config
 from constants.languages import languages
+from events.tenant_event import tenant_was_created
 from extensions.ext_database import db
-from libs.helper import get_remote_ip
+from libs.helper import extract_remote_ip
 from libs.oauth import GitHubOAuth, GoogleOAuth, OAuthUserInfo
-from models.account import Account, AccountStatus
+from models import Account
+from models.account import AccountStatus
 from services.account_service import AccountService, RegisterService, TenantService
+from services.errors.account import AccountNotFoundError
+from services.errors.workspace import WorkSpaceNotAllowedCreateError, WorkSpaceNotFoundError
+from services.feature_service import FeatureService
 
 from .. import api
 
@@ -42,6 +48,7 @@ def get_oauth_providers():
 
 class OAuthLogin(Resource):
     def get(self, provider: str):
+        invite_token = request.args.get("invite_token") or None
         OAUTH_PROVIDERS = get_oauth_providers()
         with current_app.app_context():
             oauth_provider = OAUTH_PROVIDERS.get(provider)
@@ -49,7 +56,7 @@ class OAuthLogin(Resource):
         if not oauth_provider:
             return {"error": "Invalid provider"}, 400
 
-        auth_url = oauth_provider.get_authorization_url()
+        auth_url = oauth_provider.get_authorization_url(invite_token=invite_token)
         return redirect(auth_url)
 
 
@@ -62,6 +69,11 @@ class OAuthCallback(Resource):
             return {"error": "Invalid provider"}, 400
 
         code = request.args.get("code")
+        state = request.args.get("state")
+        invite_token = None
+        if state:
+            invite_token = state
+
         try:
             token = oauth_provider.get_access_token(code)
             user_info = oauth_provider.get_user_info(token)
@@ -69,21 +81,52 @@ class OAuthCallback(Resource):
             logging.exception(f"An error occurred during the OAuth process with {provider}: {e.response.text}")
             return {"error": "OAuth process failed"}, 400
 
-        account = _generate_account(provider, user_info)
+        if invite_token and RegisterService.is_valid_invite_token(invite_token):
+            invitation = RegisterService._get_invitation_by_token(token=invite_token)
+            if invitation:
+                invitation_email = invitation.get("email", None)
+                if invitation_email != user_info.email:
+                    return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Invalid invitation token.")
+
+            return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin/invite-settings?invite_token={invite_token}")
+
+        try:
+            account = _generate_account(provider, user_info)
+        except AccountNotFoundError:
+            return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Account not found.")
+        except (WorkSpaceNotFoundError, WorkSpaceNotAllowedCreateError):
+            return redirect(
+                f"{dify_config.CONSOLE_WEB_URL}/signin"
+                "?message=Workspace not found, please contact system admin to invite you to join in a workspace."
+            )
+
         # Check account status
-        if account.status in {AccountStatus.BANNED.value, AccountStatus.CLOSED.value}:
-            return {"error": "Account is banned or closed."}, 403
+        if account.status == AccountStatus.BANNED.value:
+            return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Account is banned.")
 
         if account.status == AccountStatus.PENDING.value:
             account.status = AccountStatus.ACTIVE.value
             account.initialized_at = datetime.now(timezone.utc).replace(tzinfo=None)
             db.session.commit()
 
-        TenantService.create_owner_tenant_if_not_exist(account)
+        try:
+            TenantService.create_owner_tenant_if_not_exist(account)
+        except Unauthorized:
+            return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Workspace not found.")
+        except WorkSpaceNotAllowedCreateError:
+            return redirect(
+                f"{dify_config.CONSOLE_WEB_URL}/signin"
+                "?message=Workspace not found, please contact system admin to invite you to join in a workspace."
+            )
 
-        token = AccountService.login(account, ip_address=get_remote_ip(request))
+        token_pair = AccountService.login(
+            account=account,
+            ip_address=extract_remote_ip(request),
+        )
 
-        return redirect(f"{dify_config.CONSOLE_WEB_URL}?console_token={token}")
+        return redirect(
+            f"{dify_config.CONSOLE_WEB_URL}?access_token={token_pair.access_token}&refresh_token={token_pair.refresh_token}"
+        )
 
 
 def _get_account_by_openid_or_email(provider: str, user_info: OAuthUserInfo) -> Optional[Account]:
@@ -99,8 +142,20 @@ def _generate_account(provider: str, user_info: OAuthUserInfo):
     # Get account by openid or email.
     account = _get_account_by_openid_or_email(provider, user_info)
 
+    if account:
+        tenant = TenantService.get_join_tenants(account)
+        if not tenant:
+            if not FeatureService.get_system_features().is_allow_create_workspace:
+                raise WorkSpaceNotAllowedCreateError()
+            else:
+                tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
+                TenantService.create_tenant_member(tenant, account, role="owner")
+                account.current_tenant = tenant
+                tenant_was_created.send(tenant)
+
     if not account:
-        # Create account
+        if not FeatureService.get_system_features().is_allow_register:
+            raise AccountNotFoundError()
         account_name = user_info.name or "Dify"
         account = RegisterService.register(
             email=user_info.email, name=account_name, password=None, open_id=user_info.id, provider=provider

api/controllers/console/datasets/data_source.py

@@ -15,8 +15,7 @@ from core.rag.extractor.notion_extractor import NotionExtractor
 from extensions.ext_database import db
 from fields.data_source_fields import integrate_list_fields, integrate_notion_info_list_fields
 from libs.login import login_required
-from models.dataset import Document
-from models.source import DataSourceOauthBinding
+from models import DataSourceOauthBinding, Document
 from services.dataset_service import DatasetService, DocumentService
 from tasks.document_indexing_sync_task import document_indexing_sync_task
 

api/controllers/console/datasets/datasets.py

@@ -24,8 +24,8 @@ from fields.app_fields import related_app_list
 from fields.dataset_fields import dataset_detail_fields, dataset_query_detail_fields
 from fields.document_fields import document_status_fields
 from libs.login import login_required
-from models.dataset import Dataset, DatasetPermissionEnum, Document, DocumentSegment
-from models.model import ApiToken, UploadFile
+from models import ApiToken, Dataset, Document, DocumentSegment, UploadFile
+from models.dataset import DatasetPermissionEnum
 from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService
 
 
@@ -102,6 +102,13 @@ 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 +147,7 @@ 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,
@@ -613,10 +621,13 @@ class DatasetRetrievalSettingApi(Resource):
             case (
                 VectorType.MILVUS
                 | VectorType.RELYT
-                | VectorType.PGVECTOR
                 | VectorType.TIDB_VECTOR
                 | VectorType.CHROMA
                 | VectorType.TENCENT
+                | VectorType.PGVECTO_RS
+                | VectorType.BAIDU
+                | VectorType.VIKINGDB
+                | VectorType.UPSTASH
             ):
                 return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
             case (
@@ -627,6 +638,8 @@ class DatasetRetrievalSettingApi(Resource):
                 | VectorType.MYSCALE
                 | VectorType.ORACLE
                 | VectorType.ELASTICSEARCH
+                | VectorType.PGVECTOR
+                | VectorType.TIDB_ON_QDRANT
             ):
                 return {
                     "retrieval_method": [
@@ -652,6 +665,9 @@ class DatasetRetrievalSettingMockApi(Resource):
                 | VectorType.CHROMA
                 | VectorType.TENCENT
                 | VectorType.PGVECTO_RS
+                | VectorType.BAIDU
+                | VectorType.VIKINGDB
+                | VectorType.UPSTASH
             ):
                 return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
             case (

api/controllers/console/datasets/datasets_document.py

@@ -46,8 +46,7 @@ from fields.document_fields import (
     document_with_segments_fields,
 )
 from libs.login import login_required
-from models.dataset import Dataset, DatasetProcessRule, Document, DocumentSegment
-from models.model import UploadFile
+from models import Dataset, DatasetProcessRule, Document, DocumentSegment, UploadFile
 from services.dataset_service import DatasetService, DocumentService
 from tasks.add_document_to_index_task import add_document_to_index_task
 from tasks.remove_document_from_index_task import remove_document_from_index_task

api/controllers/console/datasets/datasets_segments.py

@@ -24,7 +24,7 @@ from extensions.ext_database import db
 from extensions.ext_redis import redis_client
 from fields.segment_fields import segment_fields
 from libs.login import login_required
-from models.dataset import DocumentSegment
+from models import DocumentSegment
 from services.dataset_service import DatasetService, DocumentService, SegmentService
 from tasks.batch_create_segment_to_index_task import batch_create_segment_to_index_task
 from tasks.disable_segment_from_index_task import disable_segment_from_index_task

api/controllers/console/datasets/external.py

@@ -5,7 +5,6 @@ from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 
 import services
 from controllers.console import api
-from controllers.console.app.error import ProviderNotInitializeError
 from controllers.console.datasets.error import DatasetNameDuplicateError
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
@@ -14,6 +13,7 @@ from libs.login import login_required
 from services.dataset_service import DatasetService
 from services.external_knowledge_service import ExternalDatasetService
 from services.hit_testing_service import HitTestingService
+from services.knowledge_service import ExternalDatasetTestService
 
 
 def _validate_name(name):
@@ -158,48 +158,6 @@ class ExternalApiUseCheckApi(Resource):
         return {"is_using": external_knowledge_api_is_using, "count": count}, 200
 
 
-class ExternalDatasetInitApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    def post(self):
-        # The role of the current user in the ta table must be admin, owner, or editor
-        if not current_user.is_editor:
-            raise Forbidden()
-
-        parser = reqparse.RequestParser()
-        parser.add_argument("external_knowledge_api_id", type=str, required=True, nullable=True, location="json")
-        # parser.add_argument('name', nullable=False, required=True,
-        #                     help='name is required. Name must be between 1 to 100 characters.',
-        #                     type=_validate_name)
-        # parser.add_argument('description', type=str, required=True, nullable=True, location='json')
-        parser.add_argument("data_source", type=dict, required=True, nullable=True, location="json")
-        parser.add_argument("process_parameter", type=dict, required=True, nullable=True, location="json")
-
-        args = parser.parse_args()
-
-        # The role of the current user in the ta table must be admin, owner, or editor, or dataset_operator
-        if not current_user.is_dataset_editor:
-            raise Forbidden()
-
-        # validate args
-        ExternalDatasetService.document_create_args_validate(
-            current_user.current_tenant_id, args["external_knowledge_api_id"], args["process_parameter"]
-        )
-
-        try:
-            dataset, documents, batch = ExternalDatasetService.init_external_dataset(
-                tenant_id=current_user.current_tenant_id,
-                user_id=current_user.id,
-                args=args,
-            )
-        except Exception as ex:
-            raise ProviderNotInitializeError(ex.description)
-        response = {"dataset": dataset, "documents": documents, "batch": batch}
-
-        return response
-
-
 class ExternalDatasetCreateApi(Resource):
     @setup_required
     @login_required
@@ -275,8 +233,31 @@ class ExternalKnowledgeHitTestingApi(Resource):
             raise InternalServerError(str(e))
 
 
+class BedrockRetrievalApi(Resource):
+    # this api is only for internal testing
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("retrieval_setting", nullable=False, required=True, type=dict, location="json")
+        parser.add_argument(
+            "query",
+            nullable=False,
+            required=True,
+            type=str,
+        )
+        parser.add_argument("knowledge_id", nullable=False, required=True, type=str)
+        args = parser.parse_args()
+
+        # Call the knowledge retrieval service
+        result = ExternalDatasetTestService.knowledge_retrieval(
+            args["retrieval_setting"], args["query"], args["knowledge_id"]
+        )
+        return result, 200
+
+
 api.add_resource(ExternalKnowledgeHitTestingApi, "/datasets/<uuid:dataset_id>/external-hit-testing")
 api.add_resource(ExternalDatasetCreateApi, "/datasets/external")
 api.add_resource(ExternalApiTemplateListApi, "/datasets/external-knowledge-api")
 api.add_resource(ExternalApiTemplateApi, "/datasets/external-knowledge-api/<uuid:external_knowledge_api_id>")
 api.add_resource(ExternalApiUseCheckApi, "/datasets/external-knowledge-api/<uuid:external_knowledge_api_id>/use-check")
+# this api is only for internal test
+api.add_resource(BedrockRetrievalApi, "/test/retrieval")

api/controllers/console/datasets/file.py

@@ -1,9 +1,12 @@
+import urllib.parse
+
 from flask import request
 from flask_login import current_user
-from flask_restful import Resource, marshal_with
+from flask_restful import Resource, marshal_with, reqparse
 
 import services
 from configs import dify_config
+from constants import DOCUMENT_EXTENSIONS
 from controllers.console import api
 from controllers.console.datasets.error import (
     FileTooLargeError,
@@ -13,9 +16,10 @@ from controllers.console.datasets.error import (
 )
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
-from fields.file_fields import file_fields, upload_config_fields
+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 ALLOWED_EXTENSIONS, UNSTRUCTURED_ALLOWED_EXTENSIONS, FileService
+from services.file_service import FileService
 
 PREVIEW_WORDS_LIMIT = 3000
 
@@ -26,13 +30,12 @@ class FileApi(Resource):
     @account_initialization_required
     @marshal_with(upload_config_fields)
     def get(self):
-        file_size_limit = dify_config.UPLOAD_FILE_SIZE_LIMIT
-        batch_count_limit = dify_config.UPLOAD_FILE_BATCH_LIMIT
-        image_file_size_limit = dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT
         return {
-            "file_size_limit": file_size_limit,
-            "batch_count_limit": batch_count_limit,
-            "image_file_size_limit": image_file_size_limit,
+            "file_size_limit": dify_config.UPLOAD_FILE_SIZE_LIMIT,
+            "batch_count_limit": dify_config.UPLOAD_FILE_BATCH_LIMIT,
+            "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,
         }, 200
 
     @setup_required
@@ -44,6 +47,10 @@ class FileApi(Resource):
         # 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()
@@ -51,7 +58,7 @@ class FileApi(Resource):
         if len(request.files) > 1:
             raise TooManyFilesError()
         try:
-            upload_file = FileService.upload_file(file, current_user)
+            upload_file = FileService.upload_file(file=file, 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:
@@ -75,11 +82,24 @@ class FileSupportTypeApi(Resource):
     @login_required
     @account_initialization_required
     def get(self):
-        etl_type = dify_config.ETL_TYPE
-        allowed_extensions = UNSTRUCTURED_ALLOWED_EXTENSIONS if etl_type == "Unstructured" else ALLOWED_EXTENSIONS
-        return {"allowed_extensions": allowed_extensions}
+        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/datasets/hit_testing.py

@@ -1,88 +1,24 @@
-import logging
+from flask_restful import Resource
 
-from flask_login import current_user
-from flask_restful import Resource, marshal, reqparse
-from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
-
-import services
 from controllers.console import api
-from controllers.console.app.error import (
-    CompletionRequestError,
-    ProviderModelCurrentlyNotSupportError,
-    ProviderNotInitializeError,
-    ProviderQuotaExceededError,
-)
-from controllers.console.datasets.error import DatasetNotInitializedError
+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 core.errors.error import (
-    LLMBadRequestError,
-    ModelCurrentlyNotSupportError,
-    ProviderTokenNotInitError,
-    QuotaExceededError,
-)
-from core.model_runtime.errors.invoke import InvokeError
-from fields.hit_testing_fields import hit_testing_record_fields
 from libs.login import login_required
-from services.dataset_service import DatasetService
-from services.hit_testing_service import HitTestingService
 
 
-class HitTestingApi(Resource):
+class HitTestingApi(Resource, DatasetsHitTestingBase):
     @setup_required
     @login_required
     @account_initialization_required
     def post(self, dataset_id):
         dataset_id_str = str(dataset_id)
 
-        dataset = DatasetService.get_dataset(dataset_id_str)
-        if dataset is None:
-            raise NotFound("Dataset not found.")
+        dataset = self.get_and_validate_dataset(dataset_id_str)
+        args = self.parse_args()
+        self.hit_testing_args_check(args)
 
-        try:
-            DatasetService.check_dataset_permission(dataset, current_user)
-        except services.errors.account.NoPermissionError as e:
-            raise Forbidden(str(e))
-
-        parser = reqparse.RequestParser()
-        parser.add_argument("query", type=str, location="json")
-        parser.add_argument("retrieval_model", type=dict, required=False, location="json")
-        parser.add_argument("external_retrieval_model", type=dict, required=False, location="json")
-        args = parser.parse_args()
-
-        HitTestingService.hit_testing_args_check(args)
-
-        try:
-            response = HitTestingService.retrieve(
-                dataset=dataset,
-                query=args["query"],
-                account=current_user,
-                retrieval_model=args["retrieval_model"],
-                external_retrieval_model=args["external_retrieval_model"],
-                limit=10,
-            )
-
-            return {"query": response["query"], "records": marshal(response["records"], hit_testing_record_fields)}
-        except services.errors.index.IndexNotInitializedError:
-            raise DatasetNotInitializedError()
-        except ProviderTokenNotInitError as ex:
-            raise ProviderNotInitializeError(ex.description)
-        except QuotaExceededError:
-            raise ProviderQuotaExceededError()
-        except ModelCurrentlyNotSupportError:
-            raise ProviderModelCurrentlyNotSupportError()
-        except LLMBadRequestError:
-            raise ProviderNotInitializeError(
-                "No Embedding Model or Reranking Model available. Please configure a valid provider "
-                "in the Settings -> Model Provider."
-            )
-        except InvokeError as e:
-            raise CompletionRequestError(e.description)
-        except ValueError as e:
-            raise ValueError(str(e))
-        except Exception as e:
-            logging.exception("Hit testing failed.")
-            raise InternalServerError(str(e))
+        return self.perform_hit_testing(dataset, args)
 
 
 api.add_resource(HitTestingApi, "/datasets/<uuid:dataset_id>/hit-testing")

api/controllers/console/datasets/hit_testing_base.py

@@ -0,0 +1,85 @@
+import logging
+
+from flask_login import current_user
+from flask_restful import marshal, reqparse
+from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
+
+import services.dataset_service
+from controllers.console.app.error import (
+    CompletionRequestError,
+    ProviderModelCurrentlyNotSupportError,
+    ProviderNotInitializeError,
+    ProviderQuotaExceededError,
+)
+from controllers.console.datasets.error import DatasetNotInitializedError
+from core.errors.error import (
+    LLMBadRequestError,
+    ModelCurrentlyNotSupportError,
+    ProviderTokenNotInitError,
+    QuotaExceededError,
+)
+from core.model_runtime.errors.invoke import InvokeError
+from fields.hit_testing_fields import hit_testing_record_fields
+from services.dataset_service import DatasetService
+from services.hit_testing_service import HitTestingService
+
+
+class DatasetsHitTestingBase:
+    @staticmethod
+    def get_and_validate_dataset(dataset_id: str):
+        dataset = DatasetService.get_dataset(dataset_id)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+
+        return dataset
+
+    @staticmethod
+    def hit_testing_args_check(args):
+        HitTestingService.hit_testing_args_check(args)
+
+    @staticmethod
+    def parse_args():
+        parser = reqparse.RequestParser()
+
+        parser.add_argument("query", type=str, location="json")
+        parser.add_argument("retrieval_model", type=dict, required=False, location="json")
+        parser.add_argument("external_retrieval_model", type=dict, required=False, location="json")
+        return parser.parse_args()
+
+    @staticmethod
+    def perform_hit_testing(dataset, args):
+        try:
+            response = HitTestingService.retrieve(
+                dataset=dataset,
+                query=args["query"],
+                account=current_user,
+                retrieval_model=args["retrieval_model"],
+                external_retrieval_model=args["external_retrieval_model"],
+                limit=10,
+            )
+            return {"query": response["query"], "records": marshal(response["records"], hit_testing_record_fields)}
+        except services.errors.index.IndexNotInitializedError:
+            raise DatasetNotInitializedError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        except QuotaExceededError:
+            raise ProviderQuotaExceededError()
+        except ModelCurrentlyNotSupportError:
+            raise ProviderModelCurrentlyNotSupportError()
+        except LLMBadRequestError:
+            raise ProviderNotInitializeError(
+                "No Embedding Model or Reranking Model available. Please configure a valid provider "
+                "in the Settings -> Model Provider."
+            )
+        except InvokeError as e:
+            raise CompletionRequestError(e.description)
+        except ValueError as e:
+            raise ValueError(str(e))
+        except Exception as e:
+            logging.exception("Hit testing failed.")
+            raise InternalServerError(str(e))

api/controllers/console/datasets/test_external.py

@@ -1,33 +0,0 @@
-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 libs.login import login_required
-from services.external_knowledge_service import ExternalDatasetService
-
-
-class TestExternalApi(Resource):
-    def post(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument("retrieval_setting", nullable=False, required=True, type=dict, location="json")
-        parser.add_argument(
-            "query",
-            nullable=False,
-            required=True,
-            type=str,
-        )
-        parser.add_argument(
-            "knowledge_id",
-            nullable=False,
-            required=True,
-            type=str,
-        )
-        args = parser.parse_args()
-        result = ExternalDatasetService.test_external_knowledge_retrieval(
-            args["retrieval_setting"], args["query"], args["knowledge_id"]
-        )
-        return result, 200
-
-
-api.add_resource(TestExternalApi, "/retrieval")

api/controllers/console/datasets/website.py

@@ -14,7 +14,9 @@ class WebsiteCrawlApi(Resource):
     @account_initialization_required
     def post(self):
         parser = reqparse.RequestParser()
-        parser.add_argument("provider", type=str, choices=["firecrawl"], required=True, nullable=True, location="json")
+        parser.add_argument(
+            "provider", type=str, choices=["firecrawl", "jinareader"], required=True, nullable=True, location="json"
+        )
         parser.add_argument("url", type=str, required=True, nullable=True, location="json")
         parser.add_argument("options", type=dict, required=True, nullable=True, location="json")
         args = parser.parse_args()
@@ -33,7 +35,7 @@ class WebsiteCrawlStatusApi(Resource):
     @account_initialization_required
     def get(self, job_id: str):
         parser = reqparse.RequestParser()
-        parser.add_argument("provider", type=str, choices=["firecrawl"], required=True, location="args")
+        parser.add_argument("provider", type=str, choices=["firecrawl", "jinareader"], required=True, location="args")
         args = parser.parse_args()
         # get crawl status
         try:

api/controllers/console/error.py

@@ -38,3 +38,27 @@ class AlreadyActivateError(BaseHTTPException):
     error_code = "already_activate"
     description = "Auth Token is invalid or account already activated, please check again."
     code = 403
+
+
+class NotAllowedCreateWorkspace(BaseHTTPException):
+    error_code = "not_allowed_create_workspace"
+    description = "Workspace not found, please contact system admin to invite you to join in a workspace."
+    code = 400
+
+
+class AccountBannedError(BaseHTTPException):
+    error_code = "account_banned"
+    description = "Account is banned."
+    code = 400
+
+
+class NotAllowedRegister(BaseHTTPException):
+    error_code = "unauthorized"
+    description = "Account not found."
+    code = 400
+
+
+class EmailSendIpLimitError(BaseHTTPException):
+    error_code = "email_send_ip_limit"
+    description = "Too many emails have been sent from this IP address recently. Please try again later."
+    code = 429

api/controllers/console/explore/installed_app.py

@@ -11,7 +11,7 @@ from controllers.console.wraps import account_initialization_required, cloud_edi
 from extensions.ext_database import db
 from fields.installed_app_fields import installed_app_list_fields
 from libs.login import login_required
-from models.model import App, InstalledApp, RecommendedApp
+from models import App, InstalledApp, RecommendedApp
 from services.account_service import TenantService
 
 

api/controllers/console/explore/parameter.py

@@ -21,7 +21,12 @@ class AppParameterApi(InstalledAppResource):
         "options": fields.List(fields.String),
     }
 
-    system_parameters_fields = {"image_file_size_limit": fields.String}
+    system_parameters_fields = {
+        "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 = {
         "opening_statement": fields.String,
@@ -82,7 +87,12 @@ class AppParameterApi(InstalledAppResource):
                     }
                 },
             ),
-            "system_parameters": {"image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT},
+            "system_parameters": {
+                "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/explore/saved_message.py

@@ -18,7 +18,7 @@ message_fields = {
     "inputs": fields.Raw,
     "query": fields.String,
     "answer": fields.String,
-    "message_files": fields.List(fields.Nested(message_file_fields), attribute="files"),
+    "message_files": fields.List(fields.Nested(message_file_fields)),
     "feedback": fields.Nested(feedback_fields, attribute="user_feedback", allow_null=True),
     "created_at": TimestampField,
 }

api/controllers/console/explore/wraps.py

@@ -7,7 +7,7 @@ from werkzeug.exceptions import NotFound
 from controllers.console.wraps import account_initialization_required
 from extensions.ext_database import db
 from libs.login import login_required
-from models.model import InstalledApp
+from models import InstalledApp
 
 
 def installed_app_required(view=None):

api/controllers/console/setup.py

@@ -4,7 +4,7 @@ from flask import request
 from flask_restful import Resource, reqparse
 
 from configs import dify_config
-from libs.helper import StrLen, email, get_remote_ip
+from libs.helper import StrLen, email, extract_remote_ip
 from libs.password import valid_password
 from models.model import DifySetup
 from services.account_service import RegisterService, TenantService
@@ -46,7 +46,7 @@ class SetupApi(Resource):
 
         # setup
         RegisterService.setup(
-            email=args["email"], name=args["name"], password=args["password"], ip_address=get_remote_ip(request)
+            email=args["email"], name=args["name"], password=args["password"], ip_address=extract_remote_ip(request)
         )
 
         return {"result": "success"}, 201

api/controllers/console/version.py

@@ -38,11 +38,52 @@ class VersionApi(Resource):
             return result
 
         content = json.loads(response.content)
-        result["version"] = content["version"]
-        result["release_date"] = content["releaseDate"]
-        result["release_notes"] = content["releaseNotes"]
-        result["can_auto_update"] = content["canAutoUpdate"]
+        if _has_new_version(latest_version=content["version"], current_version=f"{args.get('current_version')}"):
+            result["version"] = content["version"]
+            result["release_date"] = content["releaseDate"]
+            result["release_notes"] = content["releaseNotes"]
+            result["can_auto_update"] = content["canAutoUpdate"]
         return result
 
 
+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
+
+        # 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:
+        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

@@ -20,7 +20,7 @@ from extensions.ext_database import db
 from fields.member_fields import account_fields
 from libs.helper import TimestampField, timezone
 from libs.login import login_required
-from models.account import AccountIntegrate, InvitationCode
+from models import AccountIntegrate, InvitationCode
 from services.account_service import AccountService
 from services.errors.account import CurrentPasswordIncorrectError as ServiceCurrentPasswordIncorrectError
 

api/controllers/console/workspace/model_providers.py

@@ -126,13 +126,12 @@ class ModelProviderIconApi(Resource):
     Get model provider icon
     """
 
-    @setup_required
-    @login_required
-    @account_initialization_required
     def get(self, provider: str, icon_type: str, lang: str):
         model_provider_service = ModelProviderService()
         icon, mimetype = model_provider_service.get_model_provider_icon(
-            provider=provider, icon_type=icon_type, lang=lang
+            provider=provider,
+            icon_type=icon_type,
+            lang=lang,
         )
 
         return send_file(io.BytesIO(icon), mimetype=mimetype)

api/controllers/console/workspace/models.py

@@ -72,8 +72,9 @@ class DefaultModelApi(Resource):
                     provider=model_setting["provider"],
                     model=model_setting["model"],
                 )
-            except Exception:
-                logging.warning(f"{model_setting['model_type']} save error")
+            except Exception as ex:
+                logging.exception(f"{model_setting['model_type']} save error: {ex}")
+                raise ex
 
         return {"result": "success"}
 

api/controllers/console/workspace/tool_providers.py

@@ -360,16 +360,15 @@ class ToolWorkflowProviderCreateApi(Resource):
         args = reqparser.parse_args()
 
         return WorkflowToolManageService.create_workflow_tool(
-            user_id,
-            tenant_id,
-            args["workflow_app_id"],
-            args["name"],
-            args["label"],
-            args["icon"],
-            args["description"],
-            args["parameters"],
-            args["privacy_policy"],
-            args.get("labels", []),
+            user_id=user_id,
+            tenant_id=tenant_id,
+            workflow_app_id=args["workflow_app_id"],
+            name=args["name"],
+            label=args["label"],
+            icon=args["icon"],
+            description=args["description"],
+            parameters=args["parameters"],
+            privacy_policy=args["privacy_policy"],
         )
 
 

api/controllers/console/workspace/workspace.py

@@ -198,7 +198,7 @@ class WebappLogoWorkspaceApi(Resource):
             raise UnsupportedFileTypeError()
 
         try:
-            upload_file = FileService.upload_file(file, current_user, True)
+            upload_file = FileService.upload_file(file=file, user=current_user)
 
         except services.errors.file.FileTooLargeError as file_too_large_error:
             raise FileTooLargeError(file_too_large_error.description)

api/controllers/files/error.py

@@ -0,0 +1,7 @@
+from libs.exception import BaseHTTPException
+
+
+class UnsupportedFileTypeError(BaseHTTPException):
+    error_code = "unsupported_file_type"
+    description = "File type not allowed."
+    code = 415

api/controllers/files/image_preview.py

@@ -1,15 +1,19 @@
 from flask import Response, request
-from flask_restful import Resource
+from flask_restful import Resource, reqparse
 from werkzeug.exceptions import NotFound
 
 import services
 from controllers.files import api
-from libs.exception import BaseHTTPException
+from controllers.files.error import UnsupportedFileTypeError
 from services.account_service import TenantService
 from services.file_service import FileService
 
 
 class ImagePreviewApi(Resource):
+    """
+    Deprecated
+    """
+
     def get(self, file_id):
         file_id = str(file_id)
 
@@ -21,13 +25,57 @@ class ImagePreviewApi(Resource):
             return {"content": "Invalid request."}, 400
 
         try:
-            generator, mimetype = FileService.get_image_preview(file_id, timestamp, nonce, sign)
+            generator, mimetype = FileService.get_image_preview(
+                file_id=file_id,
+                timestamp=timestamp,
+                nonce=nonce,
+                sign=sign,
+            )
         except services.errors.file.UnsupportedFileTypeError:
             raise UnsupportedFileTypeError()
 
         return Response(generator, mimetype=mimetype)
 
 
+class FilePreviewApi(Resource):
+    def get(self, file_id):
+        file_id = str(file_id)
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("timestamp", type=str, required=True, location="args")
+        parser.add_argument("nonce", type=str, required=True, location="args")
+        parser.add_argument("sign", type=str, required=True, location="args")
+        parser.add_argument("as_attachment", type=bool, required=False, default=False, location="args")
+
+        args = parser.parse_args()
+
+        if not args["timestamp"] or not args["nonce"] or not args["sign"]:
+            return {"content": "Invalid request."}, 400
+
+        try:
+            generator, upload_file = FileService.get_file_generator_by_file_id(
+                file_id=file_id,
+                timestamp=args["timestamp"],
+                nonce=args["nonce"],
+                sign=args["sign"],
+            )
+        except services.errors.file.UnsupportedFileTypeError:
+            raise UnsupportedFileTypeError()
+
+        response = Response(
+            generator,
+            mimetype=upload_file.mime_type,
+            direct_passthrough=True,
+            headers={},
+        )
+        if upload_file.size > 0:
+            response.headers["Content-Length"] = str(upload_file.size)
+        if args["as_attachment"]:
+            response.headers["Content-Disposition"] = f"attachment; filename={upload_file.name}"
+
+        return response
+
+
 class WorkspaceWebappLogoApi(Resource):
     def get(self, workspace_id):
         workspace_id = str(workspace_id)
@@ -49,10 +97,5 @@ class WorkspaceWebappLogoApi(Resource):
 
 
 api.add_resource(ImagePreviewApi, "/files/<uuid:file_id>/image-preview")
+api.add_resource(FilePreviewApi, "/files/<uuid:file_id>/file-preview")
 api.add_resource(WorkspaceWebappLogoApi, "/files/workspaces/<uuid:workspace_id>/webapp-logo")
-
-
-class UnsupportedFileTypeError(BaseHTTPException):
-    error_code = "unsupported_file_type"
-    description = "File type not allowed."
-    code = 415

api/controllers/files/tool_files.py

@@ -3,8 +3,8 @@ from flask_restful import Resource, reqparse
 from werkzeug.exceptions import Forbidden, NotFound
 
 from controllers.files import api
+from controllers.files.error import UnsupportedFileTypeError
 from core.tools.tool_file_manager import ToolFileManager
-from libs.exception import BaseHTTPException
 
 
 class ToolFilePreviewApi(Resource):
@@ -16,6 +16,7 @@ class ToolFilePreviewApi(Resource):
         parser.add_argument("timestamp", type=str, required=True, location="args")
         parser.add_argument("nonce", type=str, required=True, location="args")
         parser.add_argument("sign", type=str, required=True, location="args")
+        parser.add_argument("as_attachment", type=bool, required=False, default=False, location="args")
 
         args = parser.parse_args()
 
@@ -28,24 +29,27 @@ class ToolFilePreviewApi(Resource):
             raise Forbidden("Invalid request.")
 
         try:
-            result = ToolFileManager.get_file_generator_by_tool_file_id(
+            stream, tool_file = ToolFileManager.get_file_generator_by_tool_file_id(
                 file_id,
             )
 
-            if not result:
+            if not stream or not tool_file:
                 raise NotFound("file is not found")
-
-            generator, mimetype = result
         except Exception:
             raise UnsupportedFileTypeError()
 
-        return Response(generator, mimetype=mimetype)
+        response = Response(
+            stream,
+            mimetype=tool_file.mimetype,
+            direct_passthrough=True,
+            headers={},
+        )
+        if tool_file.size > 0:
+            response.headers["Content-Length"] = str(tool_file.size)
+        if args["as_attachment"]:
+            response.headers["Content-Disposition"] = f"attachment; filename={tool_file.name}"
+
+        return response
 
 
 api.add_resource(ToolFilePreviewApi, "/files/tools/<uuid:file_id>.<string:extension>")
-
-
-class UnsupportedFileTypeError(BaseHTTPException):
-    error_code = "unsupported_file_type"
-    description = "File type not allowed."
-    code = 415

api/controllers/inner_api/workspace/workspace.py

@@ -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/__init__.py

@@ -5,7 +5,6 @@ from libs.external_api import ExternalApi
 bp = Blueprint("service_api", __name__, url_prefix="/v1")
 api = ExternalApi(bp)
 
-
 from . import index
 from .app import app, audio, completion, conversation, file, message, workflow
-from .dataset import dataset, document, segment
+from .dataset import dataset, document, hit_testing, segment

api/controllers/service_api/app/app.py

@@ -21,7 +21,12 @@ class AppParameterApi(Resource):
         "options": fields.List(fields.String),
     }
 
-    system_parameters_fields = {"image_file_size_limit": fields.String}
+    system_parameters_fields = {
+        "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 = {
         "opening_statement": fields.String,
@@ -81,7 +86,12 @@ class AppParameterApi(Resource):
                     }
                 },
             ),
-            "system_parameters": {"image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT},
+            "system_parameters": {
+                "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/message.py

@@ -48,7 +48,7 @@ class MessageListApi(Resource):
         "tool_input": fields.String,
         "created_at": TimestampField,
         "observation": fields.String,
-        "message_files": fields.List(fields.String, attribute="files"),
+        "message_files": fields.List(fields.Nested(message_file_fields)),
     }
 
     message_fields = {
@@ -58,7 +58,7 @@ class MessageListApi(Resource):
         "inputs": fields.Raw,
         "query": fields.String,
         "answer": fields.String(attribute="re_sign_file_url_answer"),
-        "message_files": fields.List(fields.Nested(message_file_fields), attribute="files"),
+        "message_files": fields.List(fields.Nested(message_file_fields)),
         "feedback": fields.Nested(feedback_fields, attribute="user_feedback", allow_null=True),
         "retriever_resources": fields.List(fields.Nested(retriever_resource_fields)),
         "created_at": TimestampField,

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/hit_testing.py

@@ -0,0 +1,17 @@
+from controllers.console.datasets.hit_testing_base import DatasetsHitTestingBase
+from controllers.service_api import api
+from controllers.service_api.wraps import DatasetApiResource
+
+
+class HitTestingApi(DatasetApiResource, DatasetsHitTestingBase):
+    def post(self, tenant_id, dataset_id):
+        dataset_id_str = str(dataset_id)
+
+        dataset = self.get_and_validate_dataset(dataset_id_str)
+        args = self.parse_args()
+        self.hit_testing_args_check(args)
+
+        return self.perform_hit_testing(dataset, args)
+
+
+api.add_resource(HitTestingApi, "/datasets/<uuid:dataset_id>/hit-testing")

api/controllers/web/app.py

@@ -21,7 +21,12 @@ class AppParameterApi(WebApiResource):
         "options": fields.List(fields.String),
     }
 
-    system_parameters_fields = {"image_file_size_limit": fields.String}
+    system_parameters_fields = {
+        "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 = {
         "opening_statement": fields.String,
@@ -80,7 +85,12 @@ class AppParameterApi(WebApiResource):
                     }
                 },
             ),
-            "system_parameters": {"image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT},
+            "system_parameters": {
+                "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

@@ -1,11 +1,14 @@
+import urllib.parse
+
 from flask import request
-from flask_restful import marshal_with
+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 fields.file_fields import file_fields
+from core.helper import ssrf_proxy
+from fields.file_fields import file_fields, remote_file_info_fields
 from services.file_service import FileService
 
 
@@ -15,6 +18,10 @@ class FileApi(WebApiResource):
         # 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()
@@ -22,7 +29,7 @@ class FileApi(WebApiResource):
         if len(request.files) > 1:
             raise TooManyFilesError()
         try:
-            upload_file = FileService.upload_file(file, end_user)
+            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:
@@ -31,4 +38,19 @@ class FileApi(WebApiResource):
         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/message.py

@@ -22,6 +22,7 @@ from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotIni
 from core.model_runtime.errors.invoke import InvokeError
 from fields.conversation_fields import message_file_fields
 from fields.message_fields import agent_thought_fields
+from fields.raws import FilesContainedField
 from libs import helper
 from libs.helper import TimestampField, uuid_value
 from models.model import AppMode
@@ -58,10 +59,10 @@ class MessageListApi(WebApiResource):
         "id": fields.String,
         "conversation_id": fields.String,
         "parent_message_id": fields.String,
-        "inputs": fields.Raw,
+        "inputs": FilesContainedField,
         "query": fields.String,
         "answer": fields.String(attribute="re_sign_file_url_answer"),
-        "message_files": fields.List(fields.Nested(message_file_fields), attribute="files"),
+        "message_files": fields.List(fields.Nested(message_file_fields)),
         "feedback": fields.Nested(feedback_fields, attribute="user_feedback", allow_null=True),
         "retriever_resources": fields.List(fields.Nested(retriever_resource_fields)),
         "created_at": TimestampField,

api/controllers/web/saved_message.py

@@ -17,7 +17,7 @@ message_fields = {
     "inputs": fields.Raw,
     "query": fields.String,
     "answer": fields.String,
-    "message_files": fields.List(fields.Nested(message_file_fields), attribute="files"),
+    "message_files": fields.List(fields.Nested(message_file_fields)),
     "feedback": fields.Nested(feedback_fields, attribute="user_feedback", allow_null=True),
     "created_at": TimestampField,
 }

api/core/agent/base_agent_runner.py

@@ -16,13 +16,14 @@ from core.app.entities.app_invoke_entities import (
 )
 from core.callback_handler.agent_tool_callback_handler import DifyAgentCallbackHandler
 from core.callback_handler.index_tool_callback_handler import DatasetIndexToolCallbackHandler
-from core.file.message_file_parser import MessageFileParser
+from core.file import file_manager
 from core.memory.token_buffer_memory import TokenBufferMemory
 from core.model_manager import ModelInstance
-from core.model_runtime.entities.llm_entities import LLMUsage
-from core.model_runtime.entities.message_entities import (
+from core.model_runtime.entities import (
     AssistantPromptMessage,
+    LLMUsage,
     PromptMessage,
+    PromptMessageContent,
     PromptMessageTool,
     SystemPromptMessage,
     TextPromptMessageContent,
@@ -40,9 +41,9 @@ from core.tools.entities.tool_entities import (
 from core.tools.tool.dataset_retriever_tool import DatasetRetrieverTool
 from core.tools.tool.tool import Tool
 from core.tools.tool_manager import ToolManager
-from core.tools.utils.tool_parameter_converter import ToolParameterConverter
 from extensions.ext_database import db
-from models.model import Conversation, Message, MessageAgentThought
+from factories import file_factory
+from models.model import Conversation, Message, MessageAgentThought, MessageFile
 from models.tools import ToolConversationVariables
 
 logger = logging.getLogger(__name__)
@@ -66,23 +67,6 @@ class BaseAgentRunner(AppRunner):
         db_variables: Optional[ToolConversationVariables] = None,
         model_instance: ModelInstance = None,
     ) -> None:
-        """
-        Agent runner
-        :param tenant_id: tenant id
-        :param application_generate_entity: application generate entity
-        :param conversation: conversation
-        :param app_config: app generate entity
-        :param model_config: model config
-        :param config: dataset config
-        :param queue_manager: queue manager
-        :param message: message
-        :param user_id: user id
-        :param memory: memory
-        :param prompt_messages: prompt messages
-        :param variables_pool: variables pool
-        :param db_variables: db variables
-        :param model_instance: model instance
-        """
         self.tenant_id = tenant_id
         self.application_generate_entity = application_generate_entity
         self.conversation = conversation
@@ -180,7 +164,13 @@ class BaseAgentRunner(AppRunner):
             if parameter.form != ToolParameter.ToolParameterForm.LLM:
                 continue
 
-            parameter_type = ToolParameterConverter.get_parameter_type(parameter.type)
+            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]
@@ -265,7 +255,13 @@ class BaseAgentRunner(AppRunner):
             if parameter.form != ToolParameter.ToolParameterForm.LLM:
                 continue
 
-            parameter_type = ToolParameterConverter.get_parameter_type(parameter.type)
+            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]
@@ -511,26 +507,24 @@ class BaseAgentRunner(AppRunner):
         return result
 
     def organize_agent_user_prompt(self, message: Message) -> UserPromptMessage:
-        message_file_parser = MessageFileParser(
-            tenant_id=self.tenant_id,
-            app_id=self.app_config.app_id,
-        )
-
-        files = message.message_files
+        files = db.session.query(MessageFile).filter(MessageFile.message_id == message.id).all()
         if files:
             file_extra_config = FileUploadConfigManager.convert(message.app_model_config.to_dict())
 
             if file_extra_config:
-                file_objs = message_file_parser.transform_message_files(files, file_extra_config)
+                file_objs = file_factory.build_from_message_files(
+                    message_files=files, tenant_id=self.tenant_id, config=file_extra_config
+                )
             else:
                 file_objs = []
 
             if not file_objs:
                 return UserPromptMessage(content=message.query)
             else:
-                prompt_message_contents = [TextPromptMessageContent(data=message.query)]
+                prompt_message_contents: list[PromptMessageContent] = []
+                prompt_message_contents.append(TextPromptMessageContent(data=message.query))
                 for file_obj in file_objs:
-                    prompt_message_contents.append(file_obj.prompt_message_content)
+                    prompt_message_contents.append(file_manager.to_prompt_message_content(file_obj))
 
                 return UserPromptMessage(content=prompt_message_contents)
         else:

api/core/agent/cot_agent_runner.py

@@ -369,7 +369,7 @@ class CotAgentRunner(BaseAgentRunner, ABC):
         return message
 
     def _organize_historic_prompt_messages(
-        self, current_session_messages: list[PromptMessage] = None
+        self, current_session_messages: Optional[list[PromptMessage]] = None
     ) -> list[PromptMessage]:
         """
         organize historic prompt messages

api/core/agent/cot_chat_agent_runner.py

@@ -1,9 +1,11 @@
 import json
 
 from core.agent.cot_agent_runner import CotAgentRunner
-from core.model_runtime.entities.message_entities import (
+from core.file import file_manager
+from core.model_runtime.entities import (
     AssistantPromptMessage,
     PromptMessage,
+    PromptMessageContent,
     SystemPromptMessage,
     TextPromptMessageContent,
     UserPromptMessage,
@@ -27,14 +29,15 @@ class CotChatAgentRunner(CotAgentRunner):
 
         return SystemPromptMessage(content=system_prompt)
 
-    def _organize_user_query(self, query, prompt_messages: list[PromptMessage] = None) -> list[PromptMessage]:
+    def _organize_user_query(self, query, prompt_messages: list[PromptMessage]) -> list[PromptMessage]:
         """
         Organize user query
         """
         if self.files:
-            prompt_message_contents = [TextPromptMessageContent(data=query)]
+            prompt_message_contents: list[PromptMessageContent] = []
+            prompt_message_contents.append(TextPromptMessageContent(data=query))
             for file_obj in self.files:
-                prompt_message_contents.append(file_obj.prompt_message_content)
+                prompt_message_contents.append(file_manager.to_prompt_message_content(file_obj))
 
             prompt_messages.append(UserPromptMessage(content=prompt_message_contents))
         else:

api/core/agent/cot_completion_agent_runner.py

@@ -1,4 +1,5 @@
 import json
+from typing import Optional
 
 from core.agent.cot_agent_runner import CotAgentRunner
 from core.model_runtime.entities.message_entities import AssistantPromptMessage, PromptMessage, UserPromptMessage
@@ -21,7 +22,7 @@ class CotCompletionAgentRunner(CotAgentRunner):
 
         return system_prompt
 
-    def _organize_historic_prompt(self, current_session_messages: list[PromptMessage] = None) -> str:
+    def _organize_historic_prompt(self, current_session_messages: Optional[list[PromptMessage]] = None) -> str:
         """
         Organize historic prompt
         """

api/core/agent/fc_agent_runner.py

@@ -2,15 +2,20 @@ import json
 import logging
 from collections.abc import Generator
 from copy import deepcopy
-from typing import Any, Union
+from typing import Any, Optional, Union
 
 from core.agent.base_agent_runner import BaseAgentRunner
 from core.app.apps.base_app_queue_manager import PublishFrom
 from core.app.entities.queue_entities import QueueAgentThoughtEvent, QueueMessageEndEvent, QueueMessageFileEvent
-from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
-from core.model_runtime.entities.message_entities import (
+from core.file import file_manager
+from core.model_runtime.entities import (
     AssistantPromptMessage,
+    LLMResult,
+    LLMResultChunk,
+    LLMResultChunkDelta,
+    LLMUsage,
     PromptMessage,
+    PromptMessageContent,
     PromptMessageContentType,
     SystemPromptMessage,
     TextPromptMessageContent,
@@ -370,7 +375,7 @@ class FunctionCallAgentRunner(BaseAgentRunner):
         return tool_calls
 
     def _init_system_message(
-        self, prompt_template: str, prompt_messages: list[PromptMessage] = None
+        self, prompt_template: str, prompt_messages: Optional[list[PromptMessage]] = None
     ) -> list[PromptMessage]:
         """
         Initialize system message
@@ -385,14 +390,15 @@ class FunctionCallAgentRunner(BaseAgentRunner):
 
         return prompt_messages
 
-    def _organize_user_query(self, query, prompt_messages: list[PromptMessage] = None) -> list[PromptMessage]:
+    def _organize_user_query(self, query, prompt_messages: list[PromptMessage]) -> list[PromptMessage]:
         """
         Organize user query
         """
         if self.files:
-            prompt_message_contents = [TextPromptMessageContent(data=query)]
+            prompt_message_contents: list[PromptMessageContent] = []
+            prompt_message_contents.append(TextPromptMessageContent(data=query))
             for file_obj in self.files:
-                prompt_message_contents.append(file_obj.prompt_message_content)
+                prompt_message_contents.append(file_manager.to_prompt_message_content(file_obj))
 
             prompt_messages.append(UserPromptMessage(content=prompt_message_contents))
         else:

api/core/agent/output_parser/cot_output_parser.py

@@ -14,7 +14,7 @@ class CotAgentOutputParser:
     ) -> Generator[Union[str, AgentScratchpadUnit.Action], None, None]:
         def parse_action(json_str):
             try:
-                action = json.loads(json_str)
+                action = json.loads(json_str, strict=False)
                 action_name = None
                 action_input = None
 
@@ -62,6 +62,8 @@ class CotAgentOutputParser:
         thought_str = "thought:"
         thought_idx = 0
 
+        last_character = ""
+
         for response in llm_response:
             if response.delta.usage:
                 usage_dict["usage"] = response.delta.usage
@@ -74,35 +76,38 @@ class CotAgentOutputParser:
             while index < len(response):
                 steps = 1
                 delta = response[index : index + steps]
-                last_character = response[index - 1] if index > 0 else ""
+                yield_delta = False
 
                 if delta == "`":
+                    last_character = delta
                     code_block_cache += delta
                     code_block_delimiter_count += 1
                 else:
                     if not in_code_block:
                         if code_block_delimiter_count > 0:
+                            last_character = delta
                             yield code_block_cache
                         code_block_cache = ""
                     else:
+                        last_character = delta
                         code_block_cache += delta
                     code_block_delimiter_count = 0
 
                 if not in_code_block and not in_json:
                     if delta.lower() == action_str[action_idx] and action_idx == 0:
                         if last_character not in {"\n", " ", ""}:
+                            yield_delta = True
+                        else:
+                            last_character = delta
+                            action_cache += delta
+                            action_idx += 1
+                            if action_idx == len(action_str):
+                                action_cache = ""
+                                action_idx = 0
                             index += steps
-                            yield delta
                             continue
-
-                        action_cache += delta
-                        action_idx += 1
-                        if action_idx == len(action_str):
-                            action_cache = ""
-                            action_idx = 0
-                        index += steps
-                        continue
                     elif delta.lower() == action_str[action_idx] and action_idx > 0:
+                        last_character = delta
                         action_cache += delta
                         action_idx += 1
                         if action_idx == len(action_str):
@@ -112,24 +117,25 @@ class CotAgentOutputParser:
                         continue
                     else:
                         if action_cache:
+                            last_character = delta
                             yield action_cache
                             action_cache = ""
                             action_idx = 0
 
                     if delta.lower() == thought_str[thought_idx] and thought_idx == 0:
                         if last_character not in {"\n", " ", ""}:
+                            yield_delta = True
+                        else:
+                            last_character = delta
+                            thought_cache += delta
+                            thought_idx += 1
+                            if thought_idx == len(thought_str):
+                                thought_cache = ""
+                                thought_idx = 0
                             index += steps
-                            yield delta
                             continue
-
-                        thought_cache += delta
-                        thought_idx += 1
-                        if thought_idx == len(thought_str):
-                            thought_cache = ""
-                            thought_idx = 0
-                        index += steps
-                        continue
                     elif delta.lower() == thought_str[thought_idx] and thought_idx > 0:
+                        last_character = delta
                         thought_cache += delta
                         thought_idx += 1
                         if thought_idx == len(thought_str):
@@ -139,12 +145,20 @@ class CotAgentOutputParser:
                         continue
                     else:
                         if thought_cache:
+                            last_character = delta
                             yield thought_cache
                             thought_cache = ""
                             thought_idx = 0
 
+                    if yield_delta:
+                        index += steps
+                        last_character = delta
+                        yield delta
+                        continue
+
                 if code_block_delimiter_count == 3:
                     if in_code_block:
+                        last_character = delta
                         yield from extra_json_from_code_block(code_block_cache)
                         code_block_cache = ""
 
@@ -156,8 +170,10 @@ class CotAgentOutputParser:
                     if delta == "{":
                         json_quote_count += 1
                         in_json = True
+                        last_character = delta
                         json_cache += delta
                     elif delta == "}":
+                        last_character = delta
                         json_cache += delta
                         if json_quote_count > 0:
                             json_quote_count -= 1
@@ -168,16 +184,19 @@ class CotAgentOutputParser:
                                 continue
                     else:
                         if in_json:
+                            last_character = delta
                             json_cache += delta
 
                     if got_json:
                         got_json = False
+                        last_character = delta
                         yield parse_action(json_cache)
                         json_cache = ""
                         json_quote_count = 0
                         in_json = False
 
                 if not in_code_block and not in_json:
+                    last_character = delta
                     yield delta.replace("`", "")
 
                 index += steps

api/core/app/app_config/easy_ui_based_app/variables/manager.py

@@ -53,12 +53,11 @@ class BasicVariablesConfigManager:
                     VariableEntity(
                         type=variable_type,
                         variable=variable.get("variable"),
-                        description=variable.get("description"),
+                        description=variable.get("description") or "",
                         label=variable.get("label"),
                         required=variable.get("required", False),
                         max_length=variable.get("max_length"),
-                        options=variable.get("options"),
-                        default=variable.get("default"),
+                        options=variable.get("options") or [],
                     )
                 )
 

api/core/app/app_config/entities.py

@@ -1,11 +1,12 @@
+from collections.abc import Sequence
 from enum import Enum
 from typing import Any, Optional
 
-from pydantic import BaseModel
+from pydantic import BaseModel, Field, field_validator
 
-from core.file.file_obj import FileExtraConfig
+from core.file import FileExtraConfig, FileTransferMethod, FileType
 from core.model_runtime.entities.message_entities import PromptMessageRole
-from models import AppMode
+from models.model import AppMode
 
 
 class ModelConfigEntity(BaseModel):
@@ -69,7 +70,7 @@ class PromptTemplateEntity(BaseModel):
         ADVANCED = "advanced"
 
         @classmethod
-        def value_of(cls, value: str) -> "PromptType":
+        def value_of(cls, value: str):
             """
             Get value of given mode.
 
@@ -93,6 +94,8 @@ class VariableEntityType(str, Enum):
     PARAGRAPH = "paragraph"
     NUMBER = "number"
     EXTERNAL_DATA_TOOL = "external_data_tool"
+    FILE = "file"
+    FILE_LIST = "file-list"
 
 
 class VariableEntity(BaseModel):
@@ -102,13 +105,24 @@ class VariableEntity(BaseModel):
 
     variable: str
     label: str
-    description: Optional[str] = None
+    description: str = ""
     type: VariableEntityType
     required: bool = False
     max_length: Optional[int] = None
-    options: Optional[list[str]] = None
-    default: Optional[str] = None
-    hint: Optional[str] = None
+    options: Sequence[str] = Field(default_factory=list)
+    allowed_file_types: Sequence[FileType] = Field(default_factory=list)
+    allowed_file_extensions: Sequence[str] = Field(default_factory=list)
+    allowed_file_upload_methods: Sequence[FileTransferMethod] = Field(default_factory=list)
+
+    @field_validator("description", mode="before")
+    @classmethod
+    def convert_none_description(cls, v: Any) -> str:
+        return v or ""
+
+    @field_validator("options", mode="before")
+    @classmethod
+    def convert_none_options(cls, v: Any) -> Sequence[str]:
+        return v or []
 
 
 class ExternalDataVariableEntity(BaseModel):
@@ -136,7 +150,7 @@ class DatasetRetrieveConfigEntity(BaseModel):
         MULTIPLE = "multiple"
 
         @classmethod
-        def value_of(cls, value: str) -> "RetrieveStrategy":
+        def value_of(cls, value: str):
             """
             Get value of given mode.
 

api/core/app/app_config/features/file_upload/manager.py

@@ -1,12 +1,13 @@
 from collections.abc import Mapping
-from typing import Any, Optional
+from typing import Any
 
-from core.file.file_obj import FileExtraConfig
+from core.file.models import FileExtraConfig
+from models import FileUploadConfig
 
 
 class FileUploadConfigManager:
     @classmethod
-    def convert(cls, config: Mapping[str, Any], is_vision: bool = True) -> Optional[FileExtraConfig]:
+    def convert(cls, config: Mapping[str, Any], is_vision: bool = True):
         """
         Convert model config to model config
 
@@ -15,19 +16,21 @@ class FileUploadConfigManager:
         """
         file_upload_dict = config.get("file_upload")
         if file_upload_dict:
-            if file_upload_dict.get("image"):
-                if "enabled" in file_upload_dict["image"] and file_upload_dict["image"]["enabled"]:
-                    image_config = {
-                        "number_limits": file_upload_dict["image"]["number_limits"],
-                        "transfer_methods": file_upload_dict["image"]["transfer_methods"],
+            if file_upload_dict.get("enabled"):
+                transform_methods = file_upload_dict.get("allowed_file_upload_methods") or file_upload_dict.get(
+                    "allowed_upload_methods", []
+                )
+                data = {
+                    "image_config": {
+                        "number_limits": file_upload_dict["number_limits"],
+                        "transfer_methods": transform_methods,
                     }
+                }
 
-                    if is_vision:
-                        image_config["detail"] = file_upload_dict["image"]["detail"]
+                if is_vision:
+                    data["image_config"]["detail"] = file_upload_dict.get("image", {}).get("detail", "low")
 
-                    return FileExtraConfig(image_config=image_config)
-
-        return None
+                return FileExtraConfig.model_validate(data)
 
     @classmethod
     def validate_and_set_defaults(cls, config: dict, is_vision: bool = True) -> tuple[dict, list[str]]:
@@ -39,29 +42,7 @@ class FileUploadConfigManager:
         """
         if not config.get("file_upload"):
             config["file_upload"] = {}
-
-        if not isinstance(config["file_upload"], dict):
-            raise ValueError("file_upload must be of dict type")
-
-        # check image config
-        if not config["file_upload"].get("image"):
-            config["file_upload"]["image"] = {"enabled": False}
-
-        if config["file_upload"]["image"]["enabled"]:
-            number_limits = config["file_upload"]["image"]["number_limits"]
-            if number_limits < 1 or number_limits > 6:
-                raise ValueError("number_limits must be in [1, 6]")
-
-            if is_vision:
-                detail = config["file_upload"]["image"]["detail"]
-                if detail not in {"high", "low"}:
-                    raise ValueError("detail must be in ['high', 'low']")
-
-            transfer_methods = config["file_upload"]["image"]["transfer_methods"]
-            if not isinstance(transfer_methods, list):
-                raise ValueError("transfer_methods must be of list type")
-            for method in transfer_methods:
-                if method not in {"remote_url", "local_file"}:
-                    raise ValueError("transfer_methods must be in ['remote_url', 'local_file']")
+        else:
+            FileUploadConfig.model_validate(config["file_upload"])
 
         return config, ["file_upload"]

api/core/app/app_config/workflow_ui_based_app/variables/manager.py

@@ -17,6 +17,6 @@ class WorkflowVariablesConfigManager:
 
         # variables
         for variable in user_input_form:
-            variables.append(VariableEntity(**variable))
+            variables.append(VariableEntity.model_validate(variable))
 
         return variables

api/core/app/apps/advanced_chat/app_generator.py

@@ -10,6 +10,7 @@ from flask import Flask, current_app
 from pydantic import ValidationError
 
 import contexts
+from constants import UUID_NIL
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
 from core.app.apps.advanced_chat.app_config_manager import AdvancedChatAppConfigManager
 from core.app.apps.advanced_chat.app_runner import AdvancedChatAppRunner
@@ -20,11 +21,12 @@ from core.app.apps.message_based_app_generator import MessageBasedAppGenerator
 from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueManager
 from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity, InvokeFrom
 from core.app.entities.task_entities import ChatbotAppBlockingResponse, ChatbotAppStreamResponse
-from core.file.message_file_parser import MessageFileParser
 from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
 from core.ops.ops_trace_manager import TraceQueueManager
 from extensions.ext_database import db
+from factories import file_factory
 from models.account import Account
+from models.enums import CreatedByRole
 from models.model import App, Conversation, EndUser, Message
 from models.workflow import Workflow
 
@@ -95,10 +97,16 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
 
         # parse files
         files = args["files"] if args.get("files") else []
-        message_file_parser = MessageFileParser(tenant_id=app_model.tenant_id, app_id=app_model.id)
         file_extra_config = FileUploadConfigManager.convert(workflow.features_dict, is_vision=False)
+        role = CreatedByRole.ACCOUNT if isinstance(user, Account) else CreatedByRole.END_USER
         if file_extra_config:
-            file_objs = message_file_parser.validate_and_transform_files_arg(files, file_extra_config, user)
+            file_objs = file_factory.build_from_mappings(
+                mappings=files,
+                tenant_id=app_model.tenant_id,
+                user_id=user.id,
+                role=role,
+                config=file_extra_config,
+            )
         else:
             file_objs = []
 
@@ -106,27 +114,32 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
         app_config = AdvancedChatAppConfigManager.get_app_config(app_model=app_model, workflow=workflow)
 
         # get tracing instance
-        user_id = user.id if isinstance(user, Account) else user.session_id
-        trace_manager = TraceQueueManager(app_model.id, user_id)
+        trace_manager = TraceQueueManager(
+            app_id=app_model.id, user_id=user.id if isinstance(user, Account) else user.session_id
+        )
 
         if invoke_from == InvokeFrom.DEBUGGER:
             # always enable retriever resource in debugger mode
             app_config.additional_features.show_retrieve_source = True
 
+        workflow_run_id = str(uuid.uuid4())
         # init application generate entity
         application_generate_entity = AdvancedChatAppGenerateEntity(
             task_id=str(uuid.uuid4()),
             app_config=app_config,
             conversation_id=conversation.id if conversation else None,
-            inputs=conversation.inputs if conversation else self._get_cleaned_inputs(inputs, app_config),
+            inputs=conversation.inputs
+            if conversation
+            else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config, user_id=user.id, role=role),
             query=query,
             files=file_objs,
-            parent_message_id=args.get("parent_message_id"),
+            parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
             user_id=user.id,
             stream=stream,
             invoke_from=invoke_from,
             extras=extras,
             trace_manager=trace_manager,
+            workflow_run_id=workflow_run_id,
         )
         contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)