Update build-push.yml

web retrieval resource fix
Merge branch 'fix/agent-external-knowledge-retrieval' into fix/external-knowledge-retrieval-issues
2026-01-09 07:44:12 +00:00 · 2024-10-11 19:49:28 +08:00 · 2024-10-11 19:47:50 +08:00 · 2024-10-11 19:44:52 +08:00 · 2024-10-11 19:13:19 +08:00 · 2024-10-11 18:56:24 +08:00
1223 changed files with 39788 additions and 5595 deletions
--- a/.github/workflows/api-tests.yml
+++ b/.github/workflows/api-tests.yml
@@ -39,7 +39,7 @@ jobs:
            api/pyproject.toml
            api/poetry.lock

-      - name: Poetry check
+      - name: Check Poetry lockfile
        run: |
          poetry check -C api --lock
          poetry show -C api
@@ -47,6 +47,9 @@ 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

--- a/.github/workflows/build-push.yml
+++ b/.github/workflows/build-push.yml
@@ -5,6 +5,7 @@ on:
    branches:
      - "main"
      - "deploy/dev"
+      - "fix/external-knowledge-retrieval-issues"
  release:
    types: [published]

@@ -125,7 +126,7 @@ jobs:
        with:
          images: ${{ env[matrix.image_name_env] }}
          tags: |
-            type=raw,value=latest,enable=${{ startsWith(github.ref, 'refs/tags/') }}
+            type=raw,value=latest,enable=${{ startsWith(github.ref, 'refs/tags/') && !contains(github.ref, '-beta') }}
            type=ref,event=branch
            type=sha,enable=true,priority=100,prefix=,suffix=,format=long
            type=raw,value=${{ github.ref_name }},enable=${{ startsWith(github.ref, 'refs/tags/') }}
--- a/.github/workflows/web-tests.yml
+++ b/.github/workflows/web-tests.yml
@@ -0,0 +1,46 @@
+name: Web Tests
+
+on:
+  pull_request:
+    branches:
+      - main
+    paths:
+      - web/**
+
+concurrency:
+  group: web-tests-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    name: Web Tests
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: ./web
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Check changed files
+        id: changed-files
+        uses: tj-actions/changed-files@v45
+        with:
+          files: web/**
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        if: steps.changed-files.outputs.any_changed == 'true'
+        with:
+          node-version: 20
+          cache: yarn
+          cache-dependency-path: ./web/package.json
+
+      - name: Install dependencies
+        if: steps.changed-files.outputs.any_changed == 'true'
+        run: yarn install --frozen-lockfile
+
+      - name: Run tests
+        if: steps.changed-files.outputs.any_changed == 'true'
+        run: yarn test
--- a/.gitignore
+++ b/.gitignore
@@ -153,6 +153,9 @@ docker-legacy/volumes/etcd/*
 docker-legacy/volumes/minio/*
 docker-legacy/volumes/milvus/*
 docker-legacy/volumes/chroma/*
+docker-legacy/volumes/opensearch/data/*
+docker-legacy/volumes/pgvectors/data/*
+docker-legacy/volumes/pgvector/data/*

 docker/volumes/app/storage/*
 docker/volumes/certbot/*
@@ -164,6 +167,12 @@ docker/volumes/etcd/*
 docker/volumes/minio/*
 docker/volumes/milvus/*
 docker/volumes/chroma/*
+docker/volumes/opensearch/data/*
+docker/volumes/myscale/data/*
+docker/volumes/myscale/log/*
+docker/volumes/unstructured/*
+docker/volumes/pgvector/data/*
+docker/volumes/pgvecto_rs/data/*

 docker/nginx/conf.d/default.conf
 docker/middleware.env
--- a/CONTRIBUTING_CN.md
+++ b/CONTRIBUTING_CN.md
@@ -36,7 +36,7 @@
  | 被团队成员标记为高优先级的功能    | 高优先级   |
  | 在 [community feedback board](https://github.com/langgenius/dify/discussions/categories/feedbacks) 内反馈的常见功能请求 | 中等优先级 |
  | 非核心功能和小幅改进                     | 低优先级    |
-  | 有价值当不紧急                                   | 未来功能  |
+  | 有价值但不紧急                                   | 未来功能  |

 ### 其他任何事情（例如 bug 报告、性能优化、拼写错误更正）：
 * 立即开始编码。
@@ -138,7 +138,7 @@ Dify 的后端使用 Python 编写，使用 [Flask](https://flask.palletsproject
 ├── models                // 描述数据模型和 API 响应的形状
 ├── public                // 如 favicon 等元资源
 ├── service               // 定义 API 操作的形状
-├── test                  
+├── test
 ├── types                 // 函数参数和返回值的描述
 └── utils                 // 共享的实用函数
 ```
--- a/README.md
+++ b/README.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">
@@ -196,10 +196,14 @@ 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 +223,7 @@ 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

--- a/README_AR.md
+++ b/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

--- a/README_CN.md
+++ b/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">
@@ -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"/>
--- a/README_ES.md
+++ b/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

--- a/README_FR.md
+++ b/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

--- a/README_JA.md
+++ b/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。



--- a/README_KL.md
+++ b/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

--- a/README_KR.md
+++ b/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.
--- a/README_TR.md
+++ b/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

--- a/README_VI.md
+++ b/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

--- a/api/.env.example
+++ b/api/.env.example
@@ -39,7 +39,7 @@ 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, azure-blob, google-storage, tencent-cos, huawei-obs, volcengine-tos, baidu-obs
 STORAGE_TYPE=local
 STORAGE_LOCAL_PATH=storage
 S3_USE_AWS_MANAGED_IAM=false
@@ -79,6 +79,12 @@ 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
@@ -162,6 +168,8 @@ PGVECTOR_PORT=5433
 PGVECTOR_USER=postgres
 PGVECTOR_PASSWORD=postgres
 PGVECTOR_DATABASE=postgres
+PGVECTOR_MIN_CONNECTION=1
+PGVECTOR_MAX_CONNECTION=5

 # Tidb Vector configuration
 TIDB_VECTOR_HOST=xxx.eu-central-1.xxx.aws.tidbcloud.com
@@ -263,6 +271,9 @@ 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=

--- a/api/README.md
+++ b/api/README.md
@@ -65,14 +65,12 @@

 8. Start Dify [web](../web) service.
 9. Setup your application by visiting `http://localhost:3000`...
-10. If you need to debug local async processing, please start the worker service.
+10. If you need to handle and debug the async tasks (e.g. dataset importing and documents indexing), please start the worker service.

   ```bash
   poetry run python -m celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail,ops_trace,app_deletion
   ```

-   The started celery app handles the async tasks, e.g. dataset importing and documents indexing.
-
 ## Testing

 1. Install dependencies for both the backend and the test environment
--- a/api/app.py
+++ b/api/app.py
@@ -26,7 +26,7 @@ from commands import register_commands
 from configs import dify_config

 # DO NOT REMOVE BELOW
-from events import event_handlers
+from events import event_handlers  # noqa: F401
 from extensions import (
    ext_celery,
    ext_code_based_extension,
@@ -36,6 +36,7 @@ from extensions import (
    ext_login,
    ext_mail,
    ext_migrate,
+    ext_proxy_fix,
    ext_redis,
    ext_sentry,
    ext_storage,
@@ -45,7 +46,7 @@ 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 models import account, dataset, model, source, task, tool, tools, web  # noqa: F401
 from services.account_service import AccountService

 # DO NOT REMOVE ABOVE
@@ -53,11 +54,9 @@ from services.account_service import AccountService

 warnings.simplefilter("ignore", ResourceWarning)

-# fix windows platform
-if os.name == "nt":
-    os.system('tzutil /s "UTC"')
-else:
-    os.environ["TZ"] = "UTC"
+os.environ["TZ"] = "UTC"
+# windows platform not support tzset
+if hasattr(time, "tzset"):
    time.tzset()


@@ -158,13 +157,14 @@ def initialize_extensions(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"]:
+    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", "")
@@ -183,10 +183,10 @@ def load_user_from_request(request_from_flask_login):
    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
+    logged_in_account = AccountService.load_logged_in_account(account_id=user_id, token=auth_token)
+    if logged_in_account:
+        contexts.tenant_id.set(logged_in_account.current_tenant_id)
+    return logged_in_account


@login_manager.unauthorized_handler
--- a/api/commands.py
+++ b/api/commands.py
@@ -28,28 +28,28 @@ from services.account_service import RegisterService, TenantService


@click.command("reset-password", help="Reset the account password.")
-@click.option("--email", prompt=True, help="The email address of the account whose password you need to reset")
-@click.option("--new-password", prompt=True, help="the new password.")
-@click.option("--password-confirm", prompt=True, help="the new password confirm.")
+@click.option("--email", prompt=True, help="Account email to reset password for")
+@click.option("--new-password", prompt=True, help="New password")
+@click.option("--password-confirm", prompt=True, help="Confirm new password")
 def reset_password(email, new_password, password_confirm):
    """
    Reset password of owner account
    Only available in SELF_HOSTED mode
    """
    if str(new_password).strip() != str(password_confirm).strip():
-        click.echo(click.style("sorry. The two passwords do not match.", fg="red"))
+        click.echo(click.style("Passwords do not match.", fg="red"))
        return

    account = db.session.query(Account).filter(Account.email == email).one_or_none()

    if not account:
-        click.echo(click.style("sorry. the account: [{}] not exist .".format(email), fg="red"))
+        click.echo(click.style("Account not found for email: {}".format(email), fg="red"))
        return

    try:
        valid_password(new_password)
    except:
-        click.echo(click.style("sorry. The passwords must match {} ".format(password_pattern), fg="red"))
+        click.echo(click.style("Invalid password. Must match {}".format(password_pattern), fg="red"))
        return

    # generate password salt
@@ -62,37 +62,37 @@ def reset_password(email, new_password, password_confirm):
    account.password = base64_password_hashed
    account.password_salt = base64_salt
    db.session.commit()
-    click.echo(click.style("Congratulations! Password has been reset.", fg="green"))
+    click.echo(click.style("Password reset successfully.", fg="green"))


@click.command("reset-email", help="Reset the account email.")
-@click.option("--email", prompt=True, help="The old email address of the account whose email you need to reset")
-@click.option("--new-email", prompt=True, help="the new email.")
-@click.option("--email-confirm", prompt=True, help="the new email confirm.")
+@click.option("--email", prompt=True, help="Current account email")
+@click.option("--new-email", prompt=True, help="New email")
+@click.option("--email-confirm", prompt=True, help="Confirm new email")
 def reset_email(email, new_email, email_confirm):
    """
    Replace account email
    :return:
    """
    if str(new_email).strip() != str(email_confirm).strip():
-        click.echo(click.style("Sorry, new email and confirm email do not match.", fg="red"))
+        click.echo(click.style("New emails do not match.", fg="red"))
        return

    account = db.session.query(Account).filter(Account.email == email).one_or_none()

    if not account:
-        click.echo(click.style("sorry. the account: [{}] not exist .".format(email), fg="red"))
+        click.echo(click.style("Account not found for email: {}".format(email), fg="red"))
        return

    try:
        email_validate(new_email)
    except:
-        click.echo(click.style("sorry. {} is not a valid email. ".format(email), fg="red"))
+        click.echo(click.style("Invalid email: {}".format(new_email), fg="red"))
        return

    account.email = new_email
    db.session.commit()
-    click.echo(click.style("Congratulations!, email has been reset.", fg="green"))
+    click.echo(click.style("Email updated successfully.", fg="green"))


@click.command(
@@ -104,7 +104,7 @@ def reset_email(email, new_email, email_confirm):
 )
@click.confirmation_option(
    prompt=click.style(
-        "Are you sure you want to reset encrypt key pair?" " this operation cannot be rolled back!", fg="red"
+        "Are you sure you want to reset encrypt key pair? This operation cannot be rolled back!", fg="red"
    )
 )
 def reset_encrypt_key_pair():
@@ -114,13 +114,13 @@ def reset_encrypt_key_pair():
    Only support SELF_HOSTED mode.
    """
    if dify_config.EDITION != "SELF_HOSTED":
-        click.echo(click.style("Sorry, only support SELF_HOSTED mode.", fg="red"))
+        click.echo(click.style("This command is only for SELF_HOSTED installations.", fg="red"))
        return

    tenants = db.session.query(Tenant).all()
    for tenant in tenants:
        if not tenant:
-            click.echo(click.style("Sorry, no workspace found. Please enter /install to initialize.", fg="red"))
+            click.echo(click.style("No workspaces found. Run /install first.", fg="red"))
            return

        tenant.encrypt_public_key = generate_key_pair(tenant.id)
@@ -131,18 +131,18 @@ def reset_encrypt_key_pair():

        click.echo(
            click.style(
-                "Congratulations! " "the asymmetric key pair of workspace {} has been reset.".format(tenant.id),
+                "Congratulations! The asymmetric key pair of workspace {} has been reset.".format(tenant.id),
                fg="green",
            )
        )


-@click.command("vdb-migrate", help="migrate vector db.")
+@click.command("vdb-migrate", help="Migrate vector db.")
@click.option("--scope", default="all", prompt=False, help="The scope of vector database to migrate, Default is All.")
 def vdb_migrate(scope: str):
-    if scope in ["knowledge", "all"]:
+    if scope in {"knowledge", "all"}:
        migrate_knowledge_vector_database()
-    if scope in ["annotation", "all"]:
+    if scope in {"annotation", "all"}:
        migrate_annotation_vector_database()


@@ -150,7 +150,7 @@ def migrate_annotation_vector_database():
    """
    Migrate annotation datas to target vector database .
    """
-    click.echo(click.style("Start migrate annotation data.", fg="green"))
+    click.echo(click.style("Starting annotation data migration.", fg="green"))
    create_count = 0
    skipped_count = 0
    total_count = 0
@@ -174,14 +174,14 @@ def migrate_annotation_vector_database():
                f"Processing the {total_count} app {app.id}. " + f"{create_count} created, {skipped_count} skipped."
            )
            try:
-                click.echo("Create app annotation index: {}".format(app.id))
+                click.echo("Creating app annotation index: {}".format(app.id))
                app_annotation_setting = (
                    db.session.query(AppAnnotationSetting).filter(AppAnnotationSetting.app_id == app.id).first()
                )

                if not app_annotation_setting:
                    skipped_count = skipped_count + 1
-                    click.echo("App annotation setting is disabled: {}".format(app.id))
+                    click.echo("App annotation setting disabled: {}".format(app.id))
                    continue
                # get dataset_collection_binding info
                dataset_collection_binding = (
@@ -190,7 +190,7 @@ def migrate_annotation_vector_database():
                    .first()
                )
                if not dataset_collection_binding:
-                    click.echo("App annotation collection binding is not exist: {}".format(app.id))
+                    click.echo("App annotation collection binding not found: {}".format(app.id))
                    continue
                annotations = db.session.query(MessageAnnotation).filter(MessageAnnotation.app_id == app.id).all()
                dataset = Dataset(
@@ -211,11 +211,11 @@ def migrate_annotation_vector_database():
                        documents.append(document)

                vector = Vector(dataset, attributes=["doc_id", "annotation_id", "app_id"])
-                click.echo(f"Start to migrate annotation, app_id: {app.id}.")
+                click.echo(f"Migrating annotations for app: {app.id}.")

                try:
                    vector.delete()
-                    click.echo(click.style(f"Successfully delete vector index for app: {app.id}.", fg="green"))
+                    click.echo(click.style(f"Deleted vector index for app {app.id}.", fg="green"))
                except Exception as e:
                    click.echo(click.style(f"Failed to delete vector index for app {app.id}.", fg="red"))
                    raise e
@@ -223,12 +223,12 @@ def migrate_annotation_vector_database():
                    try:
                        click.echo(
                            click.style(
-                                f"Start to created vector index with {len(documents)} annotations for app {app.id}.",
+                                f"Creating vector index with {len(documents)} annotations for app {app.id}.",
                                fg="green",
                            )
                        )
                        vector.create(documents)
-                        click.echo(click.style(f"Successfully created vector index for app {app.id}.", fg="green"))
+                        click.echo(click.style(f"Created vector index for app {app.id}.", fg="green"))
                    except Exception as e:
                        click.echo(click.style(f"Failed to created vector index for app {app.id}.", fg="red"))
                        raise e
@@ -237,14 +237,14 @@ def migrate_annotation_vector_database():
            except Exception as e:
                click.echo(
                    click.style(
-                        "Create app annotation index error: {} {}".format(e.__class__.__name__, str(e)), fg="red"
+                        "Error creating app annotation index: {} {}".format(e.__class__.__name__, str(e)), fg="red"
                    )
                )
                continue

    click.echo(
        click.style(
-            f"Congratulations! Create {create_count} app annotation indexes, and skipped {skipped_count} apps.",
+            f"Migration complete. Created {create_count} app annotation indexes. Skipped {skipped_count} apps.",
            fg="green",
        )
    )
@@ -254,7 +254,7 @@ def migrate_knowledge_vector_database():
    """
    Migrate vector database datas to target vector database .
    """
-    click.echo(click.style("Start migrate vector db.", fg="green"))
+    click.echo(click.style("Starting vector database migration.", fg="green"))
    create_count = 0
    skipped_count = 0
    total_count = 0
@@ -275,11 +275,10 @@ def migrate_knowledge_vector_database():
        for dataset in datasets:
            total_count = total_count + 1
            click.echo(
-                f"Processing the {total_count} dataset {dataset.id}. "
-                + f"{create_count} created, {skipped_count} skipped."
+                f"Processing the {total_count} dataset {dataset.id}. {create_count} created, {skipped_count} skipped."
            )
            try:
-                click.echo("Create dataset vdb index: {}".format(dataset.id))
+                click.echo("Creating dataset vector database index: {}".format(dataset.id))
                if dataset.index_struct_dict:
                    if dataset.index_struct_dict["type"] == vector_type:
                        skipped_count = skipped_count + 1
@@ -300,7 +299,7 @@ def migrate_knowledge_vector_database():
                        if dataset_collection_binding:
                            collection_name = dataset_collection_binding.collection_name
                        else:
-                            raise ValueError("Dataset Collection Bindings is not exist!")
+                            raise ValueError("Dataset Collection Binding not found")
                    else:
                        dataset_id = dataset.id
                        collection_name = Dataset.gen_collection_name_by_id(dataset_id)
@@ -352,14 +351,12 @@ def migrate_knowledge_vector_database():
                    raise ValueError(f"Vector store {vector_type} is not supported.")

                vector = Vector(dataset)
-                click.echo(f"Start to migrate dataset {dataset.id}.")
+                click.echo(f"Migrating dataset {dataset.id}.")

                try:
                    vector.delete()
                    click.echo(
-                        click.style(
-                            f"Successfully delete vector index {collection_name} for dataset {dataset.id}.", fg="green"
-                        )
+                        click.style(f"Deleted vector index {collection_name} for dataset {dataset.id}.", fg="green")
                    )
                except Exception as e:
                    click.echo(
@@ -411,15 +408,13 @@ def migrate_knowledge_vector_database():
                    try:
                        click.echo(
                            click.style(
-                                f"Start to created vector index with {len(documents)} documents of {segments_count}"
+                                f"Creating vector index with {len(documents)} documents of {segments_count}"
                                f" segments for dataset {dataset.id}.",
                                fg="green",
                            )
                        )
                        vector.create(documents)
-                        click.echo(
-                            click.style(f"Successfully created vector index for dataset {dataset.id}.", fg="green")
-                        )
+                        click.echo(click.style(f"Created vector index for dataset {dataset.id}.", fg="green"))
                    except Exception as e:
                        click.echo(click.style(f"Failed to created vector index for dataset {dataset.id}.", fg="red"))
                        raise e
@@ -430,13 +425,13 @@ def migrate_knowledge_vector_database():
            except Exception as e:
                db.session.rollback()
                click.echo(
-                    click.style("Create dataset index error: {} {}".format(e.__class__.__name__, str(e)), fg="red")
+                    click.style("Error creating dataset index: {} {}".format(e.__class__.__name__, str(e)), fg="red")
                )
                continue

    click.echo(
        click.style(
-            f"Congratulations! Create {create_count} dataset indexes, and skipped {skipped_count} datasets.", fg="green"
+            f"Migration complete. Created {create_count} dataset indexes. Skipped {skipped_count} datasets.", fg="green"
        )
    )

@@ -446,7 +441,7 @@ def convert_to_agent_apps():
    """
    Convert Agent Assistant to Agent App.
    """
-    click.echo(click.style("Start convert to agent apps.", fg="green"))
+    click.echo(click.style("Starting convert to agent apps.", fg="green"))

    proceeded_app_ids = []

@@ -497,23 +492,23 @@ def convert_to_agent_apps():
            except Exception as e:
                click.echo(click.style("Convert app error: {} {}".format(e.__class__.__name__, str(e)), fg="red"))

-    click.echo(click.style("Congratulations! Converted {} agent apps.".format(len(proceeded_app_ids)), fg="green"))
+    click.echo(click.style("Conversion complete. Converted {} agent apps.".format(len(proceeded_app_ids)), fg="green"))


-@click.command("add-qdrant-doc-id-index", help="add qdrant doc_id index.")
-@click.option("--field", default="metadata.doc_id", prompt=False, help="index field , default is metadata.doc_id.")
+@click.command("add-qdrant-doc-id-index", help="Add Qdrant doc_id index.")
+@click.option("--field", default="metadata.doc_id", prompt=False, help="Index field , default is metadata.doc_id.")
 def add_qdrant_doc_id_index(field: str):
-    click.echo(click.style("Start add qdrant doc_id index.", fg="green"))
+    click.echo(click.style("Starting Qdrant doc_id index creation.", fg="green"))
    vector_type = dify_config.VECTOR_STORE
    if vector_type != "qdrant":
-        click.echo(click.style("Sorry, only support qdrant vector store.", fg="red"))
+        click.echo(click.style("This command only supports Qdrant vector store.", fg="red"))
        return
    create_count = 0

    try:
        bindings = db.session.query(DatasetCollectionBinding).all()
        if not bindings:
-            click.echo(click.style("Sorry, no dataset collection bindings found.", fg="red"))
+            click.echo(click.style("No dataset collection bindings found.", fg="red"))
            return
        import qdrant_client
        from qdrant_client.http.exceptions import UnexpectedResponse
@@ -523,7 +518,7 @@ def add_qdrant_doc_id_index(field: str):

        for binding in bindings:
            if dify_config.QDRANT_URL is None:
-                raise ValueError("Qdrant url is required.")
+                raise ValueError("Qdrant URL is required.")
            qdrant_config = QdrantConfig(
                endpoint=dify_config.QDRANT_URL,
                api_key=dify_config.QDRANT_API_KEY,
@@ -540,41 +535,39 @@ def add_qdrant_doc_id_index(field: str):
            except UnexpectedResponse as e:
                # Collection does not exist, so return
                if e.status_code == 404:
-                    click.echo(
-                        click.style(f"Collection not found, collection_name:{binding.collection_name}.", fg="red")
-                    )
+                    click.echo(click.style(f"Collection not found: {binding.collection_name}.", fg="red"))
                    continue
                # Some other error occurred, so re-raise the exception
                else:
                    click.echo(
                        click.style(
-                            f"Failed to create qdrant index, collection_name:{binding.collection_name}.", fg="red"
+                            f"Failed to create Qdrant index for collection: {binding.collection_name}.", fg="red"
                        )
                    )

    except Exception as e:
-        click.echo(click.style("Failed to create qdrant client.", fg="red"))
+        click.echo(click.style("Failed to create Qdrant client.", fg="red"))

-    click.echo(click.style(f"Congratulations! Create {create_count} collection indexes.", fg="green"))
+    click.echo(click.style(f"Index creation complete. Created {create_count} collection indexes.", fg="green"))


@click.command("create-tenant", help="Create account and tenant.")
-@click.option("--email", prompt=True, help="The email address of the tenant account.")
-@click.option("--name", prompt=True, help="The workspace name of the tenant account.")
+@click.option("--email", prompt=True, help="Tenant account email.")
+@click.option("--name", prompt=True, help="Workspace name.")
@click.option("--language", prompt=True, help="Account language, default: en-US.")
 def create_tenant(email: str, language: Optional[str] = None, name: Optional[str] = None):
    """
    Create tenant account
    """
    if not email:
-        click.echo(click.style("Sorry, email is required.", fg="red"))
+        click.echo(click.style("Email is required.", fg="red"))
        return

    # Create account
    email = email.strip()

    if "@" not in email:
-        click.echo(click.style("Sorry, invalid email address.", fg="red"))
+        click.echo(click.style("Invalid email address.", fg="red"))
        return

    account_name = email.split("@")[0]
@@ -594,19 +587,19 @@ def create_tenant(email: str, language: Optional[str] = None, name: Optional[str

    click.echo(
        click.style(
-            "Congratulations! Account and tenant created.\n" "Account: {}\nPassword: {}".format(email, new_password),
+            "Account and tenant created.\nAccount: {}\nPassword: {}".format(email, new_password),
            fg="green",
        )
    )


-@click.command("upgrade-db", help="upgrade the database")
+@click.command("upgrade-db", help="Upgrade the database")
 def upgrade_db():
    click.echo("Preparing database migration...")
    lock = redis_client.lock(name="db_upgrade_lock", timeout=60)
    if lock.acquire(blocking=False):
        try:
-            click.echo(click.style("Start database migration.", fg="green"))
+            click.echo(click.style("Starting database migration.", fg="green"))

            # run db migration
            import flask_migrate
@@ -616,7 +609,7 @@ def upgrade_db():
            click.echo(click.style("Database migration successful!", fg="green"))

        except Exception as e:
-            logging.exception(f"Database migration failed, error: {e}")
+            logging.exception(f"Database migration failed: {e}")
        finally:
            lock.release()
    else:
@@ -628,7 +621,7 @@ def fix_app_site_missing():
    """
    Fix app related site missing issue.
    """
-    click.echo(click.style("Start fix app related site missing issue.", fg="green"))
+    click.echo(click.style("Starting fix for missing app-related sites.", fg="green"))

    failed_app_ids = []
    while True:
@@ -651,22 +644,22 @@ where sites.id is null limit 1000"""
                    if tenant:
                        accounts = tenant.get_accounts()
                        if not accounts:
-                            print("Fix app {} failed.".format(app.id))
+                            print("Fix failed for app {}".format(app.id))
                            continue

                        account = accounts[0]
-                        print("Fix app {} related site missing issue.".format(app.id))
+                        print("Fixing missing site for app {}".format(app.id))
                        app_was_created.send(app, account=account)
                except Exception as e:
                    failed_app_ids.append(app_id)
-                    click.echo(click.style("Fix app {} related site missing issue failed!".format(app_id), fg="red"))
+                    click.echo(click.style("Failed to fix missing site for app {}".format(app_id), fg="red"))
                    logging.exception(f"Fix app related site missing issue failed, error: {e}")
                    continue

            if not processed_count:
                break

-    click.echo(click.style("Congratulations! Fix app related site missing issue successful!", fg="green"))
+    click.echo(click.style("Fix for missing app-related sites completed successfully!", fg="green"))


 def register_commands(app):
--- a/api/configs/deploy/init.py
+++ b/api/configs/deploy/init.py
@@ -4,30 +4,30 @@ from pydantic_settings import BaseSettings

 class DeploymentConfig(BaseSettings):
    """
-    Deployment configs
+    Configuration settings for application deployment
    """

    APPLICATION_NAME: str = Field(
-        description="application name",
+        description="Name of the application, used for identification and logging purposes",
        default="langgenius/dify",
    )

    DEBUG: bool = Field(
-        description="whether to enable debug mode.",
+        description="Enable debug mode for additional logging and development features",
        default=False,
    )

    TESTING: bool = Field(
-        description="",
+        description="Enable testing mode for running automated tests",
        default=False,
    )

    EDITION: str = Field(
-        description="deployment edition",
+        description="Deployment edition of the application (e.g., 'SELF_HOSTED', 'CLOUD')",
        default="SELF_HOSTED",
    )

    DEPLOY_ENV: str = Field(
-        description="deployment environment, default to PRODUCTION.",
+        description="Deployment environment (e.g., 'PRODUCTION', 'DEVELOPMENT'), default to PRODUCTION",
        default="PRODUCTION",
    )
--- a/api/configs/enterprise/init.py
+++ b/api/configs/enterprise/init.py
@@ -4,17 +4,17 @@ from pydantic_settings import BaseSettings

 class EnterpriseFeatureConfig(BaseSettings):
    """
-    Enterprise feature configs.
+    Configuration for enterprise-level features.
    **Before using, please contact business@dify.ai by email to inquire about licensing matters.**
    """

    ENTERPRISE_ENABLED: bool = Field(
-        description="whether to enable enterprise features."
+        description="Enable or disable enterprise-level features."
        "Before using, please contact business@dify.ai by email to inquire about licensing matters.",
        default=False,
    )

    CAN_REPLACE_LOGO: bool = Field(
-        description="whether to allow replacing enterprise logo.",
+        description="Allow customization of the enterprise logo.",
        default=False,
    )
--- a/api/configs/extra/notion_config.py
+++ b/api/configs/extra/notion_config.py
@@ -6,30 +6,31 @@ from pydantic_settings import BaseSettings

 class NotionConfig(BaseSettings):
    """
-    Notion integration configs
+    Configuration settings for Notion integration
    """

    NOTION_CLIENT_ID: Optional[str] = Field(
-        description="Notion client ID",
+        description="Client ID for Notion API authentication. Required for OAuth 2.0 flow.",
        default=None,
    )

    NOTION_CLIENT_SECRET: Optional[str] = Field(
-        description="Notion client secret key",
+        description="Client secret for Notion API authentication. Required for OAuth 2.0 flow.",
        default=None,
    )

    NOTION_INTEGRATION_TYPE: Optional[str] = Field(
-        description="Notion integration type, default to None, available values: internal.",
+        description="Type of Notion integration."
+        " Set to 'internal' for internal integrations, or None for public integrations.",
        default=None,
    )

    NOTION_INTERNAL_SECRET: Optional[str] = Field(
-        description="Notion internal secret key",
+        description="Secret key for internal Notion integrations. Required when NOTION_INTEGRATION_TYPE is 'internal'.",
        default=None,
    )

    NOTION_INTEGRATION_TOKEN: Optional[str] = Field(
-        description="Notion integration token",
+        description="Integration token for Notion API access. Used for direct API calls without OAuth flow.",
        default=None,
    )
--- a/api/configs/extra/sentry_config.py
+++ b/api/configs/extra/sentry_config.py
@@ -6,20 +6,23 @@ from pydantic_settings import BaseSettings

 class SentryConfig(BaseSettings):
    """
-    Sentry configs
+    Configuration settings for Sentry error tracking and performance monitoring
    """

    SENTRY_DSN: Optional[str] = Field(
-        description="Sentry DSN",
+        description="Sentry Data Source Name (DSN)."
+        " This is the unique identifier of your Sentry project, used to send events to the correct project.",
        default=None,
    )

    SENTRY_TRACES_SAMPLE_RATE: NonNegativeFloat = Field(
-        description="Sentry trace sample rate",
+        description="Sample rate for Sentry performance monitoring traces."
+        " Value between 0.0 and 1.0, where 1.0 means 100% of traces are sent to Sentry.",
        default=1.0,
    )

    SENTRY_PROFILES_SAMPLE_RATE: NonNegativeFloat = Field(
-        description="Sentry profiles sample rate",
+        description="Sample rate for Sentry profiling."
+        " Value between 0.0 and 1.0, where 1.0 means 100% of profiles are sent to Sentry.",
        default=1.0,
    )
--- a/api/configs/feature/init.py
+++ b/api/configs/feature/init.py
@@ -8,145 +8,143 @@ from configs.feature.hosted_service import HostedServiceConfig

 class SecurityConfig(BaseSettings):
    """
-    Secret Key configs
+    Security-related configurations for the application
    """

    SECRET_KEY: Optional[str] = Field(
-        description="Your App secret key will be used for securely signing the session cookie"
+        description="Secret key for secure session cookie signing."
        "Make sure you are changing this key for your deployment with a strong key."
-        "You can generate a strong key using `openssl rand -base64 42`."
-        "Alternatively you can set it with `SECRET_KEY` environment variable.",
+        "Generate a strong key using `openssl rand -base64 42` or set via the `SECRET_KEY` environment variable.",
        default=None,
    )

    RESET_PASSWORD_TOKEN_EXPIRY_HOURS: PositiveInt = Field(
-        description="Expiry time in hours for reset token",
+        description="Duration in hours for which a password reset token remains valid",
        default=24,
    )


 class AppExecutionConfig(BaseSettings):
    """
-    App Execution configs
+    Configuration parameters for application execution
    """

    APP_MAX_EXECUTION_TIME: PositiveInt = Field(
-        description="execution timeout in seconds for app execution",
+        description="Maximum allowed execution time for the application in seconds",
        default=1200,
    )
    APP_MAX_ACTIVE_REQUESTS: NonNegativeInt = Field(
-        description="max active request per app, 0 means unlimited",
+        description="Maximum number of concurrent active requests per app (0 for unlimited)",
        default=0,
    )


 class CodeExecutionSandboxConfig(BaseSettings):
    """
-    Code Execution Sandbox configs
+    Configuration for the code execution sandbox environment
    """

    CODE_EXECUTION_ENDPOINT: HttpUrl = Field(
-        description="endpoint URL of code execution service",
+        description="URL endpoint for the code execution service",
        default="http://sandbox:8194",
    )

    CODE_EXECUTION_API_KEY: str = Field(
-        description="API key for code execution service",
+        description="API key for accessing the code execution service",
        default="dify-sandbox",
    )

    CODE_EXECUTION_CONNECT_TIMEOUT: Optional[float] = Field(
-        description="connect timeout in seconds for code execution request",
+        description="Connection timeout in seconds for code execution requests",
        default=10.0,
    )

    CODE_EXECUTION_READ_TIMEOUT: Optional[float] = Field(
-        description="read timeout in seconds for code execution request",
+        description="Read timeout in seconds for code execution requests",
        default=60.0,
    )

    CODE_EXECUTION_WRITE_TIMEOUT: Optional[float] = Field(
-        description="write timeout in seconds for code execution request",
+        description="Write timeout in seconds for code execution request",
        default=10.0,
    )

    CODE_MAX_NUMBER: PositiveInt = Field(
-        description="max depth for code execution",
+        description="Maximum allowed numeric value in code execution",
        default=9223372036854775807,
    )

    CODE_MIN_NUMBER: NegativeInt = Field(
-        description="",
+        description="Minimum allowed numeric value in code execution",
        default=-9223372036854775807,
    )

    CODE_MAX_DEPTH: PositiveInt = Field(
-        description="max depth for code execution",
+        description="Maximum allowed depth for nested structures in code execution",
        default=5,
    )

    CODE_MAX_PRECISION: PositiveInt = Field(
-        description="max precision digits for float type in code execution",
+        description="mMaximum number of decimal places for floating-point numbers in code execution",
        default=20,
    )

    CODE_MAX_STRING_LENGTH: PositiveInt = Field(
-        description="max string length for code execution",
+        description="Maximum allowed length for strings in code execution",
        default=80000,
    )

    CODE_MAX_STRING_ARRAY_LENGTH: PositiveInt = Field(
-        description="",
+        description="Maximum allowed length for string arrays in code execution",
        default=30,
    )

    CODE_MAX_OBJECT_ARRAY_LENGTH: PositiveInt = Field(
-        description="",
+        description="Maximum allowed length for object arrays in code execution",
        default=30,
    )

    CODE_MAX_NUMBER_ARRAY_LENGTH: PositiveInt = Field(
-        description="",
+        description="Maximum allowed length for numeric arrays in code execution",
        default=1000,
    )


 class EndpointConfig(BaseSettings):
    """
-    Module URL configs
+    Configuration for various application endpoints and URLs
    """

    CONSOLE_API_URL: str = Field(
-        description="The backend URL prefix of the console API."
-        "used to concatenate the login authorization callback or notion integration callback.",
+        description="Base URL for the console API,"
+        "used for login authentication callback or notion integration callbacks",
        default="",
    )

    CONSOLE_WEB_URL: str = Field(
-        description="The front-end URL prefix of the console web."
-        "used to concatenate some front-end addresses and for CORS configuration use.",
+        description="Base URL for the console web interface," "used for frontend references and CORS configuration",
        default="",
    )

    SERVICE_API_URL: str = Field(
-        description="Service API Url prefix." "used to display Service API Base Url to the front-end.",
+        description="Base URL for the service API, displayed to users for API access",
        default="",
    )

    APP_WEB_URL: str = Field(
-        description="WebApp Url prefix." "used to display WebAPP API Base Url to the front-end.",
+        description="Base URL for the web application, used for frontend references",
        default="",
    )


 class FileAccessConfig(BaseSettings):
    """
-    File Access configs
+    Configuration for file access and handling
    """

    FILES_URL: str = Field(
-        description="File preview or download Url prefix."
-        " used to display File preview or download Url to the front-end or as Multi-model inputs;"
+        description="Base URL for file preview or download,"
+        " used for frontend display and multi-model inputs"
        "Url is signed and has expiration time.",
        validation_alias=AliasChoices("FILES_URL", "CONSOLE_API_URL"),
        alias_priority=1,
@@ -154,49 +152,49 @@ class FileAccessConfig(BaseSettings):
    )

    FILES_ACCESS_TIMEOUT: int = Field(
-        description="timeout in seconds for file accessing",
+        description="Expiration time in seconds for file access URLs",
        default=300,
    )


 class FileUploadConfig(BaseSettings):
    """
-    File Uploading configs
+    Configuration for file upload limitations
    """

    UPLOAD_FILE_SIZE_LIMIT: NonNegativeInt = Field(
-        description="size limit in Megabytes for uploading files",
+        description="Maximum allowed file size for uploads in megabytes",
        default=15,
    )

    UPLOAD_FILE_BATCH_LIMIT: NonNegativeInt = Field(
-        description="batch size limit for uploading files",
+        description="Maximum number of files allowed in a single upload batch",
        default=5,
    )

    UPLOAD_IMAGE_FILE_SIZE_LIMIT: NonNegativeInt = Field(
-        description="image file size limit in Megabytes for uploading files",
+        description="Maximum allowed image file size for uploads in megabytes",
        default=10,
    )

    BATCH_UPLOAD_LIMIT: NonNegativeInt = Field(
-        description="",  # todo: to be clarified
+        description="Maximum number of files allowed in a batch upload operation",
        default=20,
    )


 class HttpConfig(BaseSettings):
    """
-    HTTP configs
+    HTTP-related configurations for the application
    """

    API_COMPRESSION_ENABLED: bool = Field(
-        description="whether to enable HTTP response compression of gzip",
+        description="Enable or disable gzip compression for HTTP responses",
        default=False,
    )

    inner_CONSOLE_CORS_ALLOW_ORIGINS: str = Field(
-        description="",
+        description="Comma-separated list of allowed origins for CORS in the console",
        validation_alias=AliasChoices("CONSOLE_CORS_ALLOW_ORIGINS", "CONSOLE_WEB_URL"),
        default="",
    )
@@ -218,359 +216,366 @@ class HttpConfig(BaseSettings):
        return self.inner_WEB_API_CORS_ALLOW_ORIGINS.split(",")

    HTTP_REQUEST_MAX_CONNECT_TIMEOUT: Annotated[
-        PositiveInt, Field(ge=10, description="connect timeout in seconds for HTTP request")
+        PositiveInt, Field(ge=10, description="Maximum connection timeout in seconds for HTTP requests")
    ] = 10

    HTTP_REQUEST_MAX_READ_TIMEOUT: Annotated[
-        PositiveInt, Field(ge=60, description="read timeout in seconds for HTTP request")
+        PositiveInt, Field(ge=60, description="Maximum read timeout in seconds for HTTP requests")
    ] = 60

    HTTP_REQUEST_MAX_WRITE_TIMEOUT: Annotated[
-        PositiveInt, Field(ge=10, description="read timeout in seconds for HTTP request")
+        PositiveInt, Field(ge=10, description="Maximum write timeout in seconds for HTTP requests")
    ] = 20

    HTTP_REQUEST_NODE_MAX_BINARY_SIZE: PositiveInt = Field(
-        description="",
+        description="Maximum allowed size in bytes for binary data in HTTP requests",
        default=10 * 1024 * 1024,
    )

    HTTP_REQUEST_NODE_MAX_TEXT_SIZE: PositiveInt = Field(
-        description="",
+        description="Maximum allowed size in bytes for text data in HTTP requests",
        default=1 * 1024 * 1024,
    )

    SSRF_PROXY_HTTP_URL: Optional[str] = Field(
-        description="HTTP URL for SSRF proxy",
+        description="Proxy URL for HTTP requests to prevent Server-Side Request Forgery (SSRF)",
        default=None,
    )

    SSRF_PROXY_HTTPS_URL: Optional[str] = Field(
-        description="HTTPS URL for SSRF proxy",
+        description="Proxy URL for HTTPS requests to prevent Server-Side Request Forgery (SSRF)",
        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):
    """
-    Inner API configs
+    Configuration for internal API functionality
    """

    INNER_API: bool = Field(
-        description="whether to enable the inner API",
+        description="Enable or disable the internal API",
        default=False,
    )

    INNER_API_KEY: Optional[str] = Field(
-        description="The inner API key is used to authenticate the inner API",
+        description="API key for accessing the internal API",
        default=None,
    )


 class LoggingConfig(BaseSettings):
    """
-    Logging configs
+    Configuration for application logging
    """

    LOG_LEVEL: str = Field(
-        description="Log output level, default to INFO." "It is recommended to set it to ERROR for production.",
+        description="Logging level, default to INFO. Set to ERROR for production environments.",
        default="INFO",
    )

    LOG_FILE: Optional[str] = Field(
-        description="logging output file path",
+        description="File path for log output.",
        default=None,
    )

    LOG_FORMAT: str = Field(
-        description="log format",
+        description="Format string for log messages",
        default="%(asctime)s.%(msecs)03d %(levelname)s [%(threadName)s] [%(filename)s:%(lineno)d] - %(message)s",
    )

    LOG_DATEFORMAT: Optional[str] = Field(
-        description="log date format",
+        description="Date format string for log timestamps",
        default=None,
    )

    LOG_TZ: Optional[str] = Field(
-        description="specify log timezone, eg: America/New_York",
+        description="Timezone for log timestamps (e.g., 'America/New_York')",
        default=None,
    )


 class ModelLoadBalanceConfig(BaseSettings):
    """
-    Model load balance configs
+    Configuration for model load balancing
    """

    MODEL_LB_ENABLED: bool = Field(
-        description="whether to enable model load balancing",
+        description="Enable or disable load balancing for models",
        default=False,
    )


 class BillingConfig(BaseSettings):
    """
-    Platform Billing Configurations
+    Configuration for platform billing features
    """

    BILLING_ENABLED: bool = Field(
-        description="whether to enable billing",
+        description="Enable or disable billing functionality",
        default=False,
    )


 class UpdateConfig(BaseSettings):
    """
-    Update configs
+    Configuration for application update checks
    """

    CHECK_UPDATE_URL: str = Field(
-        description="url for checking updates",
+        description="URL to check for application updates",
        default="https://updates.dify.ai",
    )


 class WorkflowConfig(BaseSettings):
    """
-    Workflow feature configs
+    Configuration for workflow execution
    """

    WORKFLOW_MAX_EXECUTION_STEPS: PositiveInt = Field(
-        description="max execution steps in single workflow execution",
+        description="Maximum number of steps allowed in a single workflow execution",
        default=500,
    )

    WORKFLOW_MAX_EXECUTION_TIME: PositiveInt = Field(
-        description="max execution time in seconds in single workflow execution",
+        description="Maximum execution time in seconds for a single workflow",
        default=1200,
    )

    WORKFLOW_CALL_MAX_DEPTH: PositiveInt = Field(
-        description="max depth of calling in single workflow execution",
+        description="Maximum allowed depth for nested workflow calls",
        default=5,
    )

    MAX_VARIABLE_SIZE: PositiveInt = Field(
-        description="The maximum size in bytes of a variable. default to 5KB.",
+        description="Maximum size in bytes for a single variable in workflows. Default to 5KB.",
        default=5 * 1024,
    )


 class OAuthConfig(BaseSettings):
    """
-    oauth configs
+    Configuration for OAuth authentication
    """

    OAUTH_REDIRECT_PATH: str = Field(
-        description="redirect path for OAuth",
+        description="Redirect path for OAuth authentication callbacks",
        default="/console/api/oauth/authorize",
    )

    GITHUB_CLIENT_ID: Optional[str] = Field(
-        description="GitHub client id for OAuth",
+        description="GitHub OAuth client secret",
        default=None,
    )

    GITHUB_CLIENT_SECRET: Optional[str] = Field(
-        description="GitHub client secret key for OAuth",
+        description="GitHub OAuth client secret",
        default=None,
    )

    GOOGLE_CLIENT_ID: Optional[str] = Field(
-        description="Google client id for OAuth",
+        description="Google OAuth client ID",
        default=None,
    )

    GOOGLE_CLIENT_SECRET: Optional[str] = Field(
-        description="Google client secret key for OAuth",
+        description="Google OAuth client secret",
        default=None,
    )


 class ModerationConfig(BaseSettings):
    """
-    Moderation in app configs.
+    Configuration for content moderation
    """

    MODERATION_BUFFER_SIZE: PositiveInt = Field(
-        description="buffer size for moderation",
+        description="Size of the buffer for content moderation processing",
        default=300,
    )


 class ToolConfig(BaseSettings):
    """
-    Tool configs
+    Configuration for tool management
    """

    TOOL_ICON_CACHE_MAX_AGE: PositiveInt = Field(
-        description="max age in seconds for tool icon caching",
+        description="Maximum age in seconds for caching tool icons",
        default=3600,
    )


 class MailConfig(BaseSettings):
    """
-    Mail Configurations
+    Configuration for email services
    """

    MAIL_TYPE: Optional[str] = Field(
-        description="Mail provider type name, default to None, available values are `smtp` and `resend`.",
+        description="Email service provider type ('smtp' or 'resend'), default to None.",
        default=None,
    )

    MAIL_DEFAULT_SEND_FROM: Optional[str] = Field(
-        description="default email address for sending from ",
+        description="Default email address to use as the sender",
        default=None,
    )

    RESEND_API_KEY: Optional[str] = Field(
-        description="API key for Resend",
+        description="API key for Resend email service",
        default=None,
    )

    RESEND_API_URL: Optional[str] = Field(
-        description="API URL for Resend",
+        description="API URL for Resend email service",
        default=None,
    )

    SMTP_SERVER: Optional[str] = Field(
-        description="smtp server host",
+        description="SMTP server hostname",
        default=None,
    )

    SMTP_PORT: Optional[int] = Field(
-        description="smtp server port",
+        description="SMTP server port number",
        default=465,
    )

    SMTP_USERNAME: Optional[str] = Field(
-        description="smtp server username",
+        description="Username for SMTP authentication",
        default=None,
    )

    SMTP_PASSWORD: Optional[str] = Field(
-        description="smtp server password",
+        description="Password for SMTP authentication",
        default=None,
    )

    SMTP_USE_TLS: bool = Field(
-        description="whether to use TLS connection to smtp server",
+        description="Enable TLS encryption for SMTP connections",
        default=False,
    )

    SMTP_OPPORTUNISTIC_TLS: bool = Field(
-        description="whether to use opportunistic TLS connection to smtp server",
+        description="Enable opportunistic TLS for SMTP connections",
        default=False,
    )


 class RagEtlConfig(BaseSettings):
    """
-    RAG ETL Configurations.
+    Configuration for RAG ETL processes
    """

    ETL_TYPE: str = Field(
-        description="RAG ETL type name, default to `dify`, available values are `dify` and `Unstructured`. ",
+        description="RAG ETL type ('dify' or 'Unstructured'), default to 'dify'",
        default="dify",
    )

    KEYWORD_DATA_SOURCE_TYPE: str = Field(
-        description="source type for keyword data, default to `database`, available values are `database` .",
+        description="Data source type for keyword extraction"
+        " ('database' or other supported types), default to 'database'",
        default="database",
    )

    UNSTRUCTURED_API_URL: Optional[str] = Field(
-        description="API URL for Unstructured",
+        description="API URL for Unstructured.io service",
        default=None,
    )

    UNSTRUCTURED_API_KEY: Optional[str] = Field(
-        description="API key for Unstructured",
+        description="API key for Unstructured.io service",
        default=None,
    )


 class DataSetConfig(BaseSettings):
    """
-    Dataset configs
+    Configuration for dataset management
    """

    CLEAN_DAY_SETTING: PositiveInt = Field(
-        description="interval in days for cleaning up dataset",
+        description="Interval in days for dataset cleanup operations",
        default=30,
    )

    DATASET_OPERATOR_ENABLED: bool = Field(
-        description="whether to enable dataset operator",
+        description="Enable or disable dataset operator functionality",
        default=False,
    )


 class WorkspaceConfig(BaseSettings):
    """
-    Workspace configs
+    Configuration for workspace management
    """

    INVITE_EXPIRY_HOURS: PositiveInt = Field(
-        description="workspaces invitation expiration in hours",
+        description="Expiration time in hours for workspace invitation links",
        default=72,
    )


 class IndexingConfig(BaseSettings):
    """
-    Indexing configs.
+    Configuration for indexing operations
    """

    INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH: PositiveInt = Field(
-        description="max segmentation token length for indexing",
+        description="Maximum token length for text segmentation during indexing",
        default=1000,
    )


 class ImageFormatConfig(BaseSettings):
    MULTIMODAL_SEND_IMAGE_FORMAT: str = Field(
-        description="multi model send image format, support base64, url, default is base64",
+        description="Format for sending images in multimodal contexts ('base64' or 'url'), default is base64",
        default="base64",
    )


 class CeleryBeatConfig(BaseSettings):
    CELERY_BEAT_SCHEDULER_TIME: int = Field(
-        description="the time of the celery scheduler, default to 1 day",
+        description="Interval in days for Celery Beat scheduler execution, default to 1 day",
        default=1,
    )


 class PositionConfig(BaseSettings):
    POSITION_PROVIDER_PINS: str = Field(
-        description="The heads of model providers",
+        description="Comma-separated list of pinned model providers",
        default="",
    )

    POSITION_PROVIDER_INCLUDES: str = Field(
-        description="The included model providers",
+        description="Comma-separated list of included model providers",
        default="",
    )

    POSITION_PROVIDER_EXCLUDES: str = Field(
-        description="The excluded model providers",
+        description="Comma-separated list of excluded model providers",
        default="",
    )

    POSITION_TOOL_PINS: str = Field(
-        description="The heads of tools",
+        description="Comma-separated list of pinned tools",
        default="",
    )

    POSITION_TOOL_INCLUDES: str = Field(
-        description="The included tools",
+        description="Comma-separated list of included tools",
        default="",
    )

    POSITION_TOOL_EXCLUDES: str = Field(
-        description="The excluded tools",
+        description="Comma-separated list of excluded tools",
        default="",
    )

--- a/api/configs/feature/hosted_service/init.py
+++ b/api/configs/feature/hosted_service/init.py
@@ -6,31 +6,31 @@ from pydantic_settings import BaseSettings

 class HostedOpenAiConfig(BaseSettings):
    """
-    Hosted OpenAI service config
+    Configuration for hosted OpenAI service
    """

    HOSTED_OPENAI_API_KEY: Optional[str] = Field(
-        description="",
+        description="API key for hosted OpenAI service",
        default=None,
    )

    HOSTED_OPENAI_API_BASE: Optional[str] = Field(
-        description="",
+        description="Base URL for hosted OpenAI API",
        default=None,
    )

    HOSTED_OPENAI_API_ORGANIZATION: Optional[str] = Field(
-        description="",
+        description="Organization ID for hosted OpenAI service",
        default=None,
    )

    HOSTED_OPENAI_TRIAL_ENABLED: bool = Field(
-        description="",
+        description="Enable trial access to hosted OpenAI service",
        default=False,
    )

    HOSTED_OPENAI_TRIAL_MODELS: str = Field(
-        description="",
+        description="Comma-separated list of available models for trial access",
        default="gpt-3.5-turbo,"
        "gpt-3.5-turbo-1106,"
        "gpt-3.5-turbo-instruct,"
@@ -42,17 +42,17 @@ class HostedOpenAiConfig(BaseSettings):
    )

    HOSTED_OPENAI_QUOTA_LIMIT: NonNegativeInt = Field(
-        description="",
+        description="Quota limit for hosted OpenAI service usage",
        default=200,
    )

    HOSTED_OPENAI_PAID_ENABLED: bool = Field(
-        description="",
+        description="Enable paid access to hosted OpenAI service",
        default=False,
    )

    HOSTED_OPENAI_PAID_MODELS: str = Field(
-        description="",
+        description="Comma-separated list of available models for paid access",
        default="gpt-4,"
        "gpt-4-turbo-preview,"
        "gpt-4-turbo-2024-04-09,"
@@ -71,124 +71,122 @@ class HostedOpenAiConfig(BaseSettings):

 class HostedAzureOpenAiConfig(BaseSettings):
    """
-    Hosted OpenAI service config
+    Configuration for hosted Azure OpenAI service
    """

    HOSTED_AZURE_OPENAI_ENABLED: bool = Field(
-        description="",
+        description="Enable hosted Azure OpenAI service",
        default=False,
    )

    HOSTED_AZURE_OPENAI_API_KEY: Optional[str] = Field(
-        description="",
+        description="API key for hosted Azure OpenAI service",
        default=None,
    )

    HOSTED_AZURE_OPENAI_API_BASE: Optional[str] = Field(
-        description="",
+        description="Base URL for hosted Azure OpenAI API",
        default=None,
    )

    HOSTED_AZURE_OPENAI_QUOTA_LIMIT: NonNegativeInt = Field(
-        description="",
+        description="Quota limit for hosted Azure OpenAI service usage",
        default=200,
    )


 class HostedAnthropicConfig(BaseSettings):
    """
-    Hosted Azure OpenAI service config
+    Configuration for hosted Anthropic service
    """

    HOSTED_ANTHROPIC_API_BASE: Optional[str] = Field(
-        description="",
+        description="Base URL for hosted Anthropic API",
        default=None,
    )

    HOSTED_ANTHROPIC_API_KEY: Optional[str] = Field(
-        description="",
+        description="API key for hosted Anthropic service",
        default=None,
    )

    HOSTED_ANTHROPIC_TRIAL_ENABLED: bool = Field(
-        description="",
+        description="Enable trial access to hosted Anthropic service",
        default=False,
    )

    HOSTED_ANTHROPIC_QUOTA_LIMIT: NonNegativeInt = Field(
-        description="",
+        description="Quota limit for hosted Anthropic service usage",
        default=600000,
    )

    HOSTED_ANTHROPIC_PAID_ENABLED: bool = Field(
-        description="",
+        description="Enable paid access to hosted Anthropic service",
        default=False,
    )


 class HostedMinmaxConfig(BaseSettings):
    """
-    Hosted Minmax service config
+    Configuration for hosted Minmax service
    """

    HOSTED_MINIMAX_ENABLED: bool = Field(
-        description="",
+        description="Enable hosted Minmax service",
        default=False,
    )


 class HostedSparkConfig(BaseSettings):
    """
-    Hosted Spark service config
+    Configuration for hosted Spark service
    """

    HOSTED_SPARK_ENABLED: bool = Field(
-        description="",
+        description="Enable hosted Spark service",
        default=False,
    )


 class HostedZhipuAIConfig(BaseSettings):
    """
-    Hosted Minmax service config
+    Configuration for hosted ZhipuAI service
    """

    HOSTED_ZHIPUAI_ENABLED: bool = Field(
-        description="",
+        description="Enable hosted ZhipuAI service",
        default=False,
    )


 class HostedModerationConfig(BaseSettings):
    """
-    Hosted Moderation service config
+    Configuration for hosted Moderation service
    """

    HOSTED_MODERATION_ENABLED: bool = Field(
-        description="",
+        description="Enable hosted Moderation service",
        default=False,
    )

    HOSTED_MODERATION_PROVIDERS: str = Field(
-        description="",
+        description="Comma-separated list of moderation providers",
        default="",
    )


 class HostedFetchAppTemplateConfig(BaseSettings):
    """
-    Hosted Moderation service config
+    Configuration for fetching app templates
    """

    HOSTED_FETCH_APP_TEMPLATES_MODE: str = Field(
-        description="the mode for fetching app templates,"
-        " default to remote,"
-        " available values: remote, db, builtin",
+        description="Mode for fetching app templates: remote, db, or builtin" " default to remote,",
        default="remote",
    )

    HOSTED_FETCH_APP_TEMPLATES_REMOTE_DOMAIN: str = Field(
-        description="the domain for fetching remote app templates",
+        description="Domain for fetching remote app templates",
        default="https://tmpl.dify.ai",
    )

--- a/api/configs/middleware/init.py
+++ b/api/configs/middleware/init.py
@@ -8,6 +8,7 @@ from configs.middleware.cache.redis_config import RedisConfig
 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
@@ -31,70 +32,71 @@ from configs.middleware.vdb.weaviate_config import WeaviateConfig

 class StorageConfig(BaseSettings):
    STORAGE_TYPE: str = Field(
-        description="storage type,"
-        " default to `local`,"
-        " available values are `local`, `s3`, `azure-blob`, `aliyun-oss`, `google-storage`.",
+        description="Type of storage to use."
+        " Options: 'local', 's3', 'azure-blob', 'aliyun-oss', 'google-storage'. Default is 'local'.",
        default="local",
    )

    STORAGE_LOCAL_PATH: str = Field(
-        description="local storage path",
+        description="Path for local storage when STORAGE_TYPE is set to 'local'.",
        default="storage",
    )


 class VectorStoreConfig(BaseSettings):
    VECTOR_STORE: Optional[str] = Field(
-        description="vector store type",
+        description="Type of vector store to use for efficient similarity search."
+        " Set to None if not using a vector store.",
        default=None,
    )


 class KeywordStoreConfig(BaseSettings):
    KEYWORD_STORE: str = Field(
-        description="keyword store type",
+        description="Method for keyword extraction and storage."
+        " Default is 'jieba', a Chinese text segmentation library.",
        default="jieba",
    )


 class DatabaseConfig:
    DB_HOST: str = Field(
-        description="db host",
+        description="Hostname or IP address of the database server.",
        default="localhost",
    )

    DB_PORT: PositiveInt = Field(
-        description="db port",
+        description="Port number for database connection.",
        default=5432,
    )

    DB_USERNAME: str = Field(
-        description="db username",
+        description="Username for database authentication.",
        default="postgres",
    )

    DB_PASSWORD: str = Field(
-        description="db password",
+        description="Password for database authentication.",
        default="",
    )

    DB_DATABASE: str = Field(
-        description="db database",
+        description="Name of the database to connect to.",
        default="dify",
    )

    DB_CHARSET: str = Field(
-        description="db charset",
+        description="Character set for database connection.",
        default="",
    )

    DB_EXTRAS: str = Field(
-        description="db extras options. Example: keepalives_idle=60&keepalives=1",
+        description="Additional database connection parameters. Example: 'keepalives_idle=60&keepalives=1'",
        default="",
    )

    SQLALCHEMY_DATABASE_URI_SCHEME: str = Field(
-        description="db uri scheme",
+        description="Database URI scheme for SQLAlchemy connection.",
        default="postgresql",
    )

@@ -112,27 +114,27 @@ class DatabaseConfig:
        )

    SQLALCHEMY_POOL_SIZE: NonNegativeInt = Field(
-        description="pool size of SqlAlchemy",
+        description="Maximum number of database connections in the pool.",
        default=30,
    )

    SQLALCHEMY_MAX_OVERFLOW: NonNegativeInt = Field(
-        description="max overflows for SqlAlchemy",
+        description="Maximum number of connections that can be created beyond the pool_size.",
        default=10,
    )

    SQLALCHEMY_POOL_RECYCLE: NonNegativeInt = Field(
-        description="SqlAlchemy pool recycle",
+        description="Number of seconds after which a connection is automatically recycled.",
        default=3600,
    )

    SQLALCHEMY_POOL_PRE_PING: bool = Field(
-        description="whether to enable pool pre-ping in SqlAlchemy",
+        description="If True, enables connection pool pre-ping feature to check connections.",
        default=False,
    )

    SQLALCHEMY_ECHO: bool | str = Field(
-        description="whether to enable SqlAlchemy echo",
+        description="If True, SQLAlchemy will log all SQL statements.",
        default=False,
    )

@@ -150,27 +152,27 @@ class DatabaseConfig:

 class CeleryConfig(DatabaseConfig):
    CELERY_BACKEND: str = Field(
-        description="Celery backend, available values are `database`, `redis`",
+        description="Backend for Celery task results. Options: 'database', 'redis'.",
        default="database",
    )

    CELERY_BROKER_URL: Optional[str] = Field(
-        description="CELERY_BROKER_URL",
+        description="URL of the message broker for Celery tasks.",
        default=None,
    )

    CELERY_USE_SENTINEL: Optional[bool] = Field(
-        description="Whether to use Redis Sentinel mode",
+        description="Whether to use Redis Sentinel for high availability.",
        default=False,
    )

    CELERY_SENTINEL_MASTER_NAME: Optional[str] = Field(
-        description="Redis Sentinel master name",
+        description="Name of the Redis Sentinel master.",
        default=None,
    )

    CELERY_SENTINEL_SOCKET_TIMEOUT: Optional[PositiveFloat] = Field(
-        description="Redis Sentinel socket timeout",
+        description="Timeout for Redis Sentinel socket operations in seconds.",
        default=0.1,
    )

@@ -189,6 +191,22 @@ 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,
@@ -199,12 +217,13 @@ class MiddlewareConfig(
    StorageConfig,
    AliyunOSSStorageConfig,
    AzureBlobStorageConfig,
+    BaiduOBSStorageConfig,
    GoogleCloudStorageConfig,
-    TencentCloudCOSStorageConfig,
    HuaweiCloudOBSStorageConfig,
-    VolcengineTOSStorageConfig,
-    S3StorageConfig,
    OCIStorageConfig,
+    S3StorageConfig,
+    TencentCloudCOSStorageConfig,
+    VolcengineTOSStorageConfig,
    # configs of vdb and vdb providers
    VectorStoreConfig,
    AnalyticdbConfig,
@@ -221,5 +240,6 @@ class MiddlewareConfig(
    TiDBVectorConfig,
    WeaviateConfig,
    ElasticsearchConfig,
+    InternalTestConfig,
 ):
    pass
--- a/api/configs/middleware/cache/redis_config.py
+++ b/api/configs/middleware/cache/redis_config.py
@@ -6,65 +6,65 @@ from pydantic_settings import BaseSettings

 class RedisConfig(BaseSettings):
    """
-    Redis configs
+    Configuration settings for Redis connection
    """

    REDIS_HOST: str = Field(
-        description="Redis host",
+        description="Hostname or IP address of the Redis server",
        default="localhost",
    )

    REDIS_PORT: PositiveInt = Field(
-        description="Redis port",
+        description="Port number on which the Redis server is listening",
        default=6379,
    )

    REDIS_USERNAME: Optional[str] = Field(
-        description="Redis username",
+        description="Username for Redis authentication (if required)",
        default=None,
    )

    REDIS_PASSWORD: Optional[str] = Field(
-        description="Redis password",
+        description="Password for Redis authentication (if required)",
        default=None,
    )

    REDIS_DB: NonNegativeInt = Field(
-        description="Redis database id, default to 0",
+        description="Redis database number to use (0-15)",
        default=0,
    )

    REDIS_USE_SSL: bool = Field(
-        description="whether to use SSL for Redis connection",
+        description="Enable SSL/TLS for the Redis connection",
        default=False,
    )

    REDIS_USE_SENTINEL: Optional[bool] = Field(
-        description="Whether to use Redis Sentinel mode",
+        description="Enable Redis Sentinel mode for high availability",
        default=False,
    )

    REDIS_SENTINELS: Optional[str] = Field(
-        description="Redis Sentinel nodes",
+        description="Comma-separated list of Redis Sentinel nodes (host:port)",
        default=None,
    )

    REDIS_SENTINEL_SERVICE_NAME: Optional[str] = Field(
-        description="Redis Sentinel service name",
+        description="Name of the Redis Sentinel service to monitor",
        default=None,
    )

    REDIS_SENTINEL_USERNAME: Optional[str] = Field(
-        description="Redis Sentinel username",
+        description="Username for Redis Sentinel authentication (if required)",
        default=None,
    )

    REDIS_SENTINEL_PASSWORD: Optional[str] = Field(
-        description="Redis Sentinel password",
+        description="Password for Redis Sentinel authentication (if required)",
        default=None,
    )

    REDIS_SENTINEL_SOCKET_TIMEOUT: Optional[PositiveFloat] = Field(
-        description="Redis Sentinel socket timeout",
+        description="Socket timeout in seconds for Redis Sentinel connections",
        default=0.1,
    )
--- a/api/configs/middleware/storage/aliyun_oss_storage_config.py
+++ b/api/configs/middleware/storage/aliyun_oss_storage_config.py
@@ -6,40 +6,40 @@ from pydantic_settings import BaseSettings

 class AliyunOSSStorageConfig(BaseSettings):
    """
-    Aliyun storage configs
+    Configuration settings for Aliyun Object Storage Service (OSS)
    """

    ALIYUN_OSS_BUCKET_NAME: Optional[str] = Field(
-        description="Aliyun OSS bucket name",
+        description="Name of the Aliyun OSS bucket to store and retrieve objects",
        default=None,
    )

    ALIYUN_OSS_ACCESS_KEY: Optional[str] = Field(
-        description="Aliyun OSS access key",
+        description="Access key ID for authenticating with Aliyun OSS",
        default=None,
    )

    ALIYUN_OSS_SECRET_KEY: Optional[str] = Field(
-        description="Aliyun OSS secret key",
+        description="Secret access key for authenticating with Aliyun OSS",
        default=None,
    )

    ALIYUN_OSS_ENDPOINT: Optional[str] = Field(
-        description="Aliyun OSS endpoint URL",
+        description="URL of the Aliyun OSS endpoint for your chosen region",
        default=None,
    )

    ALIYUN_OSS_REGION: Optional[str] = Field(
-        description="Aliyun OSS region",
+        description="Aliyun OSS region where your bucket is located (e.g., 'oss-cn-hangzhou')",
        default=None,
    )

    ALIYUN_OSS_AUTH_VERSION: Optional[str] = Field(
-        description="Aliyun OSS authentication version",
+        description="Version of the authentication protocol to use with Aliyun OSS (e.g., 'v4')",
        default=None,
    )

    ALIYUN_OSS_PATH: Optional[str] = Field(
-        description="Aliyun OSS path",
+        description="Base path within the bucket to store objects (e.g., 'my-app-data/')",
        default=None,
    )
--- a/api/configs/middleware/storage/amazon_s3_storage_config.py
+++ b/api/configs/middleware/storage/amazon_s3_storage_config.py
@@ -6,40 +6,40 @@ from pydantic_settings import BaseSettings

 class S3StorageConfig(BaseSettings):
    """
-    S3 storage configs
+    Configuration settings for S3-compatible object storage
    """

    S3_ENDPOINT: Optional[str] = Field(
-        description="S3 storage endpoint",
+        description="URL of the S3-compatible storage endpoint (e.g., 'https://s3.amazonaws.com')",
        default=None,
    )

    S3_REGION: Optional[str] = Field(
-        description="S3 storage region",
+        description="Region where the S3 bucket is located (e.g., 'us-east-1')",
        default=None,
    )

    S3_BUCKET_NAME: Optional[str] = Field(
-        description="S3 storage bucket name",
+        description="Name of the S3 bucket to store and retrieve objects",
        default=None,
    )

    S3_ACCESS_KEY: Optional[str] = Field(
-        description="S3 storage access key",
+        description="Access key ID for authenticating with the S3 service",
        default=None,
    )

    S3_SECRET_KEY: Optional[str] = Field(
-        description="S3 storage secret key",
+        description="Secret access key for authenticating with the S3 service",
        default=None,
    )

    S3_ADDRESS_STYLE: str = Field(
-        description="S3 storage address style",
+        description="S3 addressing style: 'auto', 'path', or 'virtual'",
        default="auto",
    )

    S3_USE_AWS_MANAGED_IAM: bool = Field(
-        description="whether to use aws managed IAM for S3",
+        description="Use AWS managed IAM roles for authentication instead of access/secret keys",
        default=False,
    )
--- a/api/configs/middleware/storage/azure_blob_storage_config.py
+++ b/api/configs/middleware/storage/azure_blob_storage_config.py
@@ -6,25 +6,25 @@ from pydantic_settings import BaseSettings

 class AzureBlobStorageConfig(BaseSettings):
    """
-    Azure Blob storage configs
+    Configuration settings for Azure Blob Storage
    """

    AZURE_BLOB_ACCOUNT_NAME: Optional[str] = Field(
-        description="Azure Blob account name",
+        description="Name of the Azure Storage account (e.g., 'mystorageaccount')",
        default=None,
    )

    AZURE_BLOB_ACCOUNT_KEY: Optional[str] = Field(
-        description="Azure Blob account key",
+        description="Access key for authenticating with the Azure Storage account",
        default=None,
    )

    AZURE_BLOB_CONTAINER_NAME: Optional[str] = Field(
-        description="Azure Blob container name",
+        description="Name of the Azure Blob container to store and retrieve objects",
        default=None,
    )

    AZURE_BLOB_ACCOUNT_URL: Optional[str] = Field(
-        description="Azure Blob account URL",
+        description="URL of the Azure Blob storage endpoint (e.g., 'https://mystorageaccount.blob.core.windows.net')",
        default=None,
    )
--- a/api/configs/middleware/storage/baidu_obs_storage_config.py
+++ b/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,
+    )
--- a/api/configs/middleware/storage/google_cloud_storage_config.py
+++ b/api/configs/middleware/storage/google_cloud_storage_config.py
@@ -6,15 +6,15 @@ from pydantic_settings import BaseSettings

 class GoogleCloudStorageConfig(BaseSettings):
    """
-    Google Cloud storage configs
+    Configuration settings for Google Cloud Storage
    """

    GOOGLE_STORAGE_BUCKET_NAME: Optional[str] = Field(
-        description="Google Cloud storage bucket name",
+        description="Name of the Google Cloud Storage bucket to store and retrieve objects (e.g., 'my-gcs-bucket')",
        default=None,
    )

    GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64: Optional[str] = Field(
-        description="Google Cloud storage service account json base64",
+        description="Base64-encoded JSON key file for Google Cloud service account authentication",
        default=None,
    )
--- a/api/configs/middleware/storage/huawei_obs_storage_config.py
+++ b/api/configs/middleware/storage/huawei_obs_storage_config.py
@@ -5,25 +5,25 @@ from pydantic import BaseModel, Field

 class HuaweiCloudOBSStorageConfig(BaseModel):
    """
-    Huawei Cloud OBS storage configs
+    Configuration settings for Huawei Cloud Object Storage Service (OBS)
    """

    HUAWEI_OBS_BUCKET_NAME: Optional[str] = Field(
-        description="Huawei Cloud OBS bucket name",
+        description="Name of the Huawei Cloud OBS bucket to store and retrieve objects (e.g., 'my-obs-bucket')",
        default=None,
    )

    HUAWEI_OBS_ACCESS_KEY: Optional[str] = Field(
-        description="Huawei Cloud OBS Access key",
+        description="Access Key ID for authenticating with Huawei Cloud OBS",
        default=None,
    )

    HUAWEI_OBS_SECRET_KEY: Optional[str] = Field(
-        description="Huawei Cloud OBS Secret key",
+        description="Secret Access Key for authenticating with Huawei Cloud OBS",
        default=None,
    )

    HUAWEI_OBS_SERVER: Optional[str] = Field(
-        description="Huawei Cloud OBS server URL",
+        description="Endpoint URL for Huawei Cloud OBS (e.g., 'https://obs.cn-north-4.myhuaweicloud.com')",
        default=None,
    )
--- a/api/configs/middleware/storage/oci_storage_config.py
+++ b/api/configs/middleware/storage/oci_storage_config.py
@@ -6,30 +6,30 @@ from pydantic_settings import BaseSettings

 class OCIStorageConfig(BaseSettings):
    """
-    OCI storage configs
+    Configuration settings for Oracle Cloud Infrastructure (OCI) Object Storage
    """

    OCI_ENDPOINT: Optional[str] = Field(
-        description="OCI storage endpoint",
+        description="URL of the OCI Object Storage endpoint (e.g., 'https://objectstorage.us-phoenix-1.oraclecloud.com')",
        default=None,
    )

    OCI_REGION: Optional[str] = Field(
-        description="OCI storage region",
+        description="OCI region where the bucket is located (e.g., 'us-phoenix-1')",
        default=None,
    )

    OCI_BUCKET_NAME: Optional[str] = Field(
-        description="OCI storage bucket name",
+        description="Name of the OCI Object Storage bucket to store and retrieve objects (e.g., 'my-oci-bucket')",
        default=None,
    )

    OCI_ACCESS_KEY: Optional[str] = Field(
-        description="OCI storage access key",
+        description="Access key (also known as API key) for authenticating with OCI Object Storage",
        default=None,
    )

    OCI_SECRET_KEY: Optional[str] = Field(
-        description="OCI storage secret key",
+        description="Secret key associated with the access key for authenticating with OCI Object Storage",
        default=None,
    )
--- a/api/configs/middleware/storage/tencent_cos_storage_config.py
+++ b/api/configs/middleware/storage/tencent_cos_storage_config.py
@@ -6,30 +6,30 @@ from pydantic_settings import BaseSettings

 class TencentCloudCOSStorageConfig(BaseSettings):
    """
-    Tencent Cloud COS storage configs
+    Configuration settings for Tencent Cloud Object Storage (COS)
    """

    TENCENT_COS_BUCKET_NAME: Optional[str] = Field(
-        description="Tencent Cloud COS bucket name",
+        description="Name of the Tencent Cloud COS bucket to store and retrieve objects",
        default=None,
    )

    TENCENT_COS_REGION: Optional[str] = Field(
-        description="Tencent Cloud COS region",
+        description="Tencent Cloud region where the COS bucket is located (e.g., 'ap-guangzhou')",
        default=None,
    )

    TENCENT_COS_SECRET_ID: Optional[str] = Field(
-        description="Tencent Cloud COS secret id",
+        description="SecretId for authenticating with Tencent Cloud COS (part of API credentials)",
        default=None,
    )

    TENCENT_COS_SECRET_KEY: Optional[str] = Field(
-        description="Tencent Cloud COS secret key",
+        description="SecretKey for authenticating with Tencent Cloud COS (part of API credentials)",
        default=None,
    )

    TENCENT_COS_SCHEME: Optional[str] = Field(
-        description="Tencent Cloud COS scheme",
+        description="Protocol scheme for COS requests: 'https' (recommended) or 'http'",
        default=None,
    )
--- a/api/configs/middleware/storage/volcengine_tos_storage_config.py
+++ b/api/configs/middleware/storage/volcengine_tos_storage_config.py
@@ -5,30 +5,30 @@ from pydantic import BaseModel, Field

 class VolcengineTOSStorageConfig(BaseModel):
    """
-    Volcengine tos storage configs
+    Configuration settings for Volcengine Tinder Object Storage (TOS)
    """

    VOLCENGINE_TOS_BUCKET_NAME: Optional[str] = Field(
-        description="Volcengine TOS Bucket Name",
+        description="Name of the Volcengine TOS bucket to store and retrieve objects (e.g., 'my-tos-bucket')",
        default=None,
    )

    VOLCENGINE_TOS_ACCESS_KEY: Optional[str] = Field(
-        description="Volcengine TOS Access Key",
+        description="Access Key ID for authenticating with Volcengine TOS",
        default=None,
    )

    VOLCENGINE_TOS_SECRET_KEY: Optional[str] = Field(
-        description="Volcengine TOS Secret Key",
+        description="Secret Access Key for authenticating with Volcengine TOS",
        default=None,
    )

    VOLCENGINE_TOS_ENDPOINT: Optional[str] = Field(
-        description="Volcengine TOS Endpoint URL",
+        description="URL of the Volcengine TOS endpoint (e.g., 'https://tos-cn-beijing.volces.com')",
        default=None,
    )

    VOLCENGINE_TOS_REGION: Optional[str] = Field(
-        description="Volcengine TOS Region",
+        description="Volcengine region where the TOS bucket is located (e.g., 'cn-beijing')",
        default=None,
    )
--- a/api/configs/middleware/vdb/analyticdb_config.py
+++ b/api/configs/middleware/vdb/analyticdb_config.py
@@ -5,33 +5,38 @@ from pydantic import BaseModel, Field

 class AnalyticdbConfig(BaseModel):
    """
-    Configuration for connecting to AnalyticDB.
+    Configuration for connecting to Alibaba Cloud AnalyticDB for PostgreSQL.
    Refer to the following documentation for details on obtaining credentials:
    https://www.alibabacloud.com/help/en/analyticdb-for-postgresql/getting-started/create-an-instance-instances-with-vector-engine-optimization-enabled
    """

    ANALYTICDB_KEY_ID: Optional[str] = Field(
-        default=None, description="The Access Key ID provided by Alibaba Cloud for authentication."
+        default=None, description="The Access Key ID provided by Alibaba Cloud for API authentication."
    )
    ANALYTICDB_KEY_SECRET: Optional[str] = Field(
-        default=None, description="The Secret Access Key corresponding to the Access Key ID for secure access."
+        default=None, description="The Secret Access Key corresponding to the Access Key ID for secure API access."
    )
    ANALYTICDB_REGION_ID: Optional[str] = Field(
-        default=None, description="The region where the AnalyticDB instance is deployed (e.g., 'cn-hangzhou')."
+        default=None,
+        description="The region where the AnalyticDB instance is deployed (e.g., 'cn-hangzhou', 'ap-southeast-1').",
    )
    ANALYTICDB_INSTANCE_ID: Optional[str] = Field(
        default=None,
-        description="The unique identifier of the AnalyticDB instance you want to connect to (e.g., 'gp-ab123456')..",
+        description="The unique identifier of the AnalyticDB instance you want to connect to.",
    )
    ANALYTICDB_ACCOUNT: Optional[str] = Field(
-        default=None, description="The account name used to log in to the AnalyticDB instance."
+        default=None,
+        description="The account name used to log in to the AnalyticDB instance"
+        " (usually the initial account created with the instance).",
    )
    ANALYTICDB_PASSWORD: Optional[str] = Field(
-        default=None, description="The password associated with the AnalyticDB account for authentication."
+        default=None, description="The password associated with the AnalyticDB account for database authentication."
    )
    ANALYTICDB_NAMESPACE: Optional[str] = Field(
-        default=None, description="The namespace within AnalyticDB for schema isolation."
+        default=None, description="The namespace within AnalyticDB for schema isolation (if using namespace feature)."
    )
    ANALYTICDB_NAMESPACE_PASSWORD: Optional[str] = Field(
-        default=None, description="The password for accessing the specified namespace within the AnalyticDB instance."
+        default=None,
+        description="The password for accessing the specified namespace within the AnalyticDB instance"
+        " (if namespace feature is enabled).",
    )
--- a/api/configs/middleware/vdb/chroma_config.py
+++ b/api/configs/middleware/vdb/chroma_config.py
@@ -6,35 +6,35 @@ from pydantic_settings import BaseSettings

 class ChromaConfig(BaseSettings):
    """
-    Chroma configs
+    Configuration settings for Chroma vector database
    """

    CHROMA_HOST: Optional[str] = Field(
-        description="Chroma host",
+        description="Hostname or IP address of the Chroma server (e.g., 'localhost' or '192.168.1.100')",
        default=None,
    )

    CHROMA_PORT: PositiveInt = Field(
-        description="Chroma port",
+        description="Port number on which the Chroma server is listening (default is 8000)",
        default=8000,
    )

    CHROMA_TENANT: Optional[str] = Field(
-        description="Chroma database",
+        description="Tenant identifier for multi-tenancy support in Chroma",
        default=None,
    )

    CHROMA_DATABASE: Optional[str] = Field(
-        description="Chroma database",
+        description="Name of the Chroma database to connect to",
        default=None,
    )

    CHROMA_AUTH_PROVIDER: Optional[str] = Field(
-        description="Chroma authentication provider",
+        description="Authentication provider for Chroma (e.g., 'basic', 'token', or a custom provider)",
        default=None,
    )

    CHROMA_AUTH_CREDENTIALS: Optional[str] = Field(
-        description="Chroma authentication credentials",
+        description="Authentication credentials for Chroma (format depends on the auth provider)",
        default=None,
    )
--- a/api/configs/middleware/vdb/elasticsearch_config.py
+++ b/api/configs/middleware/vdb/elasticsearch_config.py
@@ -6,25 +6,25 @@ from pydantic_settings import BaseSettings

 class ElasticsearchConfig(BaseSettings):
    """
-    Elasticsearch configs
+    Configuration settings for Elasticsearch
    """

    ELASTICSEARCH_HOST: Optional[str] = Field(
-        description="Elasticsearch host",
+        description="Hostname or IP address of the Elasticsearch server (e.g., 'localhost' or '192.168.1.100')",
        default="127.0.0.1",
    )

    ELASTICSEARCH_PORT: PositiveInt = Field(
-        description="Elasticsearch port",
+        description="Port number on which the Elasticsearch server is listening (default is 9200)",
        default=9200,
    )

    ELASTICSEARCH_USERNAME: Optional[str] = Field(
-        description="Elasticsearch username",
+        description="Username for authenticating with Elasticsearch (default is 'elastic')",
        default="elastic",
    )

    ELASTICSEARCH_PASSWORD: Optional[str] = Field(
-        description="Elasticsearch password",
+        description="Password for authenticating with Elasticsearch (default is 'elastic')",
        default="elastic",
    )
--- a/api/configs/middleware/vdb/milvus_config.py
+++ b/api/configs/middleware/vdb/milvus_config.py
@@ -6,30 +6,30 @@ from pydantic_settings import BaseSettings

 class MilvusConfig(BaseSettings):
    """
-    Milvus configs
+    Configuration settings for Milvus vector database
    """

    MILVUS_URI: Optional[str] = Field(
-        description="Milvus uri",
+        description="URI for connecting to the Milvus server (e.g., 'http://localhost:19530' or 'https://milvus-instance.example.com:19530')",
        default="http://127.0.0.1:19530",
    )

    MILVUS_TOKEN: Optional[str] = Field(
-        description="Milvus token",
+        description="Authentication token for Milvus, if token-based authentication is enabled",
        default=None,
    )

    MILVUS_USER: Optional[str] = Field(
-        description="Milvus user",
+        description="Username for authenticating with Milvus, if username/password authentication is enabled",
        default=None,
    )

    MILVUS_PASSWORD: Optional[str] = Field(
-        description="Milvus password",
+        description="Password for authenticating with Milvus, if username/password authentication is enabled",
        default=None,
    )

    MILVUS_DATABASE: str = Field(
-        description="Milvus database, default to `default`",
+        description="Name of the Milvus database to connect to (default is 'default')",
        default="default",
    )
--- a/api/configs/middleware/vdb/myscale_config.py
+++ b/api/configs/middleware/vdb/myscale_config.py
@@ -3,35 +3,35 @@ from pydantic import BaseModel, Field, PositiveInt

 class MyScaleConfig(BaseModel):
    """
-    MyScale configs
+    Configuration settings for MyScale vector database
    """

    MYSCALE_HOST: str = Field(
-        description="MyScale host",
+        description="Hostname or IP address of the MyScale server (e.g., 'localhost' or 'myscale.example.com')",
        default="localhost",
    )

    MYSCALE_PORT: PositiveInt = Field(
-        description="MyScale port",
+        description="Port number on which the MyScale server is listening (default is 8123)",
        default=8123,
    )

    MYSCALE_USER: str = Field(
-        description="MyScale user",
+        description="Username for authenticating with MyScale (default is 'default')",
        default="default",
    )

    MYSCALE_PASSWORD: str = Field(
-        description="MyScale password",
+        description="Password for authenticating with MyScale (default is an empty string)",
        default="",
    )

    MYSCALE_DATABASE: str = Field(
-        description="MyScale database name",
+        description="Name of the MyScale database to connect to (default is 'default')",
        default="default",
    )

    MYSCALE_FTS_PARAMS: str = Field(
-        description="MyScale fts index parameters",
+        description="Additional parameters for MyScale Full Text Search index)",
        default="",
    )
--- a/api/configs/middleware/vdb/opensearch_config.py
+++ b/api/configs/middleware/vdb/opensearch_config.py
@@ -6,30 +6,30 @@ from pydantic_settings import BaseSettings

 class OpenSearchConfig(BaseSettings):
    """
-    OpenSearch configs
+    Configuration settings for OpenSearch
    """

    OPENSEARCH_HOST: Optional[str] = Field(
-        description="OpenSearch host",
+        description="Hostname or IP address of the OpenSearch server (e.g., 'localhost' or 'opensearch.example.com')",
        default=None,
    )

    OPENSEARCH_PORT: PositiveInt = Field(
-        description="OpenSearch port",
+        description="Port number on which the OpenSearch server is listening (default is 9200)",
        default=9200,
    )

    OPENSEARCH_USER: Optional[str] = Field(
-        description="OpenSearch user",
+        description="Username for authenticating with OpenSearch",
        default=None,
    )

    OPENSEARCH_PASSWORD: Optional[str] = Field(
-        description="OpenSearch password",
+        description="Password for authenticating with OpenSearch",
        default=None,
    )

    OPENSEARCH_SECURE: bool = Field(
-        description="whether to use SSL connection for OpenSearch",
+        description="Whether to use SSL/TLS encrypted connection for OpenSearch (True for HTTPS, False for HTTP)",
        default=False,
    )
--- a/api/configs/middleware/vdb/oracle_config.py
+++ b/api/configs/middleware/vdb/oracle_config.py
@@ -6,30 +6,30 @@ from pydantic_settings import BaseSettings

 class OracleConfig(BaseSettings):
    """
-    ORACLE configs
+    Configuration settings for Oracle database
    """

    ORACLE_HOST: Optional[str] = Field(
-        description="ORACLE host",
+        description="Hostname or IP address of the Oracle database server (e.g., 'localhost' or 'oracle.example.com')",
        default=None,
    )

    ORACLE_PORT: Optional[PositiveInt] = Field(
-        description="ORACLE port",
+        description="Port number on which the Oracle database server is listening (default is 1521)",
        default=1521,
    )

    ORACLE_USER: Optional[str] = Field(
-        description="ORACLE user",
+        description="Username for authenticating with the Oracle database",
        default=None,
    )

    ORACLE_PASSWORD: Optional[str] = Field(
-        description="ORACLE password",
+        description="Password for authenticating with the Oracle database",
        default=None,
    )

    ORACLE_DATABASE: Optional[str] = Field(
-        description="ORACLE database",
+        description="Name of the Oracle database or service to connect to (e.g., 'ORCL' or 'pdborcl')",
        default=None,
    )
--- a/api/configs/middleware/vdb/pgvector_config.py
+++ b/api/configs/middleware/vdb/pgvector_config.py
@@ -6,30 +6,40 @@ from pydantic_settings import BaseSettings

 class PGVectorConfig(BaseSettings):
    """
-    PGVector configs
+    Configuration settings for PGVector (PostgreSQL with vector extension)
    """

    PGVECTOR_HOST: Optional[str] = Field(
-        description="PGVector host",
+        description="Hostname or IP address of the PostgreSQL server with PGVector extension (e.g., 'localhost')",
        default=None,
    )

    PGVECTOR_PORT: Optional[PositiveInt] = Field(
-        description="PGVector port",
+        description="Port number on which the PostgreSQL server is listening (default is 5433)",
        default=5433,
    )

    PGVECTOR_USER: Optional[str] = Field(
-        description="PGVector user",
+        description="Username for authenticating with the PostgreSQL database",
        default=None,
    )

    PGVECTOR_PASSWORD: Optional[str] = Field(
-        description="PGVector password",
+        description="Password for authenticating with the PostgreSQL database",
        default=None,
    )

    PGVECTOR_DATABASE: Optional[str] = Field(
-        description="PGVector database",
+        description="Name of the PostgreSQL database to connect to",
        default=None,
    )
+
+    PGVECTOR_MIN_CONNECTION: PositiveInt = Field(
+        description="Min connection of the PostgreSQL database",
+        default=1,
+    )
+
+    PGVECTOR_MAX_CONNECTION: PositiveInt = Field(
+        description="Max connection of the PostgreSQL database",
+        default=5,
+    )
--- a/api/configs/middleware/vdb/pgvectors_config.py
+++ b/api/configs/middleware/vdb/pgvectors_config.py
@@ -6,30 +6,30 @@ from pydantic_settings import BaseSettings

 class PGVectoRSConfig(BaseSettings):
    """
-    PGVectoRS configs
+    Configuration settings for PGVecto.RS (Rust-based vector extension for PostgreSQL)
    """

    PGVECTO_RS_HOST: Optional[str] = Field(
-        description="PGVectoRS host",
+        description="Hostname or IP address of the PostgreSQL server with PGVecto.RS extension (e.g., 'localhost')",
        default=None,
    )

    PGVECTO_RS_PORT: Optional[PositiveInt] = Field(
-        description="PGVectoRS port",
+        description="Port number on which the PostgreSQL server with PGVecto.RS is listening (default is 5431)",
        default=5431,
    )

    PGVECTO_RS_USER: Optional[str] = Field(
-        description="PGVectoRS user",
+        description="Username for authenticating with the PostgreSQL database using PGVecto.RS",
        default=None,
    )

    PGVECTO_RS_PASSWORD: Optional[str] = Field(
-        description="PGVectoRS password",
+        description="Password for authenticating with the PostgreSQL database using PGVecto.RS",
        default=None,
    )

    PGVECTO_RS_DATABASE: Optional[str] = Field(
-        description="PGVectoRS database",
+        description="Name of the PostgreSQL database with PGVecto.RS extension to connect to",
        default=None,
    )
--- a/api/configs/middleware/vdb/qdrant_config.py
+++ b/api/configs/middleware/vdb/qdrant_config.py
@@ -6,30 +6,30 @@ from pydantic_settings import BaseSettings

 class QdrantConfig(BaseSettings):
    """
-    Qdrant configs
+    Configuration settings for Qdrant vector database
    """

    QDRANT_URL: Optional[str] = Field(
-        description="Qdrant url",
+        description="URL of the Qdrant server (e.g., 'http://localhost:6333' or 'https://qdrant.example.com')",
        default=None,
    )

    QDRANT_API_KEY: Optional[str] = Field(
-        description="Qdrant api key",
+        description="API key for authenticating with the Qdrant server",
        default=None,
    )

    QDRANT_CLIENT_TIMEOUT: NonNegativeInt = Field(
-        description="Qdrant client timeout in seconds",
+        description="Timeout in seconds for Qdrant client operations (default is 20 seconds)",
        default=20,
    )

    QDRANT_GRPC_ENABLED: bool = Field(
-        description="whether enable grpc support for Qdrant connection",
+        description="Whether to enable gRPC support for Qdrant connection (True for gRPC, False for HTTP)",
        default=False,
    )

    QDRANT_GRPC_PORT: PositiveInt = Field(
-        description="Qdrant grpc port",
+        description="Port number for gRPC connection to Qdrant server (default is 6334)",
        default=6334,
    )
--- a/api/configs/middleware/vdb/relyt_config.py
+++ b/api/configs/middleware/vdb/relyt_config.py
@@ -6,30 +6,30 @@ from pydantic_settings import BaseSettings

 class RelytConfig(BaseSettings):
    """
-    Relyt configs
+    Configuration settings for Relyt database
    """

    RELYT_HOST: Optional[str] = Field(
-        description="Relyt host",
+        description="Hostname or IP address of the Relyt server (e.g., 'localhost' or 'relyt.example.com')",
        default=None,
    )

    RELYT_PORT: PositiveInt = Field(
-        description="Relyt port",
+        description="Port number on which the Relyt server is listening (default is 9200)",
        default=9200,
    )

    RELYT_USER: Optional[str] = Field(
-        description="Relyt user",
+        description="Username for authenticating with the Relyt database",
        default=None,
    )

    RELYT_PASSWORD: Optional[str] = Field(
-        description="Relyt password",
+        description="Password for authenticating with the Relyt database",
        default=None,
    )

    RELYT_DATABASE: Optional[str] = Field(
-        description="Relyt database",
+        description="Name of the Relyt database to connect to (default is 'default')",
        default="default",
    )
--- a/api/configs/middleware/vdb/tencent_vector_config.py
+++ b/api/configs/middleware/vdb/tencent_vector_config.py
@@ -6,45 +6,45 @@ from pydantic_settings import BaseSettings

 class TencentVectorDBConfig(BaseSettings):
    """
-    Tencent Vector configs
+    Configuration settings for Tencent Vector Database
    """

    TENCENT_VECTOR_DB_URL: Optional[str] = Field(
-        description="Tencent Vector URL",
+        description="URL of the Tencent Vector Database service (e.g., 'https://vectordb.tencentcloudapi.com')",
        default=None,
    )

    TENCENT_VECTOR_DB_API_KEY: Optional[str] = Field(
-        description="Tencent Vector API key",
+        description="API key for authenticating with the Tencent Vector Database service",
        default=None,
    )

    TENCENT_VECTOR_DB_TIMEOUT: PositiveInt = Field(
-        description="Tencent Vector timeout in seconds",
+        description="Timeout in seconds for Tencent Vector Database operations (default is 30 seconds)",
        default=30,
    )

    TENCENT_VECTOR_DB_USERNAME: Optional[str] = Field(
-        description="Tencent Vector username",
+        description="Username for authenticating with the Tencent Vector Database (if required)",
        default=None,
    )

    TENCENT_VECTOR_DB_PASSWORD: Optional[str] = Field(
-        description="Tencent Vector password",
+        description="Password for authenticating with the Tencent Vector Database (if required)",
        default=None,
    )

    TENCENT_VECTOR_DB_SHARD: PositiveInt = Field(
-        description="Tencent Vector sharding number",
+        description="Number of shards for the Tencent Vector Database (default is 1)",
        default=1,
    )

    TENCENT_VECTOR_DB_REPLICAS: NonNegativeInt = Field(
-        description="Tencent Vector replicas",
+        description="Number of replicas for the Tencent Vector Database (default is 2)",
        default=2,
    )

    TENCENT_VECTOR_DB_DATABASE: Optional[str] = Field(
-        description="Tencent Vector Database",
+        description="Name of the specific Tencent Vector Database to connect to",
        default=None,
    )
--- a/api/configs/middleware/vdb/tidb_vector_config.py
+++ b/api/configs/middleware/vdb/tidb_vector_config.py
@@ -6,30 +6,30 @@ from pydantic_settings import BaseSettings

 class TiDBVectorConfig(BaseSettings):
    """
-    TiDB Vector configs
+    Configuration settings for TiDB Vector database
    """

    TIDB_VECTOR_HOST: Optional[str] = Field(
-        description="TiDB Vector host",
+        description="Hostname or IP address of the TiDB Vector server (e.g., 'localhost' or 'tidb.example.com')",
        default=None,
    )

    TIDB_VECTOR_PORT: Optional[PositiveInt] = Field(
-        description="TiDB Vector port",
+        description="Port number on which the TiDB Vector server is listening (default is 4000)",
        default=4000,
    )

    TIDB_VECTOR_USER: Optional[str] = Field(
-        description="TiDB Vector user",
+        description="Username for authenticating with the TiDB Vector database",
        default=None,
    )

    TIDB_VECTOR_PASSWORD: Optional[str] = Field(
-        description="TiDB Vector password",
+        description="Password for authenticating with the TiDB Vector database",
        default=None,
    )

    TIDB_VECTOR_DATABASE: Optional[str] = Field(
-        description="TiDB Vector database",
+        description="Name of the TiDB Vector database to connect to",
        default=None,
    )
--- a/api/configs/middleware/vdb/weaviate_config.py
+++ b/api/configs/middleware/vdb/weaviate_config.py
@@ -6,25 +6,25 @@ from pydantic_settings import BaseSettings

 class WeaviateConfig(BaseSettings):
    """
-    Weaviate configs
+    Configuration settings for Weaviate vector database
    """

    WEAVIATE_ENDPOINT: Optional[str] = Field(
-        description="Weaviate endpoint URL",
+        description="URL of the Weaviate server (e.g., 'http://localhost:8080' or 'https://weaviate.example.com')",
        default=None,
    )

    WEAVIATE_API_KEY: Optional[str] = Field(
-        description="Weaviate API key",
+        description="API key for authenticating with the Weaviate server",
        default=None,
    )

    WEAVIATE_GRPC_ENABLED: bool = Field(
-        description="whether to enable gRPC for Weaviate connection",
+        description="Whether to enable gRPC for Weaviate connection (True for gRPC, False for HTTP)",
        default=True,
    )

    WEAVIATE_BATCH_SIZE: PositiveInt = Field(
-        description="Weaviate batch size",
+        description="Number of objects to be processed in a single batch operation (default is 100)",
        default=100,
    )
--- a/api/configs/packaging/init.py
+++ b/api/configs/packaging/init.py
@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):

    CURRENT_VERSION: str = Field(
        description="Dify version",
-        default="0.8.1",
+        default="0.9.1-fix1",
    )

    COMMIT_SHA: str = Field(
--- a/api/constants/init.py
+++ b/api/constants/init.py
@@ -1 +1,2 @@
 HIDDEN_VALUE = "[__HIDDEN__]"
+UUID_NIL = "00000000-0000-0000-0000-000000000000"
--- a/api/controllers/console/init.py
+++ b/api/controllers/console/init.py
@@ -37,7 +37,16 @@ from .auth import activate, data_source_bearer_auth, data_source_oauth, forgot_p
 from .billing import billing

 # Import datasets controllers
-from .datasets import data_source, datasets, datasets_document, datasets_segments, file, hit_testing, website
+from .datasets import (
+    data_source,
+    datasets,
+    datasets_document,
+    datasets_segments,
+    external,
+    file,
+    hit_testing,
+    website,
+)

 # Import explore controllers
 from .explore import (
--- a/api/controllers/console/app/audio.py
+++ b/api/controllers/console/app/audio.py
@@ -94,7 +94,7 @@ class ChatMessageTextApi(Resource):
            message_id = args.get("message_id", None)
            text = args.get("text", None)
            if (
-                app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]
+                app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}
                and app_model.workflow
                and app_model.workflow.features_dict
            ):
--- a/api/controllers/console/app/completion.py
+++ b/api/controllers/console/app/completion.py
@@ -109,6 +109,7 @@ class ChatMessageApi(Resource):
        parser.add_argument("files", type=list, required=False, location="json")
        parser.add_argument("model_config", type=dict, required=True, location="json")
        parser.add_argument("conversation_id", type=uuid_value, location="json")
+        parser.add_argument("parent_message_id", type=uuid_value, required=False, location="json")
        parser.add_argument("response_mode", type=str, choices=["blocking", "streaming"], location="json")
        parser.add_argument("retriever_from", type=str, required=False, default="dev", location="json")
        args = parser.parse_args()
--- a/api/controllers/console/app/conversation.py
+++ b/api/controllers/console/app/conversation.py
@@ -188,6 +188,7 @@ class ChatConversationApi(Resource):
                        subquery.c.from_end_user_session_id.ilike(keyword_filter),
                    ),
                )
+                .group_by(Conversation.id)
            )

        account = current_user
--- a/api/controllers/console/app/message.py
+++ b/api/controllers/console/app/message.py
@@ -105,8 +105,6 @@ 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)


--- a/api/controllers/console/app/workflow.py
+++ b/api/controllers/console/app/workflow.py
@@ -166,6 +166,8 @@ class AdvancedChatDraftWorkflowRunApi(Resource):
        parser.add_argument("query", type=str, required=True, location="json", default="")
        parser.add_argument("files", type=list, location="json")
        parser.add_argument("conversation_id", type=uuid_value, location="json")
+        parser.add_argument("parent_message_id", type=uuid_value, required=False, location="json")
+
        args = parser.parse_args()

        try:
@@ -465,6 +467,6 @@ api.add_resource(
 api.add_resource(PublishedWorkflowApi, "/apps/<uuid:app_id>/workflows/publish")
 api.add_resource(DefaultBlockConfigsApi, "/apps/<uuid:app_id>/workflows/default-workflow-block-configs")
 api.add_resource(
-    DefaultBlockConfigApi, "/apps/<uuid:app_id>/workflows/default-workflow-block-configs" "/<string:block_type>"
+    DefaultBlockConfigApi, "/apps/<uuid:app_id>/workflows/default-workflow-block-configs/<string:block_type>"
 )
 api.add_resource(ConvertToWorkflowApi, "/apps/<uuid:app_id>/convert-to-workflow")
--- a/api/controllers/console/auth/oauth.py
+++ b/api/controllers/console/auth/oauth.py
@@ -71,7 +71,7 @@ class OAuthCallback(Resource):

        account = _generate_account(provider, user_info)
        # Check account status
-        if account.status == AccountStatus.BANNED.value or account.status == AccountStatus.CLOSED.value:
+        if account.status in {AccountStatus.BANNED.value, AccountStatus.CLOSED.value}:
            return {"error": "Account is banned or closed."}, 403

        if account.status == AccountStatus.PENDING.value:
--- a/api/controllers/console/datasets/datasets.py
+++ b/api/controllers/console/datasets/datasets.py
@@ -49,7 +49,7 @@ class DatasetListApi(Resource):
        page = request.args.get("page", default=1, type=int)
        limit = request.args.get("limit", default=20, type=int)
        ids = request.args.getlist("ids")
-        provider = request.args.get("provider", default="vendor")
+        # provider = request.args.get("provider", default="vendor")
        search = request.args.get("keyword", default=None, type=str)
        tag_ids = request.args.getlist("tag_ids")

@@ -57,7 +57,7 @@ class DatasetListApi(Resource):
            datasets, total = DatasetService.get_datasets_by_ids(ids, current_user.current_tenant_id)
        else:
            datasets, total = DatasetService.get_datasets(
-                page, limit, provider, current_user.current_tenant_id, current_user, search, tag_ids
+                page, limit, current_user.current_tenant_id, current_user, search, tag_ids
            )

        # check embedding setting
@@ -110,6 +110,26 @@ class DatasetListApi(Resource):
            nullable=True,
            help="Invalid indexing technique.",
        )
+        parser.add_argument(
+            "external_knowledge_api_id",
+            type=str,
+            nullable=True,
+            required=False,
+        )
+        parser.add_argument(
+            "provider",
+            type=str,
+            nullable=True,
+            choices=Dataset.PROVIDER_LIST,
+            required=False,
+            default="vendor",
+        )
+        parser.add_argument(
+            "external_knowledge_id",
+            type=str,
+            nullable=True,
+            required=False,
+        )
        args = parser.parse_args()

        # The role of the current user in the ta table must be admin, owner, or editor, or dataset_operator
@@ -123,6 +143,9 @@ class DatasetListApi(Resource):
                indexing_technique=args["indexing_technique"],
                account=current_user,
                permission=DatasetPermissionEnum.ONLY_ME,
+                provider=args["provider"],
+                external_knowledge_api_id=args["external_knowledge_api_id"],
+                external_knowledge_id=args["external_knowledge_id"],
            )
        except services.errors.dataset.DatasetNameDuplicateError:
            raise DatasetNameDuplicateError()
@@ -211,6 +234,33 @@ class DatasetApi(Resource):
        )
        parser.add_argument("retrieval_model", type=dict, location="json", help="Invalid retrieval model.")
        parser.add_argument("partial_member_list", type=list, location="json", help="Invalid parent user list.")
+
+        parser.add_argument(
+            "external_retrieval_model",
+            type=dict,
+            required=False,
+            nullable=True,
+            location="json",
+            help="Invalid external retrieval model.",
+        )
+
+        parser.add_argument(
+            "external_knowledge_id",
+            type=str,
+            required=False,
+            nullable=True,
+            location="json",
+            help="Invalid external knowledge id.",
+        )
+
+        parser.add_argument(
+            "external_knowledge_api_id",
+            type=str,
+            required=False,
+            nullable=True,
+            location="json",
+            help="Invalid external knowledge api id.",
+        )
        args = parser.parse_args()
        data = request.get_json()

@@ -399,7 +449,7 @@ class DatasetIndexingEstimateApi(Resource):
            )
        except LLMBadRequestError:
            raise ProviderNotInitializeError(
-                "No Embedding Model available. Please configure a valid provider " "in the Settings -> Model Provider."
+                "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
            )
        except ProviderTokenNotInitError as ex:
            raise ProviderNotInitializeError(ex.description)
@@ -563,10 +613,10 @@ class DatasetRetrievalSettingApi(Resource):
            case (
                VectorType.MILVUS
                | VectorType.RELYT
-                | VectorType.PGVECTOR
                | VectorType.TIDB_VECTOR
                | VectorType.CHROMA
                | VectorType.TENCENT
+                | VectorType.PGVECTO_RS
            ):
                return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
            case (
@@ -577,6 +627,7 @@ class DatasetRetrievalSettingApi(Resource):
                | VectorType.MYSCALE
                | VectorType.ORACLE
                | VectorType.ELASTICSEARCH
+                | VectorType.PGVECTOR
            ):
                return {
                    "retrieval_method": [
--- a/api/controllers/console/datasets/datasets_document.py
+++ b/api/controllers/console/datasets/datasets_document.py
@@ -354,7 +354,7 @@ class DocumentIndexingEstimateApi(DocumentResource):
        document_id = str(document_id)
        document = self.get_document(dataset_id, document_id)

-        if document.indexing_status in ["completed", "error"]:
+        if document.indexing_status in {"completed", "error"}:
            raise DocumentAlreadyFinishedError()

        data_process_rule = document.dataset_process_rule
@@ -421,7 +421,7 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
        info_list = []
        extract_settings = []
        for document in documents:
-            if document.indexing_status in ["completed", "error"]:
+            if document.indexing_status in {"completed", "error"}:
                raise DocumentAlreadyFinishedError()
            data_source_info = document.data_source_info_dict
            # format document files info
@@ -665,7 +665,7 @@ class DocumentProcessingApi(DocumentResource):
            db.session.commit()

        elif action == "resume":
-            if document.indexing_status not in ["paused", "error"]:
+            if document.indexing_status not in {"paused", "error"}:
                raise InvalidActionError("Document not in paused or error state.")

            document.paused_by = None
--- a/api/controllers/console/datasets/external.py
+++ b/api/controllers/console/datasets/external.py
@@ -0,0 +1,263 @@
+from flask import request
+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.datasets.error import DatasetNameDuplicateError
+from controllers.console.setup import setup_required
+from controllers.console.wraps import account_initialization_required
+from fields.dataset_fields import dataset_detail_fields
+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):
+    if not name or len(name) < 1 or len(name) > 100:
+        raise ValueError("Name must be between 1 to 100 characters.")
+    return name
+
+
+def _validate_description_length(description):
+    if description and len(description) > 400:
+        raise ValueError("Description cannot exceed 400 characters.")
+    return description
+
+
+class ExternalApiTemplateListApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+        page = request.args.get("page", default=1, type=int)
+        limit = request.args.get("limit", default=20, type=int)
+        search = request.args.get("keyword", default=None, type=str)
+
+        external_knowledge_apis, total = ExternalDatasetService.get_external_knowledge_apis(
+            page, limit, current_user.current_tenant_id, search
+        )
+        response = {
+            "data": [item.to_dict() for item in external_knowledge_apis],
+            "has_more": len(external_knowledge_apis) == limit,
+            "limit": limit,
+            "total": total,
+            "page": page,
+        }
+        return response, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        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(
+            "settings",
+            type=dict,
+            location="json",
+            nullable=False,
+            required=True,
+        )
+        args = parser.parse_args()
+
+        ExternalDatasetService.validate_api_list(args["settings"])
+
+        # 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()
+
+        try:
+            external_knowledge_api = ExternalDatasetService.create_external_knowledge_api(
+                tenant_id=current_user.current_tenant_id, user_id=current_user.id, args=args
+            )
+        except services.errors.dataset.DatasetNameDuplicateError:
+            raise DatasetNameDuplicateError()
+
+        return external_knowledge_api.to_dict(), 201
+
+
+class ExternalApiTemplateApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, external_knowledge_api_id):
+        external_knowledge_api_id = str(external_knowledge_api_id)
+        external_knowledge_api = ExternalDatasetService.get_external_knowledge_api(external_knowledge_api_id)
+        if external_knowledge_api is None:
+            raise NotFound("API template not found.")
+
+        return external_knowledge_api.to_dict(), 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def patch(self, external_knowledge_api_id):
+        external_knowledge_api_id = str(external_knowledge_api_id)
+
+        parser = reqparse.RequestParser()
+        parser.add_argument(
+            "name",
+            nullable=False,
+            required=True,
+            help="type is required. Name must be between 1 to 100 characters.",
+            type=_validate_name,
+        )
+        parser.add_argument(
+            "settings",
+            type=dict,
+            location="json",
+            nullable=False,
+            required=True,
+        )
+        args = parser.parse_args()
+        ExternalDatasetService.validate_api_list(args["settings"])
+
+        external_knowledge_api = ExternalDatasetService.update_external_knowledge_api(
+            tenant_id=current_user.current_tenant_id,
+            user_id=current_user.id,
+            external_knowledge_api_id=external_knowledge_api_id,
+            args=args,
+        )
+
+        return external_knowledge_api.to_dict(), 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, external_knowledge_api_id):
+        external_knowledge_api_id = str(external_knowledge_api_id)
+
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor or current_user.is_dataset_operator:
+            raise Forbidden()
+
+        ExternalDatasetService.delete_external_knowledge_api(current_user.current_tenant_id, external_knowledge_api_id)
+        return {"result": "success"}, 200
+
+
+class ExternalApiUseCheckApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, external_knowledge_api_id):
+        external_knowledge_api_id = str(external_knowledge_api_id)
+
+        external_knowledge_api_is_using, count = ExternalDatasetService.external_knowledge_api_use_check(
+            external_knowledge_api_id
+        )
+        return {"is_using": external_knowledge_api_is_using, "count": count}, 200
+
+
+class ExternalDatasetCreateApi(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=False, location="json")
+        parser.add_argument("external_knowledge_id", type=str, required=True, nullable=False, 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=False, nullable=True, location="json")
+        parser.add_argument("external_retrieval_model", type=dict, required=False, 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()
+
+        try:
+            dataset = ExternalDatasetService.create_external_dataset(
+                tenant_id=current_user.current_tenant_id,
+                user_id=current_user.id,
+                args=args,
+            )
+        except services.errors.dataset.DatasetNameDuplicateError:
+            raise DatasetNameDuplicateError()
+
+        return marshal(dataset, dataset_detail_fields), 201
+
+
+class ExternalKnowledgeHitTestingApi(Resource):
+    @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.")
+
+        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("external_retrieval_model", type=dict, required=False, location="json")
+        args = parser.parse_args()
+
+        HitTestingService.hit_testing_args_check(args)
+
+        try:
+            response = HitTestingService.external_retrieve(
+                dataset=dataset,
+                query=args["query"],
+                account=current_user,
+                external_retrieval_model=args["external_retrieval_model"],
+            )
+
+            return response
+        except Exception as e:
+            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")
--- a/api/controllers/console/datasets/hit_testing.py
+++ b/api/controllers/console/datasets/hit_testing.py
@@ -47,6 +47,7 @@ class HitTestingApi(Resource):
        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)
@@ -57,6 +58,7 @@ class HitTestingApi(Resource):
                query=args["query"],
                account=current_user,
                retrieval_model=args["retrieval_model"],
+                external_retrieval_model=args["external_retrieval_model"],
                limit=10,
            )

--- a/api/controllers/console/datasets/website.py
+++ b/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:
--- a/api/controllers/console/error.py
+++ b/api/controllers/console/error.py
@@ -18,9 +18,7 @@ class NotSetupError(BaseHTTPException):

 class NotInitValidateError(BaseHTTPException):
    error_code = "not_init_validated"
-    description = (
-        "Init validation has not been completed yet. " "Please proceed with the init validation process first."
-    )
+    description = "Init validation has not been completed yet. Please proceed with the init validation process first."
    code = 401


--- a/api/controllers/console/explore/audio.py
+++ b/api/controllers/console/explore/audio.py
@@ -81,7 +81,7 @@ class ChatTextApi(InstalledAppResource):
            message_id = args.get("message_id", None)
            text = args.get("text", None)
            if (
-                app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]
+                app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}
                and app_model.workflow
                and app_model.workflow.features_dict
            ):
--- a/api/controllers/console/explore/completion.py
+++ b/api/controllers/console/explore/completion.py
@@ -92,7 +92,7 @@ class ChatApi(InstalledAppResource):
    def post(self, installed_app):
        app_model = installed_app.app
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        parser = reqparse.RequestParser()
@@ -100,6 +100,7 @@ class ChatApi(InstalledAppResource):
        parser.add_argument("query", type=str, required=True, location="json")
        parser.add_argument("files", type=list, required=False, location="json")
        parser.add_argument("conversation_id", type=uuid_value, location="json")
+        parser.add_argument("parent_message_id", type=uuid_value, required=False, location="json")
        parser.add_argument("retriever_from", type=str, required=False, default="explore_app", location="json")
        args = parser.parse_args()

@@ -140,7 +141,7 @@ class ChatStopApi(InstalledAppResource):
    def post(self, installed_app, task_id):
        app_model = installed_app.app
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        AppQueueManager.set_stop_flag(task_id, InvokeFrom.EXPLORE, current_user.id)
--- a/api/controllers/console/explore/conversation.py
+++ b/api/controllers/console/explore/conversation.py
@@ -20,7 +20,7 @@ class ConversationListApi(InstalledAppResource):
    def get(self, installed_app):
        app_model = installed_app.app
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        parser = reqparse.RequestParser()
@@ -50,7 +50,7 @@ class ConversationApi(InstalledAppResource):
    def delete(self, installed_app, c_id):
        app_model = installed_app.app
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        conversation_id = str(c_id)
@@ -68,7 +68,7 @@ class ConversationRenameApi(InstalledAppResource):
    def post(self, installed_app, c_id):
        app_model = installed_app.app
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        conversation_id = str(c_id)
@@ -90,7 +90,7 @@ class ConversationPinApi(InstalledAppResource):
    def patch(self, installed_app, c_id):
        app_model = installed_app.app
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        conversation_id = str(c_id)
@@ -107,7 +107,7 @@ class ConversationUnPinApi(InstalledAppResource):
    def patch(self, installed_app, c_id):
        app_model = installed_app.app
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        conversation_id = str(c_id)
--- a/api/controllers/console/explore/installed_app.py
+++ b/api/controllers/console/explore/installed_app.py
@@ -31,7 +31,7 @@ class InstalledAppsListApi(Resource):
                "app_owner_tenant_id": installed_app.app_owner_tenant_id,
                "is_pinned": installed_app.is_pinned,
                "last_used_at": installed_app.last_used_at,
-                "editable": current_user.role in ["owner", "admin"],
+                "editable": current_user.role in {"owner", "admin"},
                "uninstallable": current_tenant_id == installed_app.app_owner_tenant_id,
            }
            for installed_app in installed_apps
--- a/api/controllers/console/explore/message.py
+++ b/api/controllers/console/explore/message.py
@@ -40,7 +40,7 @@ class MessageListApi(InstalledAppResource):
        app_model = installed_app.app

        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        parser = reqparse.RequestParser()
@@ -51,7 +51,7 @@ class MessageListApi(InstalledAppResource):

        try:
            return MessageService.pagination_by_first_id(
-                app_model, current_user, args["conversation_id"], args["first_id"], args["limit"]
+                app_model, current_user, args["conversation_id"], args["first_id"], args["limit"], "desc"
            )
        except services.errors.conversation.ConversationNotExistsError:
            raise NotFound("Conversation Not Exists.")
@@ -125,7 +125,7 @@ class MessageSuggestedQuestionApi(InstalledAppResource):
    def get(self, installed_app, message_id):
        app_model = installed_app.app
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        message_id = str(message_id)
--- a/api/controllers/console/explore/parameter.py
+++ b/api/controllers/console/explore/parameter.py
@@ -43,7 +43,7 @@ class AppParameterApi(InstalledAppResource):
        """Retrieve app parameters."""
        app_model = installed_app.app

-        if app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]:
+        if app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}:
            workflow = app_model.workflow
            if workflow is None:
                raise AppUnavailableError()
--- a/api/controllers/console/version.py
+++ b/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")
--- a/api/controllers/console/workspace/model_providers.py
+++ b/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)
@@ -218,7 +217,7 @@ api.add_resource(ModelProviderCredentialApi, "/workspaces/current/model-provider
 api.add_resource(ModelProviderValidateApi, "/workspaces/current/model-providers/<string:provider>/credentials/validate")
 api.add_resource(ModelProviderApi, "/workspaces/current/model-providers/<string:provider>")
 api.add_resource(
-    ModelProviderIconApi, "/workspaces/current/model-providers/<string:provider>/" "<string:icon_type>/<string:lang>"
+    ModelProviderIconApi, "/workspaces/current/model-providers/<string:provider>/<string:icon_type>/<string:lang>"
 )

 api.add_resource(
--- a/api/controllers/console/workspace/models.py
+++ b/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"}

--- a/api/controllers/console/workspace/workspace.py
+++ b/api/controllers/console/workspace/workspace.py
@@ -194,7 +194,7 @@ class WebappLogoWorkspaceApi(Resource):
            raise TooManyFilesError()

        extension = file.filename.split(".")[-1]
-        if extension.lower() not in ["svg", "png"]:
+        if extension.lower() not in {"svg", "png"}:
            raise UnsupportedFileTypeError()

        try:
--- a/api/controllers/files/error.py
+++ b/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
--- a/api/controllers/files/image_preview.py
+++ b/api/controllers/files/image_preview.py
@@ -4,7 +4,7 @@ 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

@@ -50,9 +50,3 @@ class WorkspaceWebappLogoApi(Resource):

 api.add_resource(ImagePreviewApi, "/files/<uuid:file_id>/image-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
--- a/api/controllers/files/tool_files.py
+++ b/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):
@@ -43,9 +43,3 @@ class ToolFilePreviewApi(Resource):


 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
--- a/api/controllers/service_api/app/app.py
+++ b/api/controllers/service_api/app/app.py
@@ -42,7 +42,7 @@ class AppParameterApi(Resource):
    @marshal_with(parameters_fields)
    def get(self, app_model: App):
        """Retrieve app parameters."""
-        if app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]:
+        if app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}:
            workflow = app_model.workflow
            if workflow is None:
                raise AppUnavailableError()
--- a/api/controllers/service_api/app/audio.py
+++ b/api/controllers/service_api/app/audio.py
@@ -79,7 +79,7 @@ class TextApi(Resource):
            message_id = args.get("message_id", None)
            text = args.get("text", None)
            if (
-                app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]
+                app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}
                and app_model.workflow
                and app_model.workflow.features_dict
            ):
--- a/api/controllers/service_api/app/completion.py
+++ b/api/controllers/service_api/app/completion.py
@@ -4,6 +4,7 @@ from flask_restful import Resource, reqparse
 from werkzeug.exceptions import InternalServerError, NotFound

 import services
+from constants import UUID_NIL
 from controllers.service_api import api
 from controllers.service_api.app.error import (
    AppUnavailableError,
@@ -96,7 +97,7 @@ class ChatApi(Resource):
    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON, required=True))
    def post(self, app_model: App, end_user: EndUser):
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        parser = reqparse.RequestParser()
@@ -107,6 +108,7 @@ class ChatApi(Resource):
        parser.add_argument("conversation_id", type=uuid_value, location="json")
        parser.add_argument("retriever_from", type=str, required=False, default="dev", location="json")
        parser.add_argument("auto_generate_name", type=bool, required=False, default=True, location="json")
+        parser.add_argument("parent_message_id", type=uuid_value, required=False, default=UUID_NIL, location="json")

        args = parser.parse_args()

@@ -144,7 +146,7 @@ class ChatStopApi(Resource):
    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON, required=True))
    def post(self, app_model: App, end_user: EndUser, task_id):
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        AppQueueManager.set_stop_flag(task_id, InvokeFrom.SERVICE_API, end_user.id)
--- a/api/controllers/service_api/app/conversation.py
+++ b/api/controllers/service_api/app/conversation.py
@@ -18,7 +18,7 @@ class ConversationApi(Resource):
    @marshal_with(conversation_infinite_scroll_pagination_fields)
    def get(self, app_model: App, end_user: EndUser):
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        parser = reqparse.RequestParser()
@@ -52,7 +52,7 @@ class ConversationDetailApi(Resource):
    @marshal_with(simple_conversation_fields)
    def delete(self, app_model: App, end_user: EndUser, c_id):
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        conversation_id = str(c_id)
@@ -69,7 +69,7 @@ class ConversationRenameApi(Resource):
    @marshal_with(simple_conversation_fields)
    def post(self, app_model: App, end_user: EndUser, c_id):
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        conversation_id = str(c_id)
--- a/api/controllers/service_api/app/message.py
+++ b/api/controllers/service_api/app/message.py
@@ -54,6 +54,7 @@ class MessageListApi(Resource):
    message_fields = {
        "id": fields.String,
        "conversation_id": fields.String,
+        "parent_message_id": fields.String,
        "inputs": fields.Raw,
        "query": fields.String,
        "answer": fields.String(attribute="re_sign_file_url_answer"),
@@ -76,7 +77,7 @@ class MessageListApi(Resource):
    @marshal_with(message_infinite_scroll_pagination_fields)
    def get(self, app_model: App, end_user: EndUser):
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        parser = reqparse.RequestParser()
@@ -117,7 +118,7 @@ class MessageSuggestedApi(Resource):
    def get(self, app_model: App, end_user: EndUser, message_id):
        message_id = str(message_id)
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        try:
--- a/api/controllers/service_api/app/workflow.py
+++ b/api/controllers/service_api/app/workflow.py
@@ -1,6 +1,7 @@
 import logging

 from flask_restful import Resource, fields, marshal_with, reqparse
+from flask_restful.inputs import int_range
 from werkzeug.exceptions import InternalServerError

 from controllers.service_api import api
@@ -22,10 +23,12 @@ from core.errors.error import (
 )
 from core.model_runtime.errors.invoke import InvokeError
 from extensions.ext_database import db
+from fields.workflow_app_log_fields import workflow_app_log_pagination_fields
 from libs import helper
 from models.model import App, AppMode, EndUser
 from models.workflow import WorkflowRun
 from services.app_generate_service import AppGenerateService
+from services.workflow_app_service import WorkflowAppService

 logger = logging.getLogger(__name__)

@@ -113,6 +116,30 @@ class WorkflowTaskStopApi(Resource):
        return {"result": "success"}


+class WorkflowAppLogApi(Resource):
+    @validate_app_token
+    @marshal_with(workflow_app_log_pagination_fields)
+    def get(self, app_model: App):
+        """
+        Get workflow app logs
+        """
+        parser = reqparse.RequestParser()
+        parser.add_argument("keyword", type=str, location="args")
+        parser.add_argument("status", type=str, choices=["succeeded", "failed", "stopped"], location="args")
+        parser.add_argument("page", type=int_range(1, 99999), default=1, location="args")
+        parser.add_argument("limit", type=int_range(1, 100), default=20, location="args")
+        args = parser.parse_args()
+
+        # get paginate workflow app logs
+        workflow_app_service = WorkflowAppService()
+        workflow_app_log_pagination = workflow_app_service.get_paginate_workflow_app_logs(
+            app_model=app_model, args=args
+        )
+
+        return workflow_app_log_pagination
+
+
 api.add_resource(WorkflowRunApi, "/workflows/run")
 api.add_resource(WorkflowRunDetailApi, "/workflows/run/<string:workflow_id>")
 api.add_resource(WorkflowTaskStopApi, "/workflows/tasks/<string:task_id>/stop")
+api.add_resource(WorkflowAppLogApi, "/workflows/logs")
--- a/api/controllers/service_api/dataset/dataset.py
+++ b/api/controllers/service_api/dataset/dataset.py
@@ -28,11 +28,11 @@ class DatasetListApi(DatasetApiResource):

        page = request.args.get("page", default=1, type=int)
        limit = request.args.get("limit", default=20, type=int)
-        provider = request.args.get("provider", default="vendor")
+        # provider = request.args.get("provider", default="vendor")
        search = request.args.get("keyword", default=None, type=str)
        tag_ids = request.args.getlist("tag_ids")

-        datasets, total = DatasetService.get_datasets(page, limit, provider, tenant_id, current_user, search, tag_ids)
+        datasets, total = DatasetService.get_datasets(page, limit, tenant_id, current_user, search, tag_ids)
        # check embedding setting
        provider_manager = ProviderManager()
        configurations = provider_manager.get_configurations(tenant_id=current_user.current_tenant_id)
@@ -82,6 +82,26 @@ class DatasetListApi(DatasetApiResource):
            required=False,
            nullable=False,
        )
+        parser.add_argument(
+            "external_knowledge_api_id",
+            type=str,
+            nullable=True,
+            required=False,
+            default="_validate_name",
+        )
+        parser.add_argument(
+            "provider",
+            type=str,
+            nullable=True,
+            required=False,
+            default="vendor",
+        )
+        parser.add_argument(
+            "external_knowledge_id",
+            type=str,
+            nullable=True,
+            required=False,
+        )
        args = parser.parse_args()

        try:
@@ -91,6 +111,9 @@ class DatasetListApi(DatasetApiResource):
                indexing_technique=args["indexing_technique"],
                account=current_user,
                permission=args["permission"],
+                provider=args["provider"],
+                external_knowledge_api_id=args["external_knowledge_api_id"],
+                external_knowledge_id=args["external_knowledge_id"],
            )
        except services.errors.dataset.DatasetNameDuplicateError:
            raise DatasetNameDuplicateError()
--- a/api/controllers/web/app.py
+++ b/api/controllers/web/app.py
@@ -41,7 +41,7 @@ class AppParameterApi(WebApiResource):
    @marshal_with(parameters_fields)
    def get(self, app_model: App, end_user):
        """Retrieve app parameters."""
-        if app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]:
+        if app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}:
            workflow = app_model.workflow
            if workflow is None:
                raise AppUnavailableError()
--- a/api/controllers/web/audio.py
+++ b/api/controllers/web/audio.py
@@ -78,7 +78,7 @@ class TextApi(WebApiResource):
            message_id = args.get("message_id", None)
            text = args.get("text", None)
            if (
-                app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]
+                app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}
                and app_model.workflow
                and app_model.workflow.features_dict
            ):
--- a/api/controllers/web/completion.py
+++ b/api/controllers/web/completion.py
@@ -87,7 +87,7 @@ class CompletionStopApi(WebApiResource):
 class ChatApi(WebApiResource):
    def post(self, app_model, end_user):
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        parser = reqparse.RequestParser()
@@ -96,6 +96,7 @@ class ChatApi(WebApiResource):
        parser.add_argument("files", type=list, required=False, location="json")
        parser.add_argument("response_mode", type=str, choices=["blocking", "streaming"], location="json")
        parser.add_argument("conversation_id", type=uuid_value, location="json")
+        parser.add_argument("parent_message_id", type=uuid_value, required=False, location="json")
        parser.add_argument("retriever_from", type=str, required=False, default="web_app", location="json")

        args = parser.parse_args()
@@ -136,7 +137,7 @@ class ChatApi(WebApiResource):
 class ChatStopApi(WebApiResource):
    def post(self, app_model, end_user, task_id):
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        AppQueueManager.set_stop_flag(task_id, InvokeFrom.WEB_APP, end_user.id)
--- a/api/controllers/web/conversation.py
+++ b/api/controllers/web/conversation.py
@@ -18,7 +18,7 @@ class ConversationListApi(WebApiResource):
    @marshal_with(conversation_infinite_scroll_pagination_fields)
    def get(self, app_model, end_user):
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        parser = reqparse.RequestParser()
@@ -56,7 +56,7 @@ class ConversationListApi(WebApiResource):
 class ConversationApi(WebApiResource):
    def delete(self, app_model, end_user, c_id):
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        conversation_id = str(c_id)
@@ -73,7 +73,7 @@ class ConversationRenameApi(WebApiResource):
    @marshal_with(simple_conversation_fields)
    def post(self, app_model, end_user, c_id):
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        conversation_id = str(c_id)
@@ -92,7 +92,7 @@ class ConversationRenameApi(WebApiResource):
 class ConversationPinApi(WebApiResource):
    def patch(self, app_model, end_user, c_id):
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        conversation_id = str(c_id)
@@ -108,7 +108,7 @@ class ConversationPinApi(WebApiResource):
 class ConversationUnPinApi(WebApiResource):
    def patch(self, app_model, end_user, c_id):
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        conversation_id = str(c_id)
--- a/api/controllers/web/message.py
+++ b/api/controllers/web/message.py
@@ -57,6 +57,7 @@ class MessageListApi(WebApiResource):
    message_fields = {
        "id": fields.String,
        "conversation_id": fields.String,
+        "parent_message_id": fields.String,
        "inputs": fields.Raw,
        "query": fields.String,
        "answer": fields.String(attribute="re_sign_file_url_answer"),
@@ -78,7 +79,7 @@ class MessageListApi(WebApiResource):
    @marshal_with(message_infinite_scroll_pagination_fields)
    def get(self, app_model, end_user):
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        parser = reqparse.RequestParser()
@@ -89,7 +90,7 @@ class MessageListApi(WebApiResource):

        try:
            return MessageService.pagination_by_first_id(
-                app_model, end_user, args["conversation_id"], args["first_id"], args["limit"]
+                app_model, end_user, args["conversation_id"], args["first_id"], args["limit"], "desc"
            )
        except services.errors.conversation.ConversationNotExistsError:
            raise NotFound("Conversation Not Exists.")
@@ -160,7 +161,7 @@ class MessageMoreLikeThisApi(WebApiResource):
 class MessageSuggestedQuestionApi(WebApiResource):
    def get(self, app_model, end_user, message_id):
        app_mode = AppMode.value_of(app_model.mode)
-        if app_mode not in [AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT]:
+        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotCompletionAppError()

        message_id = str(message_id)
--- a/api/core/agent/base_agent_runner.py
+++ b/api/core/agent/base_agent_runner.py
@@ -32,6 +32,7 @@ from core.model_runtime.entities.message_entities import (
 from core.model_runtime.entities.model_entities import ModelFeature
 from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
 from core.model_runtime.utils.encoders import jsonable_encoder
+from core.prompt.utils.extract_thread_messages import extract_thread_messages
 from core.tools.entities.tool_entities import (
    ToolParameter,
    ToolRuntimeVariablePool,
@@ -441,10 +442,12 @@ class BaseAgentRunner(AppRunner):
            .filter(
                Message.conversation_id == self.message.conversation_id,
            )
-            .order_by(Message.created_at.asc())
+            .order_by(Message.created_at.desc())
            .all()
        )

+        messages = list(reversed(extract_thread_messages(messages)))
+
        for message in messages:
            if message.id == self.message.id:
                continue
--- a/api/core/agent/cot_agent_runner.py
+++ b/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
--- a/api/core/agent/cot_chat_agent_runner.py
+++ b/api/core/agent/cot_chat_agent_runner.py
@@ -27,7 +27,7 @@ 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
        """
--- a/api/core/agent/cot_completion_agent_runner.py
+++ b/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
        """
--- a/api/core/agent/fc_agent_runner.py
+++ b/api/core/agent/fc_agent_runner.py
@@ -2,7 +2,7 @@ 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
@@ -370,7 +370,7 @@ 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
@@ -385,7 +385,7 @@ 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
        """
--- a/api/core/agent/output_parser/cot_output_parser.py
+++ b/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

@@ -90,7 +90,7 @@ class CotAgentOutputParser:

                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", " ", ""]:
+                        if last_character not in {"\n", " ", ""}:
                            index += steps
                            yield delta
                            continue
@@ -117,7 +117,7 @@ class CotAgentOutputParser:
                            action_idx = 0

                    if delta.lower() == thought_str[thought_idx] and thought_idx == 0:
-                        if last_character not in ["\n", " ", ""]:
+                        if last_character not in {"\n", " ", ""}:
                            index += steps
                            yield delta
                            continue
--- a/api/core/app/app_config/base_app_config_manager.py
+++ b/api/core/app/app_config/base_app_config_manager.py
@@ -29,7 +29,7 @@ class BaseAppConfigManager:
        additional_features.show_retrieve_source = RetrievalResourceConfigManager.convert(config=config_dict)

        additional_features.file_upload = FileUploadConfigManager.convert(
-            config=config_dict, is_vision=app_mode in [AppMode.CHAT, AppMode.COMPLETION, AppMode.AGENT_CHAT]
+            config=config_dict, is_vision=app_mode in {AppMode.CHAT, AppMode.COMPLETION, AppMode.AGENT_CHAT}
        )

        additional_features.opening_statement, additional_features.suggested_questions = (
--- a/api/core/app/app_config/easy_ui_based_app/agent/manager.py
+++ b/api/core/app/app_config/easy_ui_based_app/agent/manager.py
@@ -18,7 +18,7 @@ class AgentConfigManager:

            if agent_strategy == "function_call":
                strategy = AgentEntity.Strategy.FUNCTION_CALLING
-            elif agent_strategy == "cot" or agent_strategy == "react":
+            elif agent_strategy in {"cot", "react"}:
                strategy = AgentEntity.Strategy.CHAIN_OF_THOUGHT
            else:
                # old configs, try to detect default strategy
@@ -43,10 +43,10 @@ class AgentConfigManager:

                    agent_tools.append(AgentToolEntity(**agent_tool_properties))

-            if "strategy" in config["agent_mode"] and config["agent_mode"]["strategy"] not in [
+            if "strategy" in config["agent_mode"] and config["agent_mode"]["strategy"] not in {
                "react_router",
                "router",
-            ]:
+            }:
                agent_prompt = agent_dict.get("prompt", None) or {}
                # check model mode
                model_mode = config.get("model", {}).get("mode", "completion")
--- a/api/core/app/app_config/easy_ui_based_app/dataset/manager.py
+++ b/api/core/app/app_config/easy_ui_based_app/dataset/manager.py
@@ -167,7 +167,7 @@ class DatasetConfigManager:
            config["agent_mode"]["strategy"] = PlanningStrategy.ROUTER.value

        has_datasets = False
-        if config["agent_mode"]["strategy"] in [PlanningStrategy.ROUTER.value, PlanningStrategy.REACT_ROUTER.value]:
+        if config["agent_mode"]["strategy"] in {PlanningStrategy.ROUTER.value, PlanningStrategy.REACT_ROUTER.value}:
            for tool in config["agent_mode"]["tools"]:
                key = list(tool.keys())[0]
                if key == "dataset":
--- a/api/core/app/app_config/easy_ui_based_app/prompt_template/manager.py
+++ b/api/core/app/app_config/easy_ui_based_app/prompt_template/manager.py
@@ -86,7 +86,7 @@ class PromptTemplateConfigManager:
        if config["prompt_type"] == PromptTemplateEntity.PromptType.ADVANCED.value:
            if not config["chat_prompt_config"] and not config["completion_prompt_config"]:
                raise ValueError(
-                    "chat_prompt_config or completion_prompt_config is required " "when prompt_type is advanced"
+                    "chat_prompt_config or completion_prompt_config is required when prompt_type is advanced"
                )

            model_mode_vals = [mode.value for mode in ModelMode]
--- a/Show More
+++ b/Show More