build: update react refresh ignore

build: eslint plugin react-refresh
Merge branch 'feat/plugins' of github.com:langgenius/dify into feat/plugins
2024-10-22 14:09:31 +08:00 · 2024-10-22 13:49:39 +08:00 · 2024-10-22 13:43:15 +08:00 · 2024-10-22 13:43:01 +08:00 · 2024-10-22 11:43:23 +08:00 · 2024-10-22 11:36:42 +08:00
1412 changed files with 52804 additions and 28044 deletions
@@ -1,11 +1,12 @@
 #!/bin/bash

-cd web && npm install
+npm add -g pnpm@9.12.2
+cd web && pnpm install
 pipx install poetry

 echo 'alias start-api="cd /workspaces/dify/api && poetry run python -m flask run --host 0.0.0.0 --port=5001 --debug"' >> ~/.bashrc
 echo 'alias start-worker="cd /workspaces/dify/api && poetry run python -m celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail,ops_trace,app_deletion"' >> ~/.bashrc
-echo 'alias start-web="cd /workspaces/dify/web && npm run dev"' >> ~/.bashrc
+echo 'alias start-web="cd /workspaces/dify/web && pnpm dev"' >> ~/.bashrc
 echo 'alias start-containers="cd /workspaces/dify/docker && docker-compose -f docker-compose.middleware.yaml -p dify up -d"' >> ~/.bashrc

-source /home/vscode/.bashrc
+source /home/vscode/.bashrc
@@ -27,19 +27,18 @@ jobs:
      - name: Checkout code
        uses: actions/checkout@v4

-      - name: Install Poetry
-        uses: abatilo/actions-poetry@v3
-
      - name: Set up Python ${{ matrix.python-version }}
        uses: actions/setup-python@v5
        with:
          python-version: ${{ matrix.python-version }}
-          cache: 'poetry'
          cache-dependency-path: |
            api/pyproject.toml
            api/poetry.lock

-      - name: Poetry check
+      - name: Install Poetry
+        uses: abatilo/actions-poetry@v3
+
+      - name: Check Poetry lockfile
        run: |
          poetry check -C api --lock
          poetry show -C api
@@ -47,6 +46,9 @@ jobs:
      - name: Install dependencies
        run: poetry install -C api --with dev

+      - name: Check dependencies in pyproject.toml
+        run: poetry run -C api bash dev/pytest/pytest_artifacts.sh
+
      - name: Run Unit tests
        run: poetry run -C api bash dev/pytest/pytest_unit_tests.sh

@@ -5,7 +5,6 @@ on:
    branches:
      - "main"
      - "deploy/dev"
-      - "release/0.10.0-beta"
  release:
    types: [published]

@@ -23,18 +23,17 @@ jobs:
      - name: Checkout code
        uses: actions/checkout@v4

-      - name: Install Poetry
-        uses: abatilo/actions-poetry@v3
-
      - name: Set up Python ${{ matrix.python-version }}
        uses: actions/setup-python@v5
        with:
          python-version: ${{ matrix.python-version }}
-          cache: 'poetry'
          cache-dependency-path: |
            api/pyproject.toml
            api/poetry.lock

+      - name: Install Poetry
+        uses: abatilo/actions-poetry@v3
+
      - name: Install dependencies
        run: poetry install -C api

@@ -24,15 +24,16 @@ jobs:
        with:
          files: api/**

-      - name: Install Poetry
-        uses: abatilo/actions-poetry@v3
-
      - name: Set up Python
        uses: actions/setup-python@v5
        if: steps.changed-files.outputs.any_changed == 'true'
        with:
          python-version: '3.10'

+      - name: Install Poetry
+        if: steps.changed-files.outputs.any_changed == 'true'
+        uses: abatilo/actions-poetry@v3
+
      - name: Python dependencies
        if: steps.changed-files.outputs.any_changed == 'true'
        run: poetry install -C api --only lint
@@ -75,16 +76,16 @@ jobs:
        if: steps.changed-files.outputs.any_changed == 'true'
        with:
          node-version: 20
-          cache: yarn
+          cache: pnpm
          cache-dependency-path: ./web/package.json

      - name: Web dependencies
        if: steps.changed-files.outputs.any_changed == 'true'
-        run: yarn install --frozen-lockfile
+        run: pnpm install --frozen-lockfile

      - name: Web style check
        if: steps.changed-files.outputs.any_changed == 'true'
-        run: yarn run lint
+        run: pnpm run lint


  superlinter:
@@ -32,10 +32,10 @@ jobs:
        with:
          node-version: ${{ matrix.node-version }}
          cache: ''
-          cache-dependency-path: 'yarn.lock'
+          cache-dependency-path: 'pnpm-lock.yaml'

      - name: Install Dependencies
-        run: yarn install
+        run: pnpm install

      - name: Test
-        run: yarn test
+        run: pnpm test
@@ -38,11 +38,11 @@ jobs:

      - name: Install dependencies
        if: env.FILES_CHANGED == 'true'
-        run: yarn install --frozen-lockfile
+        run: pnpm install --frozen-lockfile

      - name: Run npm script
        if: env.FILES_CHANGED == 'true'
-        run: npm run auto-gen-i18n
+        run: pnpm run auto-gen-i18n

      - name: Create Pull Request
        if: env.FILES_CHANGED == 'true'
@@ -34,13 +34,13 @@ jobs:
        if: steps.changed-files.outputs.any_changed == 'true'
        with:
          node-version: 20
-          cache: yarn
+          cache: pnpm
          cache-dependency-path: ./web/package.json

      - name: Install dependencies
        if: steps.changed-files.outputs.any_changed == 'true'
-        run: yarn install --frozen-lockfile
+        run: pnpm install --frozen-lockfile

      - name: Run tests
        if: steps.changed-files.outputs.any_changed == 'true'
-        run: yarn test
+        run: pnpm test
@@ -187,4 +187,7 @@ pyrightconfig.json
 api/.vscode

 .idea/
-.vscode
+.vscode
+
+# pnpm
+/.pnpm-store
@@ -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

@@ -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

@@ -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"/>
@@ -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

@@ -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

@@ -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。



@@ -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

@@ -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.
@@ -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

@@ -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

@@ -20,6 +20,9 @@ FILES_URL=http://127.0.0.1:5001
 # The time in seconds after the signature is rejected
 FILES_ACCESS_TIMEOUT=300

+# Access token expiration time in minutes
+ACCESS_TOKEN_EXPIRE_MINUTES=60
+
 # celery configuration
 CELERY_BROKER_URL=redis://:difyai123456@localhost:6379/1

@@ -39,7 +42,7 @@ 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, supabase
 STORAGE_TYPE=local
 STORAGE_LOCAL_PATH=storage
 S3_USE_AWS_MANAGED_IAM=false
@@ -79,6 +82,12 @@ HUAWEI_OBS_SECRET_KEY=your-secret-key
 HUAWEI_OBS_ACCESS_KEY=your-access-key
 HUAWEI_OBS_SERVER=your-server-url

+# Baidu OBS Storage Configuration
+BAIDU_OBS_BUCKET_NAME=your-bucket-name
+BAIDU_OBS_SECRET_KEY=your-secret-key
+BAIDU_OBS_ACCESS_KEY=your-access-key
+BAIDU_OBS_ENDPOINT=your-server-url
+
 # OCI Storage configuration
 OCI_ENDPOINT=your-endpoint
 OCI_BUCKET_NAME=your-bucket-name
@@ -93,11 +102,16 @@ VOLCENGINE_TOS_ACCESS_KEY=your-access-key
 VOLCENGINE_TOS_SECRET_KEY=your-secret-key
 VOLCENGINE_TOS_REGION=your-region

+# Supabase Storage Configuration
+SUPABASE_BUCKET_NAME=your-bucket-name
+SUPABASE_API_KEY=your-access-key
+SUPABASE_URL=your-server-url
+
 # CORS configuration
 WEB_API_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 CONSOLE_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*

-# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector
+# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, vikingdb
 VECTOR_STORE=weaviate

 # Weaviate configuration
@@ -197,12 +211,28 @@ OPENSEARCH_USER=admin
 OPENSEARCH_PASSWORD=admin
 OPENSEARCH_SECURE=true

+# Baidu configuration
+BAIDU_VECTOR_DB_ENDPOINT=http://127.0.0.1:5287
+BAIDU_VECTOR_DB_CONNECTION_TIMEOUT_MS=30000
+BAIDU_VECTOR_DB_ACCOUNT=root
+BAIDU_VECTOR_DB_API_KEY=dify
+BAIDU_VECTOR_DB_DATABASE=dify
+BAIDU_VECTOR_DB_SHARD=1
+BAIDU_VECTOR_DB_REPLICAS=3
+
+# ViKingDB configuration
+VIKINGDB_ACCESS_KEY=your-ak
+VIKINGDB_SECRET_KEY=your-sk
+VIKINGDB_REGION=cn-shanghai
+VIKINGDB_HOST=api-vikingdb.xxx.volces.com
+VIKINGDB_SCHEMA=http
+VIKINGDB_CONNECTION_TIMEOUT=30
+VIKINGDB_SOCKET_TIMEOUT=30
+
 # Upload configuration
 UPLOAD_FILE_SIZE_LIMIT=15
 UPLOAD_FILE_BATCH_LIMIT=5
 UPLOAD_IMAGE_FILE_SIZE_LIMIT=10
-UPLOAD_VIDEO_FILE_SIZE_LIMIT=100
-UPLOAD_AUDIO_FILE_SIZE_LIMIT=50

 # Model Configuration
 MULTIMODAL_SEND_IMAGE_FORMAT=base64
@@ -267,6 +297,9 @@ 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=

@@ -277,7 +310,6 @@ INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=1000
 WORKFLOW_MAX_EXECUTION_STEPS=500
 WORKFLOW_MAX_EXECUTION_TIME=1200
 WORKFLOW_CALL_MAX_DEPTH=5
-MAX_VARIABLE_SIZE=204800

 # App configuration
 APP_MAX_EXECUTION_TIME=1200
@@ -1,15 +1,8 @@
 {
    "version": "0.2.0",
-    "compounds": [
-        {
-            "name": "Launch Flask and Celery",
-            "configurations": ["Python: Flask", "Python: Celery"]
-        }
-    ],
    "configurations": [
        {
            "name": "Python: Flask",
-            "consoleName": "Flask",
            "type": "debugpy",
            "request": "launch",
            "python": "${workspaceFolder}/.venv/bin/python",
@@ -24,12 +17,12 @@
            },
            "args": [
                "run",
+                "--host=0.0.0.0",
                "--port=5001"
            ]
        },
        {
            "name": "Python: Celery",
-            "consoleName": "Celery",
            "type": "debugpy",
            "request": "launch",
            "python": "${workspaceFolder}/.venv/bin/python",
@@ -52,10 +45,10 @@
                "-c",
                "1",
                "--loglevel",
-                "DEBUG",
+                "info",
                "-Q",
                "dataset,generation,mail,ops_trace,app_deletion"
            ]
-        }
+        },
    ]
-}
+}
@@ -85,3 +85,4 @@
   cd ../
   poetry run -C api bash dev/pytest/pytest_all_tests.sh
   ```
+
@@ -10,43 +10,19 @@ if os.environ.get("DEBUG", "false").lower() != "true":
    grpc.experimental.gevent.init_gevent()

 import json
-import logging
-import sys
 import threading
 import time
 import warnings
-from logging.handlers import RotatingFileHandler

-from flask import Flask, Response, request
-from flask_cors import CORS
-from werkzeug.exceptions import Unauthorized
+from flask import Response

-import contexts
-from commands import register_commands
-from configs import dify_config
+from app_factory import create_app

 # DO NOT REMOVE BELOW
-from events import event_handlers
-from extensions import (
-    ext_celery,
-    ext_code_based_extension,
-    ext_compress,
-    ext_database,
-    ext_hosting_provider,
-    ext_login,
-    ext_mail,
-    ext_migrate,
-    ext_redis,
-    ext_sentry,
-    ext_storage,
-)
-from extensions.ext_database import db
-from extensions.ext_login import login_manager
-from libs.passport import PassportService
+from events import event_handlers  # noqa: F401

 # TODO: Find a way to avoid importing models here
-from models import account, dataset, model, source, task, tool, tools, web
-from services.account_service import AccountService
+from models import account, dataset, model, source, task, tool, tools, web  # noqa: F401

 # DO NOT REMOVE ABOVE

@@ -59,188 +35,12 @@ if hasattr(time, "tzset"):
    time.tzset()


-class DifyApp(Flask):
-    pass
-
-
 # -------------
 # Configuration
 # -------------
-
-
 config_type = os.getenv("EDITION", default="SELF_HOSTED")  # ce edition first


-# ----------------------------
-# Application Factory Function
-# ----------------------------
-
-
-def create_flask_app_with_configs() -> Flask:
-    """
-    create a raw flask app
-    with configs loaded from .env file
-    """
-    dify_app = DifyApp(__name__)
-    dify_app.config.from_mapping(dify_config.model_dump())
-
-    # populate configs into system environment variables
-    for key, value in dify_app.config.items():
-        if isinstance(value, str):
-            os.environ[key] = value
-        elif isinstance(value, int | float | bool):
-            os.environ[key] = str(value)
-        elif value is None:
-            os.environ[key] = ""
-
-    return dify_app
-
-
-def create_app() -> Flask:
-    app = create_flask_app_with_configs()
-
-    app.secret_key = app.config["SECRET_KEY"]
-
-    log_handlers = None
-    log_file = app.config.get("LOG_FILE")
-    if log_file:
-        log_dir = os.path.dirname(log_file)
-        os.makedirs(log_dir, exist_ok=True)
-        log_handlers = [
-            RotatingFileHandler(
-                filename=log_file,
-                maxBytes=1024 * 1024 * 1024,
-                backupCount=5,
-            ),
-            logging.StreamHandler(sys.stdout),
-        ]
-
-    logging.basicConfig(
-        level=app.config.get("LOG_LEVEL"),
-        format=app.config["LOG_FORMAT"],
-        datefmt=app.config.get("LOG_DATEFORMAT"),
-        handlers=log_handlers,
-        force=True,
-    )
-    log_tz = app.config.get("LOG_TZ")
-    if log_tz:
-        from datetime import datetime
-
-        import pytz
-
-        timezone = pytz.timezone(log_tz)
-
-        def time_converter(seconds):
-            return datetime.utcfromtimestamp(seconds).astimezone(timezone).timetuple()
-
-        for handler in logging.root.handlers:
-            assert handler.formatter
-            handler.formatter.converter = time_converter
-    initialize_extensions(app)
-    register_blueprints(app)
-    register_commands(app)
-
-    return app
-
-
-def initialize_extensions(app):
-    # Since the application instance is now created, pass it to each Flask
-    # extension instance to bind it to the Flask application instance (app)
-    ext_compress.init_app(app)
-    ext_code_based_extension.init()
-    ext_database.init_app(app)
-    ext_migrate.init(app, db)
-    ext_redis.init_app(app)
-    ext_storage.init_app(app)
-    ext_celery.init_app(app)
-    ext_login.init_app(app)
-    ext_mail.init_app(app)
-    ext_hosting_provider.init_app(app)
-    ext_sentry.init_app(app)
-
-
-# Flask-Login configuration
-@login_manager.request_loader
-def load_user_from_request(request_from_flask_login):
-    """Load user based on the request."""
-    if request.blueprint not in {"console", "inner_api"}:
-        return None
-    # Check if the user_id contains a dot, indicating the old format
-    auth_header = request.headers.get("Authorization", "")
-    if not auth_header:
-        auth_token = request.args.get("_token")
-        if not auth_token:
-            raise Unauthorized("Invalid Authorization token.")
-    else:
-        if " " not in auth_header:
-            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
-        auth_scheme, auth_token = auth_header.split(None, 1)
-        auth_scheme = auth_scheme.lower()
-        if auth_scheme != "bearer":
-            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
-
-    decoded = PassportService().verify(auth_token)
-    user_id = decoded.get("user_id")
-
-    account = AccountService.load_logged_in_account(account_id=user_id, token=auth_token)
-    if account:
-        contexts.tenant_id.set(account.current_tenant_id)
-    return account
-
-
-@login_manager.unauthorized_handler
-def unauthorized_handler():
-    """Handle unauthorized requests."""
-    return Response(
-        json.dumps({"code": "unauthorized", "message": "Unauthorized."}),
-        status=401,
-        content_type="application/json",
-    )
-
-
-# register blueprint routers
-def register_blueprints(app):
-    from controllers.console import bp as console_app_bp
-    from controllers.files import bp as files_bp
-    from controllers.inner_api import bp as inner_api_bp
-    from controllers.service_api import bp as service_api_bp
-    from controllers.web import bp as web_bp
-
-    CORS(
-        service_api_bp,
-        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-    )
-    app.register_blueprint(service_api_bp)
-
-    CORS(
-        web_bp,
-        resources={r"/*": {"origins": app.config["WEB_API_CORS_ALLOW_ORIGINS"]}},
-        supports_credentials=True,
-        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-        expose_headers=["X-Version", "X-Env"],
-    )
-
-    app.register_blueprint(web_bp)
-
-    CORS(
-        console_app_bp,
-        resources={r"/*": {"origins": app.config["CONSOLE_CORS_ALLOW_ORIGINS"]}},
-        supports_credentials=True,
-        allow_headers=["Content-Type", "Authorization"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-        expose_headers=["X-Version", "X-Env"],
-    )
-
-    app.register_blueprint(console_app_bp)
-
-    CORS(files_bp, allow_headers=["Content-Type"], methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"])
-    app.register_blueprint(files_bp)
-
-    app.register_blueprint(inner_api_bp)
-
-
 # create app
 app = create_app()
 celery = app.extensions["celery"]
@@ -0,0 +1,213 @@
+import os
+
+if os.environ.get("DEBUG", "false").lower() != "true":
+    from gevent import monkey
+
+    monkey.patch_all()
+
+    import grpc.experimental.gevent
+
+    grpc.experimental.gevent.init_gevent()
+
+import json
+import logging
+import sys
+from logging.handlers import RotatingFileHandler
+
+from flask import Flask, Response, request
+from flask_cors import CORS
+from werkzeug.exceptions import Unauthorized
+
+import contexts
+from commands import register_commands
+from configs import dify_config
+from extensions import (
+    ext_celery,
+    ext_code_based_extension,
+    ext_compress,
+    ext_database,
+    ext_hosting_provider,
+    ext_login,
+    ext_mail,
+    ext_migrate,
+    ext_proxy_fix,
+    ext_redis,
+    ext_sentry,
+    ext_storage,
+)
+from extensions.ext_database import db
+from extensions.ext_login import login_manager
+from libs.passport import PassportService
+from services.account_service import AccountService
+
+
+class DifyApp(Flask):
+    pass
+
+
+# ----------------------------
+# Application Factory Function
+# ----------------------------
+def create_flask_app_with_configs() -> Flask:
+    """
+    create a raw flask app
+    with configs loaded from .env file
+    """
+    dify_app = DifyApp(__name__)
+    dify_app.config.from_mapping(dify_config.model_dump())
+
+    # populate configs into system environment variables
+    for key, value in dify_app.config.items():
+        if isinstance(value, str):
+            os.environ[key] = value
+        elif isinstance(value, int | float | bool):
+            os.environ[key] = str(value)
+        elif value is None:
+            os.environ[key] = ""
+
+    return dify_app
+
+
+def create_app() -> Flask:
+    app = create_flask_app_with_configs()
+
+    app.secret_key = app.config["SECRET_KEY"]
+
+    log_handlers = None
+    log_file = app.config.get("LOG_FILE")
+    if log_file:
+        log_dir = os.path.dirname(log_file)
+        os.makedirs(log_dir, exist_ok=True)
+        log_handlers = [
+            RotatingFileHandler(
+                filename=log_file,
+                maxBytes=1024 * 1024 * 1024,
+                backupCount=5,
+            ),
+            logging.StreamHandler(sys.stdout),
+        ]
+
+    logging.basicConfig(
+        level=app.config.get("LOG_LEVEL"),
+        format=app.config.get("LOG_FORMAT"),
+        datefmt=app.config.get("LOG_DATEFORMAT"),
+        handlers=log_handlers,
+        force=True,
+    )
+    log_tz = app.config.get("LOG_TZ")
+    if log_tz:
+        from datetime import datetime
+
+        import pytz
+
+        timezone = pytz.timezone(log_tz)
+
+        def time_converter(seconds):
+            return datetime.utcfromtimestamp(seconds).astimezone(timezone).timetuple()
+
+        for handler in logging.root.handlers:
+            handler.formatter.converter = time_converter
+    initialize_extensions(app)
+    register_blueprints(app)
+    register_commands(app)
+
+    return app
+
+
+def initialize_extensions(app):
+    # Since the application instance is now created, pass it to each Flask
+    # extension instance to bind it to the Flask application instance (app)
+    ext_compress.init_app(app)
+    ext_code_based_extension.init()
+    ext_database.init_app(app)
+    ext_migrate.init(app, db)
+    ext_redis.init_app(app)
+    ext_storage.init_app(app)
+    ext_celery.init_app(app)
+    ext_login.init_app(app)
+    ext_mail.init_app(app)
+    ext_hosting_provider.init_app(app)
+    ext_sentry.init_app(app)
+    ext_proxy_fix.init_app(app)
+
+
+# Flask-Login configuration
+@login_manager.request_loader
+def load_user_from_request(request_from_flask_login):
+    """Load user based on the request."""
+    if request.blueprint not in {"console", "inner_api"}:
+        return None
+    # Check if the user_id contains a dot, indicating the old format
+    auth_header = request.headers.get("Authorization", "")
+    if not auth_header:
+        auth_token = request.args.get("_token")
+        if not auth_token:
+            raise Unauthorized("Invalid Authorization token.")
+    else:
+        if " " not in auth_header:
+            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
+        auth_scheme, auth_token = auth_header.split(None, 1)
+        auth_scheme = auth_scheme.lower()
+        if auth_scheme != "bearer":
+            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
+
+    decoded = PassportService().verify(auth_token)
+    user_id = decoded.get("user_id")
+
+    logged_in_account = AccountService.load_logged_in_account(account_id=user_id)
+    if logged_in_account:
+        contexts.tenant_id.set(logged_in_account.current_tenant_id)
+    return logged_in_account
+
+
+@login_manager.unauthorized_handler
+def unauthorized_handler():
+    """Handle unauthorized requests."""
+    return Response(
+        json.dumps({"code": "unauthorized", "message": "Unauthorized."}),
+        status=401,
+        content_type="application/json",
+    )
+
+
+# register blueprint routers
+def register_blueprints(app):
+    from controllers.console import bp as console_app_bp
+    from controllers.files import bp as files_bp
+    from controllers.inner_api import bp as inner_api_bp
+    from controllers.service_api import bp as service_api_bp
+    from controllers.web import bp as web_bp
+
+    CORS(
+        service_api_bp,
+        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
+        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
+    )
+    app.register_blueprint(service_api_bp)
+
+    CORS(
+        web_bp,
+        resources={r"/*": {"origins": app.config["WEB_API_CORS_ALLOW_ORIGINS"]}},
+        supports_credentials=True,
+        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
+        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
+        expose_headers=["X-Version", "X-Env"],
+    )
+
+    app.register_blueprint(web_bp)
+
+    CORS(
+        console_app_bp,
+        resources={r"/*": {"origins": app.config["CONSOLE_CORS_ALLOW_ORIGINS"]}},
+        supports_credentials=True,
+        allow_headers=["Content-Type", "Authorization"],
+        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
+        expose_headers=["X-Version", "X-Env"],
+    )
+
+    app.register_blueprint(console_app_bp)
+
+    CORS(files_bp, allow_headers=["Content-Type"], methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"])
+    app.register_blueprint(files_bp)
+
+    app.register_blueprint(inner_api_bp)
@@ -19,7 +19,7 @@ from extensions.ext_redis import redis_client
 from libs.helper import email as email_validate
 from libs.password import hash_password, password_pattern, valid_password
 from libs.rsa import generate_key_pair
-from models import Tenant
+from models.account import Tenant
 from models.dataset import Dataset, DatasetCollectionBinding, DocumentSegment
 from models.dataset import Document as DatasetDocument
 from models.model import Account, App, AppAnnotationSetting, AppMode, Conversation, MessageAnnotation
@@ -259,6 +259,25 @@ def migrate_knowledge_vector_database():
    skipped_count = 0
    total_count = 0
    vector_type = dify_config.VECTOR_STORE
+    upper_colletion_vector_types = {
+        VectorType.MILVUS,
+        VectorType.PGVECTOR,
+        VectorType.RELYT,
+        VectorType.WEAVIATE,
+        VectorType.ORACLE,
+        VectorType.ELASTICSEARCH,
+    }
+    lower_colletion_vector_types = {
+        VectorType.ANALYTICDB,
+        VectorType.CHROMA,
+        VectorType.MYSCALE,
+        VectorType.PGVECTO_RS,
+        VectorType.TIDB_VECTOR,
+        VectorType.OPENSEARCH,
+        VectorType.TENCENT,
+        VectorType.BAIDU,
+        VectorType.VIKINGDB,
+    }
    page = 1
    while True:
        try:
@@ -284,11 +303,9 @@ def migrate_knowledge_vector_database():
                        skipped_count = skipped_count + 1
                        continue
                collection_name = ""
-                if vector_type == VectorType.WEAVIATE:
-                    dataset_id = dataset.id
+                dataset_id = dataset.id
+                if vector_type in upper_colletion_vector_types:
                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.WEAVIATE, "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
                elif vector_type == VectorType.QDRANT:
                    if dataset.collection_binding_id:
                        dataset_collection_binding = (
@@ -301,55 +318,15 @@ def migrate_knowledge_vector_database():
                        else:
                            raise ValueError("Dataset Collection Binding not found")
                    else:
-                        dataset_id = dataset.id
                        collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.QDRANT, "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)

-                elif vector_type == VectorType.MILVUS:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.MILVUS, "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.RELYT:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": "relyt", "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.TENCENT:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.TENCENT, "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.PGVECTOR:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.PGVECTOR, "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.OPENSEARCH:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {
-                        "type": VectorType.OPENSEARCH,
-                        "vector_store": {"class_prefix": collection_name},
-                    }
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.ANALYTICDB:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {
-                        "type": VectorType.ANALYTICDB,
-                        "vector_store": {"class_prefix": collection_name},
-                    }
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.ELASTICSEARCH:
-                    dataset_id = dataset.id
-                    index_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": "elasticsearch", "vector_store": {"class_prefix": index_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
+                elif vector_type in lower_colletion_vector_types:
+                    collection_name = Dataset.gen_collection_name_by_id(dataset_id).lower()
                else:
                    raise ValueError(f"Vector store {vector_type} is not supported.")

+                index_struct_dict = {"type": vector_type, "vector_store": {"class_prefix": collection_name}}
+                dataset.index_struct = json.dumps(index_struct_dict)
                vector = Vector(dataset)
                click.echo(f"Migrating dataset {dataset.id}.")

@@ -449,14 +426,14 @@ def convert_to_agent_apps():
        # fetch first 1000 apps
        sql_query = """SELECT a.id AS id FROM apps a
            INNER JOIN app_model_configs am ON a.app_model_config_id=am.id
-            WHERE a.mode = 'chat'
-            AND am.agent_mode is not null
+            WHERE a.mode = 'chat' 
+            AND am.agent_mode is not null 
            AND (
-				am.agent_mode like '%"strategy": "function_call"%'
+				am.agent_mode like '%"strategy": "function_call"%' 
                OR am.agent_mode  like '%"strategy": "react"%'
-			)
+			) 
            AND (
-				am.agent_mode like '{"enabled": true%'
+				am.agent_mode like '{"enabled": true%' 
                OR am.agent_mode like '{"max_iteration": %'
 			) ORDER BY a.created_at DESC LIMIT 1000
        """
@@ -1,4 +1,4 @@
-from typing import Annotated, Literal, Optional
+from typing import Annotated, Optional

 from pydantic import AliasChoices, Field, HttpUrl, NegativeInt, NonNegativeInt, PositiveInt, computed_field
 from pydantic_settings import BaseSettings
@@ -11,11 +11,11 @@ class SecurityConfig(BaseSettings):
    Security-related configurations for the application
    """

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

    RESET_PASSWORD_TOKEN_EXPIRY_HOURS: PositiveInt = Field(
@@ -177,16 +177,6 @@ class FileUploadConfig(BaseSettings):
        default=10,
    )

-    UPLOAD_VIDEO_FILE_SIZE_LIMIT: NonNegativeInt = Field(
-        description="video file size limit in Megabytes for uploading files",
-        default=100,
-    )
-
-    UPLOAD_AUDIO_FILE_SIZE_LIMIT: NonNegativeInt = Field(
-        description="audio file size limit in Megabytes for uploading files",
-        default=50,
-    )
-
    BATCH_UPLOAD_LIMIT: NonNegativeInt = Field(
        description="Maximum number of files allowed in a batch upload operation",
        default=20,
@@ -257,6 +247,12 @@ class HttpConfig(BaseSettings):
        default=None,
    )

+    RESPECT_XFORWARD_HEADERS_ENABLED: bool = Field(
+        description="Enable or disable the X-Forwarded-For Proxy Fix middleware from Werkzeug"
+        " to respect X-* headers to redirect clients",
+        default=False,
+    )
+

 class InnerAPIConfig(BaseSettings):
    """
@@ -359,14 +355,14 @@ class WorkflowConfig(BaseSettings):
    )

    MAX_VARIABLE_SIZE: PositiveInt = Field(
-        description="Maximum size in bytes for a single variable in workflows. Default to 200 KB.",
-        default=200 * 1024,
+        description="Maximum size in bytes for a single variable in workflows. Default to 5KB.",
+        default=5 * 1024,
    )


-class OAuthConfig(BaseSettings):
+class AuthConfig(BaseSettings):
    """
-    Configuration for OAuth authentication
+    Configuration for authentication and OAuth
    """

    OAUTH_REDIRECT_PATH: str = Field(
@@ -375,7 +371,7 @@ class OAuthConfig(BaseSettings):
    )

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

@@ -394,6 +390,11 @@ class OAuthConfig(BaseSettings):
        default=None,
    )

+    ACCESS_TOKEN_EXPIRE_MINUTES: PositiveInt = Field(
+        description="Expiration time for access tokens in minutes",
+        default=60,
+    )
+

 class ModerationConfig(BaseSettings):
    """
@@ -478,7 +479,6 @@ class RagEtlConfig(BaseSettings):
    Configuration for RAG ETL processes
    """

-    # TODO: This config is not only for rag etl, it is also for file upload, we should move it to file upload config
    ETL_TYPE: str = Field(
        description="RAG ETL type ('dify' or 'Unstructured'), default to 'dify'",
        default="dify",
@@ -506,11 +506,16 @@ class DataSetConfig(BaseSettings):
    Configuration for dataset management
    """

-    CLEAN_DAY_SETTING: PositiveInt = Field(
-        description="Interval in days for dataset cleanup operations",
+    PLAN_SANDBOX_CLEAN_DAY_SETTING: PositiveInt = Field(
+        description="Interval in days for dataset cleanup operations - plan: sandbox",
        default=30,
    )

+    PLAN_PRO_CLEAN_DAY_SETTING: PositiveInt = Field(
+        description="Interval in days for dataset cleanup operations - plan: pro and team",
+        default=7,
+    )
+
    DATASET_OPERATOR_ENABLED: bool = Field(
        description="Enable or disable dataset operator functionality",
        default=False,
@@ -540,7 +545,7 @@ class IndexingConfig(BaseSettings):


 class ImageFormatConfig(BaseSettings):
-    MULTIMODAL_SEND_IMAGE_FORMAT: Literal["base64", "url"] = Field(
+    MULTIMODAL_SEND_IMAGE_FORMAT: str = Field(
        description="Format for sending images in multimodal contexts ('base64' or 'url'), default is base64",
        default="base64",
    )
@@ -612,6 +617,7 @@ class PositionConfig(BaseSettings):
 class FeatureConfig(
    # place the configs in alphabet order
    AppExecutionConfig,
+    AuthConfig,  # Changed from OAuthConfig to AuthConfig
    BillingConfig,
    CodeExecutionSandboxConfig,
    DataSetConfig,
@@ -626,14 +632,13 @@ class FeatureConfig(
    MailConfig,
    ModelLoadBalanceConfig,
    ModerationConfig,
-    OAuthConfig,
+    PositionConfig,
    RagEtlConfig,
    SecurityConfig,
    ToolConfig,
    UpdateConfig,
    WorkflowConfig,
    WorkspaceConfig,
-    PositionConfig,
    # hosted services config
    HostedServiceConfig,
    CeleryBeatConfig,
@@ -8,9 +8,11 @@ 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
+from configs.middleware.storage.supabase_storage_config import SupabaseStorageConfig
 from configs.middleware.storage.tencent_cos_storage_config import TencentCloudCOSStorageConfig
 from configs.middleware.storage.volcengine_tos_storage_config import VolcengineTOSStorageConfig
 from configs.middleware.vdb.analyticdb_config import AnalyticdbConfig
@@ -26,6 +28,7 @@ from configs.middleware.vdb.qdrant_config import QdrantConfig
 from configs.middleware.vdb.relyt_config import RelytConfig
 from configs.middleware.vdb.tencent_vector_config import TencentVectorDBConfig
 from configs.middleware.vdb.tidb_vector_config import TiDBVectorConfig
+from configs.middleware.vdb.vikingdb_config import VikingDBConfig
 from configs.middleware.vdb.weaviate_config import WeaviateConfig


@@ -190,6 +193,22 @@ 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,
@@ -200,12 +219,14 @@ class MiddlewareConfig(
    StorageConfig,
    AliyunOSSStorageConfig,
    AzureBlobStorageConfig,
+    BaiduOBSStorageConfig,
    GoogleCloudStorageConfig,
-    TencentCloudCOSStorageConfig,
    HuaweiCloudOBSStorageConfig,
-    VolcengineTOSStorageConfig,
-    S3StorageConfig,
    OCIStorageConfig,
+    S3StorageConfig,
+    SupabaseStorageConfig,
+    TencentCloudCOSStorageConfig,
+    VolcengineTOSStorageConfig,
    # configs of vdb and vdb providers
    VectorStoreConfig,
    AnalyticdbConfig,
@@ -222,5 +243,7 @@ class MiddlewareConfig(
    TiDBVectorConfig,
    WeaviateConfig,
    ElasticsearchConfig,
+    InternalTestConfig,
+    VikingDBConfig,
 ):
    pass
@@ -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,
+    )
@@ -0,0 +1,24 @@
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+
+class SupabaseStorageConfig(BaseModel):
+    """
+    Configuration settings for Supabase Object Storage Service
+    """
+
+    SUPABASE_BUCKET_NAME: Optional[str] = Field(
+        description="Name of the Supabase bucket to store and retrieve objects (e.g., 'dify-bucket')",
+        default=None,
+    )
+
+    SUPABASE_API_KEY: Optional[str] = Field(
+        description="API KEY for authenticating with Supabase",
+        default=None,
+    )
+
+    SUPABASE_URL: Optional[str] = Field(
+        description="URL of the Supabase",
+        default=None,
+    )
@@ -0,0 +1,45 @@
+from typing import Optional
+
+from pydantic import Field, NonNegativeInt, PositiveInt
+from pydantic_settings import BaseSettings
+
+
+class BaiduVectorDBConfig(BaseSettings):
+    """
+    Configuration settings for Baidu Vector Database
+    """
+
+    BAIDU_VECTOR_DB_ENDPOINT: Optional[str] = Field(
+        description="URL of the Baidu Vector Database service (e.g., 'http://vdb.bj.baidubce.com')",
+        default=None,
+    )
+
+    BAIDU_VECTOR_DB_CONNECTION_TIMEOUT_MS: PositiveInt = Field(
+        description="Timeout in milliseconds for Baidu Vector Database operations (default is 30000 milliseconds)",
+        default=30000,
+    )
+
+    BAIDU_VECTOR_DB_ACCOUNT: Optional[str] = Field(
+        description="Account for authenticating with the Baidu Vector Database",
+        default=None,
+    )
+
+    BAIDU_VECTOR_DB_API_KEY: Optional[str] = Field(
+        description="API key for authenticating with the Baidu Vector Database service",
+        default=None,
+    )
+
+    BAIDU_VECTOR_DB_DATABASE: Optional[str] = Field(
+        description="Name of the specific Baidu Vector Database to connect to",
+        default=None,
+    )
+
+    BAIDU_VECTOR_DB_SHARD: PositiveInt = Field(
+        description="Number of shards for the Baidu Vector Database (default is 1)",
+        default=1,
+    )
+
+    BAIDU_VECTOR_DB_REPLICAS: NonNegativeInt = Field(
+        description="Number of replicas for the Baidu Vector Database (default is 3)",
+        default=3,
+    )
@@ -14,7 +14,7 @@ class OracleConfig(BaseSettings):
        default=None,
    )

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

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

-    PGVECTO_RS_PORT: Optional[PositiveInt] = Field(
+    PGVECTO_RS_PORT: PositiveInt = Field(
        description="Port number on which the PostgreSQL server with PGVecto.RS is listening (default is 5431)",
        default=5431,
    )
@@ -0,0 +1,49 @@
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+
+class VikingDBConfig(BaseModel):
+    """
+    Configuration for connecting to Volcengine VikingDB.
+    Refer to the following documentation for details on obtaining credentials:
+    https://www.volcengine.com/docs/6291/65568
+    """
+
+    VIKINGDB_ACCESS_KEY: Optional[str] = Field(
+        description="The Access Key provided by Volcengine VikingDB for API authentication."
+        "Refer to the following documentation for details on obtaining credentials:"
+        "https://www.volcengine.com/docs/6291/65568",
+        default=None,
+    )
+
+    VIKINGDB_SECRET_KEY: Optional[str] = Field(
+        description="The Secret Key provided by Volcengine VikingDB for API authentication.",
+        default=None,
+    )
+
+    VIKINGDB_REGION: str = Field(
+        description="The region of the Volcengine VikingDB service.(e.g., 'cn-shanghai', 'cn-beijing').",
+        default="cn-shanghai",
+    )
+
+    VIKINGDB_HOST: str = Field(
+        description="The host of the Volcengine VikingDB service.(e.g., 'api-vikingdb.volces.com', \
+            'api-vikingdb.mlp.cn-shanghai.volces.com')",
+        default="api-vikingdb.mlp.cn-shanghai.volces.com",
+    )
+
+    VIKINGDB_SCHEME: str = Field(
+        description="The scheme of the Volcengine VikingDB service.(e.g., 'http', 'https').",
+        default="http",
+    )
+
+    VIKINGDB_CONNECTION_TIMEOUT: int = Field(
+        description="The connection timeout of the Volcengine VikingDB service.",
+        default=30,
+    )
+
+    VIKINGDB_SOCKET_TIMEOUT: int = Field(
+        description="The socket timeout of the Volcengine VikingDB service.",
+        default=30,
+    )
@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):

    CURRENT_VERSION: str = Field(
        description="Dify version",
-        default="0.10.0-beta2",
+        default="0.9.2",
    )

    COMMIT_SHA: str = Field(
@@ -1,21 +1,2 @@
-from configs import dify_config
-
 HIDDEN_VALUE = "[__HIDDEN__]"
 UUID_NIL = "00000000-0000-0000-0000-000000000000"
-
-IMAGE_EXTENSIONS = ["jpg", "jpeg", "png", "webp", "gif", "svg"]
-IMAGE_EXTENSIONS.extend([ext.upper() for ext in IMAGE_EXTENSIONS])
-
-VIDEO_EXTENSIONS = ["mp4", "mov", "mpeg", "mpga"]
-VIDEO_EXTENSIONS.extend([ext.upper() for ext in VIDEO_EXTENSIONS])
-
-AUDIO_EXTENSIONS = ["mp3", "m4a", "wav", "webm", "amr"]
-AUDIO_EXTENSIONS.extend([ext.upper() for ext in AUDIO_EXTENSIONS])
-
-DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "pdf", "html", "htm", "xlsx", "xls", "docx", "csv"]
-DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])
-
-if dify_config.ETL_TYPE == "Unstructured":
-    DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "pdf", "html", "htm", "xlsx", "xls"]
-    DOCUMENT_EXTENSIONS.extend(("docx", "csv", "eml", "msg", "pptx", "ppt", "xml", "epub"))
-    DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])
@@ -1,9 +1,7 @@
 from contextvars import ContextVar
-from typing import TYPE_CHECKING

-if TYPE_CHECKING:
-    from core.workflow.entities.variable_pool import VariablePool
+from core.workflow.entities.variable_pool import VariablePool

 tenant_id: ContextVar[str] = ContextVar("tenant_id")

-workflow_variable_pool: ContextVar["VariablePool"] = ContextVar("workflow_variable_pool")
+workflow_variable_pool: ContextVar[VariablePool] = ContextVar("workflow_variable_pool")
@@ -22,8 +22,7 @@ from fields.conversation_fields import (
 )
 from libs.helper import DatetimeString
 from libs.login import login_required
-from models import Conversation, EndUser, Message, MessageAnnotation
-from models.model import AppMode
+from models.model import AppMode, Conversation, EndUser, Message, MessageAnnotation


 class CompletionConversationApi(Resource):
@@ -189,6 +188,7 @@ class ChatConversationApi(Resource):
                        subquery.c.from_end_user_session_id.ilike(keyword_filter),
                    ),
                )
+                .group_by(Conversation.id)
            )

        account = current_user
@@ -12,7 +12,7 @@ from controllers.console.wraps import account_initialization_required
 from extensions.ext_database import db
 from fields.app_fields import app_site_fields
 from libs.login import login_required
-from models import Site
+from models.model import Site


 def parse_app_site_args():
@@ -13,14 +13,14 @@ from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
-from factories import variable_factory
+from core.app.segments import factory
+from core.errors.error import AppInvokeQuotaExceededError
 from fields.workflow_fields import workflow_fields
 from fields.workflow_run_fields import workflow_run_node_execution_fields
 from libs import helper
 from libs.helper import TimestampField, uuid_value
 from libs.login import current_user, login_required
-from models import App
-from models.model import AppMode
+from models.model import App, AppMode
 from services.app_dsl_service import AppDslService
 from services.app_generate_service import AppGenerateService
 from services.errors.app import WorkflowHashNotEqualError
@@ -101,13 +101,9 @@ class DraftWorkflowApi(Resource):

        try:
            environment_variables_list = args.get("environment_variables") or []
-            environment_variables = [
-                variable_factory.build_variable_from_mapping(obj) for obj in environment_variables_list
-            ]
+            environment_variables = [factory.build_variable_from_mapping(obj) for obj in environment_variables_list]
            conversation_variables_list = args.get("conversation_variables") or []
-            conversation_variables = [
-                variable_factory.build_variable_from_mapping(obj) for obj in conversation_variables_list
-            ]
+            conversation_variables = [factory.build_variable_from_mapping(obj) for obj in conversation_variables_list]
            workflow = workflow_service.sync_draft_workflow(
                app_model=app_model,
                graph=args["graph"],
@@ -277,15 +273,17 @@ class DraftWorkflowRunApi(Resource):
        parser.add_argument("files", type=list, required=False, location="json")
        args = parser.parse_args()

-        response = AppGenerateService.generate(
-            app_model=app_model,
-            user=current_user,
-            args=args,
-            invoke_from=InvokeFrom.DEBUGGER,
-            streaming=True,
-        )
+        try:
+            response = AppGenerateService.generate(
+                app_model=app_model, user=current_user, args=args, invoke_from=InvokeFrom.DEBUGGER, streaming=True
+            )

-        return helper.compact_generate_response(response)
+            return helper.compact_generate_response(response)
+        except (ValueError, AppInvokeQuotaExceededError) as e:
+            raise e
+        except Exception as e:
+            logging.exception("internal server error.")
+            raise InternalServerError()


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


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


@@ -10,11 +10,11 @@ from controllers.console import api
 from controllers.console.app.wraps import get_app_model
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
-from enums import WorkflowRunTriggeredFrom
 from extensions.ext_database import db
 from libs.helper import DatetimeString
 from libs.login import login_required
 from models.model import AppMode
+from models.workflow import WorkflowRunTriggeredFrom


 class WorkflowDailyRunsStatistic(Resource):
@@ -5,8 +5,7 @@ from typing import Optional, Union
 from controllers.console.app.error import AppNotFoundError
 from extensions.ext_database import db
 from libs.login import current_user
-from models import App
-from models.model import AppMode
+from models.model import App, AppMode


 def get_app_model(view: Optional[Callable] = None, *, mode: Union[AppMode, list[AppMode]] = None):
@@ -15,7 +15,7 @@ from controllers.console.setup import setup_required
 from extensions.ext_database import db
 from libs.helper import email as email_validate
 from libs.password import hash_password, valid_password
-from models import Account
+from models.account import Account
 from services.account_service import AccountService
 from services.errors.account import RateLimitExceededError

@@ -7,9 +7,9 @@ from flask_restful import Resource, reqparse
 import services
 from controllers.console import api
 from controllers.console.setup import setup_required
-from libs.helper import email, get_remote_ip
+from libs.helper import email, extract_remote_ip
 from libs.password import valid_password
-from models import Account
+from models.account import Account
 from services.account_service import AccountService, TenantService


@@ -40,17 +40,16 @@ class LoginApi(Resource):
                "data": "workspace not found, please contact system admin to invite you to join in a workspace",
            }

-        token = AccountService.login(account, ip_address=get_remote_ip(request))
+        token_pair = AccountService.login(account=account, ip_address=extract_remote_ip(request))

-        return {"result": "success", "data": token}
+        return {"result": "success", "data": token_pair.model_dump()}


 class LogoutApi(Resource):
    @setup_required
    def get(self):
        account = cast(Account, flask_login.current_user)
-        token = request.headers.get("Authorization", "").split(" ")[1]
-        AccountService.logout(account=account, token=token)
+        AccountService.logout(account=account)
        flask_login.logout_user()
        return {"result": "success"}

@@ -106,5 +105,19 @@ class ResetPasswordApi(Resource):
        return {"result": "success"}


+class RefreshTokenApi(Resource):
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("refresh_token", type=str, required=True, location="json")
+        args = parser.parse_args()
+
+        try:
+            new_token_pair = AccountService.refresh_token(args["refresh_token"])
+            return {"result": "success", "data": new_token_pair.model_dump()}
+        except Exception as e:
+            return {"result": "fail", "data": str(e)}, 401
+
+
 api.add_resource(LoginApi, "/login")
 api.add_resource(LogoutApi, "/logout")
+api.add_resource(RefreshTokenApi, "/refresh-token")
@@ -9,10 +9,9 @@ from flask_restful import Resource
 from configs import dify_config
 from constants.languages import languages
 from extensions.ext_database import db
-from libs.helper import get_remote_ip
+from libs.helper import extract_remote_ip
 from libs.oauth import GitHubOAuth, GoogleOAuth, OAuthUserInfo
-from models import Account
-from models.account import AccountStatus
+from models.account import Account, AccountStatus
 from services.account_service import AccountService, RegisterService, TenantService

 from .. import api
@@ -82,9 +81,14 @@ class OAuthCallback(Resource):

        TenantService.create_owner_tenant_if_not_exist(account)

-        token = AccountService.login(account, ip_address=get_remote_ip(request))
+        token_pair = AccountService.login(
+            account=account,
+            ip_address=extract_remote_ip(request),
+        )

-        return redirect(f"{dify_config.CONSOLE_WEB_URL}?console_token={token}")
+        return redirect(
+            f"{dify_config.CONSOLE_WEB_URL}?access_token={token_pair.access_token}&refresh_token={token_pair.refresh_token}"
+        )


 def _get_account_by_openid_or_email(provider: str, user_info: OAuthUserInfo) -> Optional[Account]:
@@ -15,7 +15,8 @@ from core.rag.extractor.notion_extractor import NotionExtractor
 from extensions.ext_database import db
 from fields.data_source_fields import integrate_list_fields, integrate_notion_info_list_fields
 from libs.login import login_required
-from models import DataSourceOauthBinding, Document
+from models.dataset import Document
+from models.source import DataSourceOauthBinding
 from services.dataset_service import DatasetService, DocumentService
 from tasks.document_indexing_sync_task import document_indexing_sync_task

@@ -24,8 +24,8 @@ from fields.app_fields import related_app_list
 from fields.dataset_fields import dataset_detail_fields, dataset_query_detail_fields
 from fields.document_fields import document_status_fields
 from libs.login import login_required
-from models import ApiToken, Dataset, Document, DocumentSegment, UploadFile
-from models.dataset import DatasetPermissionEnum
+from models.dataset import Dataset, DatasetPermissionEnum, Document, DocumentSegment
+from models.model import ApiToken, UploadFile
 from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService


@@ -617,6 +617,8 @@ class DatasetRetrievalSettingApi(Resource):
                | VectorType.CHROMA
                | VectorType.TENCENT
                | VectorType.PGVECTO_RS
+                | VectorType.BAIDU
+                | VectorType.VIKINGDB
            ):
                return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
            case (
@@ -653,6 +655,8 @@ class DatasetRetrievalSettingMockApi(Resource):
                | VectorType.CHROMA
                | VectorType.TENCENT
                | VectorType.PGVECTO_RS
+                | VectorType.BAIDU
+                | VectorType.VIKINGDB
            ):
                return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
            case (
@@ -46,7 +46,8 @@ from fields.document_fields import (
    document_with_segments_fields,
 )
 from libs.login import login_required
-from models import Dataset, DatasetProcessRule, Document, DocumentSegment, UploadFile
+from models.dataset import Dataset, DatasetProcessRule, Document, DocumentSegment
+from models.model import UploadFile
 from services.dataset_service import DatasetService, DocumentService
 from tasks.add_document_to_index_task import add_document_to_index_task
 from tasks.remove_document_from_index_task import remove_document_from_index_task
@@ -24,7 +24,7 @@ from extensions.ext_database import db
 from extensions.ext_redis import redis_client
 from fields.segment_fields import segment_fields
 from libs.login import login_required
-from models import DocumentSegment
+from models.dataset import DocumentSegment
 from services.dataset_service import DatasetService, DocumentService, SegmentService
 from tasks.batch_create_segment_to_index_task import batch_create_segment_to_index_task
 from tasks.disable_segment_from_index_task import disable_segment_from_index_task
@@ -13,6 +13,7 @@ from libs.login import login_required
 from services.dataset_service import DatasetService
 from services.external_knowledge_service import ExternalDatasetService
 from services.hit_testing_service import HitTestingService
+from services.knowledge_service import ExternalDatasetTestService


 def _validate_name(name):
@@ -232,8 +233,31 @@ class ExternalKnowledgeHitTestingApi(Resource):
            raise InternalServerError(str(e))


+class BedrockRetrievalApi(Resource):
+    # this api is only for internal testing
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("retrieval_setting", nullable=False, required=True, type=dict, location="json")
+        parser.add_argument(
+            "query",
+            nullable=False,
+            required=True,
+            type=str,
+        )
+        parser.add_argument("knowledge_id", nullable=False, required=True, type=str)
+        args = parser.parse_args()
+
+        # Call the knowledge retrieval service
+        result = ExternalDatasetTestService.knowledge_retrieval(
+            args["retrieval_setting"], args["query"], args["knowledge_id"]
+        )
+        return result, 200
+
+
 api.add_resource(ExternalKnowledgeHitTestingApi, "/datasets/<uuid:dataset_id>/external-hit-testing")
 api.add_resource(ExternalDatasetCreateApi, "/datasets/external")
 api.add_resource(ExternalApiTemplateListApi, "/datasets/external-knowledge-api")
 api.add_resource(ExternalApiTemplateApi, "/datasets/external-knowledge-api/<uuid:external_knowledge_api_id>")
 api.add_resource(ExternalApiUseCheckApi, "/datasets/external-knowledge-api/<uuid:external_knowledge_api_id>/use-check")
+# this api is only for internal test
+api.add_resource(BedrockRetrievalApi, "/test/retrieval")
@@ -1,12 +1,9 @@
-import urllib.parse
-
 from flask import request
 from flask_login import current_user
 from flask_restful import Resource, marshal_with

 import services
 from configs import dify_config
-from constants import DOCUMENT_EXTENSIONS
 from controllers.console import api
 from controllers.console.datasets.error import (
    FileTooLargeError,
@@ -16,10 +13,9 @@ from controllers.console.datasets.error import (
 )
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
-from core.helper import ssrf_proxy
-from fields.file_fields import file_fields, remote_file_info_fields, upload_config_fields
+from fields.file_fields import file_fields, upload_config_fields
 from libs.login import login_required
-from services.file_service import FileService
+from services.file_service import ALLOWED_EXTENSIONS, UNSTRUCTURED_ALLOWED_EXTENSIONS, FileService

 PREVIEW_WORDS_LIMIT = 3000

@@ -55,7 +51,7 @@ class FileApi(Resource):
        if len(request.files) > 1:
            raise TooManyFilesError()
        try:
-            upload_file = FileService.upload_file(file=file, user=current_user)
+            upload_file = FileService.upload_file(file, current_user)
        except services.errors.file.FileTooLargeError as file_too_large_error:
            raise FileTooLargeError(file_too_large_error.description)
        except services.errors.file.UnsupportedFileTypeError:
@@ -79,24 +75,11 @@ class FileSupportTypeApi(Resource):
    @login_required
    @account_initialization_required
    def get(self):
-        return {"allowed_extensions": DOCUMENT_EXTENSIONS}
-
-
-class RemoteFileInfoApi(Resource):
-    @marshal_with(remote_file_info_fields)
-    def get(self, url):
-        decoded_url = urllib.parse.unquote(url)
-        try:
-            response = ssrf_proxy.head(decoded_url)
-            return {
-                "file_type": response.headers.get("Content-Type", "application/octet-stream"),
-                "file_length": int(response.headers.get("Content-Length", 0)),
-            }
-        except Exception as e:
-            return {"error": str(e)}, 400
+        etl_type = dify_config.ETL_TYPE
+        allowed_extensions = UNSTRUCTURED_ALLOWED_EXTENSIONS if etl_type == "Unstructured" else ALLOWED_EXTENSIONS
+        return {"allowed_extensions": allowed_extensions}


 api.add_resource(FileApi, "/files/upload")
 api.add_resource(FilePreviewApi, "/files/<uuid:file_id>/preview")
 api.add_resource(FileSupportTypeApi, "/files/support-type")
-api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")
@@ -1,88 +1,24 @@
-import logging
+from flask_restful import Resource

-from flask_login import current_user
-from flask_restful import Resource, marshal, reqparse
-from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
-
-import services
 from controllers.console import api
-from controllers.console.app.error import (
-    CompletionRequestError,
-    ProviderModelCurrentlyNotSupportError,
-    ProviderNotInitializeError,
-    ProviderQuotaExceededError,
-)
-from controllers.console.datasets.error import DatasetNotInitializedError
+from controllers.console.datasets.hit_testing_base import DatasetsHitTestingBase
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
-from core.errors.error import (
-    LLMBadRequestError,
-    ModelCurrentlyNotSupportError,
-    ProviderTokenNotInitError,
-    QuotaExceededError,
-)
-from core.model_runtime.errors.invoke import InvokeError
-from fields.hit_testing_fields import hit_testing_record_fields
 from libs.login import login_required
-from services.dataset_service import DatasetService
-from services.hit_testing_service import HitTestingService


-class HitTestingApi(Resource):
+class HitTestingApi(Resource, DatasetsHitTestingBase):
    @setup_required
    @login_required
    @account_initialization_required
    def post(self, dataset_id):
        dataset_id_str = str(dataset_id)

-        dataset = DatasetService.get_dataset(dataset_id_str)
-        if dataset is None:
-            raise NotFound("Dataset not found.")
+        dataset = self.get_and_validate_dataset(dataset_id_str)
+        args = self.parse_args()
+        self.hit_testing_args_check(args)

-        try:
-            DatasetService.check_dataset_permission(dataset, current_user)
-        except services.errors.account.NoPermissionError as e:
-            raise Forbidden(str(e))
-
-        parser = reqparse.RequestParser()
-        parser.add_argument("query", type=str, location="json")
-        parser.add_argument("retrieval_model", type=dict, required=False, location="json")
-        parser.add_argument("external_retrieval_model", type=dict, required=False, location="json")
-        args = parser.parse_args()
-
-        HitTestingService.hit_testing_args_check(args)
-
-        try:
-            response = HitTestingService.retrieve(
-                dataset=dataset,
-                query=args["query"],
-                account=current_user,
-                retrieval_model=args["retrieval_model"],
-                external_retrieval_model=args["external_retrieval_model"],
-                limit=10,
-            )
-
-            return {"query": response["query"], "records": marshal(response["records"], hit_testing_record_fields)}
-        except services.errors.index.IndexNotInitializedError:
-            raise DatasetNotInitializedError()
-        except ProviderTokenNotInitError as ex:
-            raise ProviderNotInitializeError(ex.description)
-        except QuotaExceededError:
-            raise ProviderQuotaExceededError()
-        except ModelCurrentlyNotSupportError:
-            raise ProviderModelCurrentlyNotSupportError()
-        except LLMBadRequestError:
-            raise ProviderNotInitializeError(
-                "No Embedding Model or Reranking Model available. Please configure a valid provider "
-                "in the Settings -> Model Provider."
-            )
-        except InvokeError as e:
-            raise CompletionRequestError(e.description)
-        except ValueError as e:
-            raise ValueError(str(e))
-        except Exception as e:
-            logging.exception("Hit testing failed.")
-            raise InternalServerError(str(e))
+        return self.perform_hit_testing(dataset, args)


 api.add_resource(HitTestingApi, "/datasets/<uuid:dataset_id>/hit-testing")
@@ -0,0 +1,85 @@
+import logging
+
+from flask_login import current_user
+from flask_restful import marshal, reqparse
+from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
+
+import services.dataset_service
+from controllers.console.app.error import (
+    CompletionRequestError,
+    ProviderModelCurrentlyNotSupportError,
+    ProviderNotInitializeError,
+    ProviderQuotaExceededError,
+)
+from controllers.console.datasets.error import DatasetNotInitializedError
+from core.errors.error import (
+    LLMBadRequestError,
+    ModelCurrentlyNotSupportError,
+    ProviderTokenNotInitError,
+    QuotaExceededError,
+)
+from core.model_runtime.errors.invoke import InvokeError
+from fields.hit_testing_fields import hit_testing_record_fields
+from services.dataset_service import DatasetService
+from services.hit_testing_service import HitTestingService
+
+
+class DatasetsHitTestingBase:
+    @staticmethod
+    def get_and_validate_dataset(dataset_id: str):
+        dataset = DatasetService.get_dataset(dataset_id)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+
+        return dataset
+
+    @staticmethod
+    def hit_testing_args_check(args):
+        HitTestingService.hit_testing_args_check(args)
+
+    @staticmethod
+    def parse_args():
+        parser = reqparse.RequestParser()
+
+        parser.add_argument("query", type=str, location="json")
+        parser.add_argument("retrieval_model", type=dict, required=False, location="json")
+        parser.add_argument("external_retrieval_model", type=dict, required=False, location="json")
+        return parser.parse_args()
+
+    @staticmethod
+    def perform_hit_testing(dataset, args):
+        try:
+            response = HitTestingService.retrieve(
+                dataset=dataset,
+                query=args["query"],
+                account=current_user,
+                retrieval_model=args["retrieval_model"],
+                external_retrieval_model=args["external_retrieval_model"],
+                limit=10,
+            )
+            return {"query": response["query"], "records": marshal(response["records"], hit_testing_record_fields)}
+        except services.errors.index.IndexNotInitializedError:
+            raise DatasetNotInitializedError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        except QuotaExceededError:
+            raise ProviderQuotaExceededError()
+        except ModelCurrentlyNotSupportError:
+            raise ProviderModelCurrentlyNotSupportError()
+        except LLMBadRequestError:
+            raise ProviderNotInitializeError(
+                "No Embedding Model or Reranking Model available. Please configure a valid provider "
+                "in the Settings -> Model Provider."
+            )
+        except InvokeError as e:
+            raise CompletionRequestError(e.description)
+        except ValueError as e:
+            raise ValueError(str(e))
+        except Exception as e:
+            logging.exception("Hit testing failed.")
+            raise InternalServerError(str(e))
@@ -11,7 +11,7 @@ from controllers.console.wraps import account_initialization_required, cloud_edi
 from extensions.ext_database import db
 from fields.installed_app_fields import installed_app_list_fields
 from libs.login import login_required
-from models import App, InstalledApp, RecommendedApp
+from models.model import App, InstalledApp, RecommendedApp
 from services.account_service import TenantService


@@ -7,7 +7,7 @@ from werkzeug.exceptions import NotFound
 from controllers.console.wraps import account_initialization_required
 from extensions.ext_database import db
 from libs.login import login_required
-from models import InstalledApp
+from models.model import InstalledApp


 def installed_app_required(view=None):
@@ -4,7 +4,7 @@ from flask import request
 from flask_restful import Resource, reqparse

 from configs import dify_config
-from libs.helper import StrLen, email, get_remote_ip
+from libs.helper import StrLen, email, extract_remote_ip
 from libs.password import valid_password
 from models.model import DifySetup
 from services.account_service import RegisterService, TenantService
@@ -46,7 +46,7 @@ class SetupApi(Resource):

        # setup
        RegisterService.setup(
-            email=args["email"], name=args["name"], password=args["password"], ip_address=get_remote_ip(request)
+            email=args["email"], name=args["name"], password=args["password"], ip_address=extract_remote_ip(request)
        )

        return {"result": "success"}, 201
@@ -20,7 +20,7 @@ from extensions.ext_database import db
 from fields.member_fields import account_fields
 from libs.helper import TimestampField, timezone
 from libs.login import login_required
-from models import AccountIntegrate, InvitationCode
+from models.account import AccountIntegrate, InvitationCode
 from services.account_service import AccountService
 from services.errors.account import CurrentPasswordIncorrectError as ServiceCurrentPasswordIncorrectError

@@ -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)
@@ -360,15 +360,16 @@ class ToolWorkflowProviderCreateApi(Resource):
        args = reqparser.parse_args()

        return WorkflowToolManageService.create_workflow_tool(
-            user_id=user_id,
-            tenant_id=tenant_id,
-            workflow_app_id=args["workflow_app_id"],
-            name=args["name"],
-            label=args["label"],
-            icon=args["icon"],
-            description=args["description"],
-            parameters=args["parameters"],
-            privacy_policy=args["privacy_policy"],
+            user_id,
+            tenant_id,
+            args["workflow_app_id"],
+            args["name"],
+            args["label"],
+            args["icon"],
+            args["description"],
+            args["parameters"],
+            args["privacy_policy"],
+            args.get("labels", []),
        )


@@ -198,7 +198,7 @@ class WebappLogoWorkspaceApi(Resource):
            raise UnsupportedFileTypeError()

        try:
-            upload_file = FileService.upload_file(file=file, user=current_user)
+            upload_file = FileService.upload_file(file, current_user, True)

        except services.errors.file.FileTooLargeError as file_too_large_error:
            raise FileTooLargeError(file_too_large_error.description)
@@ -0,0 +1,7 @@
+from libs.exception import BaseHTTPException
+
+
+class UnsupportedFileTypeError(BaseHTTPException):
+    error_code = "unsupported_file_type"
+    description = "File type not allowed."
+    code = 415
@@ -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

@@ -21,36 +21,7 @@ class ImagePreviewApi(Resource):
            return {"content": "Invalid request."}, 400

        try:
-            generator, mimetype = FileService.get_image_preview(
-                file_id=file_id,
-                timestamp=timestamp,
-                nonce=nonce,
-                sign=sign,
-            )
-        except services.errors.file.UnsupportedFileTypeError:
-            raise UnsupportedFileTypeError()
-
-        return Response(generator, mimetype=mimetype)
-
-
-class FilePreviewApi(Resource):
-    def get(self, file_id):
-        file_id = str(file_id)
-
-        timestamp = request.args.get("timestamp")
-        nonce = request.args.get("nonce")
-        sign = request.args.get("sign")
-
-        if not timestamp or not nonce or not sign:
-            return {"content": "Invalid request."}, 400
-
-        try:
-            generator, mimetype = FileService.get_signed_file_preview(
-                file_id=file_id,
-                timestamp=timestamp,
-                nonce=nonce,
-                sign=sign,
-            )
+            generator, mimetype = FileService.get_image_preview(file_id, timestamp, nonce, sign)
        except services.errors.file.UnsupportedFileTypeError:
            raise UnsupportedFileTypeError()

@@ -78,11 +49,4 @@ class WorkspaceWebappLogoApi(Resource):


 api.add_resource(ImagePreviewApi, "/files/<uuid:file_id>/image-preview")
-api.add_resource(FilePreviewApi, "/files/<uuid:file_id>/file-preview")
 api.add_resource(WorkspaceWebappLogoApi, "/files/workspaces/<uuid:workspace_id>/webapp-logo")
-
-
-class UnsupportedFileTypeError(BaseHTTPException):
-    error_code = "unsupported_file_type"
-    description = "File type not allowed."
-    code = 415
@@ -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
@@ -5,7 +5,6 @@ from libs.external_api import ExternalApi
 bp = Blueprint("service_api", __name__, url_prefix="/v1")
 api = ExternalApi(bp)

-
 from . import index
 from .app import app, audio, completion, conversation, file, message, workflow
-from .dataset import dataset, document, segment
+from .dataset import dataset, document, hit_testing, segment
@@ -0,0 +1,17 @@
+from controllers.console.datasets.hit_testing_base import DatasetsHitTestingBase
+from controllers.service_api import api
+from controllers.service_api.wraps import DatasetApiResource
+
+
+class HitTestingApi(DatasetApiResource, DatasetsHitTestingBase):
+    def post(self, tenant_id, dataset_id):
+        dataset_id_str = str(dataset_id)
+
+        dataset = self.get_and_validate_dataset(dataset_id_str)
+        args = self.parse_args()
+        self.hit_testing_args_check(args)
+
+        return self.perform_hit_testing(dataset, args)
+
+
+api.add_resource(HitTestingApi, "/datasets/<uuid:dataset_id>/hit-testing")
@@ -1,5 +1,3 @@
-import urllib.parse
-
 from flask import request
 from flask_restful import marshal_with

@@ -7,8 +5,7 @@ import services
 from controllers.web import api
 from controllers.web.error import FileTooLargeError, NoFileUploadedError, TooManyFilesError, UnsupportedFileTypeError
 from controllers.web.wraps import WebApiResource
-from core.helper import ssrf_proxy
-from fields.file_fields import file_fields, remote_file_info_fields
+from fields.file_fields import file_fields
 from services.file_service import FileService


@@ -34,19 +31,4 @@ class FileApi(WebApiResource):
        return upload_file, 201


-class RemoteFileInfoApi(WebApiResource):
-    @marshal_with(remote_file_info_fields)
-    def get(self, url):
-        decoded_url = urllib.parse.unquote(url)
-        try:
-            response = ssrf_proxy.head(decoded_url)
-            return {
-                "file_type": response.headers.get("Content-Type", "application/octet-stream"),
-                "file_length": int(response.headers.get("Content-Length", 0)),
-            }
-        except Exception as e:
-            return {"error": str(e)}, 400
-
-
 api.add_resource(FileApi, "/files/upload")
-api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")
@@ -22,7 +22,6 @@ from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotIni
 from core.model_runtime.errors.invoke import InvokeError
 from fields.conversation_fields import message_file_fields
 from fields.message_fields import agent_thought_fields
-from fields.raws import FilesContainedField
 from libs import helper
 from libs.helper import TimestampField, uuid_value
 from models.model import AppMode
@@ -59,7 +58,7 @@ class MessageListApi(WebApiResource):
        "id": fields.String,
        "conversation_id": fields.String,
        "parent_message_id": fields.String,
-        "inputs": FilesContainedField,
+        "inputs": fields.Raw,
        "query": fields.String,
        "answer": fields.String(attribute="re_sign_file_url_answer"),
        "message_files": fields.List(fields.Nested(message_file_fields), attribute="files"),
@@ -16,14 +16,13 @@ from core.app.entities.app_invoke_entities import (
 )
 from core.callback_handler.agent_tool_callback_handler import DifyAgentCallbackHandler
 from core.callback_handler.index_tool_callback_handler import DatasetIndexToolCallbackHandler
-from core.file import file_manager
+from core.file.message_file_parser import MessageFileParser
 from core.memory.token_buffer_memory import TokenBufferMemory
 from core.model_manager import ModelInstance
-from core.model_runtime.entities import (
+from core.model_runtime.entities.llm_entities import LLMUsage
+from core.model_runtime.entities.message_entities import (
    AssistantPromptMessage,
-    LLMUsage,
    PromptMessage,
-    PromptMessageContent,
    PromptMessageTool,
    SystemPromptMessage,
    TextPromptMessageContent,
@@ -41,8 +40,8 @@ from core.tools.entities.tool_entities import (
 from core.tools.tool.dataset_retriever_tool import DatasetRetrieverTool
 from core.tools.tool.tool import Tool
 from core.tools.tool_manager import ToolManager
+from core.tools.utils.tool_parameter_converter import ToolParameterConverter
 from extensions.ext_database import db
-from factories import file_factory
 from models.model import Conversation, Message, MessageAgentThought
 from models.tools import ToolConversationVariables

@@ -67,6 +66,23 @@ class BaseAgentRunner(AppRunner):
        db_variables: Optional[ToolConversationVariables] = None,
        model_instance: ModelInstance = None,
    ) -> None:
+        """
+        Agent runner
+        :param tenant_id: tenant id
+        :param application_generate_entity: application generate entity
+        :param conversation: conversation
+        :param app_config: app generate entity
+        :param model_config: model config
+        :param config: dataset config
+        :param queue_manager: queue manager
+        :param message: message
+        :param user_id: user id
+        :param memory: memory
+        :param prompt_messages: prompt messages
+        :param variables_pool: variables pool
+        :param db_variables: db variables
+        :param model_instance: model instance
+        """
        self.tenant_id = tenant_id
        self.application_generate_entity = application_generate_entity
        self.conversation = conversation
@@ -164,7 +180,7 @@ class BaseAgentRunner(AppRunner):
            if parameter.form != ToolParameter.ToolParameterForm.LLM:
                continue

-            parameter_type = parameter.type.as_normal_type()
+            parameter_type = ToolParameterConverter.get_parameter_type(parameter.type)
            enum = []
            if parameter.type == ToolParameter.ToolParameterType.SELECT:
                enum = [option.value for option in parameter.options]
@@ -249,7 +265,7 @@ class BaseAgentRunner(AppRunner):
            if parameter.form != ToolParameter.ToolParameterForm.LLM:
                continue

-            parameter_type = parameter.type.as_normal_type()
+            parameter_type = ToolParameterConverter.get_parameter_type(parameter.type)
            enum = []
            if parameter.type == ToolParameter.ToolParameterType.SELECT:
                enum = [option.value for option in parameter.options]
@@ -495,24 +511,26 @@ class BaseAgentRunner(AppRunner):
        return result

    def organize_agent_user_prompt(self, message: Message) -> UserPromptMessage:
+        message_file_parser = MessageFileParser(
+            tenant_id=self.tenant_id,
+            app_id=self.app_config.app_id,
+        )
+
        files = message.message_files
        if files:
            file_extra_config = FileUploadConfigManager.convert(message.app_model_config.to_dict())

            if file_extra_config:
-                file_objs = file_factory.build_from_message_files(
-                    message_files=files, tenant_id=self.tenant_id, config=file_extra_config
-                )
+                file_objs = message_file_parser.transform_message_files(files, file_extra_config)
            else:
                file_objs = []

            if not file_objs:
                return UserPromptMessage(content=message.query)
            else:
-                prompt_message_contents: list[PromptMessageContent] = []
-                prompt_message_contents.append(TextPromptMessageContent(data=message.query))
+                prompt_message_contents = [TextPromptMessageContent(data=message.query)]
                for file_obj in file_objs:
-                    prompt_message_contents.append(file_manager.to_prompt_message_content(file_obj))
+                    prompt_message_contents.append(file_obj.prompt_message_content)

                return UserPromptMessage(content=prompt_message_contents)
        else:
@@ -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
@@ -1,11 +1,9 @@
 import json

 from core.agent.cot_agent_runner import CotAgentRunner
-from core.file import file_manager
-from core.model_runtime.entities import (
+from core.model_runtime.entities.message_entities import (
    AssistantPromptMessage,
    PromptMessage,
-    PromptMessageContent,
    SystemPromptMessage,
    TextPromptMessageContent,
    UserPromptMessage,
@@ -29,15 +27,14 @@ class CotChatAgentRunner(CotAgentRunner):

        return SystemPromptMessage(content=system_prompt)

-    def _organize_user_query(self, query, prompt_messages: list[PromptMessage] = None) -> list[PromptMessage]:
+    def _organize_user_query(self, query, prompt_messages: list[PromptMessage]) -> list[PromptMessage]:
        """
        Organize user query
        """
        if self.files:
-            prompt_message_contents: list[PromptMessageContent] = []
-            prompt_message_contents.append(TextPromptMessageContent(data=query))
+            prompt_message_contents = [TextPromptMessageContent(data=query)]
            for file_obj in self.files:
-                prompt_message_contents.append(file_manager.to_prompt_message_content(file_obj))
+                prompt_message_contents.append(file_obj.prompt_message_content)

            prompt_messages.append(UserPromptMessage(content=prompt_message_contents))
        else:
@@ -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
        """
@@ -2,20 +2,15 @@ import json
 import logging
 from collections.abc import Generator
 from copy import deepcopy
-from typing import Any, Union
+from typing import Any, Optional, Union

 from core.agent.base_agent_runner import BaseAgentRunner
 from core.app.apps.base_app_queue_manager import PublishFrom
 from core.app.entities.queue_entities import QueueAgentThoughtEvent, QueueMessageEndEvent, QueueMessageFileEvent
-from core.file import file_manager
-from core.model_runtime.entities import (
+from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
+from core.model_runtime.entities.message_entities import (
    AssistantPromptMessage,
-    LLMResult,
-    LLMResultChunk,
-    LLMResultChunkDelta,
-    LLMUsage,
    PromptMessage,
-    PromptMessageContent,
    PromptMessageContentType,
    SystemPromptMessage,
    TextPromptMessageContent,
@@ -375,7 +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
@@ -390,15 +385,14 @@ class FunctionCallAgentRunner(BaseAgentRunner):

        return prompt_messages

-    def _organize_user_query(self, query, prompt_messages: list[PromptMessage] = None) -> list[PromptMessage]:
+    def _organize_user_query(self, query, prompt_messages: list[PromptMessage]) -> list[PromptMessage]:
        """
        Organize user query
        """
        if self.files:
-            prompt_message_contents: list[PromptMessageContent] = []
-            prompt_message_contents.append(TextPromptMessageContent(data=query))
+            prompt_message_contents = [TextPromptMessageContent(data=query)]
            for file_obj in self.files:
-                prompt_message_contents.append(file_manager.to_prompt_message_content(file_obj))
+                prompt_message_contents.append(file_obj.prompt_message_content)

            prompt_messages.append(UserPromptMessage(content=prompt_message_contents))
        else:
@@ -14,7 +14,7 @@ class CotAgentOutputParser:
    ) -> Generator[Union[str, AgentScratchpadUnit.Action], None, None]:
        def parse_action(json_str):
            try:
-                action = json.loads(json_str)
+                action = json.loads(json_str, strict=False)
                action_name = None
                action_input = None

@@ -62,6 +62,8 @@ class CotAgentOutputParser:
        thought_str = "thought:"
        thought_idx = 0

+        last_character = ""
+
        for response in llm_response:
            if response.delta.usage:
                usage_dict["usage"] = response.delta.usage
@@ -74,35 +76,38 @@ class CotAgentOutputParser:
            while index < len(response):
                steps = 1
                delta = response[index : index + steps]
-                last_character = response[index - 1] if index > 0 else ""
+                yield_delta = False

                if delta == "`":
+                    last_character = delta
                    code_block_cache += delta
                    code_block_delimiter_count += 1
                else:
                    if not in_code_block:
                        if code_block_delimiter_count > 0:
+                            last_character = delta
                            yield code_block_cache
                        code_block_cache = ""
                    else:
+                        last_character = delta
                        code_block_cache += delta
                    code_block_delimiter_count = 0

                if not in_code_block and not in_json:
                    if delta.lower() == action_str[action_idx] and action_idx == 0:
                        if last_character not in {"\n", " ", ""}:
+                            yield_delta = True
+                        else:
+                            last_character = delta
+                            action_cache += delta
+                            action_idx += 1
+                            if action_idx == len(action_str):
+                                action_cache = ""
+                                action_idx = 0
                            index += steps
-                            yield delta
                            continue
-
-                        action_cache += delta
-                        action_idx += 1
-                        if action_idx == len(action_str):
-                            action_cache = ""
-                            action_idx = 0
-                        index += steps
-                        continue
                    elif delta.lower() == action_str[action_idx] and action_idx > 0:
+                        last_character = delta
                        action_cache += delta
                        action_idx += 1
                        if action_idx == len(action_str):
@@ -112,24 +117,25 @@ class CotAgentOutputParser:
                        continue
                    else:
                        if action_cache:
+                            last_character = delta
                            yield action_cache
                            action_cache = ""
                            action_idx = 0

                    if delta.lower() == thought_str[thought_idx] and thought_idx == 0:
                        if last_character not in {"\n", " ", ""}:
+                            yield_delta = True
+                        else:
+                            last_character = delta
+                            thought_cache += delta
+                            thought_idx += 1
+                            if thought_idx == len(thought_str):
+                                thought_cache = ""
+                                thought_idx = 0
                            index += steps
-                            yield delta
                            continue
-
-                        thought_cache += delta
-                        thought_idx += 1
-                        if thought_idx == len(thought_str):
-                            thought_cache = ""
-                            thought_idx = 0
-                        index += steps
-                        continue
                    elif delta.lower() == thought_str[thought_idx] and thought_idx > 0:
+                        last_character = delta
                        thought_cache += delta
                        thought_idx += 1
                        if thought_idx == len(thought_str):
@@ -139,12 +145,20 @@ class CotAgentOutputParser:
                        continue
                    else:
                        if thought_cache:
+                            last_character = delta
                            yield thought_cache
                            thought_cache = ""
                            thought_idx = 0

+                    if yield_delta:
+                        index += steps
+                        last_character = delta
+                        yield delta
+                        continue
+
                if code_block_delimiter_count == 3:
                    if in_code_block:
+                        last_character = delta
                        yield from extra_json_from_code_block(code_block_cache)
                        code_block_cache = ""

@@ -156,8 +170,10 @@ class CotAgentOutputParser:
                    if delta == "{":
                        json_quote_count += 1
                        in_json = True
+                        last_character = delta
                        json_cache += delta
                    elif delta == "}":
+                        last_character = delta
                        json_cache += delta
                        if json_quote_count > 0:
                            json_quote_count -= 1
@@ -168,16 +184,19 @@ class CotAgentOutputParser:
                                continue
                    else:
                        if in_json:
+                            last_character = delta
                            json_cache += delta

                    if got_json:
                        got_json = False
+                        last_character = delta
                        yield parse_action(json_cache)
                        json_cache = ""
                        json_quote_count = 0
                        in_json = False

                if not in_code_block and not in_json:
+                    last_character = delta
                    yield delta.replace("`", "")

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

@@ -1,12 +1,11 @@
-from collections.abc import Sequence
 from enum import Enum
 from typing import Any, Optional

-from pydantic import BaseModel, Field
+from pydantic import BaseModel

-from core.file import FileExtraConfig, FileTransferMethod, FileType
+from core.file.file_obj import FileExtraConfig
 from core.model_runtime.entities.message_entities import PromptMessageRole
-from models.model import AppMode
+from models import AppMode


 class ModelConfigEntity(BaseModel):
@@ -70,7 +69,7 @@ class PromptTemplateEntity(BaseModel):
        ADVANCED = "advanced"

        @classmethod
-        def value_of(cls, value: str):
+        def value_of(cls, value: str) -> "PromptType":
            """
            Get value of given mode.

@@ -94,8 +93,6 @@ class VariableEntityType(str, Enum):
    PARAGRAPH = "paragraph"
    NUMBER = "number"
    EXTERNAL_DATA_TOOL = "external_data_tool"
-    FILE = "file"
-    FILE_LIST = "file-list"


 class VariableEntity(BaseModel):
@@ -105,14 +102,13 @@ class VariableEntity(BaseModel):

    variable: str
    label: str
-    description: str = ""
+    description: Optional[str] = None
    type: VariableEntityType
    required: bool = False
    max_length: Optional[int] = None
-    options: Sequence[str] = Field(default_factory=list)
-    allowed_file_types: Sequence[FileType] = Field(default_factory=list)
-    allowed_file_extensions: Sequence[str] = Field(default_factory=list)
-    allowed_file_upload_methods: Sequence[FileTransferMethod] = Field(default_factory=list)
+    options: Optional[list[str]] = None
+    default: Optional[str] = None
+    hint: Optional[str] = None


 class ExternalDataVariableEntity(BaseModel):
@@ -140,7 +136,7 @@ class DatasetRetrieveConfigEntity(BaseModel):
        MULTIPLE = "multiple"

        @classmethod
-        def value_of(cls, value: str):
+        def value_of(cls, value: str) -> "RetrieveStrategy":
            """
            Get value of given mode.

@@ -1,13 +1,12 @@
 from collections.abc import Mapping
-from typing import Any
+from typing import Any, Optional

-from core.file.models import FileExtraConfig
-from models import FileUploadConfig
+from core.file.file_obj import FileExtraConfig


 class FileUploadConfigManager:
    @classmethod
-    def convert(cls, config: Mapping[str, Any], is_vision: bool = True):
+    def convert(cls, config: Mapping[str, Any], is_vision: bool = True) -> Optional[FileExtraConfig]:
        """
        Convert model config to model config

@@ -16,18 +15,19 @@ class FileUploadConfigManager:
        """
        file_upload_dict = config.get("file_upload")
        if file_upload_dict:
-            if file_upload_dict.get("enabled"):
-                data = {
-                    "image_config": {
-                        "number_limits": file_upload_dict["number_limits"],
-                        "transfer_methods": file_upload_dict["allowed_file_upload_methods"],
+            if file_upload_dict.get("image"):
+                if "enabled" in file_upload_dict["image"] and file_upload_dict["image"]["enabled"]:
+                    image_config = {
+                        "number_limits": file_upload_dict["image"]["number_limits"],
+                        "transfer_methods": file_upload_dict["image"]["transfer_methods"],
                    }
-                }

-                if is_vision:
-                    data["image_config"]["detail"] = file_upload_dict.get("image", {}).get("detail", "low")
+                    if is_vision:
+                        image_config["detail"] = file_upload_dict["image"]["detail"]

-                return FileExtraConfig.model_validate(data)
+                    return FileExtraConfig(image_config=image_config)
+
+        return None

    @classmethod
    def validate_and_set_defaults(cls, config: dict, is_vision: bool = True) -> tuple[dict, list[str]]:
@@ -39,7 +39,29 @@ class FileUploadConfigManager:
        """
        if not config.get("file_upload"):
            config["file_upload"] = {}
-        else:
-            FileUploadConfig.model_validate(config["file_upload"])
+
+        if not isinstance(config["file_upload"], dict):
+            raise ValueError("file_upload must be of dict type")
+
+        # check image config
+        if not config["file_upload"].get("image"):
+            config["file_upload"]["image"] = {"enabled": False}
+
+        if config["file_upload"]["image"]["enabled"]:
+            number_limits = config["file_upload"]["image"]["number_limits"]
+            if number_limits < 1 or number_limits > 6:
+                raise ValueError("number_limits must be in [1, 6]")
+
+            if is_vision:
+                detail = config["file_upload"]["image"]["detail"]
+                if detail not in {"high", "low"}:
+                    raise ValueError("detail must be in ['high', 'low']")
+
+            transfer_methods = config["file_upload"]["image"]["transfer_methods"]
+            if not isinstance(transfer_methods, list):
+                raise ValueError("transfer_methods must be of list type")
+            for method in transfer_methods:
+                if method not in {"remote_url", "local_file"}:
+                    raise ValueError("transfer_methods must be in ['remote_url', 'local_file']")

        return config, ["file_upload"]
@@ -17,6 +17,6 @@ class WorkflowVariablesConfigManager:

        # variables
        for variable in user_input_form:
-            variables.append(VariableEntity.model_validate(variable))
+            variables.append(VariableEntity(**variable))

        return variables
@@ -10,6 +10,7 @@ from flask import Flask, current_app
 from pydantic import ValidationError

 import contexts
+from constants import UUID_NIL
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
 from core.app.apps.advanced_chat.app_config_manager import AdvancedChatAppConfigManager
 from core.app.apps.advanced_chat.app_runner import AdvancedChatAppRunner
@@ -20,11 +21,10 @@ from core.app.apps.message_based_app_generator import MessageBasedAppGenerator
 from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueManager
 from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity, InvokeFrom
 from core.app.entities.task_entities import ChatbotAppBlockingResponse, ChatbotAppStreamResponse
+from core.file.message_file_parser import MessageFileParser
 from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
 from core.ops.ops_trace_manager import TraceQueueManager
-from enums import CreatedByRole
 from extensions.ext_database import db
-from factories import file_factory
 from models.account import Account
 from models.model import App, Conversation, EndUser, Message
 from models.workflow import Workflow
@@ -96,16 +96,10 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):

        # parse files
        files = args["files"] if args.get("files") else []
+        message_file_parser = MessageFileParser(tenant_id=app_model.tenant_id, app_id=app_model.id)
        file_extra_config = FileUploadConfigManager.convert(workflow.features_dict, is_vision=False)
-        role = CreatedByRole.ACCOUNT if isinstance(user, Account) else CreatedByRole.END_USER
        if file_extra_config:
-            file_objs = file_factory.build_from_mappings(
-                mappings=files,
-                tenant_id=app_model.tenant_id,
-                user_id=user.id,
-                role=role,
-                config=file_extra_config,
-            )
+            file_objs = message_file_parser.validate_and_transform_files_arg(files, file_extra_config, user)
        else:
            file_objs = []

@@ -113,30 +107,29 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
        app_config = AdvancedChatAppConfigManager.get_app_config(app_model=app_model, workflow=workflow)

        # get tracing instance
-        trace_manager = TraceQueueManager(
-            app_id=app_model.id, user_id=user.id if isinstance(user, Account) else user.session_id
-        )
+        user_id = user.id if isinstance(user, Account) else user.session_id
+        trace_manager = TraceQueueManager(app_model.id, user_id)

        if invoke_from == InvokeFrom.DEBUGGER:
            # always enable retriever resource in debugger mode
            app_config.additional_features.show_retrieve_source = True

+        workflow_run_id = str(uuid.uuid4())
        # init application generate entity
        application_generate_entity = AdvancedChatAppGenerateEntity(
            task_id=str(uuid.uuid4()),
            app_config=app_config,
            conversation_id=conversation.id if conversation else None,
-            inputs=conversation.inputs
-            if conversation
-            else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config, user_id=user.id, role=role),
+            inputs=conversation.inputs if conversation else self._get_cleaned_inputs(inputs, app_config),
            query=query,
            files=file_objs,
-            parent_message_id=args.get("parent_message_id"),
+            parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
            user_id=user.id,
            stream=stream,
            invoke_from=invoke_from,
            extras=extras,
            trace_manager=trace_manager,
+            workflow_run_id=workflow_run_id,
        )
        contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)

@@ -1,26 +1,30 @@
 import logging
+import os
 from collections.abc import Mapping
 from typing import Any, cast

 from sqlalchemy import select
 from sqlalchemy.orm import Session

-from configs import dify_config
 from core.app.apps.advanced_chat.app_config_manager import AdvancedChatAppConfig
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.apps.workflow_app_runner import WorkflowBasedAppRunner
-from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity, InvokeFrom
+from core.app.apps.workflow_logging_callback import WorkflowLoggingCallback
+from core.app.entities.app_invoke_entities import (
+    AdvancedChatAppGenerateEntity,
+    InvokeFrom,
+)
 from core.app.entities.queue_entities import (
    QueueAnnotationReplyEvent,
    QueueStopEvent,
    QueueTextChunkEvent,
 )
 from core.moderation.base import ModerationError
-from core.workflow.callbacks import WorkflowCallback, WorkflowLoggingCallback
+from core.workflow.callbacks.base_workflow_callback import WorkflowCallback
+from core.workflow.entities.node_entities import UserFrom
 from core.workflow.entities.variable_pool import VariablePool
 from core.workflow.enums import SystemVariableKey
 from core.workflow.workflow_entry import WorkflowEntry
-from enums import UserFrom
 from extensions.ext_database import db
 from models.model import App, Conversation, EndUser, Message
 from models.workflow import ConversationVariable, WorkflowType
@@ -40,6 +44,12 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
        conversation: Conversation,
        message: Message,
    ) -> None:
+        """
+        :param application_generate_entity: application generate entity
+        :param queue_manager: application queue manager
+        :param conversation: conversation
+        :param message: message
+        """
        super().__init__(queue_manager)

        self.application_generate_entity = application_generate_entity
@@ -47,6 +57,10 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
        self.message = message

    def run(self) -> None:
+        """
+        Run application
+        :return:
+        """
        app_config = self.application_generate_entity.app_config
        app_config = cast(AdvancedChatAppConfig, app_config)

@@ -67,7 +81,7 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
            user_id = self.application_generate_entity.user_id

        workflow_callbacks: list[WorkflowCallback] = []
-        if dify_config.DEBUG:
+        if bool(os.environ.get("DEBUG", "False").lower() == "true"):
            workflow_callbacks.append(WorkflowLoggingCallback())

        if self.application_generate_entity.single_iteration_run:
@@ -135,6 +149,9 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
                SystemVariableKey.CONVERSATION_ID: self.conversation.id,
                SystemVariableKey.USER_ID: user_id,
                SystemVariableKey.DIALOGUE_COUNT: conversation_dialogue_count,
+                SystemVariableKey.APP_ID: app_config.app_id,
+                SystemVariableKey.WORKFLOW_ID: app_config.workflow_id,
+                SystemVariableKey.WORKFLOW_RUN_ID: self.application_generate_entity.workflow_run_id,
            }

            # init variable pool
@@ -184,6 +201,15 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
        query: str,
        message_id: str,
    ) -> bool:
+        """
+        Handle input moderation
+        :param app_record: app record
+        :param app_generate_entity: application generate entity
+        :param inputs: inputs
+        :param query: query
+        :param message_id: message id
+        :return:
+        """
        try:
            # process sensitive_word_avoidance
            _, inputs, query = self.moderation_for_inputs(
@@ -203,6 +229,14 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
    def handle_annotation_reply(
        self, app_record: App, message: Message, query: str, app_generate_entity: AdvancedChatAppGenerateEntity
    ) -> bool:
+        """
+        Handle annotation reply
+        :param app_record: app record
+        :param message: message
+        :param query: query
+        :param app_generate_entity: application generate entity
+        """
+        # annotation reply
        annotation_reply = self.query_app_annotations_to_reply(
            app_record=app_record,
            message=message,
@@ -224,6 +258,8 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
    def _complete_with_stream_output(self, text: str, stopped_by: QueueStopEvent.StopBy) -> None:
        """
        Direct output
+        :param text: text
+        :return:
        """
        self._publish_event(QueueTextChunkEvent(text=text))

@@ -1,7 +1,7 @@
 import json
 import logging
 import time
-from collections.abc import Generator, Mapping
+from collections.abc import Generator
 from typing import Any, Optional, Union

 from constants.tts_auto_play_timeout import TTS_AUTO_PLAY_TIMEOUT, TTS_AUTO_PLAY_YIELD_CPU_TIME
@@ -45,17 +45,18 @@ from core.app.entities.task_entities import (
 from core.app.task_pipeline.based_generate_task_pipeline import BasedGenerateTaskPipeline
 from core.app.task_pipeline.message_cycle_manage import MessageCycleManage
 from core.app.task_pipeline.workflow_cycle_manage import WorkflowCycleManage
+from core.model_runtime.entities.llm_entities import LLMUsage
 from core.model_runtime.utils.encoders import jsonable_encoder
 from core.ops.ops_trace_manager import TraceQueueManager
 from core.workflow.enums import SystemVariableKey
 from core.workflow.graph_engine.entities.graph_runtime_state import GraphRuntimeState
-from enums.workflow_nodes import NodeType
 from events.message_event import message_was_created
 from extensions.ext_database import db
 from models.account import Account
 from models.model import Conversation, EndUser, Message
 from models.workflow import (
    Workflow,
+    WorkflowNodeExecution,
    WorkflowRunStatus,
 )

@@ -72,6 +73,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
    _workflow: Workflow
    _user: Union[Account, EndUser]
    _workflow_system_variables: dict[SystemVariableKey, Any]
+    _wip_workflow_node_executions: dict[str, WorkflowNodeExecution]

    def __init__(
        self,
@@ -108,12 +110,16 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
            SystemVariableKey.FILES: application_generate_entity.files,
            SystemVariableKey.CONVERSATION_ID: conversation.id,
            SystemVariableKey.USER_ID: user_id,
+            SystemVariableKey.DIALOGUE_COUNT: conversation.dialogue_count,
+            SystemVariableKey.APP_ID: application_generate_entity.app_config.app_id,
+            SystemVariableKey.WORKFLOW_ID: workflow.id,
+            SystemVariableKey.WORKFLOW_RUN_ID: application_generate_entity.workflow_run_id,
        }

        self._task_state = WorkflowTaskState()
+        self._wip_workflow_node_executions = {}

        self._conversation_name_generate_thread = None
-        self._recorded_files: list[Mapping[str, Any]] = []

    def process(self):
        """
@@ -292,10 +298,6 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
            elif isinstance(event, QueueNodeSucceededEvent):
                workflow_node_execution = self._handle_workflow_node_execution_success(event)

-                # Record files if it's an answer node or end node
-                if event.node_type in [NodeType.ANSWER, NodeType.END]:
-                    self._recorded_files.extend(self._fetch_files_from_node_outputs(event.outputs or {}))
-
                response = self._workflow_node_finish_to_stream_response(
                    event=event,
                    task_id=self._application_generate_entity.task_id,
@@ -362,7 +364,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
                    start_at=graph_runtime_state.start_at,
                    total_tokens=graph_runtime_state.total_tokens,
                    total_steps=graph_runtime_state.node_run_steps,
-                    outputs=event.outputs,
+                    outputs=json.dumps(event.outputs) if event.outputs else None,
                    conversation_id=self._conversation.id,
                    trace_manager=trace_manager,
                )
@@ -511,6 +513,10 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
            self._message.total_price = usage.total_price
            self._message.currency = usage.currency

+            self._task_state.metadata["usage"] = jsonable_encoder(usage)
+        else:
+            self._task_state.metadata["usage"] = jsonable_encoder(LLMUsage.empty_usage())
+
        db.session.commit()

        message_was_created.send(
@@ -534,7 +540,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
                del extras["metadata"]["annotation_reply"]

        return MessageEndStreamResponse(
-            task_id=self._application_generate_entity.task_id, id=self._message.id, files=self._recorded_files, **extras
+            task_id=self._application_generate_entity.task_id, id=self._message.id, **extras
        )

    def _handle_output_moderation_chunk(self, text: str) -> bool:
@@ -8,6 +8,7 @@ from typing import Any, Literal, Union, overload
 from flask import Flask, current_app
 from pydantic import ValidationError

+from constants import UUID_NIL
 from core.app.app_config.easy_ui_based_app.model_config.converter import ModelConfigConverter
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
 from core.app.apps.agent_chat.app_config_manager import AgentChatAppConfigManager
@@ -17,12 +18,12 @@ from core.app.apps.base_app_queue_manager import AppQueueManager, GenerateTaskSt
 from core.app.apps.message_based_app_generator import MessageBasedAppGenerator
 from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueManager
 from core.app.entities.app_invoke_entities import AgentChatAppGenerateEntity, InvokeFrom
+from core.file.message_file_parser import MessageFileParser
 from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
 from core.ops.ops_trace_manager import TraceQueueManager
-from enums import CreatedByRole
 from extensions.ext_database import db
-from factories import file_factory
-from models import Account, App, EndUser
+from models.account import Account
+from models.model import App, EndUser

 logger = logging.getLogger(__name__)

@@ -49,12 +50,7 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
    ) -> dict: ...

    def generate(
-        self,
-        app_model: App,
-        user: Union[Account, EndUser],
-        args: Any,
-        invoke_from: InvokeFrom,
-        stream: bool = True,
+        self, app_model: App, user: Union[Account, EndUser], args: Any, invoke_from: InvokeFrom, stream: bool = True
    ) -> Union[dict, Generator[dict, None, None]]:
        """
        Generate App response.
@@ -102,19 +98,12 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
            # always enable retriever resource in debugger mode
            override_model_config_dict["retriever_resource"] = {"enabled": True}

-        role = CreatedByRole.ACCOUNT if isinstance(user, Account) else CreatedByRole.END_USER
-
        # parse files
-        files = args.get("files") or []
+        files = args["files"] if args.get("files") else []
+        message_file_parser = MessageFileParser(tenant_id=app_model.tenant_id, app_id=app_model.id)
        file_extra_config = FileUploadConfigManager.convert(override_model_config_dict or app_model_config.to_dict())
        if file_extra_config:
-            file_objs = file_factory.build_from_mappings(
-                mappings=files,
-                tenant_id=app_model.tenant_id,
-                user_id=user.id,
-                role=role,
-                config=file_extra_config,
-            )
+            file_objs = message_file_parser.validate_and_transform_files_arg(files, file_extra_config, user)
        else:
            file_objs = []

@@ -127,7 +116,8 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
        )

        # get tracing instance
-        trace_manager = TraceQueueManager(app_model.id, user.id if isinstance(user, Account) else user.session_id)
+        user_id = user.id if isinstance(user, Account) else user.session_id
+        trace_manager = TraceQueueManager(app_model.id, user_id)

        # init application generate entity
        application_generate_entity = AgentChatAppGenerateEntity(
@@ -135,12 +125,10 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
            app_config=app_config,
            model_conf=ModelConfigConverter.convert(app_config),
            conversation_id=conversation.id if conversation else None,
-            inputs=conversation.inputs
-            if conversation
-            else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config, user_id=user.id, role=role),
+            inputs=conversation.inputs if conversation else self._get_cleaned_inputs(inputs, app_config),
            query=query,
            files=file_objs,
-            parent_message_id=args.get("parent_message_id"),
+            parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
            user_id=user.id,
            stream=stream,
            invoke_from=invoke_from,
@@ -1,92 +1,35 @@
 from collections.abc import Mapping
-from typing import TYPE_CHECKING, Any, Optional
+from typing import Any, Optional

-from core.app.app_config.entities import VariableEntityType
-from core.file import File, FileExtraConfig
-from factories import file_factory
-
-if TYPE_CHECKING:
-    from core.app.app_config.entities import AppConfig, VariableEntity
-    from enums import CreatedByRole
+from core.app.app_config.entities import AppConfig, VariableEntity, VariableEntityType


 class BaseAppGenerator:
-    def _prepare_user_inputs(
-        self,
-        *,
-        user_inputs: Optional[Mapping[str, Any]],
-        app_config: "AppConfig",
-        user_id: str,
-        role: "CreatedByRole",
-    ) -> Mapping[str, Any]:
+    def _get_cleaned_inputs(self, user_inputs: Optional[Mapping[str, Any]], app_config: AppConfig) -> Mapping[str, Any]:
        user_inputs = user_inputs or {}
        # Filter input variables from form configuration, handle required fields, default values, and option values
        variables = app_config.variables
-        user_inputs = {var.variable: self._validate_input(inputs=user_inputs, var=var) for var in variables}
-        user_inputs = {k: self._sanitize_value(v) for k, v in user_inputs.items()}
-        # Convert files in inputs to File
-        entity_dictionary = {item.variable: item for item in app_config.variables}
-        # Convert single file to File
-        files_inputs = {
-            k: file_factory.build_from_mapping(
-                mapping=v,
-                tenant_id=app_config.tenant_id,
-                user_id=user_id,
-                role=role,
-                config=FileExtraConfig(
-                    allowed_file_types=entity_dictionary[k].allowed_file_types,
-                    allowed_extensions=entity_dictionary[k].allowed_file_extensions,
-                    allowed_upload_methods=entity_dictionary[k].allowed_file_upload_methods,
-                ),
-            )
-            for k, v in user_inputs.items()
-            if isinstance(v, dict) and entity_dictionary[k].type == VariableEntityType.FILE
-        }
-        # Convert list of files to File
-        file_list_inputs = {
-            k: file_factory.build_from_mappings(
-                mappings=v,
-                tenant_id=app_config.tenant_id,
-                user_id=user_id,
-                role=role,
-                config=FileExtraConfig(
-                    allowed_file_types=entity_dictionary[k].allowed_file_types,
-                    allowed_extensions=entity_dictionary[k].allowed_file_extensions,
-                    allowed_upload_methods=entity_dictionary[k].allowed_file_upload_methods,
-                ),
-            )
-            for k, v in user_inputs.items()
-            if isinstance(v, list)
-            # Ensure skip List<File>
-            and all(isinstance(item, dict) for item in v)
-            and entity_dictionary[k].type == VariableEntityType.FILE_LIST
-        }
-        # Merge all inputs
-        user_inputs = {**user_inputs, **files_inputs, **file_list_inputs}
+        filtered_inputs = {var.variable: self._validate_input(inputs=user_inputs, var=var) for var in variables}
+        filtered_inputs = {k: self._sanitize_value(v) for k, v in filtered_inputs.items()}
+        return filtered_inputs

-        # Check if all files are converted to File
-        if any(filter(lambda v: isinstance(v, dict), user_inputs.values())):
-            raise ValueError("Invalid input type")
-        if any(
-            filter(lambda v: isinstance(v, dict), filter(lambda item: isinstance(item, list), user_inputs.values()))
-        ):
-            raise ValueError("Invalid input type")
-
-        return user_inputs
-
-    def _validate_input(self, *, inputs: Mapping[str, Any], var: "VariableEntity"):
+    def _validate_input(self, *, inputs: Mapping[str, Any], var: VariableEntity):
        user_input_value = inputs.get(var.variable)
-        if not user_input_value:
-            if var.required:
-                raise ValueError(f"{var.variable} is required in input form")
-            else:
-                return None
-
-        if var.type in {
-            VariableEntityType.TEXT_INPUT,
-            VariableEntityType.SELECT,
-            VariableEntityType.PARAGRAPH,
-        } and not isinstance(user_input_value, str):
+        if var.required and not user_input_value:
+            raise ValueError(f"{var.variable} is required in input form")
+        if not var.required and not user_input_value:
+            # TODO: should we return None here if the default value is None?
+            return var.default or ""
+        if (
+            var.type
+            in {
+                VariableEntityType.TEXT_INPUT,
+                VariableEntityType.SELECT,
+                VariableEntityType.PARAGRAPH,
+            }
+            and user_input_value
+            and not isinstance(user_input_value, str)
+        ):
            raise ValueError(f"(type '{var.type}') {var.variable} in input form must be a string")
        if var.type == VariableEntityType.NUMBER and isinstance(user_input_value, str):
            # may raise ValueError if user_input_value is not a valid number
@@ -98,24 +41,12 @@ class BaseAppGenerator:
            except ValueError:
                raise ValueError(f"{var.variable} in input form must be a valid number")
        if var.type == VariableEntityType.SELECT:
-            options = var.options
+            options = var.options or []
            if user_input_value not in options:
                raise ValueError(f"{var.variable} in input form must be one of the following: {options}")
        elif var.type in {VariableEntityType.TEXT_INPUT, VariableEntityType.PARAGRAPH}:
-            if var.max_length and len(user_input_value) > var.max_length:
+            if var.max_length and user_input_value and len(user_input_value) > var.max_length:
                raise ValueError(f"{var.variable} in input form must be less than {var.max_length} characters")
-        elif var.type == VariableEntityType.FILE:
-            if not isinstance(user_input_value, dict) and not isinstance(user_input_value, File):
-                raise ValueError(f"{var.variable} in input form must be a file")
-        elif var.type == VariableEntityType.FILE_LIST:
-            if not (
-                isinstance(user_input_value, list)
-                and (
-                    all(isinstance(item, dict) for item in user_input_value)
-                    or all(isinstance(item, File) for item in user_input_value)
-                )
-            ):
-                raise ValueError(f"{var.variable} in input form must be a list of files")

        return user_input_value

@@ -27,7 +27,7 @@ from core.prompt.simple_prompt_transform import ModelMode, SimplePromptTransform
 from models.model import App, AppMode, Message, MessageAnnotation

 if TYPE_CHECKING:
-    from core.file.models import File
+    from core.file.file_obj import FileVar


 class AppRunner:
@@ -37,7 +37,7 @@ class AppRunner:
        model_config: ModelConfigWithCredentialsEntity,
        prompt_template_entity: PromptTemplateEntity,
        inputs: dict[str, str],
-        files: list["File"],
+        files: list["FileVar"],
        query: Optional[str] = None,
    ) -> int:
        """
@@ -137,7 +137,7 @@ class AppRunner:
        model_config: ModelConfigWithCredentialsEntity,
        prompt_template_entity: PromptTemplateEntity,
        inputs: dict[str, str],
-        files: list["File"],
+        files: list["FileVar"],
        query: Optional[str] = None,
        context: Optional[str] = None,
        memory: Optional[TokenBufferMemory] = None,
@@ -8,6 +8,7 @@ from typing import Any, Literal, Union, overload
 from flask import Flask, current_app
 from pydantic import ValidationError

+from constants import UUID_NIL
 from core.app.app_config.easy_ui_based_app.model_config.converter import ModelConfigConverter
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
 from core.app.apps.base_app_queue_manager import AppQueueManager, GenerateTaskStoppedError, PublishFrom
@@ -17,11 +18,10 @@ from core.app.apps.chat.generate_response_converter import ChatAppGenerateRespon
 from core.app.apps.message_based_app_generator import MessageBasedAppGenerator
 from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueManager
 from core.app.entities.app_invoke_entities import ChatAppGenerateEntity, InvokeFrom
+from core.file.message_file_parser import MessageFileParser
 from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
 from core.ops.ops_trace_manager import TraceQueueManager
-from enums import CreatedByRole
 from extensions.ext_database import db
-from factories import file_factory
 from models.account import Account
 from models.model import App, EndUser

@@ -100,19 +100,12 @@ class ChatAppGenerator(MessageBasedAppGenerator):
            # always enable retriever resource in debugger mode
            override_model_config_dict["retriever_resource"] = {"enabled": True}

-        role = CreatedByRole.ACCOUNT if isinstance(user, Account) else CreatedByRole.END_USER
-
        # parse files
        files = args["files"] if args.get("files") else []
+        message_file_parser = MessageFileParser(tenant_id=app_model.tenant_id, app_id=app_model.id)
        file_extra_config = FileUploadConfigManager.convert(override_model_config_dict or app_model_config.to_dict())
        if file_extra_config:
-            file_objs = file_factory.build_from_mappings(
-                mappings=files,
-                tenant_id=app_model.tenant_id,
-                user_id=user.id,
-                role=role,
-                config=file_extra_config,
-            )
+            file_objs = message_file_parser.validate_and_transform_files_arg(files, file_extra_config, user)
        else:
            file_objs = []

@@ -125,7 +118,7 @@ class ChatAppGenerator(MessageBasedAppGenerator):
        )

        # get tracing instance
-        trace_manager = TraceQueueManager(app_id=app_model.id)
+        trace_manager = TraceQueueManager(app_model.id)

        # init application generate entity
        application_generate_entity = ChatAppGenerateEntity(
@@ -133,17 +126,15 @@ class ChatAppGenerator(MessageBasedAppGenerator):
            app_config=app_config,
            model_conf=ModelConfigConverter.convert(app_config),
            conversation_id=conversation.id if conversation else None,
-            inputs=conversation.inputs
-            if conversation
-            else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config, user_id=user.id, role=role),
+            inputs=conversation.inputs if conversation else self._get_cleaned_inputs(inputs, app_config),
            query=query,
            files=file_objs,
-            parent_message_id=args.get("parent_message_id"),
+            parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
            user_id=user.id,
+            stream=stream,
            invoke_from=invoke_from,
            extras=extras,
            trace_manager=trace_manager,
-            stream=stream,
        )

        # init generate records
@@ -17,12 +17,12 @@ from core.app.apps.completion.generate_response_converter import CompletionAppGe
 from core.app.apps.message_based_app_generator import MessageBasedAppGenerator
 from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueManager
 from core.app.entities.app_invoke_entities import CompletionAppGenerateEntity, InvokeFrom
+from core.file.message_file_parser import MessageFileParser
 from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
 from core.ops.ops_trace_manager import TraceQueueManager
-from enums import CreatedByRole
 from extensions.ext_database import db
-from factories import file_factory
-from models import Account, App, EndUser, Message
+from models.account import Account
+from models.model import App, EndUser, Message
 from services.errors.app import MoreLikeThisDisabledError
 from services.errors.message import MessageNotExistsError

@@ -88,19 +88,12 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
                tenant_id=app_model.tenant_id, config=args.get("model_config")
            )

-        role = CreatedByRole.ACCOUNT if isinstance(user, Account) else CreatedByRole.END_USER
-
        # parse files
        files = args["files"] if args.get("files") else []
+        message_file_parser = MessageFileParser(tenant_id=app_model.tenant_id, app_id=app_model.id)
        file_extra_config = FileUploadConfigManager.convert(override_model_config_dict or app_model_config.to_dict())
        if file_extra_config:
-            file_objs = file_factory.build_from_mappings(
-                mappings=files,
-                tenant_id=app_model.tenant_id,
-                user_id=user.id,
-                role=role,
-                config=file_extra_config,
-            )
+            file_objs = message_file_parser.validate_and_transform_files_arg(files, file_extra_config, user)
        else:
            file_objs = []

@@ -110,7 +103,6 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
        )

        # get tracing instance
-        user_id = user.id if isinstance(user, Account) else user.session_id
        trace_manager = TraceQueueManager(app_model.id)

        # init application generate entity
@@ -118,7 +110,7 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
            task_id=str(uuid.uuid4()),
            app_config=app_config,
            model_conf=ModelConfigConverter.convert(app_config),
-            inputs=self._prepare_user_inputs(user_inputs=inputs, app_config=app_config, user_id=user.id, role=role),
+            inputs=self._get_cleaned_inputs(inputs, app_config),
            query=query,
            files=file_objs,
            user_id=user.id,
@@ -259,16 +251,10 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
        override_model_config_dict["model"] = model_dict

        # parse files
-        role = CreatedByRole.ACCOUNT if isinstance(user, Account) else CreatedByRole.END_USER
-        file_extra_config = FileUploadConfigManager.convert(override_model_config_dict)
+        message_file_parser = MessageFileParser(tenant_id=app_model.tenant_id, app_id=app_model.id)
+        file_extra_config = FileUploadConfigManager.convert(override_model_config_dict or app_model_config.to_dict())
        if file_extra_config:
-            file_objs = file_factory.build_from_mappings(
-                mappings=message.files,
-                tenant_id=app_model.tenant_id,
-                user_id=user.id,
-                role=role,
-                config=file_extra_config,
-            )
+            file_objs = message_file_parser.validate_and_transform_files_arg(message.files, file_extra_config, user)
        else:
            file_objs = []

@@ -26,7 +26,7 @@ from core.app.entities.task_entities import (
 from core.app.task_pipeline.easy_ui_based_generate_task_pipeline import EasyUIBasedGenerateTaskPipeline
 from core.prompt.utils.prompt_template_parser import PromptTemplateParser
 from extensions.ext_database import db
-from models import Account
+from models.account import Account
 from models.model import App, AppMode, AppModelConfig, Conversation, EndUser, Message, MessageFile
 from services.errors.app_model_config import AppModelConfigBrokenError
 from services.errors.conversation import ConversationCompletedError, ConversationNotExistsError
@@ -238,7 +238,7 @@ class MessageBasedAppGenerator(BaseAppGenerator):
                type=file.type.value,
                transfer_method=file.transfer_method.value,
                belongs_to="user",
-                url=file.remote_url,
+                url=file.url,
                upload_file_id=file.related_id,
                created_by_role=("account" if account_id else "end_user"),
                created_by=account_id or end_user_id,
@@ -3,7 +3,7 @@ import logging
 import os
 import threading
 import uuid
-from collections.abc import Generator, Mapping, Sequence
+from collections.abc import Generator
 from typing import Any, Literal, Optional, Union, overload

 from flask import Flask, current_app
@@ -20,12 +20,13 @@ from core.app.apps.workflow.generate_response_converter import WorkflowAppGenera
 from core.app.apps.workflow.generate_task_pipeline import WorkflowAppGenerateTaskPipeline
 from core.app.entities.app_invoke_entities import InvokeFrom, WorkflowAppGenerateEntity
 from core.app.entities.task_entities import WorkflowAppBlockingResponse, WorkflowAppStreamResponse
+from core.file.message_file_parser import MessageFileParser
 from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
 from core.ops.ops_trace_manager import TraceQueueManager
-from enums import CreatedByRole
 from extensions.ext_database import db
-from factories import file_factory
-from models import Account, App, EndUser, Workflow
+from models.account import Account
+from models.model import App, EndUser
+from models.workflow import Workflow

 logger = logging.getLogger(__name__)

@@ -62,50 +63,55 @@ class WorkflowAppGenerator(BaseAppGenerator):
        app_model: App,
        workflow: Workflow,
        user: Union[Account, EndUser],
-        args: Mapping[str, Any],
+        args: dict,
        invoke_from: InvokeFrom,
        stream: bool = True,
        call_depth: int = 0,
        workflow_thread_pool_id: Optional[str] = None,
    ):
-        files: Sequence[Mapping[str, Any]] = args.get("files") or []
+        """
+        Generate App response.

-        role = CreatedByRole.ACCOUNT if isinstance(user, Account) else CreatedByRole.END_USER
+        :param app_model: App
+        :param workflow: Workflow
+        :param user: account or end user
+        :param args: request args
+        :param invoke_from: invoke from source
+        :param stream: is stream
+        :param call_depth: call depth
+        :param workflow_thread_pool_id: workflow thread pool id
+        """
+        inputs = args["inputs"]

        # parse files
+        files = args["files"] if args.get("files") else []
+        message_file_parser = MessageFileParser(tenant_id=app_model.tenant_id, app_id=app_model.id)
        file_extra_config = FileUploadConfigManager.convert(workflow.features_dict, is_vision=False)
-        system_files = file_factory.build_from_mappings(
-            mappings=files,
-            tenant_id=app_model.tenant_id,
-            user_id=user.id,
-            role=role,
-            config=file_extra_config,
-        )
+        if file_extra_config:
+            file_objs = message_file_parser.validate_and_transform_files_arg(files, file_extra_config, user)
+        else:
+            file_objs = []

        # convert to app config
-        app_config = WorkflowAppConfigManager.get_app_config(
-            app_model=app_model,
-            workflow=workflow,
-        )
+        app_config = WorkflowAppConfigManager.get_app_config(app_model=app_model, workflow=workflow)

        # get tracing instance
-        trace_manager = TraceQueueManager(
-            app_id=app_model.id,
-            user_id=user.id if isinstance(user, Account) else user.session_id,
-        )
+        user_id = user.id if isinstance(user, Account) else user.session_id
+        trace_manager = TraceQueueManager(app_model.id, user_id)

-        inputs: Mapping[str, Any] = args["inputs"]
+        workflow_run_id = str(uuid.uuid4())
        # init application generate entity
        application_generate_entity = WorkflowAppGenerateEntity(
            task_id=str(uuid.uuid4()),
            app_config=app_config,
-            inputs=self._prepare_user_inputs(user_inputs=inputs, app_config=app_config, user_id=user.id, role=role),
-            files=system_files,
+            inputs=self._get_cleaned_inputs(inputs, app_config),
+            files=file_objs,
            user_id=user.id,
            stream=stream,
            invoke_from=invoke_from,
            call_depth=call_depth,
            trace_manager=trace_manager,
+            workflow_run_id=workflow_run_id,
        )
        contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)

@@ -1,19 +1,20 @@
 import logging
+import os
 from typing import Optional, cast

-from configs import dify_config
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.apps.workflow.app_config_manager import WorkflowAppConfig
 from core.app.apps.workflow_app_runner import WorkflowBasedAppRunner
+from core.app.apps.workflow_logging_callback import WorkflowLoggingCallback
 from core.app.entities.app_invoke_entities import (
    InvokeFrom,
    WorkflowAppGenerateEntity,
 )
-from core.workflow.callbacks import WorkflowCallback, WorkflowLoggingCallback
+from core.workflow.callbacks.base_workflow_callback import WorkflowCallback
+from core.workflow.entities.node_entities import UserFrom
 from core.workflow.entities.variable_pool import VariablePool
 from core.workflow.enums import SystemVariableKey
 from core.workflow.workflow_entry import WorkflowEntry
-from enums import UserFrom
 from extensions.ext_database import db
 from models.model import App, EndUser
 from models.workflow import WorkflowType
@@ -70,7 +71,7 @@ class WorkflowAppRunner(WorkflowBasedAppRunner):
        db.session.close()

        workflow_callbacks: list[WorkflowCallback] = []
-        if dify_config.DEBUG:
+        if bool(os.environ.get("DEBUG", "False").lower() == "true"):
            workflow_callbacks.append(WorkflowLoggingCallback())

        # if only single iteration run is requested
@@ -89,6 +90,9 @@ class WorkflowAppRunner(WorkflowBasedAppRunner):
            system_inputs = {
                SystemVariableKey.FILES: files,
                SystemVariableKey.USER_ID: user_id,
+                SystemVariableKey.APP_ID: app_config.app_id,
+                SystemVariableKey.WORKFLOW_ID: app_config.workflow_id,
+                SystemVariableKey.WORKFLOW_RUN_ID: self.application_generate_entity.workflow_run_id,
            }

            variable_pool = VariablePool(
@@ -1,3 +1,4 @@
+import json
 import logging
 import time
 from collections.abc import Generator
@@ -51,6 +52,7 @@ from models.workflow import (
    Workflow,
    WorkflowAppLog,
    WorkflowAppLogCreatedFrom,
+    WorkflowNodeExecution,
    WorkflowRun,
    WorkflowRunStatus,
 )
@@ -68,6 +70,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
    _task_state: WorkflowTaskState
    _application_generate_entity: WorkflowAppGenerateEntity
    _workflow_system_variables: dict[SystemVariableKey, Any]
+    _wip_workflow_node_executions: dict[str, WorkflowNodeExecution]

    def __init__(
        self,
@@ -96,9 +99,13 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
        self._workflow_system_variables = {
            SystemVariableKey.FILES: application_generate_entity.files,
            SystemVariableKey.USER_ID: user_id,
+            SystemVariableKey.APP_ID: application_generate_entity.app_config.app_id,
+            SystemVariableKey.WORKFLOW_ID: workflow.id,
+            SystemVariableKey.WORKFLOW_RUN_ID: application_generate_entity.workflow_run_id,
        }

        self._task_state = WorkflowTaskState()
+        self._wip_workflow_node_executions = {}

    def process(self) -> Union[WorkflowAppBlockingResponse, Generator[WorkflowAppStreamResponse, None, None]]:
        """
@@ -327,7 +334,9 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
                    start_at=graph_runtime_state.start_at,
                    total_tokens=graph_runtime_state.total_tokens,
                    total_steps=graph_runtime_state.node_run_steps,
-                    outputs=event.outputs,
+                    outputs=json.dumps(event.outputs)
+                    if isinstance(event, QueueWorkflowSucceededEvent) and event.outputs
+                    else None,
                    conversation_id=None,
                    trace_manager=trace_manager,
                )
@@ -20,6 +20,7 @@ from core.app.entities.queue_entities import (
    QueueWorkflowStartedEvent,
    QueueWorkflowSucceededEvent,
 )
+from core.workflow.entities.node_entities import NodeType
 from core.workflow.entities.variable_pool import VariablePool
 from core.workflow.graph_engine.entities.event import (
    GraphEngineEvent,
@@ -44,7 +45,6 @@ from core.workflow.nodes.base_node import BaseNode
 from core.workflow.nodes.iteration.entities import IterationNodeData
 from core.workflow.nodes.node_mapping import node_classes
 from core.workflow.workflow_entry import WorkflowEntry
-from enums import NodeType
 from extensions.ext_database import db
 from models.model import App
 from models.workflow import Workflow
@@ -1,6 +1,7 @@
 from typing import Optional

 from core.model_runtime.utils.encoders import jsonable_encoder
+from core.workflow.callbacks.base_workflow_callback import WorkflowCallback
 from core.workflow.graph_engine.entities.event import (
    GraphEngineEvent,
    GraphRunFailedEvent,
@@ -19,8 +20,6 @@ from core.workflow.graph_engine.entities.event import (
    ParallelBranchRunSucceededEvent,
 )

-from .base_workflow_callback import WorkflowCallback
-
 _TEXT_COLOR_MAPPING = {
    "blue": "36;1",
    "yellow": "33;1",
@@ -1,12 +1,13 @@
-from collections.abc import Mapping, Sequence
+from collections.abc import Mapping
 from enum import Enum
 from typing import Any, Optional

-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel, ConfigDict, Field, ValidationInfo, field_validator

+from constants import UUID_NIL
 from core.app.app_config.entities import AppConfig, EasyUIBasedAppConfig, WorkflowUIBasedAppConfig
 from core.entities.provider_configuration import ProviderModelBundle
-from core.file.models import File
+from core.file.file_obj import FileVar
 from core.model_runtime.entities.model_entities import AIModelEntity
 from core.ops.ops_trace_manager import TraceQueueManager

@@ -22,7 +23,7 @@ class InvokeFrom(Enum):
    DEBUGGER = "debugger"

    @classmethod
-    def value_of(cls, value: str):
+    def value_of(cls, value: str) -> "InvokeFrom":
        """
        Get value of given mode.

@@ -81,7 +82,7 @@ class AppGenerateEntity(BaseModel):
    app_config: AppConfig

    inputs: Mapping[str, Any]
-    files: Sequence[File]
+    files: list[FileVar] = []
    user_id: str

    # extras
@@ -116,13 +117,36 @@ class EasyUIBasedAppGenerateEntity(AppGenerateEntity):
    model_config = ConfigDict(protected_namespaces=())


-class ChatAppGenerateEntity(EasyUIBasedAppGenerateEntity):
+class ConversationAppGenerateEntity(AppGenerateEntity):
+    """
+    Base entity for conversation-based app generation.
+    """
+
+    conversation_id: Optional[str] = None
+    parent_message_id: Optional[str] = Field(
+        default=None,
+        description=(
+            "Starting from v0.9.0, parent_message_id is used to support message regeneration for internal chat API."
+            "For service API, we need to ensure its forward compatibility, "
+            "so passing in the parent_message_id as request arg is not supported for now. "
+            "It needs to be set to UUID_NIL so that the subsequent processing will treat it as legacy messages."
+        ),
+    )
+
+    @field_validator("parent_message_id")
+    @classmethod
+    def validate_parent_message_id(cls, v, info: ValidationInfo):
+        if info.data.get("invoke_from") == InvokeFrom.SERVICE_API and v != UUID_NIL:
+            raise ValueError("parent_message_id should be UUID_NIL for service API")
+        return v
+
+
+class ChatAppGenerateEntity(ConversationAppGenerateEntity, EasyUIBasedAppGenerateEntity):
    """
    Chat Application Generate Entity.
    """

-    conversation_id: Optional[str] = None
-    parent_message_id: Optional[str] = None
+    pass


 class CompletionAppGenerateEntity(EasyUIBasedAppGenerateEntity):
@@ -133,16 +157,15 @@ class CompletionAppGenerateEntity(EasyUIBasedAppGenerateEntity):
    pass


-class AgentChatAppGenerateEntity(EasyUIBasedAppGenerateEntity):
+class AgentChatAppGenerateEntity(ConversationAppGenerateEntity, EasyUIBasedAppGenerateEntity):
    """
    Agent Chat Application Generate Entity.
    """

-    conversation_id: Optional[str] = None
-    parent_message_id: Optional[str] = None
+    pass


-class AdvancedChatAppGenerateEntity(AppGenerateEntity):
+class AdvancedChatAppGenerateEntity(ConversationAppGenerateEntity):
    """
    Advanced Chat Application Generate Entity.
    """
@@ -150,8 +173,7 @@ class AdvancedChatAppGenerateEntity(AppGenerateEntity):
    # app config
    app_config: WorkflowUIBasedAppConfig

-    conversation_id: Optional[str] = None
-    parent_message_id: Optional[str] = None
+    workflow_run_id: Optional[str] = None
    query: str

    class SingleIterationRunEntity(BaseModel):
@@ -172,6 +194,7 @@ class WorkflowAppGenerateEntity(AppGenerateEntity):

    # app config
    app_config: WorkflowUIBasedAppConfig
+    workflow_run_id: Optional[str] = None

    class SingleIterationRunEntity(BaseModel):
        """
@@ -6,9 +6,8 @@ from pydantic import BaseModel, field_validator

 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk
 from core.workflow.entities.base_node_data_entities import BaseNodeData
-from core.workflow.entities.node_entities import NodeRunMetadataKey
+from core.workflow.entities.node_entities import NodeRunMetadataKey, NodeType
 from core.workflow.graph_engine.entities.graph_runtime_state import GraphRuntimeState
-from enums import NodeType


 class QueueEvent(str, Enum):
@@ -1,4 +1,3 @@
-from collections.abc import Mapping
 from enum import Enum
 from typing import Any, Optional

@@ -120,7 +119,6 @@ class MessageEndStreamResponse(StreamResponse):
    event: StreamEvent = StreamEvent.MESSAGE_END
    id: str
    metadata: dict = {}
-    files: Optional[list[Mapping[str, Any]]] = None


 class MessageFileStreamResponse(StreamResponse):
@@ -1,12 +1,7 @@
 from .segment_group import SegmentGroup
 from .segments import (
    ArrayAnySegment,
-    ArrayFileSegment,
-    ArrayNumberSegment,
-    ArrayObjectSegment,
    ArraySegment,
-    ArrayStringSegment,
-    FileSegment,
    FloatSegment,
    IntegerSegment,
    NoneSegment,
@@ -20,7 +15,6 @@ from .variables import (
    ArrayNumberVariable,
    ArrayObjectVariable,
    ArrayStringVariable,
-    FileVariable,
    FloatVariable,
    IntegerVariable,
    NoneVariable,
@@ -52,10 +46,4 @@ __all__ = [
    "ArrayNumberVariable",
    "ArrayObjectVariable",
    "ArraySegment",
-    "ArrayFileSegment",
-    "ArrayNumberSegment",
-    "ArrayObjectSegment",
-    "ArrayStringSegment",
-    "FileSegment",
-    "FileVariable",
 ]
@@ -2,32 +2,29 @@ from collections.abc import Mapping
 from typing import Any

 from configs import dify_config
-from core.file import File
-from core.variables import (
+
+from .exc import VariableError
+from .segments import (
    ArrayAnySegment,
-    ArrayFileSegment,
-    ArrayNumberSegment,
-    ArrayNumberVariable,
-    ArrayObjectSegment,
-    ArrayObjectVariable,
-    ArrayStringSegment,
-    ArrayStringVariable,
-    FileSegment,
    FloatSegment,
-    FloatVariable,
    IntegerSegment,
-    IntegerVariable,
    NoneSegment,
    ObjectSegment,
+    Segment,
+    StringSegment,
+)
+from .types import SegmentType
+from .variables import (
+    ArrayNumberVariable,
+    ArrayObjectVariable,
+    ArrayStringVariable,
+    FloatVariable,
+    IntegerVariable,
    ObjectVariable,
    SecretVariable,
-    Segment,
-    SegmentType,
-    StringSegment,
    StringVariable,
    Variable,
 )
-from core.variables.exc import VariableError


 def build_variable_from_mapping(mapping: Mapping[str, Any], /) -> Variable:
@@ -74,22 +71,6 @@ def build_segment(value: Any, /) -> Segment:
        return FloatSegment(value=value)
    if isinstance(value, dict):
        return ObjectSegment(value=value)
-    if isinstance(value, File):
-        return FileSegment(value=value)
    if isinstance(value, list):
-        items = [build_segment(item) for item in value]
-        types = {item.value_type for item in items}
-        if len(types) != 1:
-            return ArrayAnySegment(value=value)
-        match types.pop():
-            case SegmentType.STRING:
-                return ArrayStringSegment(value=value)
-            case SegmentType.NUMBER:
-                return ArrayNumberSegment(value=value)
-            case SegmentType.OBJECT:
-                return ArrayObjectSegment(value=value)
-            case SegmentType.FILE:
-                return ArrayFileSegment(value=value)
-            case _:
-                raise ValueError(f"not supported value {value}")
+        return ArrayAnySegment(value=value)
    raise ValueError(f"not supported value {value}")
@@ -0,0 +1,18 @@
+import re
+
+from core.workflow.entities.variable_pool import VariablePool
+
+from . import SegmentGroup, factory
+
+VARIABLE_PATTERN = re.compile(r"\{\{#([a-zA-Z0-9_]{1,50}(?:\.[a-zA-Z_][a-zA-Z0-9_]{0,29}){1,10})#\}\}")
+
+
+def convert_template(*, template: str, variable_pool: VariablePool):
+    parts = re.split(VARIABLE_PATTERN, template)
+    segments = []
+    for part in filter(lambda x: x, parts):
+        if "." in part and (value := variable_pool.get(part.split("."))):
+            segments.append(value)
+        else:
+            segments.append(factory.build_segment(part))
+    return SegmentGroup(value=segments)
--- a/Show More
+++ b/Show More