Revert "add clean 7 days datasets (#9424)"

This reverts commit bd678f9ca1.

.github/workflows/api-tests.yml

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

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

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

.github/workflows/style.yml

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

README.md

@@ -17,7 +17,7 @@
             alt="chat on Discord"></a>
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
-            alt="follow on Twitter"></a>
+            alt="follow on X(Twitter)"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -196,10 +196,14 @@ If you'd like to configure a highly-available setup, there are community-contrib
 
 #### Using Terraform for Deployment
 
+Deploy Dify to Cloud Platform with a single click using [terraform](https://www.terraform.io/)
+
 ##### Azure Global
-Deploy Dify to Azure with a single click using [terraform](https://www.terraform.io/).
 - [Azure Terraform by @nikawang](https://github.com/nikawang/dify-azure-terraform)
 
+##### Google Cloud
+- [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
+
 ## Contributing
 
 For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
@@ -219,7 +223,7 @@ At the same time, please consider supporting Dify by sharing it on social media
 * [Github Discussion](https://github.com/langgenius/dify/discussions). Best for: sharing feedback and asking questions.
 * [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
 * [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
-* [Twitter](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
+* [X(Twitter)](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
 
 ## Star history
 

README_AR.md

@@ -17,7 +17,7 @@
             alt="chat on Discord"></a>
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
-            alt="follow on Twitter"></a>
+            alt="follow on X(Twitter)"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -179,10 +179,13 @@ docker compose up -d
 
 #### استخدام Terraform للتوزيع
 
+انشر Dify إلى منصة السحابة بنقرة واحدة باستخدام [terraform](https://www.terraform.io/)
+
 ##### Azure Global
-استخدم [terraform](https://www.terraform.io/) لنشر Dify على Azure بنقرة واحدة.
 - [Azure Terraform بواسطة @nikawang](https://github.com/nikawang/dify-azure-terraform)
 
+##### Google Cloud
+- [Google Cloud Terraform بواسطة @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
 ## المساهمة
 

README_CN.md

@@ -17,7 +17,7 @@
             alt="chat on Discord"></a>
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
-            alt="follow on Twitter"></a>
+            alt="follow on X(Twitter)"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -202,10 +202,14 @@ docker compose up -d
 
 #### 使用 Terraform 部署
 
+使用 [terraform](https://www.terraform.io/) 一键将 Dify 部署到云平台
+
 ##### Azure Global
-使用 [terraform](https://www.terraform.io/) 一键部署 Dify 到 Azure。
 - [Azure Terraform by @nikawang](https://github.com/nikawang/dify-azure-terraform)
 
+##### Google Cloud
+- [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
+
 ## Star History
 
 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
@@ -232,7 +236,7 @@ docker compose up -d
 - [GitHub Issues](https://github.com/langgenius/dify/issues)。👉：使用 Dify.AI 时遇到的错误和问题，请参阅[贡献指南](CONTRIBUTING.md)。
 - [电子邮件支持](mailto:hello@dify.ai?subject=[GitHub]Questions%20About%20Dify)。👉：关于使用 Dify.AI 的问题。
 - [Discord](https://discord.gg/FngNHpbcY7)。👉：分享您的应用程序并与社区交流。
-- [Twitter](https://twitter.com/dify_ai)。👉：分享您的应用程序并与社区交流。
+- [X(Twitter)](https://twitter.com/dify_ai)。👉：分享您的应用程序并与社区交流。
 - [商业许可](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)。👉：有关商业用途许可 Dify.AI 的商业咨询。
  - [微信]() 👉：扫描下方二维码，添加微信好友，备注 Dify，我们将邀请您加入 Dify 社区。  
 <img src="./images/wechat.png" alt="wechat" width="100"/>

README_ES.md

@@ -17,7 +17,7 @@
             alt="chat en Discord"></a>
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
-            alt="seguir en Twitter"></a>
+            alt="seguir en X(Twitter)"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Descargas de Docker" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -204,10 +204,13 @@ Si desea configurar una configuración de alta disponibilidad, la comunidad prop
 
 #### Uso de Terraform para el despliegue
 
+Despliega Dify en una plataforma en la nube con un solo clic utilizando [terraform](https://www.terraform.io/)
+
 ##### Azure Global
-Utiliza [terraform](https://www.terraform.io/) para desplegar Dify en Azure con un solo clic.
 - [Azure Terraform por @nikawang](https://github.com/nikawang/dify-azure-terraform)
 
+##### Google Cloud
+- [Google Cloud Terraform por @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
 ## Contribuir
 
@@ -228,7 +231,7 @@ Al mismo tiempo, considera apoyar a Dify compartiéndolo en redes sociales y en
 * [Discusión en GitHub](https://github.com/langgenius/dify/discussions). Lo mejor para: compartir comentarios y hacer preguntas.
 * [Reporte de problemas en GitHub](https://github.com/langgenius/dify/issues). Lo mejor para: errores que encuentres usando Dify.AI y propuestas de características. Consulta nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
 * [Discord](https://discord.gg/FngNHpbcY7). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad.
-* [Twitter](https://twitter.com/dify_ai). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad.
+* [X(Twitter)](https://twitter.com/dify_ai). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad.
 
 ## Historial de Estrellas
 

README_FR.md

@@ -17,7 +17,7 @@
             alt="chat sur Discord"></a>
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
-            alt="suivre sur Twitter"></a>
+            alt="suivre sur X(Twitter)"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Tirages Docker" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -202,10 +202,13 @@ Si vous souhaitez configurer une configuration haute disponibilité, la communau
 
 #### Utilisation de Terraform pour le déploiement
 
+Déployez Dify sur une plateforme cloud en un clic en utilisant [terraform](https://www.terraform.io/)
+
 ##### Azure Global
-Utilisez [terraform](https://www.terraform.io/) pour déployer Dify sur Azure en un clic.
 - [Azure Terraform par @nikawang](https://github.com/nikawang/dify-azure-terraform)
 
+##### Google Cloud
+- [Google Cloud Terraform par @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
 ## Contribuer
 
@@ -226,7 +229,7 @@ Dans le même temps, veuillez envisager de soutenir Dify en le partageant sur le
 * [Discussion GitHub](https://github.com/langgenius/dify/discussions). Meilleur pour: partager des commentaires et poser des questions.
 * [Problèmes GitHub](https://github.com/langgenius/dify/issues). Meilleur pour: les bogues que vous rencontrez en utilisant Dify.AI et les propositions de fonctionnalités. Consultez notre [Guide de contribution](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
 * [Discord](https://discord.gg/FngNHpbcY7). Meilleur pour: partager vos applications et passer du temps avec la communauté.
-* [Twitter](https://twitter.com/dify_ai). Meilleur pour: partager vos applications et passer du temps avec la communauté.
+* [X(Twitter)](https://twitter.com/dify_ai). Meilleur pour: partager vos applications et passer du temps avec la communauté.
 
 ## Historique des étoiles
 

README_JA.md

@@ -17,7 +17,7 @@
             alt="Discordでチャット"></a>
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
-            alt="Twitterでフォロー"></a>
+            alt="X(Twitter)でフォロー"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -68,7 +68,7 @@ DifyはオープンソースのLLMアプリケーション開発プラットフ
   プロンプトの作成、モデルパフォーマンスの比較が行え、チャットベースのアプリに音声合成などの機能も追加できます。
 
 **4. RAGパイプライン**: 
-  ドキュメントの取り込みから検索までをカバーする広範なRAG機能ができます。ほかにもPDF、PPT、その他の一般的なドキュメントフォーマットからのテキスト抽出のサーポイントも提供します。
+  ドキュメントの取り込みから検索までをカバーする広範なRAG機能ができます。ほかにもPDF、PPT、その他の一般的なドキュメントフォーマットからのテキスト抽出のサポートも提供します。
 
 **5. エージェント機能**: 
   LLM Function CallingやReActに基づくエージェントの定義が可能で、AIエージェント用のプリビルトまたはカスタムツールを追加できます。Difyには、Google検索、DALL·E、Stable Diffusion、WolframAlphaなどのAIエージェント用の50以上の組み込みツールが提供します。
@@ -201,10 +201,13 @@ docker compose up -d
 
 #### Terraformを使用したデプロイ
 
-##### Azure Global
-[terraform](https://www.terraform.io/) を使用して、AzureにDifyをワンクリックでデプロイします。
-- [nikawangのAzure Terraform](https://github.com/nikawang/dify-azure-terraform)
+[terraform](https://www.terraform.io/) を使用して、ワンクリックでDifyをクラウドプラットフォームにデプロイします
 
+##### Azure Global
+- [@nikawangによるAzure Terraform](https://github.com/nikawang/dify-azure-terraform)
+
+##### Google Cloud
+- [@sotazumによるGoogle Cloud Terraform](https://github.com/DeNA/dify-google-cloud-terraform)
 
 ## 貢献
 
@@ -225,7 +228,7 @@ docker compose up -d
 * [Github Discussion](https://github.com/langgenius/dify/discussions). 主に: フィードバックの共有や質問。
 * [GitHub Issues](https://github.com/langgenius/dify/issues). 主に: Dify.AIを使用する際に発生するエラーや問題については、[貢献ガイド](CONTRIBUTING_JA.md)を参照してください
 * [Discord](https://discord.gg/FngNHpbcY7). 主に: アプリケーションの共有やコミュニティとの交流。
-* [Twitter](https://twitter.com/dify_ai). 主に: アプリケーションの共有やコミュニティとの交流。
+* [X(Twitter)](https://twitter.com/dify_ai). 主に: アプリケーションの共有やコミュニティとの交流。
 
 
 

README_KL.md

@@ -17,7 +17,7 @@
             alt="chat on Discord"></a>
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
-            alt="follow on Twitter"></a>
+            alt="follow on X(Twitter)"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -202,10 +202,13 @@ If you'd like to configure a highly-available setup, there are community-contrib
 
 #### Terraform atorlugu pilersitsineq
 
-##### Azure Global
-Atoruk [terraform](https://www.terraform.io/) Dify-mik Azure-mut ataatsikkut ikkussuilluarlugu.
-- [Azure Terraform atorlugu @nikawang](https://github.com/nikawang/dify-azure-terraform)
+wa'logh nIqHom neH ghun deployment toy'wI' [terraform](https://www.terraform.io/) lo'laH.
 
+##### Azure Global
+- [Azure Terraform mung @nikawang](https://github.com/nikawang/dify-azure-terraform)
+
+##### Google Cloud
+- [Google Cloud Terraform qachlot @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
 ## Contributing
 
@@ -228,7 +231,7 @@ At the same time, please consider supporting Dify by sharing it on social media
 ). Best for: sharing feedback and asking questions.
 * [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
 * [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
-* [Twitter](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
+* [X(Twitter)](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
 
 ## Star History
 

README_KR.md

@@ -17,7 +17,7 @@
             alt="chat on Discord"></a>
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
-            alt="follow on Twitter"></a>
+            alt="follow on X(Twitter)"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -39,7 +39,6 @@
   <a href="./README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
   <a href="./README_TR.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
   <a href="./README_VI.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
-
 </p>
 
 
@@ -195,10 +194,14 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했
 
 #### Terraform을 사용한 배포
 
+[terraform](https://www.terraform.io/)을 사용하여 단 한 번의 클릭으로 Dify를 클라우드 플랫폼에 배포하십시오
+
 ##### Azure Global
-[terraform](https://www.terraform.io/)을 사용하여 Azure에 Dify를 원클릭으로 배포하세요.
 - [nikawang의 Azure Terraform](https://github.com/nikawang/dify-azure-terraform)
 
+##### Google Cloud
+- [sotazum의 Google Cloud Terraform](https://github.com/DeNA/dify-google-cloud-terraform)
+
 ## 기여
 
 코드에 기여하고 싶은 분들은 [기여 가이드](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)를 참조하세요.

README_TR.md

@@ -17,7 +17,7 @@
             alt="Discord'da sohbet et"></a>
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
-            alt="Twitter'da takip et"></a>
+            alt="X(Twitter)'da takip et"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Docker Çekmeleri" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -200,9 +200,13 @@ Yüksek kullanılabilirliğe sahip bir kurulum yapılandırmak isterseniz, Dify'
 
 #### Dağıtım için Terraform Kullanımı
 
+Dify'ı bulut platformuna tek tıklamayla dağıtın [terraform](https://www.terraform.io/) kullanarak
+
 ##### Azure Global
-[Terraform](https://www.terraform.io/) kullanarak Dify'ı Azure'a tek tıklamayla dağıtın.
-- [@nikawang tarafından Azure Terraform](https://github.com/nikawang/dify-azure-terraform)
+- [Azure Terraform tarafından @nikawang](https://github.com/nikawang/dify-azure-terraform)
+
+##### Google Cloud
+- [Google Cloud Terraform tarafından @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
 ## Katkıda Bulunma
 
@@ -222,7 +226,7 @@ Aynı zamanda, lütfen Dify'ı sosyal medyada, etkinliklerde ve konferanslarda p
 * [Github Tartışmaları](https://github.com/langgenius/dify/discussions). En uygun: geri bildirim paylaşmak ve soru sormak için.
 * [GitHub Sorunları](https://github.com/langgenius/dify/issues). En uygun: Dify.AI kullanırken karşılaştığınız hatalar ve özellik önerileri için. [Katkı Kılavuzumuza](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) bakın.
 * [Discord](https://discord.gg/FngNHpbcY7). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.
-* [Twitter](https://twitter.com/dify_ai). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.
+* [X(Twitter)](https://twitter.com/dify_ai). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.
 
 ## Star history
 

README_VI.md

@@ -17,7 +17,7 @@
             alt="chat trên Discord"></a>
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
-            alt="theo dõi trên Twitter"></a>
+            alt="theo dõi trên X(Twitter)"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -196,10 +196,14 @@ Nếu bạn muốn cấu hình một cài đặt có độ sẵn sàng cao, có
 
 #### Sử dụng Terraform để Triển khai
 
+Triển khai Dify lên nền tảng đám mây với một cú nhấp chuột bằng cách sử dụng [terraform](https://www.terraform.io/)
+
 ##### Azure Global
-Triển khai Dify lên Azure chỉ với một cú nhấp chuột bằng cách sử dụng [terraform](https://www.terraform.io/).
 - [Azure Terraform bởi @nikawang](https://github.com/nikawang/dify-azure-terraform)
 
+##### Google Cloud
+- [Google Cloud Terraform bởi @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
+
 ## Đóng góp
 
 Đối với những người muốn đóng góp mã, xem [Hướng dẫn Đóng góp](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) của chúng tôi. 
@@ -219,7 +223,7 @@ Triển khai Dify lên Azure chỉ với một cú nhấp chuột bằng cách s
 * [Thảo luận GitHub](https://github.com/langgenius/dify/discussions). Tốt nhất cho: chia sẻ phản hồi và đặt câu hỏi.
 * [Vấn đề GitHub](https://github.com/langgenius/dify/issues). Tốt nhất cho: lỗi bạn gặp phải khi sử dụng Dify.AI và đề xuất tính năng. Xem [Hướng dẫn Đóng góp](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) của chúng tôi.
 * [Discord](https://discord.gg/FngNHpbcY7). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng.
-* [Twitter](https://twitter.com/dify_ai). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng.
+* [X(Twitter)](https://twitter.com/dify_ai). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng.
 
 ## Lịch sử Yêu thích
 

api/.env.example

@@ -20,6 +20,9 @@ FILES_URL=http://127.0.0.1:5001
 # The time in seconds after the signature is rejected
 FILES_ACCESS_TIMEOUT=300
 
+# Access token expiration time in minutes
+ACCESS_TOKEN_EXPIRE_MINUTES=60
+
 # celery configuration
 CELERY_BROKER_URL=redis://:difyai123456@localhost:6379/1
 
@@ -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
@@ -197,6 +211,24 @@ 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
@@ -265,6 +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=
 

api/README.md

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

api/app.py

@@ -26,7 +26,7 @@ from commands import register_commands
 from configs import dify_config
 
 # DO NOT REMOVE BELOW
-from events import event_handlers
+from events import event_handlers  # noqa: F401
 from extensions import (
     ext_celery,
     ext_code_based_extension,
@@ -36,6 +36,7 @@ from extensions import (
     ext_login,
     ext_mail,
     ext_migrate,
+    ext_proxy_fix,
     ext_redis,
     ext_sentry,
     ext_storage,
@@ -45,7 +46,7 @@ from extensions.ext_login import login_manager
 from libs.passport import PassportService
 
 # TODO: Find a way to avoid importing models here
-from models import account, dataset, model, source, task, tool, tools, web
+from models import account, dataset, model, source, task, tool, tools, web  # noqa: F401
 from services.account_service import AccountService
 
 # DO NOT REMOVE ABOVE
@@ -156,6 +157,7 @@ def initialize_extensions(app):
     ext_mail.init_app(app)
     ext_hosting_provider.init_app(app)
     ext_sentry.init_app(app)
+    ext_proxy_fix.init_app(app)
 
 
 # Flask-Login configuration
@@ -181,10 +183,10 @@ def load_user_from_request(request_from_flask_login):
     decoded = PassportService().verify(auth_token)
     user_id = decoded.get("user_id")
 
-    account = AccountService.load_logged_in_account(account_id=user_id, token=auth_token)
-    if account:
-        contexts.tenant_id.set(account.current_tenant_id)
-    return account
+    logged_in_account = AccountService.load_logged_in_account(account_id=user_id)
+    if logged_in_account:
+        contexts.tenant_id.set(logged_in_account.current_tenant_id)
+    return logged_in_account
 
 
 @login_manager.unauthorized_handler

api/commands.py

@@ -347,6 +347,14 @@ def migrate_knowledge_vector_database():
                     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 == VectorType.BAIDU:
+                    dataset_id = dataset.id
+                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
+                    index_struct_dict = {
+                        "type": VectorType.BAIDU,
+                        "vector_store": {"class_prefix": collection_name},
+                    }
+                    dataset.index_struct = json.dumps(index_struct_dict)
                 else:
                     raise ValueError(f"Vector store {vector_type} is not supported.")
 

api/configs/feature/__init__.py

@@ -247,6 +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):
     """
@@ -354,9 +360,9 @@ class WorkflowConfig(BaseSettings):
     )
 
 
-class OAuthConfig(BaseSettings):
+class AuthConfig(BaseSettings):
     """
-    Configuration for OAuth authentication
+    Configuration for authentication and OAuth
     """
 
     OAUTH_REDIRECT_PATH: str = Field(
@@ -365,7 +371,7 @@ class OAuthConfig(BaseSettings):
     )
 
     GITHUB_CLIENT_ID: Optional[str] = Field(
-        description="GitHub OAuth client secret",
+        description="GitHub OAuth client ID",
         default=None,
     )
 
@@ -384,6 +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):
     """
@@ -601,6 +612,7 @@ class PositionConfig(BaseSettings):
 class FeatureConfig(
     # place the configs in alphabet order
     AppExecutionConfig,
+    AuthConfig,  # Changed from OAuthConfig to AuthConfig
     BillingConfig,
     CodeExecutionSandboxConfig,
     DataSetConfig,
@@ -615,14 +627,13 @@ class FeatureConfig(
     MailConfig,
     ModelLoadBalanceConfig,
     ModerationConfig,
-    OAuthConfig,
+    PositionConfig,
     RagEtlConfig,
     SecurityConfig,
     ToolConfig,
     UpdateConfig,
     WorkflowConfig,
     WorkspaceConfig,
-    PositionConfig,
     # hosted services config
     HostedServiceConfig,
     CeleryBeatConfig,

api/configs/middleware/__init__.py

@@ -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

api/configs/middleware/storage/baidu_obs_storage_config.py

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

api/configs/middleware/storage/supabase_storage_config.py

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

api/configs/middleware/vdb/baidu_vector_config.py

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

api/configs/middleware/vdb/oracle_config.py

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

api/configs/middleware/vdb/pgvector_config.py

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

api/configs/middleware/vdb/pgvectors_config.py

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

api/configs/middleware/vdb/vikingdb_config.py

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

api/configs/packaging/__init__.py

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
 
     CURRENT_VERSION: str = Field(
         description="Dify version",
-        default="0.9.1",
+        default="0.9.2",
     )
 
     COMMIT_SHA: str = Field(

api/controllers/console/app/conversation.py

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

api/controllers/console/auth/login.py

@@ -7,7 +7,7 @@ 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.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")

api/controllers/console/auth/oauth.py

@@ -9,7 +9,7 @@ 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.account import Account, AccountStatus
 from services.account_service import AccountService, RegisterService, TenantService
@@ -81,9 +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]:

api/controllers/console/datasets/datasets.py

@@ -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 (

api/controllers/console/datasets/external.py

@@ -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")

api/controllers/console/datasets/hit_testing.py

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

api/controllers/console/datasets/hit_testing_base.py

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

api/controllers/console/setup.py

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

api/controllers/console/workspace/model_providers.py

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

api/controllers/files/error.py

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

api/controllers/files/image_preview.py

@@ -4,7 +4,7 @@ from werkzeug.exceptions import NotFound
 
 import services
 from controllers.files import api
-from libs.exception import BaseHTTPException
+from controllers.files.error import UnsupportedFileTypeError
 from services.account_service import TenantService
 from services.file_service import FileService
 
@@ -50,9 +50,3 @@ class WorkspaceWebappLogoApi(Resource):
 
 api.add_resource(ImagePreviewApi, "/files/<uuid:file_id>/image-preview")
 api.add_resource(WorkspaceWebappLogoApi, "/files/workspaces/<uuid:workspace_id>/webapp-logo")
-
-
-class UnsupportedFileTypeError(BaseHTTPException):
-    error_code = "unsupported_file_type"
-    description = "File type not allowed."
-    code = 415

api/controllers/files/tool_files.py

@@ -3,8 +3,8 @@ from flask_restful import Resource, reqparse
 from werkzeug.exceptions import Forbidden, NotFound
 
 from controllers.files import api
+from controllers.files.error import UnsupportedFileTypeError
 from core.tools.tool_file_manager import ToolFileManager
-from libs.exception import BaseHTTPException
 
 
 class ToolFilePreviewApi(Resource):
@@ -43,9 +43,3 @@ class ToolFilePreviewApi(Resource):
 
 
 api.add_resource(ToolFilePreviewApi, "/files/tools/<uuid:file_id>.<string:extension>")
-
-
-class UnsupportedFileTypeError(BaseHTTPException):
-    error_code = "unsupported_file_type"
-    description = "File type not allowed."
-    code = 415

api/controllers/service_api/__init__.py

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

api/controllers/service_api/dataset/hit_testing.py

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

api/core/agent/cot_agent_runner.py

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

api/core/agent/cot_chat_agent_runner.py

@@ -27,7 +27,7 @@ class CotChatAgentRunner(CotAgentRunner):
 
         return SystemPromptMessage(content=system_prompt)
 
-    def _organize_user_query(self, query, prompt_messages: list[PromptMessage] = None) -> list[PromptMessage]:
+    def _organize_user_query(self, query, prompt_messages: list[PromptMessage]) -> list[PromptMessage]:
         """
         Organize user query
         """

api/core/agent/cot_completion_agent_runner.py

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

api/core/agent/fc_agent_runner.py

@@ -2,7 +2,7 @@ import json
 import logging
 from collections.abc import Generator
 from copy import deepcopy
-from typing import Any, Union
+from typing import Any, Optional, Union
 
 from core.agent.base_agent_runner import BaseAgentRunner
 from core.app.apps.base_app_queue_manager import PublishFrom
@@ -370,7 +370,7 @@ class FunctionCallAgentRunner(BaseAgentRunner):
         return tool_calls
 
     def _init_system_message(
-        self, prompt_template: str, prompt_messages: list[PromptMessage] = None
+        self, prompt_template: str, prompt_messages: Optional[list[PromptMessage]] = None
     ) -> list[PromptMessage]:
         """
         Initialize system message
@@ -385,7 +385,7 @@ class FunctionCallAgentRunner(BaseAgentRunner):
 
         return prompt_messages
 
-    def _organize_user_query(self, query, prompt_messages: list[PromptMessage] = None) -> list[PromptMessage]:
+    def _organize_user_query(self, query, prompt_messages: list[PromptMessage]) -> list[PromptMessage]:
         """
         Organize user query
         """

api/core/agent/output_parser/cot_output_parser.py

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

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

@@ -10,6 +10,7 @@ from flask import Flask, current_app
 from pydantic import ValidationError
 
 import contexts
+from constants import UUID_NIL
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
 from core.app.apps.advanced_chat.app_config_manager import AdvancedChatAppConfigManager
 from core.app.apps.advanced_chat.app_runner import AdvancedChatAppRunner
@@ -113,6 +114,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             # 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()),
@@ -121,12 +123,13 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             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)
 

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

@@ -149,6 +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

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

@@ -45,6 +45,7 @@ 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
@@ -55,6 +56,7 @@ from models.account import Account
 from models.model import Conversation, EndUser, Message
 from models.workflow import (
     Workflow,
+    WorkflowNodeExecution,
     WorkflowRunStatus,
 )
 
@@ -71,6 +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,
@@ -107,9 +110,14 @@ 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
 
@@ -505,6 +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(

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

@@ -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
@@ -127,7 +128,7 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
             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,

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

@@ -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
@@ -128,7 +129,7 @@ class ChatAppGenerator(MessageBasedAppGenerator):
             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,

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

@@ -99,6 +99,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
         user_id = user.id if isinstance(user, Account) else user.session_id
         trace_manager = TraceQueueManager(app_model.id, user_id)
 
+        workflow_run_id = str(uuid.uuid4())
         # init application generate entity
         application_generate_entity = WorkflowAppGenerateEntity(
             task_id=str(uuid.uuid4()),
@@ -110,6 +111,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
             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)
 

api/core/app/apps/workflow/app_runner.py

@@ -90,6 +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(

api/core/app/apps/workflow/generate_task_pipeline.py

@@ -52,6 +52,7 @@ from models.workflow import (
     Workflow,
     WorkflowAppLog,
     WorkflowAppLogCreatedFrom,
+    WorkflowNodeExecution,
     WorkflowRun,
     WorkflowRunStatus,
 )
@@ -69,6 +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,
@@ -97,9 +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]]:
         """

api/core/app/entities/app_invoke_entities.py

@@ -2,8 +2,9 @@ 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.file_obj import FileVar
@@ -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):
         """

api/core/app/task_pipeline/message_cycle_manage.py

@@ -1,8 +1,10 @@
+import logging
 from threading import Thread
 from typing import Optional, Union
 
 from flask import Flask, current_app
 
+from configs import dify_config
 from core.app.entities.app_invoke_entities import (
     AdvancedChatAppGenerateEntity,
     AgentChatAppGenerateEntity,
@@ -82,7 +84,9 @@ class MessageCycleManage:
                 try:
                     name = LLMGenerator.generate_conversation_name(app_model.tenant_id, query)
                     conversation.name = name
-                except:
+                except Exception as e:
+                    if dify_config.DEBUG:
+                        logging.exception(f"generate conversation name failed: {e}")
                     pass
 
                 db.session.merge(conversation)

api/core/app/task_pipeline/workflow_cycle_manage.py

@@ -57,6 +57,7 @@ class WorkflowCycleManage:
     _user: Union[Account, EndUser]
     _task_state: WorkflowTaskState
     _workflow_system_variables: dict[SystemVariableKey, Any]
+    _wip_workflow_node_executions: dict[str, WorkflowNodeExecution]
 
     def _handle_workflow_run_start(self) -> WorkflowRun:
         max_sequence = (
@@ -85,6 +86,9 @@ class WorkflowCycleManage:
 
         # init workflow run
         workflow_run = WorkflowRun()
+        workflow_run_id = self._workflow_system_variables[SystemVariableKey.WORKFLOW_RUN_ID]
+        if workflow_run_id:
+            workflow_run.id = workflow_run_id
         workflow_run.tenant_id = self._workflow.tenant_id
         workflow_run.app_id = self._workflow.app_id
         workflow_run.sequence_number = new_sequence_number
@@ -248,6 +252,8 @@ class WorkflowCycleManage:
         db.session.refresh(workflow_node_execution)
         db.session.close()
 
+        self._wip_workflow_node_executions[workflow_node_execution.node_execution_id] = workflow_node_execution
+
         return workflow_node_execution
 
     def _handle_workflow_node_execution_success(self, event: QueueNodeSucceededEvent) -> WorkflowNodeExecution:
@@ -260,20 +266,36 @@ class WorkflowCycleManage:
 
         inputs = WorkflowEntry.handle_special_values(event.inputs)
         outputs = WorkflowEntry.handle_special_values(event.outputs)
+        execution_metadata = (
+            json.dumps(jsonable_encoder(event.execution_metadata)) if event.execution_metadata else None
+        )
+        finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        elapsed_time = (finished_at - event.start_at).total_seconds()
+
+        db.session.query(WorkflowNodeExecution).filter(WorkflowNodeExecution.id == workflow_node_execution.id).update(
+            {
+                WorkflowNodeExecution.status: WorkflowNodeExecutionStatus.SUCCEEDED.value,
+                WorkflowNodeExecution.inputs: json.dumps(inputs) if inputs else None,
+                WorkflowNodeExecution.process_data: json.dumps(event.process_data) if event.process_data else None,
+                WorkflowNodeExecution.outputs: json.dumps(outputs) if outputs else None,
+                WorkflowNodeExecution.execution_metadata: execution_metadata,
+                WorkflowNodeExecution.finished_at: finished_at,
+                WorkflowNodeExecution.elapsed_time: elapsed_time,
+            }
+        )
+
+        db.session.commit()
+        db.session.close()
 
         workflow_node_execution.status = WorkflowNodeExecutionStatus.SUCCEEDED.value
         workflow_node_execution.inputs = json.dumps(inputs) if inputs else None
         workflow_node_execution.process_data = json.dumps(event.process_data) if event.process_data else None
         workflow_node_execution.outputs = json.dumps(outputs) if outputs else None
-        workflow_node_execution.execution_metadata = (
-            json.dumps(jsonable_encoder(event.execution_metadata)) if event.execution_metadata else None
-        )
-        workflow_node_execution.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
-        workflow_node_execution.elapsed_time = (workflow_node_execution.finished_at - event.start_at).total_seconds()
+        workflow_node_execution.execution_metadata = execution_metadata
+        workflow_node_execution.finished_at = finished_at
+        workflow_node_execution.elapsed_time = elapsed_time
 
-        db.session.commit()
-        db.session.refresh(workflow_node_execution)
-        db.session.close()
+        self._wip_workflow_node_executions.pop(workflow_node_execution.node_execution_id)
 
         return workflow_node_execution
 
@@ -287,18 +309,33 @@ class WorkflowCycleManage:
 
         inputs = WorkflowEntry.handle_special_values(event.inputs)
         outputs = WorkflowEntry.handle_special_values(event.outputs)
+        finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
+        elapsed_time = (finished_at - event.start_at).total_seconds()
+
+        db.session.query(WorkflowNodeExecution).filter(WorkflowNodeExecution.id == workflow_node_execution.id).update(
+            {
+                WorkflowNodeExecution.status: WorkflowNodeExecutionStatus.FAILED.value,
+                WorkflowNodeExecution.error: event.error,
+                WorkflowNodeExecution.inputs: json.dumps(inputs) if inputs else None,
+                WorkflowNodeExecution.process_data: json.dumps(event.process_data) if event.process_data else None,
+                WorkflowNodeExecution.outputs: json.dumps(outputs) if outputs else None,
+                WorkflowNodeExecution.finished_at: finished_at,
+                WorkflowNodeExecution.elapsed_time: elapsed_time,
+            }
+        )
+
+        db.session.commit()
+        db.session.close()
 
         workflow_node_execution.status = WorkflowNodeExecutionStatus.FAILED.value
         workflow_node_execution.error = event.error
-        workflow_node_execution.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
         workflow_node_execution.inputs = json.dumps(inputs) if inputs else None
         workflow_node_execution.process_data = json.dumps(event.process_data) if event.process_data else None
         workflow_node_execution.outputs = json.dumps(outputs) if outputs else None
-        workflow_node_execution.elapsed_time = (workflow_node_execution.finished_at - event.start_at).total_seconds()
+        workflow_node_execution.finished_at = finished_at
+        workflow_node_execution.elapsed_time = elapsed_time
 
-        db.session.commit()
-        db.session.refresh(workflow_node_execution)
-        db.session.close()
+        self._wip_workflow_node_executions.pop(workflow_node_execution.node_execution_id)
 
         return workflow_node_execution
 
@@ -675,17 +712,7 @@ class WorkflowCycleManage:
         :param node_execution_id: workflow node execution id
         :return:
         """
-        workflow_node_execution = (
-            db.session.query(WorkflowNodeExecution)
-            .filter(
-                WorkflowNodeExecution.tenant_id == self._application_generate_entity.app_config.tenant_id,
-                WorkflowNodeExecution.app_id == self._application_generate_entity.app_config.app_id,
-                WorkflowNodeExecution.workflow_id == self._workflow.id,
-                WorkflowNodeExecution.triggered_from == WorkflowNodeExecutionTriggeredFrom.WORKFLOW_RUN.value,
-                WorkflowNodeExecution.node_execution_id == node_execution_id,
-            )
-            .first()
-        )
+        workflow_node_execution = self._wip_workflow_node_executions.get(node_execution_id)
 
         if not workflow_node_execution:
             raise Exception(f"Workflow node execution not found: {node_execution_id}")

api/core/callback_handler/agent_tool_callback_handler.py

@@ -1,9 +1,9 @@
-import os
 from collections.abc import Mapping, Sequence
 from typing import Any, Optional, TextIO, Union
 
 from pydantic import BaseModel
 
+from configs import dify_config
 from core.ops.entities.trace_entity import TraceTaskName
 from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
 from core.tools.entities.tool_entities import ToolInvokeMessage
@@ -50,7 +50,8 @@ class DifyAgentCallbackHandler(BaseModel):
         tool_inputs: Mapping[str, Any],
     ) -> None:
         """Do nothing."""
-        print_text("\n[on_tool_start] ToolCall:" + tool_name + "\n" + str(tool_inputs) + "\n", color=self.color)
+        if dify_config.DEBUG:
+            print_text("\n[on_tool_start] ToolCall:" + tool_name + "\n" + str(tool_inputs) + "\n", color=self.color)
 
     def on_tool_end(
         self,
@@ -62,11 +63,12 @@ class DifyAgentCallbackHandler(BaseModel):
         trace_manager: Optional[TraceQueueManager] = None,
     ) -> None:
         """If not the final action, print out observation."""
-        print_text("\n[on_tool_end]\n", color=self.color)
-        print_text("Tool: " + tool_name + "\n", color=self.color)
-        print_text("Inputs: " + str(tool_inputs) + "\n", color=self.color)
-        print_text("Outputs: " + str(tool_outputs)[:1000] + "\n", color=self.color)
-        print_text("\n")
+        if dify_config.DEBUG:
+            print_text("\n[on_tool_end]\n", color=self.color)
+            print_text("Tool: " + tool_name + "\n", color=self.color)
+            print_text("Inputs: " + str(tool_inputs) + "\n", color=self.color)
+            print_text("Outputs: " + str(tool_outputs)[:1000] + "\n", color=self.color)
+            print_text("\n")
 
         if trace_manager:
             trace_manager.add_trace_task(
@@ -82,30 +84,33 @@ class DifyAgentCallbackHandler(BaseModel):
 
     def on_tool_error(self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any) -> None:
         """Do nothing."""
-        print_text("\n[on_tool_error] Error: " + str(error) + "\n", color="red")
+        if dify_config.DEBUG:
+            print_text("\n[on_tool_error] Error: " + str(error) + "\n", color="red")
 
     def on_agent_start(self, thought: str) -> None:
         """Run on agent start."""
-        if thought:
-            print_text(
-                "\n[on_agent_start] \nCurrent Loop: " + str(self.current_loop) + "\nThought: " + thought + "\n",
-                color=self.color,
-            )
-        else:
-            print_text("\n[on_agent_start] \nCurrent Loop: " + str(self.current_loop) + "\n", color=self.color)
+        if dify_config.DEBUG:
+            if thought:
+                print_text(
+                    "\n[on_agent_start] \nCurrent Loop: " + str(self.current_loop) + "\nThought: " + thought + "\n",
+                    color=self.color,
+                )
+            else:
+                print_text("\n[on_agent_start] \nCurrent Loop: " + str(self.current_loop) + "\n", color=self.color)
 
     def on_agent_finish(self, color: Optional[str] = None, **kwargs: Any) -> None:
         """Run on agent end."""
-        print_text("\n[on_agent_finish]\n Loop: " + str(self.current_loop) + "\n", color=self.color)
+        if dify_config.DEBUG:
+            print_text("\n[on_agent_finish]\n Loop: " + str(self.current_loop) + "\n", color=self.color)
 
         self.current_loop += 1
 
     @property
     def ignore_agent(self) -> bool:
         """Whether to ignore agent callbacks."""
-        return not os.environ.get("DEBUG") or os.environ.get("DEBUG").lower() != "true"
+        return not dify_config.DEBUG
 
     @property
     def ignore_chat_model(self) -> bool:
         """Whether to ignore chat model callbacks."""
-        return not os.environ.get("DEBUG") or os.environ.get("DEBUG").lower() != "true"
+        return not dify_config.DEBUG

api/core/callback_handler/index_tool_callback_handler.py

@@ -44,7 +44,6 @@ class DatasetIndexToolCallbackHandler:
                 DocumentSegment.index_node_id == document.metadata["doc_id"]
             )
 
-            # if 'dataset_id' in document.metadata:
             if "dataset_id" in document.metadata:
                 query = query.filter(DocumentSegment.dataset_id == document.metadata["dataset_id"])
 

api/core/embedding/cached_embedding.py

@@ -5,6 +5,7 @@ from typing import Optional, cast
 import numpy as np
 from sqlalchemy.exc import IntegrityError
 
+from configs import dify_config
 from core.embedding.embedding_constant import EmbeddingInputType
 from core.model_manager import ModelInstance
 from core.model_runtime.entities.model_entities import ModelPropertyKey
@@ -110,6 +111,8 @@ class CacheEmbedding(Embeddings):
             embedding_results = embedding_result.embeddings[0]
             embedding_results = (embedding_results / np.linalg.norm(embedding_results)).tolist()
         except Exception as ex:
+            if dify_config.DEBUG:
+                logging.exception(f"Failed to embed query text: {ex}")
             raise ex
 
         try:
@@ -122,6 +125,8 @@ class CacheEmbedding(Embeddings):
             encoded_str = encoded_vector.decode("utf-8")
             redis_client.setex(embedding_cache_key, 600, encoded_str)
         except Exception as ex:
-            logging.exception("Failed to add embedding to redis %s", ex)
+            if dify_config.DEBUG:
+                logging.exception("Failed to add embedding to redis %s", ex)
+            raise ex
 
         return embedding_results

api/core/file/message_file_parser.py

@@ -198,16 +198,34 @@ class MessageFileParser:
                     if "amazonaws.com" not in parsed_url.netloc:
                         return False
                     query_params = parse_qs(parsed_url.query)
-                    required_params = ["Signature", "Expires"]
-                    for param in required_params:
-                        if param not in query_params:
+
+                    def check_presign_v2(query_params):
+                        required_params = ["Signature", "Expires"]
+                        for param in required_params:
+                            if param not in query_params:
+                                return False
+                        if not query_params["Expires"][0].isdigit():
                             return False
-                    if not query_params["Expires"][0].isdigit():
-                        return False
-                    signature = query_params["Signature"][0]
-                    if not re.match(r"^[A-Za-z0-9+/]+={0,2}$", signature):
-                        return False
-                    return True
+                        signature = query_params["Signature"][0]
+                        if not re.match(r"^[A-Za-z0-9+/]+={0,2}$", signature):
+                            return False
+
+                        return True
+
+                    def check_presign_v4(query_params):
+                        required_params = ["X-Amz-Signature", "X-Amz-Expires"]
+                        for param in required_params:
+                            if param not in query_params:
+                                return False
+                        if not query_params["X-Amz-Expires"][0].isdigit():
+                            return False
+                        signature = query_params["X-Amz-Signature"][0]
+                        if not re.match(r"^[A-Za-z0-9+/]+={0,2}$", signature):
+                            return False
+
+                        return True
+
+                    return check_presign_v4(query_params) or check_presign_v2(query_params)
                 except Exception:
                     return False
 

api/core/indexing_runner.py

@@ -211,9 +211,9 @@ class IndexingRunner:
         tenant_id: str,
         extract_settings: list[ExtractSetting],
         tmp_processing_rule: dict,
-        doc_form: str = None,
+        doc_form: Optional[str] = None,
         doc_language: str = "English",
-        dataset_id: str = None,
+        dataset_id: Optional[str] = None,
         indexing_technique: str = "economy",
     ) -> dict:
         """

api/core/memory/token_buffer_memory.py

@@ -58,7 +58,11 @@ class TokenBufferMemory:
         # instead of all messages from the conversation, we only need to extract messages
         # that belong to the thread of last message
         thread_messages = extract_thread_messages(messages)
-        thread_messages.pop(0)
+
+        # for newly created message, its answer is temporarily empty, we don't need to add it to memory
+        if thread_messages and not thread_messages[0].answer:
+            thread_messages.pop(0)
+
         messages = list(reversed(thread_messages))
 
         message_file_parser = MessageFileParser(tenant_id=app_record.tenant_id, app_id=app_record.id)

api/core/model_runtime/model_providers/__base/large_language_model.py

@@ -94,7 +94,7 @@ class LargeLanguageModel(AIModel):
         )
 
         try:
-            if "response_format" in model_parameters:
+            if "response_format" in model_parameters and model_parameters["response_format"] in {"JSON", "XML"}:
                 result = self._code_block_mode_wrapper(
                     model=model,
                     credentials=credentials,

api/core/model_runtime/model_providers/__base/tts_model.py

@@ -1,7 +1,7 @@
 import logging
 import re
 from abc import abstractmethod
-from typing import Optional
+from typing import Any, Optional
 
 from pydantic import ConfigDict
 
@@ -88,7 +88,7 @@ class TTSModel(AIModel):
             else:
                 return [{"name": d["name"], "value": d["mode"]} for d in voices]
 
-    def _get_model_default_voice(self, model: str, credentials: dict) -> any:
+    def _get_model_default_voice(self, model: str, credentials: dict) -> Any:
         """
         Get voice for given tts model
 

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

@@ -169,7 +169,7 @@ class AnthropicLargeLanguageModel(LargeLanguageModel):
         stop: Optional[list[str]] = None,
         stream: bool = True,
         user: Optional[str] = None,
-        callbacks: list[Callback] = None,
+        callbacks: Optional[list[Callback]] = None,
     ) -> Union[LLMResult, Generator]:
         """
         Code block mode wrapper for invoking large language model

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

@@ -1081,8 +1081,97 @@ LLM_BASE_MODELS = [
             ),
         ),
     ),
+    AzureBaseModel(
+        base_model_name="o1-preview",
+        entity=AIModelEntity(
+            model="fake-deployment-name",
+            label=I18nObject(
+                en_US="fake-deployment-name-label",
+            ),
+            model_type=ModelType.LLM,
+            features=[
+                ModelFeature.AGENT_THOUGHT,
+            ],
+            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
+            model_properties={
+                ModelPropertyKey.MODE: LLMMode.CHAT.value,
+                ModelPropertyKey.CONTEXT_SIZE: 128000,
+            },
+            parameter_rules=[
+                ParameterRule(
+                    name="temperature",
+                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TEMPERATURE],
+                ),
+                ParameterRule(
+                    name="top_p",
+                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TOP_P],
+                ),
+                ParameterRule(
+                    name="response_format",
+                    label=I18nObject(zh_Hans="回复格式", en_US="response_format"),
+                    type="string",
+                    help=I18nObject(
+                        zh_Hans="指定模型必须输出的格式", en_US="specifying the format that the model must output"
+                    ),
+                    required=False,
+                    options=["text", "json_object"],
+                ),
+                _get_max_tokens(default=512, min_val=1, max_val=32768),
+            ],
+            pricing=PriceConfig(
+                input=15.00,
+                output=60.00,
+                unit=0.000001,
+                currency="USD",
+            ),
+        ),
+    ),
+    AzureBaseModel(
+        base_model_name="o1-mini",
+        entity=AIModelEntity(
+            model="fake-deployment-name",
+            label=I18nObject(
+                en_US="fake-deployment-name-label",
+            ),
+            model_type=ModelType.LLM,
+            features=[
+                ModelFeature.AGENT_THOUGHT,
+            ],
+            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
+            model_properties={
+                ModelPropertyKey.MODE: LLMMode.CHAT.value,
+                ModelPropertyKey.CONTEXT_SIZE: 128000,
+            },
+            parameter_rules=[
+                ParameterRule(
+                    name="temperature",
+                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TEMPERATURE],
+                ),
+                ParameterRule(
+                    name="top_p",
+                    **PARAMETER_RULE_TEMPLATE[DefaultParameterName.TOP_P],
+                ),
+                ParameterRule(
+                    name="response_format",
+                    label=I18nObject(zh_Hans="回复格式", en_US="response_format"),
+                    type="string",
+                    help=I18nObject(
+                        zh_Hans="指定模型必须输出的格式", en_US="specifying the format that the model must output"
+                    ),
+                    required=False,
+                    options=["text", "json_object"],
+                ),
+                _get_max_tokens(default=512, min_val=1, max_val=65536),
+            ],
+            pricing=PriceConfig(
+                input=3.00,
+                output=12.00,
+                unit=0.000001,
+                currency="USD",
+            ),
+        ),
+    ),
 ]
-
 EMBEDDING_BASE_MODELS = [
     AzureBaseModel(
         base_model_name="text-embedding-ada-002",

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

@@ -53,6 +53,9 @@ model_credential_schema:
       type: select
       required: true
       options:
+        - label:
+            en_US: 2024-09-01-preview
+          value: 2024-09-01-preview
         - label:
             en_US: 2024-08-01-preview
           value: 2024-08-01-preview
@@ -120,6 +123,18 @@ model_credential_schema:
           show_on:
             - variable: __model_type
               value: llm
+        - label:
+            en_US: o1-mini
+          value: o1-mini
+          show_on:
+            - variable: __model_type
+              value: llm
+        - label:
+            en_US: o1-preview
+          value: o1-preview
+          show_on:
+            - variable: __model_type
+              value: llm
         - label:
             en_US: gpt-4o-mini
           value: gpt-4o-mini

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

@@ -119,7 +119,15 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
         try:
             client = AzureOpenAI(**self._to_credential_kwargs(credentials))
 
-            if ai_model_entity.entity.model_properties.get(ModelPropertyKey.MODE) == LLMMode.CHAT.value:
+            if model.startswith("o1"):
+                client.chat.completions.create(
+                    messages=[{"role": "user", "content": "ping"}],
+                    model=model,
+                    temperature=1,
+                    max_completion_tokens=20,
+                    stream=False,
+                )
+            elif ai_model_entity.entity.model_properties.get(ModelPropertyKey.MODE) == LLMMode.CHAT.value:
                 # chat model
                 client.chat.completions.create(
                     messages=[{"role": "user", "content": "ping"}],
@@ -312,10 +320,24 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
         if user:
             extra_model_kwargs["user"] = user
 
+        # clear illegal prompt messages
+        prompt_messages = self._clear_illegal_prompt_messages(model, prompt_messages)
+
+        block_as_stream = False
+        if model.startswith("o1"):
+            if stream:
+                block_as_stream = True
+                stream = False
+
+                if "stream_options" in extra_model_kwargs:
+                    del extra_model_kwargs["stream_options"]
+
+            if "stop" in extra_model_kwargs:
+                del extra_model_kwargs["stop"]
+
         # chat model
-        messages = [self._convert_prompt_message_to_dict(m) for m in prompt_messages]
         response = client.chat.completions.create(
-            messages=messages,
+            messages=[self._convert_prompt_message_to_dict(m) for m in prompt_messages],
             model=model,
             stream=stream,
             **model_parameters,
@@ -325,7 +347,91 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
         if stream:
             return self._handle_chat_generate_stream_response(model, credentials, response, prompt_messages, tools)
 
-        return self._handle_chat_generate_response(model, credentials, response, prompt_messages, tools)
+        block_result = self._handle_chat_generate_response(model, credentials, response, prompt_messages, tools)
+
+        if block_as_stream:
+            return self._handle_chat_block_as_stream_response(block_result, prompt_messages, stop)
+
+        return block_result
+
+    def _handle_chat_block_as_stream_response(
+        self,
+        block_result: LLMResult,
+        prompt_messages: list[PromptMessage],
+        stop: Optional[list[str]] = None,
+    ) -> Generator[LLMResultChunk, None, None]:
+        """
+        Handle llm chat response
+
+        :param model: model name
+        :param credentials: credentials
+        :param response: response
+        :param prompt_messages: prompt messages
+        :param tools: tools for tool calling
+        :param stop: stop words
+        :return: llm response chunk generator
+        """
+        text = block_result.message.content
+        text = cast(str, text)
+
+        if stop:
+            text = self.enforce_stop_tokens(text, stop)
+
+        yield LLMResultChunk(
+            model=block_result.model,
+            prompt_messages=prompt_messages,
+            system_fingerprint=block_result.system_fingerprint,
+            delta=LLMResultChunkDelta(
+                index=0,
+                message=AssistantPromptMessage(content=text),
+                finish_reason="stop",
+                usage=block_result.usage,
+            ),
+        )
+
+    def _clear_illegal_prompt_messages(self, model: str, prompt_messages: list[PromptMessage]) -> list[PromptMessage]:
+        """
+        Clear illegal prompt messages for OpenAI API
+
+        :param model: model name
+        :param prompt_messages: prompt messages
+        :return: cleaned prompt messages
+        """
+        checklist = ["gpt-4-turbo", "gpt-4-turbo-2024-04-09"]
+
+        if model in checklist:
+            # count how many user messages are there
+            user_message_count = len([m for m in prompt_messages if isinstance(m, UserPromptMessage)])
+            if user_message_count > 1:
+                for prompt_message in prompt_messages:
+                    if isinstance(prompt_message, UserPromptMessage):
+                        if isinstance(prompt_message.content, list):
+                            prompt_message.content = "\n".join(
+                                [
+                                    item.data
+                                    if item.type == PromptMessageContentType.TEXT
+                                    else "[IMAGE]"
+                                    if item.type == PromptMessageContentType.IMAGE
+                                    else ""
+                                    for item in prompt_message.content
+                                ]
+                            )
+
+        if model.startswith("o1"):
+            system_message_count = len([m for m in prompt_messages if isinstance(m, SystemPromptMessage)])
+            if system_message_count > 0:
+                new_prompt_messages = []
+                for prompt_message in prompt_messages:
+                    if isinstance(prompt_message, SystemPromptMessage):
+                        prompt_message = UserPromptMessage(
+                            content=prompt_message.content,
+                            name=prompt_message.name,
+                        )
+
+                    new_prompt_messages.append(prompt_message)
+                prompt_messages = new_prompt_messages
+
+        return prompt_messages
 
     def _handle_chat_generate_response(
         self,
@@ -560,7 +666,7 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
             tokens_per_message = 4
             # if there's a name, the role is omitted
             tokens_per_name = -1
-        elif model.startswith("gpt-35-turbo") or model.startswith("gpt-4"):
+        elif model.startswith("gpt-35-turbo") or model.startswith("gpt-4") or model.startswith("o1"):
             tokens_per_message = 3
             tokens_per_name = 1
         else:

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

@@ -1,6 +1,6 @@
 import concurrent.futures
 import copy
-from typing import Optional
+from typing import Any, Optional
 
 from openai import AzureOpenAI
 
@@ -19,7 +19,7 @@ class AzureOpenAIText2SpeechModel(_CommonAzureOpenAI, TTSModel):
 
     def _invoke(
         self, model: str, tenant_id: str, credentials: dict, content_text: str, voice: str, user: Optional[str] = None
-    ) -> any:
+    ) -> Any:
         """
         _invoke text2speech model
 
@@ -56,7 +56,7 @@ class AzureOpenAIText2SpeechModel(_CommonAzureOpenAI, TTSModel):
         except Exception as ex:
             raise CredentialsValidateFailedError(str(ex))
 
-    def _tts_invoke_streaming(self, model: str, credentials: dict, content_text: str, voice: str) -> any:
+    def _tts_invoke_streaming(self, model: str, credentials: dict, content_text: str, voice: str) -> Any:
         """
         _tts_invoke_streaming text2speech model
         :param model: model name

api/core/model_runtime/model_providers/bedrock/bedrock.yaml

@@ -50,34 +50,62 @@ provider_credential_schema:
           label:
             en_US: US East (N. Virginia)
             zh_Hans: 美国东部 (弗吉尼亚北部)
+        - value: us-east-2
+          label:
+            en_US: US East (Ohio)
+            zh_Hans: 美国东部 (弗吉尼亚北部)
         - value: us-west-2
           label:
             en_US: US West (Oregon)
             zh_Hans: 美国西部 (俄勒冈州)
+        - value: ap-south-1
+          label:
+            en_US: Asia Pacific (Mumbai)
+            zh_Hans: 亚太地区（孟买）
         - value: ap-southeast-1
           label:
             en_US: Asia Pacific (Singapore)
             zh_Hans: 亚太地区 (新加坡)
-        - value: ap-northeast-1
-          label:
-            en_US: Asia Pacific (Tokyo)
-            zh_Hans: 亚太地区 (东京)
-        - value: eu-central-1
-          label:
-            en_US: Europe (Frankfurt)
-            zh_Hans: 欧洲 (法兰克福)
-        - value: eu-west-2
-          label:
-            en_US: Eu west London (London)
-            zh_Hans: 欧洲西部 (伦敦)
-        - value: us-gov-west-1
-          label:
-            en_US: AWS GovCloud (US-West)
-            zh_Hans: AWS GovCloud (US-West)
         - value: ap-southeast-2
           label:
             en_US: Asia Pacific (Sydney)
             zh_Hans: 亚太地区 (悉尼)
+        - value: ap-northeast-1
+          label:
+            en_US: Asia Pacific (Tokyo)
+            zh_Hans: 亚太地区 (东京)
+        - value: ap-northeast-2
+          label:
+            en_US: Asia Pacific (Seoul)
+            zh_Hans: 亚太地区（首尔）
+        - value: ca-central-1
+          label:
+            en_US: Canada (Central)
+            zh_Hans: 加拿大（中部）
+        - value: eu-central-1
+          label:
+            en_US: Europe (Frankfurt)
+            zh_Hans: 欧洲 (法兰克福)
+        - value: eu-west-1
+          label:
+            en_US: Europe (Ireland)
+            zh_Hans: 欧洲（爱尔兰）
+        - value: eu-west-2
+          label:
+            en_US: Europe (London)
+            zh_Hans: 欧洲西部 (伦敦)
+        - value: eu-west-3
+          label:
+            en_US: Europe (Paris)
+            zh_Hans: 欧洲（巴黎）
+        - value: sa-east-1
+          label:
+            en_US: South America (São Paulo)
+            zh_Hans: 南美洲（圣保罗）
+        - value: us-gov-west-1
+          label:
+            en_US: AWS GovCloud (US-West)
+            zh_Hans: AWS GovCloud (US-West)
     - variable: model_for_validation
       required: false
       label:

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

@@ -92,7 +92,7 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
         stop: Optional[list[str]] = None,
         stream: bool = True,
         user: Optional[str] = None,
-        callbacks: list[Callback] = None,
+        callbacks: Optional[list[Callback]] = None,
     ) -> Union[LLMResult, Generator]:
         """
         Code block mode wrapper for invoking large language model

api/core/model_runtime/model_providers/fireworks/fireworks.yaml

@@ -18,6 +18,7 @@ supported_model_types:
   - text-embedding
 configurate_methods:
   - predefined-model
+  - customizable-model
 provider_credential_schema:
   credential_form_schemas:
     - variable: fireworks_api_key
@@ -28,3 +29,75 @@ provider_credential_schema:
       placeholder:
         zh_Hans: 在此输入您的 API Key
         en_US: Enter your API Key
+model_credential_schema:
+  model:
+    label:
+      en_US: Model URL
+      zh_Hans: 模型URL
+    placeholder:
+      en_US: Enter your Model URL
+      zh_Hans: 输入模型URL
+  credential_form_schemas:
+    - variable: model_label_zh_Hanns
+      label:
+        zh_Hans: 模型中文名称
+        en_US: The zh_Hans of Model
+      required: true
+      type: text-input
+      placeholder:
+        zh_Hans: 在此输入您的模型中文名称
+        en_US: Enter your zh_Hans of Model
+    - variable: model_label_en_US
+      label:
+        zh_Hans: 模型英文名称
+        en_US: The en_US of Model
+      required: true
+      type: text-input
+      placeholder:
+        zh_Hans: 在此输入您的模型英文名称
+        en_US: Enter your en_US of Model
+    - variable: fireworks_api_key
+      label:
+        en_US: API Key
+      type: secret-input
+      required: true
+      placeholder:
+        zh_Hans: 在此输入您的 API Key
+        en_US: Enter your API Key
+    - variable: context_size
+      label:
+        zh_Hans: 模型上下文长度
+        en_US: Model context size
+      required: true
+      type: text-input
+      default: '4096'
+      placeholder:
+        zh_Hans: 在此输入您的模型上下文长度
+        en_US: Enter your Model context size
+    - variable: max_tokens
+      label:
+        zh_Hans: 最大 token 上限
+        en_US: Upper bound for max tokens
+      default: '4096'
+      type: text-input
+      show_on:
+        - variable: __model_type
+          value: llm
+    - variable: function_calling_type
+      label:
+        en_US: Function calling
+      type: select
+      required: false
+      default: no_call
+      options:
+        - value: no_call
+          label:
+            en_US: Not Support
+            zh_Hans: 不支持
+        - value: function_call
+          label:
+            en_US: Support
+            zh_Hans: 支持
+      show_on:
+        - variable: __model_type
+          value: llm

api/core/model_runtime/model_providers/fireworks/llm/gemma2-9b-it.yaml

@@ -43,3 +43,4 @@ pricing:
   output: '0.2'
   unit: '0.000001'
   currency: USD
+deprecated: true

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

@@ -8,7 +8,8 @@ from openai.types.chat.chat_completion_chunk import ChoiceDeltaFunctionCall, Cho
 from openai.types.chat.chat_completion_message import FunctionCall
 
 from core.model_runtime.callbacks.base_callback import Callback
-from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta
+from core.model_runtime.entities.common_entities import I18nObject
+from core.model_runtime.entities.llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta
 from core.model_runtime.entities.message_entities import (
     AssistantPromptMessage,
     ImagePromptMessageContent,
@@ -20,6 +21,15 @@ from core.model_runtime.entities.message_entities import (
     ToolPromptMessage,
     UserPromptMessage,
 )
+from core.model_runtime.entities.model_entities import (
+    AIModelEntity,
+    FetchFrom,
+    ModelFeature,
+    ModelPropertyKey,
+    ModelType,
+    ParameterRule,
+    ParameterType,
+)
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
 from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
 from core.model_runtime.model_providers.fireworks._common import _CommonFireworks
@@ -511,7 +521,7 @@ class FireworksLargeLanguageModel(_CommonFireworks, LargeLanguageModel):
         model: str,
         messages: list[PromptMessage],
         tools: Optional[list[PromptMessageTool]] = None,
-        credentials: dict = None,
+        credentials: Optional[dict] = None,
     ) -> int:
         """
         Approximate num tokens with GPT2 tokenizer.
@@ -608,3 +618,50 @@ class FireworksLargeLanguageModel(_CommonFireworks, LargeLanguageModel):
                     num_tokens += self._get_num_tokens_by_gpt2(required_field)
 
         return num_tokens
+
+    def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity:
+        return AIModelEntity(
+            model=model,
+            label=I18nObject(
+                en_US=credentials.get("model_label_en_US", model),
+                zh_Hans=credentials.get("model_label_zh_Hanns", model),
+            ),
+            model_type=ModelType.LLM,
+            features=[ModelFeature.TOOL_CALL, ModelFeature.MULTI_TOOL_CALL, ModelFeature.STREAM_TOOL_CALL]
+            if credentials.get("function_calling_type") == "function_call"
+            else [],
+            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
+            model_properties={
+                ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size", 4096)),
+                ModelPropertyKey.MODE: LLMMode.CHAT.value,
+            },
+            parameter_rules=[
+                ParameterRule(
+                    name="temperature",
+                    use_template="temperature",
+                    label=I18nObject(en_US="Temperature", zh_Hans="温度"),
+                    type=ParameterType.FLOAT,
+                ),
+                ParameterRule(
+                    name="max_tokens",
+                    use_template="max_tokens",
+                    default=512,
+                    min=1,
+                    max=int(credentials.get("max_tokens", 4096)),
+                    label=I18nObject(en_US="Max Tokens", zh_Hans="最大标记"),
+                    type=ParameterType.INT,
+                ),
+                ParameterRule(
+                    name="top_p",
+                    use_template="top_p",
+                    label=I18nObject(en_US="Top P", zh_Hans="Top P"),
+                    type=ParameterType.FLOAT,
+                ),
+                ParameterRule(
+                    name="top_k",
+                    use_template="top_k",
+                    label=I18nObject(en_US="Top K", zh_Hans="Top K"),
+                    type=ParameterType.FLOAT,
+                ),
+            ],
+        )

api/core/model_runtime/model_providers/fireworks/llm/qwen2p5-72b-instruct.yaml

@@ -0,0 +1,46 @@
+model: accounts/fireworks/models/qwen2p5-72b-instruct
+label:
+  zh_Hans: Qwen2.5 72B Instruct
+  en_US: Qwen2.5 72B Instruct
+model_type: llm
+features:
+  - agent-thought
+  - tool-call
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+  - name: max_tokens
+    use_template: max_tokens
+  - name: context_length_exceeded_behavior
+    default: None
+    label:
+      zh_Hans: 上下文长度超出行为
+      en_US: Context Length Exceeded Behavior
+    help:
+      zh_Hans: 上下文长度超出行为
+      en_US: Context Length Exceeded Behavior
+    type: string
+    options:
+      - None
+      - truncate
+      - error
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.9'
+  output: '0.9'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/fishaudio/tts/tts.py

@@ -1,4 +1,4 @@
-from typing import Optional
+from typing import Any, Optional
 
 import httpx
 
@@ -46,7 +46,7 @@ class FishAudioText2SpeechModel(TTSModel):
         content_text: str,
         voice: str,
         user: Optional[str] = None,
-    ) -> any:
+    ) -> Any:
         """
         Invoke text2speech model
 
@@ -87,7 +87,7 @@ class FishAudioText2SpeechModel(TTSModel):
         except Exception as ex:
             raise CredentialsValidateFailedError(str(ex))
 
-    def _tts_invoke_streaming(self, model: str, credentials: dict, content_text: str, voice: str) -> any:
+    def _tts_invoke_streaming(self, model: str, credentials: dict, content_text: str, voice: str) -> Any:
         """
         Invoke streaming text2speech model
         :param model: model name
@@ -112,7 +112,7 @@ class FishAudioText2SpeechModel(TTSModel):
         except Exception as ex:
             raise InvokeBadRequestError(str(ex))
 
-    def _tts_invoke_streaming_sentence(self, credentials: dict, content_text: str, voice: Optional[str] = None) -> any:
+    def _tts_invoke_streaming_sentence(self, credentials: dict, content_text: str, voice: Optional[str] = None) -> Any:
         """
         Invoke streaming text2speech model
 

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

@@ -0,0 +1,15 @@
+- gemini-1.5-pro
+- gemini-1.5-pro-latest
+- gemini-1.5-pro-001
+- gemini-1.5-pro-002
+- gemini-1.5-pro-exp-0801
+- gemini-1.5-pro-exp-0827
+- gemini-1.5-flash
+- gemini-1.5-flash-latest
+- gemini-1.5-flash-001
+- gemini-1.5-flash-002
+- gemini-1.5-flash-exp-0827
+- gemini-1.5-flash-8b-exp-0827
+- gemini-1.5-flash-8b-exp-0924
+- gemini-pro
+- gemini-pro-vision

api/core/model_runtime/model_providers/google/llm/gemini-1.5-flash-001.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-flash-002.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-flash-8b-exp-0827.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-flash-8b-exp-0924.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-flash-exp-0827.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-flash-latest.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-flash.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-pro-001.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-pro-002.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-pro-exp-0801.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-pro-exp-0827.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-pro-latest.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-1.5-pro.yaml

@@ -32,15 +32,6 @@ parameter_rules:
     max: 8192
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-pro-vision.yaml

@@ -27,15 +27,6 @@ parameter_rules:
     default: 4096
     min: 1
     max: 4096
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

api/core/model_runtime/model_providers/google/llm/gemini-pro.yaml

@@ -31,15 +31,6 @@ parameter_rules:
     max: 2048
   - name: response_format
     use_template: response_format
-  - name: stream
-    label:
-      zh_Hans: 流式输出
-      en_US: Stream
-    type: boolean
-    help:
-      zh_Hans: 流式输出允许模型在生成文本的过程中逐步返回结果，而不是一次性生成全部结果后再返回。
-      en_US: Streaming output allows the model to return results incrementally as it generates text, rather than generating all the results at once.
-    default: false
 pricing:
   input: '0.00'
   output: '0.00'

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

@@ -5,3 +5,4 @@
 - llama3-8b-8192
 - mixtral-8x7b-32768
 - llama2-70b-4096
+- llama-guard-3-8b

api/core/model_runtime/model_providers/groq/llm/llama-guard-3-8b.yaml

@@ -0,0 +1,25 @@
+model: llama-guard-3-8b
+label:
+  zh_Hans: Llama-Guard-3-8B
+  en_US: Llama-Guard-3-8B
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_tokens
+    use_template: max_tokens
+    default: 512
+    min: 1
+    max: 8192
+pricing:
+  input: '0.20'
+  output: '0.20'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/jina/rerank/rerank.py

@@ -61,11 +61,19 @@ class JinaRerankModel(RerankModel):
 
             rerank_documents = []
             for result in results["results"]:
+                index = result["index"]
+                if "document" in result:
+                    text = result["document"]["text"]
+                else:
+                    # llama.cpp rerank maynot return original documents
+                    text = docs[index]
+
                 rerank_document = RerankDocument(
-                    index=result["index"],
-                    text=result["document"]["text"],
+                    index=index,
+                    text=text,
                     score=result["relevance_score"],
                 )
+
                 if score_threshold is None or result["relevance_score"] >= score_threshold:
                     rerank_documents.append(rerank_document)
 

api/core/model_runtime/model_providers/localai/rerank/rerank.py

@@ -70,11 +70,19 @@ class LocalaiRerankModel(RerankModel):
 
             rerank_documents = []
             for result in results["results"]:
+                index = result["index"]
+                if "document" in result:
+                    text = result["document"]["text"]
+                else:
+                    # llama.cpp rerank maynot return original documents
+                    text = docs[index]
+
                 rerank_document = RerankDocument(
-                    index=result["index"],
-                    text=result["document"]["text"],
+                    index=index,
+                    text=text,
                     score=result["relevance_score"],
                 )
+
                 if score_threshold is None or result["relevance_score"] >= score_threshold:
                     rerank_documents.append(rerank_document)
 

api/core/model_runtime/model_providers/minimax/llm/abab6.5t-chat.yaml

@@ -0,0 +1,44 @@
+model: abab6.5t-chat
+label:
+  en_US: Abab6.5t-Chat
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0.01
+    max: 1
+    default: 0.9
+  - name: top_p
+    use_template: top_p
+    min: 0.01
+    max: 1
+    default: 0.95
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 3072
+    min: 1
+    max: 8192
+  - name: mask_sensitive_info
+    type: boolean
+    default: true
+    label:
+      zh_Hans: 隐私保护
+      en_US: Moderate
+    help:
+      zh_Hans: 对输出中易涉及隐私问题的文本信息进行打码，目前包括但不限于邮箱、域名、链接、证件号、家庭住址等，默认true，即开启打码
+      en_US: Mask the sensitive info of the generated content, such as email/domain/link/address/phone/id..
+  - name: presence_penalty
+    use_template: presence_penalty
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '0.005'
+  output: '0.005'
+  unit: '0.001'
+  currency: RMB

api/core/model_runtime/model_providers/minimax/text_embedding/text_embedding.py

@@ -61,7 +61,8 @@ class MinimaxTextEmbeddingModel(TextEmbeddingModel):
         url = f"{self.api_base}?GroupId={group_id}"
         headers = {"Authorization": "Bearer " + api_key, "Content-Type": "application/json"}
 
-        data = {"model": "embo-01", "texts": texts, "type": "db"}
+        embedding_type = "db" if input_type == EmbeddingInputType.DOCUMENT else "query"
+        data = {"model": "embo-01", "texts": texts, "type": embedding_type}
 
         try:
             response = post(url, headers=headers, data=dumps(data))

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

@@ -111,7 +111,7 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
         stop: Optional[list[str]] = None,
         stream: bool = True,
         user: Optional[str] = None,
-        callbacks: list[Callback] = None,
+        callbacks: Optional[list[Callback]] = None,
     ) -> Union[LLMResult, Generator]:
         """
         Code block mode wrapper for invoking large language model