fix: margin in rerank switch

# Conflicts:
#	api/poetry.lock

.github/workflows/api-tests.yml

@@ -39,7 +39,7 @@ jobs:
             api/pyproject.toml
             api/poetry.lock
 
-      - name: Check Poetry lockfile
+      - name: Poetry check
         run: |
           poetry check -C api --lock
           poetry show -C api
@@ -47,9 +47,6 @@ jobs:
       - name: Install dependencies
         run: poetry install -C api --with dev
 
-      - name: Check dependencies in pyproject.toml
-        run: poetry run -C api bash dev/pytest/pytest_artifacts.sh
-
       - name: Run Unit tests
         run: poetry run -C api bash dev/pytest/pytest_unit_tests.sh
 

.github/workflows/build-push.yml

@@ -5,7 +5,6 @@ on:
     branches:
       - "main"
       - "deploy/dev"
-      - "fix/external-knowledge-retrieval-issues"
   release:
     types: [published]
 
@@ -126,7 +125,7 @@ jobs:
         with:
           images: ${{ env[matrix.image_name_env] }}
           tags: |
-            type=raw,value=latest,enable=${{ startsWith(github.ref, 'refs/tags/') && !contains(github.ref, '-beta') }}
+            type=raw,value=latest,enable=${{ startsWith(github.ref, 'refs/tags/') }}
             type=ref,event=branch
             type=sha,enable=true,priority=100,prefix=,suffix=,format=long
             type=raw,value=${{ github.ref_name }},enable=${{ startsWith(github.ref, 'refs/tags/') }}

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 X(Twitter)"></a>
+            alt="follow on 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">
@@ -196,14 +196,10 @@ 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). 
@@ -223,7 +219,7 @@ 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.
-* [X(Twitter)](https://twitter.com/dify_ai). 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.
 
 ## 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 X(Twitter)"></a>
+            alt="follow on 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">
@@ -179,13 +179,10 @@ 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 X(Twitter)"></a>
+            alt="follow on 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">
@@ -202,14 +202,10 @@ 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)
@@ -236,7 +232,7 @@ 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。
-- [X(Twitter)](https://twitter.com/dify_ai)。👉：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。
 - [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 X(Twitter)"></a>
+            alt="seguir en 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">
@@ -204,13 +204,10 @@ 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
 
@@ -231,7 +228,7 @@ 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.
-* [X(Twitter)](https://twitter.com/dify_ai). 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.
 
 ## 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 X(Twitter)"></a>
+            alt="suivre sur 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">
@@ -202,13 +202,10 @@ 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
 
@@ -229,7 +226,7 @@ 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.
-* [X(Twitter)](https://twitter.com/dify_ai). 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.
 
 ## 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="X(Twitter)でフォロー"></a>
+            alt="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ポートも提供します。
+  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ーポイントも提供します。
 
 **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。
@@ -201,13 +201,10 @@ docker compose up -d
 
 #### Terraformを使用したデプロイ
 
-[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)
+[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)
 
-##### Google Cloud
-- [@sotazumによるGoogle Cloud Terraform](https://github.com/DeNA/dify-google-cloud-terraform)
 
 ## 貢献
 
@@ -228,7 +225,7 @@ 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。
-* [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。
+* [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 X(Twitter)"></a>
+            alt="follow on 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">
@@ -202,13 +202,10 @@ If you'd like to configure a highly-available setup, there are community-contrib
 
 #### Terraform atorlugu pilersitsineq
 
-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)
+Atoruk [terraform](https://www.terraform.io/) Dify-mik Azure-mut ataatsikkut ikkussuilluarlugu.
+- [Azure Terraform atorlugu @nikawang](https://github.com/nikawang/dify-azure-terraform)
 
-##### Google Cloud
-- [Google Cloud Terraform qachlot @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
 ## Contributing
 
@@ -231,7 +228,7 @@ 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.
-* [X(Twitter)](https://twitter.com/dify_ai). 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.
 
 ## 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 X(Twitter)"></a>
+            alt="follow on 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">
@@ -39,6 +39,7 @@
   <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>
 
 
@@ -194,14 +195,10 @@ 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="X(Twitter)'da takip et"></a>
+            alt="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">
@@ -200,13 +200,9 @@ 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
-- [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)
+[Terraform](https://www.terraform.io/) kullanarak Dify'ı Azure'a tek tıklamayla dağıtın.
+- [@nikawang tarafından Azure Terraform](https://github.com/nikawang/dify-azure-terraform)
 
 ## Katkıda Bulunma
 
@@ -226,7 +222,7 @@ 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.
-* [X(Twitter)](https://twitter.com/dify_ai). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.
+* [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 X(Twitter)"></a>
+            alt="theo dõi trên 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">
@@ -196,14 +196,10 @@ 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. 
@@ -223,7 +219,7 @@ Triển khai Dify lên nền tảng đám mây với một cú nhấp chuột b
 * [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.
-* [X(Twitter)](https://twitter.com/dify_ai). 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.
 
 ## Lịch sử Yêu thích
 

api/.env.example

@@ -39,7 +39,7 @@ DB_DATABASE=dify
 
 # Storage configuration
 # use for store upload files, private keys...
-# storage type: local, s3, azure-blob, google-storage, tencent-cos, huawei-obs, volcengine-tos, baidu-obs
+# storage type: local, s3, azure-blob, google-storage, tencent-cos, huawei-obs, volcengine-tos
 STORAGE_TYPE=local
 STORAGE_LOCAL_PATH=storage
 S3_USE_AWS_MANAGED_IAM=false
@@ -79,12 +79,6 @@ 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
@@ -271,9 +265,6 @@ 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/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  # noqa: F401
+from events import event_handlers
 from extensions import (
     ext_celery,
     ext_code_based_extension,
@@ -36,7 +36,6 @@ from extensions import (
     ext_login,
     ext_mail,
     ext_migrate,
-    ext_proxy_fix,
     ext_redis,
     ext_sentry,
     ext_storage,
@@ -46,7 +45,7 @@ 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  # noqa: F401
+from models import account, dataset, model, source, task, tool, tools, web
 from services.account_service import AccountService
 
 # DO NOT REMOVE ABOVE
@@ -157,7 +156,6 @@ 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
@@ -183,10 +181,10 @@ def load_user_from_request(request_from_flask_login):
     decoded = PassportService().verify(auth_token)
     user_id = decoded.get("user_id")
 
-    logged_in_account = AccountService.load_logged_in_account(account_id=user_id, token=auth_token)
-    if logged_in_account:
-        contexts.tenant_id.set(logged_in_account.current_tenant_id)
-    return logged_in_account
+    account = AccountService.load_logged_in_account(account_id=user_id, token=auth_token)
+    if account:
+        contexts.tenant_id.set(account.current_tenant_id)
+    return account
 
 
 @login_manager.unauthorized_handler

api/configs/feature/__init__.py

@@ -247,12 +247,6 @@ 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):
     """

api/configs/middleware/__init__.py

@@ -5,10 +5,10 @@ from pydantic import Field, NonNegativeInt, PositiveFloat, PositiveInt, computed
 from pydantic_settings import BaseSettings
 
 from configs.middleware.cache.redis_config import RedisConfig
+from configs.middleware.external.bedrock_config import BedrockConfig
 from configs.middleware.storage.aliyun_oss_storage_config import AliyunOSSStorageConfig
 from configs.middleware.storage.amazon_s3_storage_config import S3StorageConfig
 from configs.middleware.storage.azure_blob_storage_config import AzureBlobStorageConfig
-from configs.middleware.storage.baidu_obs_storage_config import BaiduOBSStorageConfig
 from configs.middleware.storage.google_cloud_storage_config import GoogleCloudStorageConfig
 from configs.middleware.storage.huawei_obs_storage_config import HuaweiCloudOBSStorageConfig
 from configs.middleware.storage.oci_storage_config import OCIStorageConfig
@@ -191,22 +191,6 @@ 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,
@@ -217,13 +201,12 @@ class MiddlewareConfig(
     StorageConfig,
     AliyunOSSStorageConfig,
     AzureBlobStorageConfig,
-    BaiduOBSStorageConfig,
     GoogleCloudStorageConfig,
-    HuaweiCloudOBSStorageConfig,
-    OCIStorageConfig,
-    S3StorageConfig,
     TencentCloudCOSStorageConfig,
+    HuaweiCloudOBSStorageConfig,
     VolcengineTOSStorageConfig,
+    S3StorageConfig,
+    OCIStorageConfig,
     # configs of vdb and vdb providers
     VectorStoreConfig,
     AnalyticdbConfig,
@@ -240,6 +223,6 @@ class MiddlewareConfig(
     TiDBVectorConfig,
     WeaviateConfig,
     ElasticsearchConfig,
-    InternalTestConfig,
+    BedrockConfig,
 ):
     pass

api/configs/middleware/external/bedrock_config.py

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

api/configs/middleware/storage/baidu_obs_storage_config.py

@@ -1,29 +0,0 @@
-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/packaging/__init__.py

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
 
     CURRENT_VERSION: str = Field(
         description="Dify version",
-        default="0.9.1-fix1",
+        default="0.8.3",
     )
 
     COMMIT_SHA: str = Field(

api/controllers/console/__init__.py

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

api/controllers/console/app/conversation.py

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

api/controllers/console/datasets/datasets.py

@@ -613,10 +613,10 @@ class DatasetRetrievalSettingApi(Resource):
             case (
                 VectorType.MILVUS
                 | VectorType.RELYT
+                | VectorType.PGVECTOR
                 | VectorType.TIDB_VECTOR
                 | VectorType.CHROMA
                 | VectorType.TENCENT
-                | VectorType.PGVECTO_RS
             ):
                 return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
             case (
@@ -627,7 +627,6 @@ class DatasetRetrievalSettingApi(Resource):
                 | VectorType.MYSCALE
                 | VectorType.ORACLE
                 | VectorType.ELASTICSEARCH
-                | VectorType.PGVECTOR
             ):
                 return {
                     "retrieval_method": [

api/controllers/console/datasets/external.py

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

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

api/controllers/console/datasets/website.py

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

api/controllers/console/version.py

@@ -38,52 +38,11 @@ class VersionApi(Resource):
             return result
 
         content = json.loads(response.content)
-        if _has_new_version(latest_version=content["version"], current_version=f"{args.get('current_version')}"):
-            result["version"] = content["version"]
-            result["release_date"] = content["releaseDate"]
-            result["release_notes"] = content["releaseNotes"]
-            result["can_auto_update"] = content["canAutoUpdate"]
+        result["version"] = content["version"]
+        result["release_date"] = content["releaseDate"]
+        result["release_notes"] = content["releaseNotes"]
+        result["can_auto_update"] = content["canAutoUpdate"]
         return result
 
 
-def _has_new_version(*, latest_version: str, current_version: str) -> bool:
-    def parse_version(version: str) -> tuple:
-        # Split version into parts and pre-release suffix if any
-        parts = version.split("-")
-        version_parts = parts[0].split(".")
-        pre_release = parts[1] if len(parts) > 1 else None
-
-        # Validate version format
-        if len(version_parts) != 3:
-            raise ValueError(f"Invalid version format: {version}")
-
-        try:
-            # Convert version parts to integers
-            major, minor, patch = map(int, version_parts)
-            return (major, minor, patch, pre_release)
-        except ValueError:
-            raise ValueError(f"Invalid version format: {version}")
-
-    latest = parse_version(latest_version)
-    current = parse_version(current_version)
-
-    # Compare major, minor, and patch versions
-    for latest_part, current_part in zip(latest[:3], current[:3]):
-        if latest_part > current_part:
-            return True
-        elif latest_part < current_part:
-            return False
-
-    # If versions are equal, check pre-release suffixes
-    if latest[3] is None and current[3] is not None:
-        return True
-    elif latest[3] is not None and current[3] is None:
-        return False
-    elif latest[3] is not None and current[3] is not None:
-        # Simple string comparison for pre-release versions
-        return latest[3] > current[3]
-
-    return False
-
-
 api.add_resource(VersionApi, "/version")

api/controllers/console/workspace/model_providers.py

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

api/controllers/console/workspace/models.py

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

api/controllers/files/error.py

@@ -1,7 +0,0 @@
-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 controllers.files.error import UnsupportedFileTypeError
+from libs.exception import BaseHTTPException
 from services.account_service import TenantService
 from services.file_service import FileService
 
@@ -50,3 +50,9 @@ 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):
@@ -43,3 +43,9 @@ 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/app/completion.py

@@ -4,7 +4,6 @@ from flask_restful import Resource, reqparse
 from werkzeug.exceptions import InternalServerError, NotFound
 
 import services
-from constants import UUID_NIL
 from controllers.service_api import api
 from controllers.service_api.app.error import (
     AppUnavailableError,
@@ -108,7 +107,6 @@ class ChatApi(Resource):
         parser.add_argument("conversation_id", type=uuid_value, location="json")
         parser.add_argument("retriever_from", type=str, required=False, default="dev", location="json")
         parser.add_argument("auto_generate_name", type=bool, required=False, default=True, location="json")
-        parser.add_argument("parent_message_id", type=uuid_value, required=False, default=UUID_NIL, location="json")
 
         args = parser.parse_args()
 

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: Optional[list[PromptMessage]] = None
+        self, current_session_messages: 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]) -> list[PromptMessage]:
+    def _organize_user_query(self, query, prompt_messages: list[PromptMessage] = None) -> list[PromptMessage]:
         """
         Organize user query
         """

api/core/agent/cot_completion_agent_runner.py

@@ -1,5 +1,4 @@
 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
@@ -22,7 +21,7 @@ class CotCompletionAgentRunner(CotAgentRunner):
 
         return system_prompt
 
-    def _organize_historic_prompt(self, current_session_messages: Optional[list[PromptMessage]] = None) -> str:
+    def _organize_historic_prompt(self, current_session_messages: 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, Optional, Union
+from typing import Any, 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: Optional[list[PromptMessage]] = None
+        self, prompt_template: str, prompt_messages: 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]) -> list[PromptMessage]:
+    def _organize_user_query(self, query, prompt_messages: list[PromptMessage] = None) -> 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, strict=False)
+                action = json.loads(json_str)
                 action_name = None
                 action_input = None
 

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

@@ -113,7 +113,6 @@ 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()),
@@ -128,7 +127,6 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             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

@@ -149,9 +149,6 @@ 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

@@ -45,7 +45,6 @@ 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
@@ -108,10 +107,6 @@ 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()
@@ -236,8 +231,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
             except Exception as e:
                 logger.error(e)
                 break
-        if tts_publisher:
-            yield MessageAudioEndStreamResponse(audio="", task_id=task_id)
+        yield MessageAudioEndStreamResponse(audio="", task_id=task_id)
 
     def _process_stream_response(
         self,
@@ -510,10 +504,6 @@ 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/workflow/app_generator.py

@@ -99,7 +99,6 @@ 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()),
@@ -111,7 +110,6 @@ 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

@@ -90,9 +90,6 @@ 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

@@ -97,9 +97,6 @@ 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()
@@ -215,8 +212,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
             except Exception as e:
                 logger.error(e)
                 break
-        if tts_publisher:
-            yield MessageAudioEndStreamResponse(audio="", task_id=task_id)
+        yield MessageAudioEndStreamResponse(audio="", task_id=task_id)
 
     def _process_stream_response(
         self,

api/core/app/entities/app_invoke_entities.py

@@ -152,7 +152,6 @@ class AdvancedChatAppGenerateEntity(AppGenerateEntity):
 
     conversation_id: Optional[str] = None
     parent_message_id: Optional[str] = None
-    workflow_run_id: Optional[str] = None
     query: str
 
     class SingleIterationRunEntity(BaseModel):
@@ -173,7 +172,6 @@ class WorkflowAppGenerateEntity(AppGenerateEntity):
 
     # app config
     app_config: WorkflowUIBasedAppConfig
-    workflow_run_id: Optional[str] = None
 
     class SingleIterationRunEntity(BaseModel):
         """

api/core/app/segments/exc.py

@@ -1,2 +1,2 @@
-class VariableError(ValueError):
+class VariableError(Exception):
     pass

api/core/app/task_pipeline/easy_ui_based_generate_task_pipeline.py

@@ -248,8 +248,7 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline, MessageCycleMan
             else:
                 start_listener_time = time.time()
                 yield MessageAudioStreamResponse(audio=audio.audio, task_id=task_id)
-        if publisher:
-            yield MessageAudioEndStreamResponse(audio="", task_id=task_id)
+        yield MessageAudioEndStreamResponse(audio="", task_id=task_id)
 
     def _process_stream_response(
         self, publisher: AppGeneratorTTSPublisher, trace_manager: Optional[TraceQueueManager] = None

api/core/app/task_pipeline/message_cycle_manage.py

@@ -82,8 +82,8 @@ class MessageCycleManage:
                 try:
                     name = LLMGenerator.generate_conversation_name(app_model.tenant_id, query)
                     conversation.name = name
-                except Exception as e:
-                    logging.exception(f"generate conversation name failed: {e}")
+                except:
+                    pass
 
                 db.session.merge(conversation)
                 db.session.commit()

api/core/app/task_pipeline/workflow_cycle_manage.py

@@ -85,9 +85,6 @@ 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

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
@@ -50,8 +50,7 @@ class DifyAgentCallbackHandler(BaseModel):
         tool_inputs: Mapping[str, Any],
     ) -> None:
         """Do nothing."""
-        if dify_config.DEBUG:
-            print_text("\n[on_tool_start] ToolCall:" + tool_name + "\n" + str(tool_inputs) + "\n", color=self.color)
+        print_text("\n[on_tool_start] ToolCall:" + tool_name + "\n" + str(tool_inputs) + "\n", color=self.color)
 
     def on_tool_end(
         self,
@@ -63,12 +62,11 @@ class DifyAgentCallbackHandler(BaseModel):
         trace_manager: Optional[TraceQueueManager] = None,
     ) -> None:
         """If not the final action, print out observation."""
-        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")
+        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(
@@ -84,33 +82,30 @@ class DifyAgentCallbackHandler(BaseModel):
 
     def on_tool_error(self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any) -> None:
         """Do nothing."""
-        if dify_config.DEBUG:
-            print_text("\n[on_tool_error] Error: " + str(error) + "\n", color="red")
+        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 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)
+        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."""
-        if dify_config.DEBUG:
-            print_text("\n[on_agent_finish]\n Loop: " + str(self.current_loop) + "\n", color=self.color)
+        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 dify_config.DEBUG
+        return not os.environ.get("DEBUG") or os.environ.get("DEBUG").lower() != "true"
 
     @property
     def ignore_chat_model(self) -> bool:
         """Whether to ignore chat model callbacks."""
-        return not dify_config.DEBUG
+        return not os.environ.get("DEBUG") or os.environ.get("DEBUG").lower() != "true"

api/core/callback_handler/index_tool_callback_handler.py

@@ -44,6 +44,7 @@ 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/entities/provider_configuration.py

@@ -119,7 +119,7 @@ class ProviderConfiguration(BaseModel):
                         credentials = model_configuration.credentials
                         break
 
-            if not credentials and self.custom_configuration.provider:
+            if self.custom_configuration.provider:
                 credentials = self.custom_configuration.provider.credentials
 
             return credentials

api/core/file/message_file_parser.py

@@ -198,34 +198,16 @@ class MessageFileParser:
                     if "amazonaws.com" not in parsed_url.netloc:
                         return False
                     query_params = parse_qs(parsed_url.query)
-
-                    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():
+                    required_params = ["Signature", "Expires"]
+                    for param in required_params:
+                        if param not in query_params:
                             return False
-                        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)
+                    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
                 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: Optional[str] = None,
+        doc_form: str = None,
         doc_language: str = "English",
-        dataset_id: Optional[str] = None,
+        dataset_id: str = None,
         indexing_technique: str = "economy",
     ) -> dict:
         """

api/core/memory/token_buffer_memory.py

@@ -58,11 +58,7 @@ 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)
-
-        # 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[-1].answer:
-            thread_messages.pop()
-
+        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/callbacks/base_callback.py

@@ -1,4 +1,3 @@
-from abc import ABC, abstractmethod
 from typing import Optional
 
 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk
@@ -14,7 +13,7 @@ _TEXT_COLOR_MAPPING = {
 }
 
 
-class Callback(ABC):
+class Callback:
     """
     Base class for callbacks.
     Only for LLM.
@@ -22,7 +21,6 @@ class Callback(ABC):
 
     raise_error: bool = False
 
-    @abstractmethod
     def on_before_invoke(
         self,
         llm_instance: AIModel,
@@ -50,7 +48,6 @@ class Callback(ABC):
         """
         raise NotImplementedError()
 
-    @abstractmethod
     def on_new_chunk(
         self,
         llm_instance: AIModel,
@@ -80,7 +77,6 @@ class Callback(ABC):
         """
         raise NotImplementedError()
 
-    @abstractmethod
     def on_after_invoke(
         self,
         llm_instance: AIModel,
@@ -110,7 +106,6 @@ class Callback(ABC):
         """
         raise NotImplementedError()
 
-    @abstractmethod
     def on_invoke_error(
         self,
         llm_instance: AIModel,

api/core/model_runtime/docs/en_US/customizable_model_scale_out.md

@@ -1,310 +0,0 @@
-## Custom Integration of Pre-defined Models
-
-### Introduction
-
-After completing the vendors integration, the next step is to connect the vendor's models. To illustrate the entire connection process, we will use Xinference as an example to demonstrate a complete vendor integration.
-
-It is important to note that for custom models, each model connection requires a complete vendor credential.
-
-Unlike pre-defined models, a custom vendor integration always includes the following two parameters, which do not need to be defined in the vendor YAML file.
-
-![](images/index/image-3.png)
-
-As mentioned earlier, vendors do not need to implement validate_provider_credential. The runtime will automatically call the corresponding model layer's validate_credentials to validate the credentials based on the model type and name selected by the user.
-
-### Writing the Vendor YAML
-
-First, we need to identify the types of models supported by the vendor we are integrating.
-
-Currently supported model types are as follows:
-
-- `llm` Text Generation Models
-
-- `text_embedding` Text Embedding Models
-
-- `rerank` Rerank Models
-
-- `speech2text` Speech-to-Text
-
-- `tts` Text-to-Speech
-
-- `moderation` Moderation
-
-Xinference supports LLM, Text Embedding, and Rerank. So we will start by writing xinference.yaml.
-
-```yaml
-provider: xinference #Define the vendor identifier
-label: # Vendor display name, supports both en_US (English) and zh_Hans (Simplified Chinese). If zh_Hans is not set, it will use en_US by default.
-  en_US: Xorbits Inference
-icon_small: # Small icon, refer to other vendors' icons stored in the _assets directory within the vendor implementation directory; follows the same language policy as the label
-  en_US: icon_s_en.svg
-icon_large: # Large icon
-  en_US: icon_l_en.svg
-help: # Help information
-  title:
-    en_US: How to deploy Xinference
-    zh_Hans: 如何部署 Xinference
-  url:
-    en_US: https://github.com/xorbitsai/inference
-supported_model_types: # Supported model types. Xinference supports LLM, Text Embedding, and Rerank
-- llm
-- text-embedding
-- rerank
-configurate_methods: # Since Xinference is a locally deployed vendor with no predefined models, users need to deploy whatever models they need according to Xinference documentation. Thus, it only supports custom models.
-- customizable-model
-provider_credential_schema:
-  credential_form_schemas:
-```
-
-
-Then, we need to determine what credentials are required to define a model in Xinference.
-
-- Since it supports three different types of models, we need to specify the model_type to denote the model type. Here is how we can define it:
-
-```yaml
-provider_credential_schema:
-  credential_form_schemas:
-  - variable: model_type
-    type: select
-    label:
-      en_US: Model type
-      zh_Hans: 模型类型
-    required: true
-    options:
-    - value: text-generation
-      label:
-        en_US: Language Model
-        zh_Hans: 语言模型
-    - value: embeddings
-      label:
-        en_US: Text Embedding
-    - value: reranking
-      label:
-        en_US: Rerank
-```
-
-- Next, each model has its own model_name, so we need to define that here:
-
-```yaml
-  - variable: model_name
-    type: text-input
-    label:
-      en_US: Model name
-      zh_Hans: 模型名称
-    required: true
-    placeholder:
-      zh_Hans: 填写模型名称
-      en_US: Input model name
-```
-
-- Specify the Xinference local deployment address:
-
-```yaml
-  - variable: server_url
-    label:
-      zh_Hans: 服务器URL
-      en_US: Server url
-    type: text-input
-    required: true
-    placeholder:
-      zh_Hans: 在此输入Xinference的服务器地址，如 https://example.com/xxx
-      en_US: Enter the url of your Xinference, for example https://example.com/xxx
-```
-
-- Each model has a unique model_uid, so we also need to define that here:
-
-```yaml
-  - variable: model_uid
-    label:
-      zh_Hans: 模型UID
-      en_US: Model uid
-    type: text-input
-    required: true
-    placeholder:
-      zh_Hans: 在此输入您的Model UID
-      en_US: Enter the model uid
-```
-
-Now, we have completed the basic definition of the vendor.
-
-### Writing the Model Code
-
-Next, let's take the `llm` type as an example and write `xinference.llm.llm.py`.
-
-In `llm.py`, create a Xinference LLM class, we name it `XinferenceAILargeLanguageModel` (this can be arbitrary), inheriting from the `__base.large_language_model.LargeLanguageModel` base class, and implement the following methods:
-
-- LLM Invocation
-
-Implement the core method for LLM invocation, supporting both stream and synchronous responses.
-
-```python
-def _invoke(self, model: str, credentials: dict,
-            prompt_messages: list[PromptMessage], model_parameters: dict,
-            tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
-            stream: bool = True, user: Optional[str] = None) \
-        -> Union[LLMResult, Generator]:
-    """
-    Invoke large language model
-    
-    :param model: model name
-	:param credentials: model credentials
-	:param prompt_messages: prompt messages
-	:param model_parameters: model parameters
-	:param tools: tools for tool usage
-	:param stop: stop words
-	:param stream: is the response a stream
-	:param user: unique user id
-	:return: full response or stream response chunk generator result
-	"""
-```
-
-When implementing, ensure to use two functions to return data separately for synchronous and stream responses. This is important because Python treats functions containing the `yield` keyword as generator functions, mandating them to return `Generator` types. Here’s an example (note that the example uses simplified parameters; in real implementation, use the parameter list as defined above):
-
-```python
-def _invoke(self, stream: bool, **kwargs) \
-        -> Union[LLMResult, Generator]:
-    if stream:
-          return self._handle_stream_response(**kwargs)
-    return self._handle_sync_response(**kwargs)
-
-def _handle_stream_response(self, **kwargs) -> Generator:
-    for chunk in response:
-          yield chunk
-def _handle_sync_response(self, **kwargs) -> LLMResult:
-    return LLMResult(**response)
-```
-
-- Pre-compute Input Tokens
-
-If the model does not provide an interface for pre-computing tokens, you can return 0 directly.
-
-```python
-def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],tools: Optional[list[PromptMessageTool]] = None) -> int:
-  """
-  Get number of tokens for given prompt messages
-
-  :param model: model name
-  :param credentials: model credentials
-  :param prompt_messages: prompt messages
-  :param tools: tools for tool usage
-  :return: token count
-  """
-```
-
-
-Sometimes, you might not want to return 0 directly. In such cases, you can use `self._get_num_tokens_by_gpt2(text: str)` to get pre-computed tokens. This method is provided by the `AIModel` base class, and it uses GPT2's Tokenizer for calculation. However, it should be noted that this is only a substitute and may not be fully accurate.
-
-- Model Credentials Validation
-
-Similar to vendor credentials validation, this method validates individual model credentials.
-
-```python
-def validate_credentials(self, model: str, credentials: dict) -> None:
-    """
-    Validate model credentials
-    
-    :param model: model name
-	:param credentials: model credentials
-	:return: None
-	"""
-```
-
-- Model Parameter Schema
-
-Unlike custom types, since the YAML file does not define which parameters a model supports, we need to dynamically generate the model parameter schema.
-
-For instance, Xinference supports `max_tokens`, `temperature`, and `top_p` parameters.
-
-However, some vendors may support different parameters for different models. For example, the `OpenLLM` vendor supports `top_k`, but not all models provided by this vendor support `top_k`. Let's say model A supports `top_k` but model B does not. In such cases, we need to dynamically generate the model parameter schema, as illustrated below:
-
-```python
-    def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity | None:
-        """
-            used to define customizable model schema
-        """
-        rules = [
-            ParameterRule(
-                name='temperature', type=ParameterType.FLOAT,
-                use_template='temperature',
-                label=I18nObject(
-                    zh_Hans='温度', en_US='Temperature'
-                )
-            ),
-            ParameterRule(
-                name='top_p', type=ParameterType.FLOAT,
-                use_template='top_p',
-                label=I18nObject(
-                    zh_Hans='Top P', en_US='Top P'
-                )
-            ),
-            ParameterRule(
-                name='max_tokens', type=ParameterType.INT,
-                use_template='max_tokens',
-                min=1,
-                default=512,
-                label=I18nObject(
-                    zh_Hans='最大生成长度', en_US='Max Tokens'
-                )
-            )
-        ]
-
-        # if model is A, add top_k to rules
-        if model == 'A':
-            rules.append(
-                ParameterRule(
-                    name='top_k', type=ParameterType.INT,
-                    use_template='top_k',
-                    min=1,
-                    default=50,
-                    label=I18nObject(
-                        zh_Hans='Top K', en_US='Top K'
-                    )
-                )
-            )
-
-        """
-            some NOT IMPORTANT code here
-        """
-
-        entity = AIModelEntity(
-            model=model,
-            label=I18nObject(
-                en_US=model
-            ),
-            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
-            model_type=model_type,
-            model_properties={ 
-                ModelPropertyKey.MODE:  ModelType.LLM,
-            },
-            parameter_rules=rules
-        )
-
-        return entity
-```
-
-- Exception Error Mapping
-
-When a model invocation error occurs, it should be mapped to the runtime's specified `InvokeError` type, enabling Dify to handle different errors appropriately.
-
-Runtime Errors:
-
-- `InvokeConnectionError` Connection error during invocation
-- `InvokeServerUnavailableError` Service provider unavailable
-- `InvokeRateLimitError` Rate limit reached
-- `InvokeAuthorizationError` Authorization failure
-- `InvokeBadRequestError` Invalid request parameters
-
-```python
-  @property
-  def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
-      """
-      Map model invoke error to unified error
-      The key is the error type thrown to the caller
-      The value is the error type thrown by the model,
-      which needs to be converted into a unified error type for the caller.
-  
-      :return: Invoke error mapping
-      """
-```
-
-For interface method details, see: [Interfaces](./interfaces.md). For specific implementations, refer to: [llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py).

api/core/model_runtime/docs/en_US/predefined_model_scale_out.md

@@ -1,173 +0,0 @@
-## Predefined Model Integration
-
-After completing the vendor integration, the next step is to integrate the models from the vendor.
-
-First, we need to determine the type of model to be integrated and create the corresponding model type `module` under the respective vendor's directory.
-
-Currently supported model types are:
-
-- `llm` Text Generation Model
-- `text_embedding` Text Embedding Model
-- `rerank` Rerank Model
-- `speech2text` Speech-to-Text
-- `tts` Text-to-Speech
-- `moderation` Moderation
-
-Continuing with `Anthropic` as an example, `Anthropic` only supports LLM, so create a `module` named `llm` under `model_providers.anthropic`.
-
-For predefined models, we first need to create a YAML file named after the model under the `llm` `module`, such as `claude-2.1.yaml`.
-
-### Prepare Model YAML
-
-```yaml
-model: claude-2.1  # Model identifier
-# Display name of the model, which can be set to en_US English or zh_Hans Chinese. If zh_Hans is not set, it will default to en_US.
-# This can also be omitted, in which case the model identifier will be used as the label
-label:
-  en_US: claude-2.1
-model_type: llm  # Model type, claude-2.1 is an LLM
-features:  # Supported features, agent-thought supports Agent reasoning, vision supports image understanding
-- agent-thought
-model_properties:  # Model properties
-  mode: chat  # LLM mode, complete for text completion models, chat for conversation models
-  context_size: 200000  # Maximum context size
-parameter_rules:  # Parameter rules for the model call; only LLM requires this
-- name: temperature  # Parameter variable name
-  # Five default configuration templates are provided: temperature/top_p/max_tokens/presence_penalty/frequency_penalty
-  # The template variable name can be set directly in use_template, which will use the default configuration in entities.defaults.PARAMETER_RULE_TEMPLATE
-  # Additional configuration parameters will override the default configuration if set
-  use_template: temperature
-- name: top_p
-  use_template: top_p
-- name: top_k
-  label:  # Display name of the parameter
-    zh_Hans: 取样数量
-    en_US: Top k
-  type: int  # Parameter type, supports float/int/string/boolean
-  help:  # Help information, describing the parameter's function
-    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.
-  required: false  # Whether the parameter is mandatory; can be omitted
-- name: max_tokens_to_sample
-  use_template: max_tokens
-  default: 4096  # Default value of the parameter
-  min: 1  # Minimum value of the parameter, applicable to float/int only
-  max: 4096  # Maximum value of the parameter, applicable to float/int only
-pricing:  # Pricing information
-  input: '8.00'  # Input unit price, i.e., prompt price
-  output: '24.00'  # Output unit price, i.e., response content price
-  unit: '0.000001'  # Price unit, meaning the above prices are per 100K
-  currency: USD  # Price currency
-```
-
-It is recommended to prepare all model configurations before starting the implementation of the model code.
-
-You can also refer to the YAML configuration information under the corresponding model type directories of other vendors in the `model_providers` directory. For the complete YAML rules, refer to: [Schema](schema.md#aimodelentity).
-
-### Implement the Model Call Code
-
-Next, create a Python file named `llm.py` under the `llm` `module` to write the implementation code.
-
-Create an Anthropic LLM class named `AnthropicLargeLanguageModel` (or any other name), inheriting from the `__base.large_language_model.LargeLanguageModel` base class, and implement the following methods:
-
-- LLM Call
-
-Implement the core method for calling the LLM, supporting both streaming and synchronous responses.
-
-```python
-  def _invoke(self, model: str, credentials: dict,
-              prompt_messages: list[PromptMessage], model_parameters: dict,
-              tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
-              stream: bool = True, user: Optional[str] = None) \
-          -> Union[LLMResult, Generator]:
-      """
-      Invoke large language model
-  
-      :param model: model name
-      :param credentials: model credentials
-      :param prompt_messages: prompt messages
-      :param model_parameters: model parameters
-      :param tools: tools for tool calling
-      :param stop: stop words
-      :param stream: is stream response
-      :param user: unique user id
-      :return: full response or stream response chunk generator result
-      """
-```
-
-Ensure to use two functions for returning data, one for synchronous returns and the other for streaming returns, because Python identifies functions containing the `yield` keyword as generator functions, fixing the return type to `Generator`. Thus, synchronous and streaming returns need to be implemented separately, as shown below (note that the example uses simplified parameters, for actual implementation follow the above parameter list):
-
-```python
-  def _invoke(self, stream: bool, **kwargs) \
-          -> Union[LLMResult, Generator]:
-      if stream:
-            return self._handle_stream_response(**kwargs)
-      return self._handle_sync_response(**kwargs)
-
-  def _handle_stream_response(self, **kwargs) -> Generator:
-      for chunk in response:
-            yield chunk
-  def _handle_sync_response(self, **kwargs) -> LLMResult:
-      return LLMResult(**response)
-```
-
-- Pre-compute Input Tokens
-
-If the model does not provide an interface to precompute tokens, return 0 directly.
-
-```python
-  def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
-                     tools: Optional[list[PromptMessageTool]] = None) -> int:
-      """
-      Get number of tokens for given prompt messages
-
-      :param model: model name
-      :param credentials: model credentials
-      :param prompt_messages: prompt messages
-      :param tools: tools for tool calling
-      :return:
-      """
-```
-
-- Validate Model Credentials
-
-Similar to vendor credential validation, but specific to a single model.
-
-```python
-  def validate_credentials(self, model: str, credentials: dict) -> None:
-      """
-      Validate model credentials
-  
-      :param model: model name
-      :param credentials: model credentials
-      :return:
-      """
-```
-
-- Map Invoke Errors
-
-When a model call fails, map it to a specific `InvokeError` type as required by Runtime, allowing Dify to handle different errors accordingly.
-
-Runtime Errors:
-
-- `InvokeConnectionError` Connection error
-
-- `InvokeServerUnavailableError` Service provider unavailable
-- `InvokeRateLimitError` Rate limit reached
-- `InvokeAuthorizationError` Authorization failed
-- `InvokeBadRequestError` Parameter error
-
-```python
-  @property
-  def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
-      """
-      Map model invoke error to unified error
-      The key is the error type thrown to the caller
-      The value is the error type thrown by the model,
-      which needs to be converted into a unified error type for the caller.
-  
-      :return: Invoke error mapping
-      """
-```
-
-For interface method explanations, see: [Interfaces](./interfaces.md). For detailed implementation, refer to: [llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py).

api/core/model_runtime/docs/en_US/provider_scale_out.md

@@ -58,7 +58,7 @@ provider_credential_schema:  # Provider credential rules, as Anthropic only supp
       en_US: Enter your API URL
 ```
 
-You can also refer to the YAML configuration information under other provider directories in `model_providers`. The complete YAML rules are available at: [Schema](schema.md#provider).
+You can also refer to the YAML configuration information under other provider directories in `model_providers`. The complete YAML rules are available at: [Schema](schema.md#Provider).
 
 ### Implementing Provider Code
 

api/core/model_runtime/docs/zh_Hans/provider_scale_out.md

@@ -117,7 +117,7 @@ model_credential_schema:
       en_US: Enter your API Base
 ```
 
-也可以参考  `model_providers` 目录下其他供应商目录下的 YAML 配置信息，完整的 YAML 规则见：[Schema](schema.md#provider)。
+也可以参考  `model_providers` 目录下其他供应商目录下的 YAML 配置信息，完整的 YAML 规则见：[Schema](schema.md#Provider)。
 
 #### 实现供应商代码
 

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 and model_parameters["response_format"] in {"JSON", "XML"}:
+            if "response_format" in model_parameters:
                 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 Any, Optional
+from typing import 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/_position.yaml

@@ -40,4 +40,3 @@
 - fireworks
 - mixedbread
 - nomic
-- voyage

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: Optional[list[Callback]] = None,
+        callbacks: 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

@@ -1081,81 +1081,8 @@ 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="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="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

@@ -53,9 +53,6 @@ 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
@@ -123,18 +120,6 @@ 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

@@ -312,24 +312,10 @@ 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=[self._convert_prompt_message_to_dict(m) for m in prompt_messages],
+            messages=messages,
             model=model,
             stream=stream,
             **model_parameters,
@@ -339,91 +325,7 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
         if stream:
             return self._handle_chat_generate_stream_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
+        return self._handle_chat_generate_response(model, credentials, response, prompt_messages, tools)
 
     def _handle_chat_generate_response(
         self,
@@ -658,7 +560,7 @@ 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") or model.startswith("o1"):
+        elif model.startswith("gpt-35-turbo") or model.startswith("gpt-4"):
             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 Any, Optional
+from typing import 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

@@ -50,62 +50,34 @@ 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-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)
+            en_US: Eu west London (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)
+        - value: ap-southeast-2
+          label:
+            en_US: Asia Pacific (Sydney)
+            zh_Hans: 亚太地区 (悉尼)
     - variable: model_for_validation
       required: false
       label:

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

@@ -6,8 +6,6 @@
 - anthropic.claude-v2:1
 - anthropic.claude-3-sonnet-v1:0
 - anthropic.claude-3-haiku-v1:0
-- ai21.jamba-1-5-large-v1:0
-- ai21.jamba-1-5-mini-v1:0
 - cohere.command-light-text-v14
 - cohere.command-text-v14
 - cohere.command-r-plus-v1.0
@@ -17,10 +15,6 @@
 - meta.llama3-1-405b-instruct-v1:0
 - meta.llama3-8b-instruct-v1:0
 - meta.llama3-70b-instruct-v1:0
-- us.meta.llama3-2-1b-instruct-v1:0
-- us.meta.llama3-2-3b-instruct-v1:0
-- us.meta.llama3-2-11b-instruct-v1:0
-- us.meta.llama3-2-90b-instruct-v1:0
 - meta.llama2-13b-chat-v1
 - meta.llama2-70b-chat-v1
 - mistral.mistral-large-2407-v1:0

api/core/model_runtime/model_providers/bedrock/llm/ai21.jamba-1-5-large-v1.0.yaml

@@ -1,26 +0,0 @@
-model: ai21.jamba-1-5-large-v1:0
-label:
-  en_US: Jamba 1.5 Large
-model_type: llm
-model_properties:
-  mode: completion
-  context_size: 256000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    default: 1
-    min: 0.0
-    max: 2.0
-  - name: top_p
-    use_template: top_p
-  - name: max_gen_len
-    use_template: max_tokens
-    required: true
-    default: 4096
-    min: 1
-    max: 4096
-pricing:
-  input: '0.002'
-  output: '0.008'
-  unit: '0.001'
-  currency: USD

api/core/model_runtime/model_providers/bedrock/llm/ai21.jamba-1-5-mini-v1.0.yaml

@@ -1,26 +0,0 @@
-model: ai21.jamba-1-5-mini-v1:0
-label:
-  en_US: Jamba 1.5 Mini
-model_type: llm
-model_properties:
-  mode: completion
-  context_size: 256000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    default: 1
-    min: 0.0
-    max: 2.0
-  - name: top_p
-    use_template: top_p
-  - name: max_gen_len
-    use_template: max_tokens
-    required: true
-    default: 4096
-    min: 1
-    max: 4096
-pricing:
-  input: '0.0002'
-  output: '0.0004'
-  unit: '0.001'
-  currency: USD

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

@@ -63,7 +63,6 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
         {"prefix": "us.anthropic.claude-3", "support_system_prompts": True, "support_tool_use": True},
         {"prefix": "eu.anthropic.claude-3", "support_system_prompts": True, "support_tool_use": True},
         {"prefix": "anthropic.claude-3", "support_system_prompts": True, "support_tool_use": True},
-        {"prefix": "us.meta.llama3-2", "support_system_prompts": True, "support_tool_use": True},
         {"prefix": "meta.llama", "support_system_prompts": True, "support_tool_use": False},
         {"prefix": "mistral.mistral-7b-instruct", "support_system_prompts": False, "support_tool_use": False},
         {"prefix": "mistral.mixtral-8x7b-instruct", "support_system_prompts": False, "support_tool_use": False},
@@ -71,7 +70,6 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
         {"prefix": "mistral.mistral-small", "support_system_prompts": True, "support_tool_use": True},
         {"prefix": "cohere.command-r", "support_system_prompts": True, "support_tool_use": True},
         {"prefix": "amazon.titan", "support_system_prompts": False, "support_tool_use": False},
-        {"prefix": "ai21.jamba-1-5", "support_system_prompts": True, "support_tool_use": False},
     ]
 
     @staticmethod
@@ -92,7 +90,7 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
         stop: Optional[list[str]] = None,
         stream: bool = True,
         user: Optional[str] = None,
-        callbacks: Optional[list[Callback]] = None,
+        callbacks: list[Callback] = None,
     ) -> Union[LLMResult, Generator]:
         """
         Code block mode wrapper for invoking large language model

api/core/model_runtime/model_providers/bedrock/llm/us.meta.llama3-2-11b-instruct-v1.0.yaml

@@ -1,29 +0,0 @@
-model: us.meta.llama3-2-11b-instruct-v1:0
-label:
-  en_US: US Meta Llama 3.2 11B Instruct
-model_type: llm
-features:
-  - vision
-  - tool-call
-model_properties:
-  mode: completion
-  context_size: 128000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    default: 0.5
-    min: 0.0
-    max: 1
-  - name: top_p
-    use_template: top_p
-  - name: max_gen_len
-    use_template: max_tokens
-    required: true
-    default: 512
-    min: 1
-    max: 2048
-pricing:
-  input: '0.00035'
-  output: '0.00035'
-  unit: '0.001'
-  currency: USD

api/core/model_runtime/model_providers/bedrock/llm/us.meta.llama3-2-1b-instruct-v1.0.yaml

@@ -1,26 +0,0 @@
-model: us.meta.llama3-2-1b-instruct-v1:0
-label:
-  en_US: US Meta Llama 3.2 1B Instruct
-model_type: llm
-model_properties:
-  mode: completion
-  context_size: 128000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    default: 0.5
-    min: 0.0
-    max: 1
-  - name: top_p
-    use_template: top_p
-  - name: max_gen_len
-    use_template: max_tokens
-    required: true
-    default: 512
-    min: 1
-    max: 2048
-pricing:
-  input: '0.0001'
-  output: '0.0001'
-  unit: '0.001'
-  currency: USD

api/core/model_runtime/model_providers/bedrock/llm/us.meta.llama3-2-3b-instruct-v1.0.yaml

@@ -1,26 +0,0 @@
-model: us.meta.llama3-2-3b-instruct-v1:0
-label:
-  en_US: US Meta Llama 3.2 3B Instruct
-model_type: llm
-model_properties:
-  mode: completion
-  context_size: 128000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    default: 0.5
-    min: 0.0
-    max: 1
-  - name: top_p
-    use_template: top_p
-  - name: max_gen_len
-    use_template: max_tokens
-    required: true
-    default: 512
-    min: 1
-    max: 2048
-pricing:
-  input: '0.00015'
-  output: '0.00015'
-  unit: '0.001'
-  currency: USD

api/core/model_runtime/model_providers/bedrock/llm/us.meta.llama3-2-90b-instruct-v1.0.yaml

@@ -1,31 +0,0 @@
-model: us.meta.llama3-2-90b-instruct-v1:0
-label:
-  en_US: US Meta Llama 3.2 90B Instruct
-model_type: llm
-features:
-  - tool-call
-model_properties:
-  mode: completion
-  context_size: 128000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    default: 0.5
-    min: 0.0
-    max: 1
-  - name: top_p
-    use_template: top_p
-    default: 0.9
-    min: 0
-    max: 1
-  - name: max_gen_len
-    use_template: max_tokens
-    required: true
-    default: 512
-    min: 1
-    max: 2048
-pricing:
-  input: '0.002'
-  output: '0.002'
-  unit: '0.001'
-  currency: USD

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

@@ -511,7 +511,7 @@ class FireworksLargeLanguageModel(_CommonFireworks, LargeLanguageModel):
         model: str,
         messages: list[PromptMessage],
         tools: Optional[list[PromptMessageTool]] = None,
-        credentials: Optional[dict] = None,
+        credentials: dict = None,
     ) -> int:
         """
         Approximate num tokens with GPT2 tokenizer.

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

@@ -1,4 +1,4 @@
-from typing import Any, Optional
+from typing import 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

@@ -1,15 +0,0 @@
-- 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/groq/llm/_position.yaml

@@ -5,4 +5,3 @@
 - 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

@@ -1,25 +0,0 @@
-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

@@ -61,19 +61,11 @@ 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=index,
-                    text=text,
+                    index=result["index"],
+                    text=result["document"]["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

@@ -70,19 +70,11 @@ 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=index,
-                    text=text,
+                    index=result["index"],
+                    text=result["document"]["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/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: Optional[list[Callback]] = None,
+        callbacks: list[Callback] = None,
     ) -> Union[LLMResult, Generator]:
         """
         Code block mode wrapper for invoking large language model

api/core/model_runtime/model_providers/openai/speech2text/speech2text.py

@@ -2,8 +2,6 @@ from typing import IO, Optional
 
 from openai import OpenAI
 
-from core.model_runtime.entities.common_entities import I18nObject
-from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelType
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
 from core.model_runtime.model_providers.__base.speech2text_model import Speech2TextModel
 from core.model_runtime.model_providers.openai._common import _CommonOpenAI
@@ -60,18 +58,3 @@ class OpenAISpeech2TextModel(_CommonOpenAI, Speech2TextModel):
         response = client.audio.transcriptions.create(model=model, file=file)
 
         return response.text
-
-    def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity | None:
-        """
-        used to define customizable model schema
-        """
-        entity = AIModelEntity(
-            model=model,
-            label=I18nObject(en_US=model),
-            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
-            model_type=ModelType.SPEECH2TEXT,
-            model_properties={},
-            parameter_rules=[],
-        )
-
-        return entity

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

@@ -1,5 +1,5 @@
 import concurrent.futures
-from typing import Any, Optional
+from typing import Optional
 
 from openai import OpenAI
 
@@ -16,7 +16,7 @@ class OpenAIText2SpeechModel(_CommonOpenAI, 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
 
@@ -55,7 +55,7 @@ class OpenAIText2SpeechModel(_CommonOpenAI, 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
 

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

@@ -688,7 +688,7 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):
         model: str,
         messages: list[PromptMessage],
         tools: Optional[list[PromptMessageTool]] = None,
-        credentials: Optional[dict] = None,
+        credentials: dict = None,
     ) -> int:
         """
         Approximate num tokens with GPT2 tokenizer.

api/core/model_runtime/model_providers/openai_api_compatible/speech2text/speech2text.py

@@ -3,8 +3,6 @@ from urllib.parse import urljoin
 
 import requests
 
-from core.model_runtime.entities.common_entities import I18nObject
-from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelType
 from core.model_runtime.errors.invoke import InvokeBadRequestError
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
 from core.model_runtime.model_providers.__base.speech2text_model import Speech2TextModel
@@ -61,18 +59,3 @@ class OAICompatSpeech2TextModel(_CommonOaiApiCompat, Speech2TextModel):
                 self._invoke(model, credentials, audio_file)
         except Exception as ex:
             raise CredentialsValidateFailedError(str(ex))
-
-    def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity | None:
-        """
-        used to define customizable model schema
-        """
-        entity = AIModelEntity(
-            model=model,
-            label=I18nObject(en_US=model),
-            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
-            model_type=ModelType.SPEECH2TEXT,
-            model_properties={},
-            parameter_rules=[],
-        )
-
-        return entity

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

@@ -14,10 +14,6 @@
 - google/gemini-pro
 - cohere/command-r-plus
 - cohere/command-r
-- meta-llama/llama-3.2-1b-instruct
-- meta-llama/llama-3.2-3b-instruct
-- meta-llama/llama-3.2-11b-vision-instruct
-- meta-llama/llama-3.2-90b-vision-instruct
 - meta-llama/llama-3.1-405b-instruct
 - meta-llama/llama-3.1-70b-instruct
 - meta-llama/llama-3.1-8b-instruct
@@ -26,7 +22,6 @@
 - mistralai/mixtral-8x22b-instruct
 - mistralai/mixtral-8x7b-instruct
 - mistralai/mistral-7b-instruct
-- qwen/qwen-2.5-72b-instruct
 - qwen/qwen-2-72b-instruct
 - deepseek/deepseek-chat
 - deepseek/deepseek-coder

api/core/model_runtime/model_providers/openrouter/llm/claude-3-5-sonnet.yaml

@@ -27,9 +27,9 @@ parameter_rules:
   - name: max_tokens
     use_template: max_tokens
     required: true
-    default: 8192
+    default: 4096
     min: 1
-    max: 8192
+    max: 4096
   - name: response_format
     use_template: response_format
 pricing:

api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-11b-vision-instruct.yaml

@@ -1,45 +0,0 @@
-model: meta-llama/llama-3.2-11b-vision-instruct
-label:
-  zh_Hans: llama-3.2-11b-vision-instruct
-  en_US: llama-3.2-11b-vision-instruct
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 131072
-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: '0.055'
-  output: '0.055'
-  unit: '0.000001'
-  currency: USD

api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-1b-instruct.yaml

@@ -1,45 +0,0 @@
-model: meta-llama/llama-3.2-1b-instruct
-label:
-  zh_Hans: llama-3.2-1b-instruct
-  en_US: llama-3.2-1b-instruct
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 131072
-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: '0.01'
-  output: '0.02'
-  unit: '0.000001'
-  currency: USD

api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-3b-instruct.yaml

@@ -1,45 +0,0 @@
-model: meta-llama/llama-3.2-3b-instruct
-label:
-  zh_Hans: llama-3.2-3b-instruct
-  en_US: llama-3.2-3b-instruct
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 131072
-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: '0.03'
-  output: '0.05'
-  unit: '0.000001'
-  currency: USD

api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-90b-vision-instruct.yaml

@@ -1,45 +0,0 @@
-model: meta-llama/llama-3.2-90b-vision-instruct
-label:
-  zh_Hans: llama-3.2-90b-vision-instruct
-  en_US: llama-3.2-90b-vision-instruct
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 131072
-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: '0.35'
-  output: '0.4'
-  unit: '0.000001'
-  currency: USD

api/core/model_runtime/model_providers/openrouter/llm/qwen2.5-72b-instruct.yaml

@@ -1,30 +0,0 @@
-model: qwen/qwen-2.5-72b-instruct
-label:
-  en_US: qwen-2.5-72b-instruct
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 131072
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: max_tokens
-    use_template: max_tokens
-    type: int
-    default: 512
-    min: 1
-    max: 8192
-    help:
-      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
-      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
-  - name: top_p
-    use_template: top_p
-  - name: frequency_penalty
-    use_template: frequency_penalty
-pricing:
-  input: "0.35"
-  output: "0.4"
-  unit: "0.000001"
-  currency: USD

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

@@ -1,23 +1,24 @@
 - Qwen2.5-72B-Instruct
 - Qwen2.5-7B-Instruct
-- Qwen2-72B-Instruct
-- Qwen2-72B-Instruct-AWQ-int4
-- Qwen2-72B-Instruct-GPTQ-Int4
-- Qwen2-7B-Instruct
-- Qwen2-7B
-- Qwen1.5-110B-Chat-GPTQ-Int4
-- Qwen1.5-72B-Chat-GPTQ-Int4
-- Qwen1.5-7B
-- Qwen-14B-Chat-Int4
 - Yi-Coder-1.5B-Chat
 - Yi-Coder-9B-Chat
+- Qwen2-72B-Instruct-AWQ-int4
 - Yi-1_5-9B-Chat-16K
+- Qwen2-7B-Instruct
 - Reflection-Llama-3.1-70B
+- Qwen2-72B-Instruct
 - Meta-Llama-3.1-8B-Instruct
+
 - Meta-Llama-3.1-405B-Instruct-AWQ-INT4
 - Meta-Llama-3-70B-Instruct-GPTQ-Int4
+- chatglm3-6b
 - Meta-Llama-3-8B-Instruct
 - Llama3-Chinese_v2
 - deepseek-v2-lite-chat
+- Qwen2-72B-Instruct-GPTQ-Int4
+- Qwen2-7B
+- Qwen-14B-Chat-Int4
+- Qwen1.5-72B-Chat-GPTQ-Int4
+- Qwen1.5-7B
+- Qwen1.5-110B-Chat-GPTQ-Int4
 - deepseek-v2-chat
-- chatglm3-6b