fix Reranking mode is null

2026-01-24 05:46:13 +08:00 · 2024-08-06 19:03:32 +08:00 · 2024-08-06 18:34:07 +08:00
661 changed files with 6437 additions and 22873 deletions
--- a/.github/workflows/api-tests.yml
+++ b/.github/workflows/api-tests.yml
@ -76,7 +76,7 @@ jobs:
      - name: Run Workflow
        run: poetry run -C api bash dev/pytest/pytest_workflow.sh

-      - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch)
+      - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale)
        uses: hoverkraft-tech/compose-action@v2.0.0
        with:
          compose-file: |
@ -90,6 +90,5 @@ jobs:
            pgvecto-rs
            pgvector
            chroma
-            elasticsearch
      - name: Test Vector Stores
        run: poetry run -C api bash dev/pytest/pytest_vdb.sh
--- a/.github/workflows/expose_service_ports.sh
+++ b/.github/workflows/expose_service_ports.sh
@ -6,6 +6,5 @@ yq eval '.services.chroma.ports += ["8000:8000"]' -i docker/docker-compose.yaml
 yq eval '.services["milvus-standalone"].ports += ["19530:19530"]' -i docker/docker-compose.yaml
 yq eval '.services.pgvector.ports += ["5433:5432"]' -i docker/docker-compose.yaml
 yq eval '.services["pgvecto-rs"].ports += ["5431:5432"]' -i docker/docker-compose.yaml
-yq eval '.services["elasticsearch"].ports += ["9200:9200"]' -i docker/docker-compose.yaml

-echo "Ports exposed for sandbox, weaviate, qdrant, chroma, milvus, pgvector, pgvecto-rs, elasticsearch"
+echo "Ports exposed for sandbox, weaviate, qdrant, chroma, milvus, pgvector, pgvecto-rs."
--- a/.github/workflows/style.yml
+++ b/.github/workflows/style.yml
@ -45,10 +45,6 @@ jobs:
        if: steps.changed-files.outputs.any_changed == 'true'
        run: poetry run -C api dotenv-linter ./api/.env.example ./web/.env.example

-      - name: Ruff formatter check
-        if: steps.changed-files.outputs.any_changed == 'true'
-        run: poetry run -C api ruff format --check ./api
-
      - name: Lint hints
        if: failure()
        run: echo "Please run 'dev/reformat' to fix the fixable linting errors."
--- a/README.md
+++ b/README.md
@ -4,7 +4,7 @@
  <a href="https://cloud.dify.ai">Dify Cloud</a> ·
  <a href="https://docs.dify.ai/getting-started/install-self-hosted">Self-hosting</a> ·
  <a href="https://docs.dify.ai">Documentation</a> ·
-  <a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Enterprise inquiry</a>
+  <a href="https://cal.com/guchenhe/60-min-meeting">Enterprise inquiry</a>
 </p>

 <p align="center">
@ -38,7 +38,6 @@
  <a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
  <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>


@ -152,7 +151,7 @@ Quickly get Dify running in your environment with this [starter guide](#quick-st
 Use our [documentation](https://docs.dify.ai) for further references and more in-depth instructions.

 - **Dify for enterprise / organizations</br>**
-We provide additional enterprise-centric features. [Log your questions for us through this chatbot](https://udify.app/chat/22L1zSxg6yW1cWQg) or [send us an email](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) to discuss enterprise needs. </br>
+We provide additional enterprise-centric features. [Schedule a meeting with us](https://cal.com/guchenhe/30min) or [send us an email](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) to discuss enterprise needs. </br>
  > For startups and small businesses using AWS, check out [Dify Premium on AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) and deploy it to your own AWS VPC with one-click. It's an affordable AMI offering with the option to create apps with custom logo and branding.


@ -221,6 +220,23 @@ At the same time, please consider supporting Dify by sharing it on social media
 * [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
 * [Twitter](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.

+Or, schedule a meeting directly with a team member:
+
+<table>
+  <tr>
+    <th>Point of Contact</th>
+    <th>Purpose</th>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/guchenhe/15min' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/9ebcd111-1205-4d71-83d5-948d70b809f5' alt='Git-Hub-README-Button-3x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>Business enquiries & product feedback</td>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/pinkbanana' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/d1edd00a-d7e4-4513-be6c-e57038e143fd' alt='Git-Hub-README-Button-2x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>Contributions, issues & feature requests</td>
+  </tr>
+</table>
+
 ## Star history

 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
--- a/README_AR.md
+++ b/README_AR.md
@ -4,7 +4,7 @@
  <a href="https://cloud.dify.ai">Dify Cloud</a> ·
  <a href="https://docs.dify.ai/getting-started/install-self-hosted">الاستضافة الذاتية</a> ·
  <a href="https://docs.dify.ai">التوثيق</a> ·
-  <a href="https://udify.app/chat/22L1zSxg6yW1cWQg">استفسار الشركات (للإنجليزية فقط)</a>
+  <a href="https://cal.com/guchenhe/60-min-meeting">استفسارات الشركات</a>
 </p>

 <p align="center">
@ -38,7 +38,6 @@
  <a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
  <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>

 <div style="text-align: right;">
@ -204,6 +203,23 @@ docker compose up -d
 * [Discord](https://discord.gg/FngNHpbcY7). الأفضل لـ: مشاركة تطبيقاتك والترفيه مع المجتمع.
 * [تويتر](https://twitter.com/dify_ai). الأفضل لـ: مشاركة تطبيقاتك والترفيه مع المجتمع.

+أو، قم بجدولة اجتماع مباشرة مع أحد أعضاء الفريق:
+
+<table>
+  <tr>
+    <th>نقطة الاتصال</th>
+    <th>الغرض</th>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/guchenhe/15min' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/9ebcd111-1205-4d71-83d5-948d70b809f5' alt='Git-Hub-README-Button-3x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>استفسارات الأعمال واقتراحات حول المنتج</td>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/pinkbanana' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/d1edd00a-d7e4-4513-be6c-e57038e143fd' alt='Git-Hub-README-Button-2x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>المساهمات والمشكلات وطلبات الميزات</td>
+  </tr>
+</table>
+
 ## تاريخ النجمة

 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
--- a/README_CN.md
+++ b/README_CN.md
@ -4,7 +4,7 @@
  <a href="https://cloud.dify.ai">Dify 云服务</a> ·
  <a href="https://docs.dify.ai/getting-started/install-self-hosted">自托管</a> ·
  <a href="https://docs.dify.ai">文档</a> ·
-  <a href="https://udify.app/chat/22L1zSxg6yW1cWQg">（需用英文）常见问题解答 / 联系团队</a>
+  <a href="https://cal.com/guchenhe/dify-demo">预约演示</a>
 </div>

 <p align="center">
@ -29,16 +29,14 @@
 </p>

 <div align="center">
-  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
-  <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
-  <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
-  <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
-  <a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
-  <a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
-  <a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
-  <a href="./README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
+  <a href="./README.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/英文-d9d9d9"></a>
+  <a href="./README_CN.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="./README_JA.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="./README_ES.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/西班牙语-d9d9d9"></a>
+  <a href="./README_KL.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/法语-d9d9d9"></a>
+  <a href="./README_FR.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/克林贡语-d9d9d9"></a>
+  <a href="./README_KR.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/韓國語-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>
 </div>


@ -158,7 +156,7 @@ Dify 是一个开源的 LLM 应用开发平台。其直观的界面结合了 AI
 使用我们的[文档](https://docs.dify.ai)进行进一步的参考和更深入的说明。

 - **面向企业/组织的 Dify</br>**
-我们提供额外的面向企业的功能。[给我们发送电子邮件](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)讨论企业需求。 </br>
+我们提供额外的面向企业的功能。[与我们安排会议](https://cal.com/guchenhe/30min)或[给我们发送电子邮件](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)讨论企业需求。 </br>
  > 对于使用 AWS 的初创公司和中小型企业，请查看 [AWS Marketplace 上的 Dify 高级版](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6)，并使用一键部署到您自己的 AWS VPC。它是一个价格实惠的 AMI 产品，提供了使用自定义徽标和品牌创建应用程序的选项。

 ## 保持领先
--- a/README_ES.md
+++ b/README_ES.md
@ -4,7 +4,7 @@
  <a href="https://cloud.dify.ai">Dify Cloud</a> ·
  <a href="https://docs.dify.ai/getting-started/install-self-hosted">Auto-alojamiento</a> ·
  <a href="https://docs.dify.ai">Documentación</a> ·
-  <a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Consultas empresariales (en inglés)</a>
+  <a href="https://cal.com/guchenhe/dify-demo">Programar demostración</a>
 </p>

 <p align="center">
@ -29,16 +29,14 @@
 </p>

 <p align="center">
-  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
-  <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
-  <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
-  <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
-  <a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
-  <a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
-  <a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
-  <a href="./README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
+  <a href="./README.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/Inglés-d9d9d9"></a>
+  <a href="./README_CN.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="./README_JA.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="./README_ES.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/Español-d9d9d9"></a>
+  <a href="./README_KL.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/Français-d9d9d9"></a>
+  <a href="./README_FR.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
+  <a href="./README_KR.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/한국어-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>

 #
@ -158,7 +156,7 @@ Pon rápidamente Dify en funcionamiento en tu entorno con esta [guía de inicio
 Usa nuestra [documentación](https://docs.dify.ai) para más referencias e instrucciones más detalladas.

 - **Dify para Empresas / Organizaciones</br>**
-Proporcionamos características adicionales centradas en la empresa. [Envíanos un correo electrónico](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) para discutir las necesidades empresariales. </br>
+Proporcionamos características adicionales centradas en la empresa. [Programa una reunión con nosotros](https://cal.com/guchenhe/30min) o [envíanos un correo electrónico](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) para discutir las necesidades empresariales. </br>
  > Para startups y pequeñas empresas que utilizan AWS, echa un vistazo a [Dify Premium en AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) e impleméntalo en tu propio VPC de AWS con un clic. Es una AMI asequible que ofrece la opción de crear aplicaciones con logotipo y marca personalizados.


@ -230,6 +228,23 @@ Al mismo tiempo, considera apoyar a Dify compartiéndolo en redes sociales y en
 * [Discord](https://discord.gg/FngNHpbcY7). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad.
 * [Twitter](https://twitter.com/dify_ai). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad.

+O, programa una reunión directamente con un miembro del equipo:
+
+<table>
+  <tr>
+    <th>Punto de Contacto</th>
+    <th>Propósito</th>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/guchenhe/15min' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/9ebcd111-1205-4d71-83d5-948d70b809f5' alt='Git-Hub-README-Button-3x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>Consultas comerciales y retroalimentación del producto</td>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/pinkbanana' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/d1edd00a-d7e4-4513-be6c-e57038e143fd' alt='Git-Hub-README-Button-2x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>Contribuciones, problemas y solicitudes de características</td>
+  </tr>
+</table>
+
 ## Historial de Estrellas

 [![Gráfico de Historial de Estrellas](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
--- a/README_FR.md
+++ b/README_FR.md
@ -4,7 +4,7 @@
  <a href="https://cloud.dify.ai">Dify Cloud</a> ·
  <a href="https://docs.dify.ai/getting-started/install-self-hosted">Auto-hébergement</a> ·
  <a href="https://docs.dify.ai">Documentation</a> ·
-  <a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Demande d’entreprise (en anglais seulement)</a>
+  <a href="https://cal.com/guchenhe/dify-demo">Planifier une démo</a>
 </p>

 <p align="center">
@ -29,16 +29,14 @@
 </p>

 <p align="center">
-  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
-  <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
-  <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
-  <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
-  <a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
-  <a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
-  <a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
-  <a href="./README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
+  <a href="./README.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/Anglais-d9d9d9"></a>
+  <a href="./README_CN.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="./README_JA.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="./README_ES.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/Español-d9d9d9"></a>
+  <a href="./README_KL.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/Français-d9d9d9"></a>
+  <a href="./README_FR.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
+  <a href="./README_KR.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/한국어-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>

 #
@ -158,7 +156,7 @@ Lancez rapidement Dify dans votre environnement avec ce [guide de démarrage](#q
 Utilisez notre [documentation](https://docs.dify.ai) pour plus de références et des instructions plus détaillées.

 - **Dify pour les entreprises / organisations</br>**
-Nous proposons des fonctionnalités supplémentaires adaptées aux entreprises. [Envoyez-nous un e-mail](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) pour discuter des besoins de l'entreprise. </br>
+Nous proposons des fonctionnalités supplémentaires adaptées aux entreprises. [Planifiez une réunion avec nous](https://cal.com/guchenhe/30min) ou [envoyez-nous un e-mail](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) pour discuter des besoins de l'entreprise. </br>
  > Pour les startups et les petites entreprises utilisant AWS, consultez [Dify Premium sur AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) et déployez-le dans votre propre VPC AWS en un clic. C'est une offre AMI abordable avec la possibilité de créer des applications avec un logo et une marque personnalisés.


@ -228,6 +226,23 @@ Dans le même temps, veuillez envisager de soutenir Dify en le partageant sur le
 * [Discord](https://discord.gg/FngNHpbcY7). Meilleur pour: partager vos applications et passer du temps avec la communauté.
 * [Twitter](https://twitter.com/dify_ai). Meilleur pour: partager vos applications et passer du temps avec la communauté.

+Ou, planifiez directement une réunion avec un membre de l'équipe:
+
+<table>
+  <tr>
+    <th>Point de contact</th>
+    <th>Objectif</th>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/guchenhe/15min' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/9ebcd111-1205-4d71-83d5-948d70b809f5' alt='Git-Hub-README-Button-3x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>Demandes commerciales & retours produit</td>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/pinkbanana' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/d1edd00a-d7e4-4513-be6c-e57038e143fd' alt='Git-Hub-README-Button-2x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>Contributions, problèmes & demandes de fonctionnalités</td>
+  </tr>
+</table>
+
 ## Historique des étoiles

 [![Graphique de l'historique des étoiles](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
--- a/README_JA.md
+++ b/README_JA.md
@ -4,7 +4,7 @@
  <a href="https://cloud.dify.ai">Dify Cloud</a> ·
  <a href="https://docs.dify.ai/getting-started/install-self-hosted">セルフホスティング</a> ·
  <a href="https://docs.dify.ai">ドキュメント</a> ·
-  <a href="https://udify.app/chat/22L1zSxg6yW1cWQg">企業のお問い合わせ（英語のみ）</a>
+  <a href="https://cal.com/guchenhe/dify-demo">デモの予約</a>
 </p>

 <p align="center">
@ -29,16 +29,14 @@
 </p>

 <p align="center">
-  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
-  <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
-  <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
-  <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
-  <a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
-  <a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
-  <a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
-  <a href="./README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
+  <a href="./README.md"><img alt="先月のコミット" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="./README_CN.md"><img alt="先月のコミット" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="./README_JA.md"><img alt="先月のコミット" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="./README_ES.md"><img alt="先月のコミット" src="https://img.shields.io/badge/Español-d9d9d9"></a>
+  <a href="./README_KL.md"><img alt="先月のコミット" src="https://img.shields.io/badge/Français-d9d9d9"></a>
+  <a href="./README_FR.md"><img alt="先月のコミット" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
+  <a href="./README_KR.md"><img alt="先月のコミット" src="https://img.shields.io/badge/한국어-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>

 #
@ -157,7 +155,7 @@ 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
 詳しくは[ドキュメント](https://docs.dify.ai)をご覧ください。

 - **企業/組織向けのDify</br>**
-企業中心の機能を提供しています。[メールを送信](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)して企業のニーズについて相談してください。 </br>
+企業中心の機能を提供しています。[こちらからミーティングを予約](https://cal.com/guchenhe/30min)したり、[メールを送信](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)して企業のニーズについて相談してください。 </br>
  > AWSを使用しているスタートアップ企業や中小企業の場合は、[AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6)のDify Premiumをチェックして、ワンクリックで自分のAWS VPCにデプロイできます。さらに、手頃な価格のAMIオファリングどして、ロゴやブランディングをカスタマイズしてアプリケーションを作成するオプションがあります。


@ -227,6 +225,28 @@ docker compose up -d
 * [Discord](https://discord.gg/FngNHpbcY7). 主に: アプリケーションの共有やコミュニティとの交流。
 * [Twitter](https://twitter.com/dify_ai). 主に: アプリケーションの共有やコミュニティとの交流。

+または、直接チームメンバーとミーティングをスケジュール：
+
+<table>
+  <tr>
+    <th>連絡先</th>
+    <th>目的</th>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com
+
+/guchenhe/30min'>ミーティング</a></td>
+    <td>無料の30分間のミーティングをスケジュール</td>
+  </tr>
+  <tr>
+    <td><a href='https://github.com/langgenius/dify/issues'>技術サポート</a></td>
+    <td>技術的な問題やサポートに関する質問</td>
+  </tr>
+  <tr>
+    <td><a href='mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry'>営業担当</a></td>
+    <td>法人ライセンスに関するお問い合わせ</td>
+  </tr>
+</table>


 ## ライセンス
--- a/README_KL.md
+++ b/README_KL.md
@ -4,7 +4,7 @@
  <a href="https://cloud.dify.ai">Dify Cloud</a> ·
  <a href="https://docs.dify.ai/getting-started/install-self-hosted">Self-hosting</a> ·
  <a href="https://docs.dify.ai">Documentation</a> ·
-  <a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Commercial enquiries</a>
+  <a href="https://cal.com/guchenhe/dify-demo">Schedule demo</a>
 </p>

 <p align="center">
@ -29,16 +29,14 @@
 </p>

 <p align="center">
-  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
-  <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
-  <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
-  <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
-  <a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
-  <a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
-  <a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
-  <a href="./README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
+  <a href="./README.md"><img alt="Commits last month" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="./README_CN.md"><img alt="Commits last month" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="./README_JA.md"><img alt="Commits last month" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="./README_ES.md"><img alt="Commits last month" src="https://img.shields.io/badge/Español-d9d9d9"></a>
+  <a href="./README_KL.md"><img alt="Commits last month" src="https://img.shields.io/badge/Français-d9d9d9"></a>
+  <a href="./README_FR.md"><img alt="Commits last month" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
+  <a href="./README_KR.md"><img alt="Commits last month" src="https://img.shields.io/badge/한국어-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>

 #
@ -158,7 +156,7 @@ Quickly get Dify running in your environment with this [starter guide](#quick-st
 Use our [documentation](https://docs.dify.ai) for further references and more in-depth instructions.

 - **Dify for Enterprise / Organizations</br>**
-We provide additional enterprise-centric features. [Send us an email](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) to discuss enterprise needs. </br>
+We provide additional enterprise-centric features. [Schedule a meeting with us](https://cal.com/guchenhe/30min) or [send us an email](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) to discuss enterprise needs. </br>
  > For startups and small businesses using AWS, check out [Dify Premium on AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) and deploy it to your own AWS VPC with one-click. It's an affordable AMI offering with the option to create apps with custom logo and branding.


@ -230,6 +228,23 @@ At the same time, please consider supporting Dify by sharing it on social media
 * [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
 * [Twitter](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.

+Or, schedule a meeting directly with a team member:
+
+<table>
+  <tr>
+    <th>Point of Contact</th>
+    <th>Purpose</th>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/guchenhe/15min' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/9ebcd111-1205-4d71-83d5-948d70b809f5' alt='Git-Hub-README-Button-3x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>Business enquiries & product feedback</td>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/pinkbanana' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/d1edd00a-d7e4-4513-be6c-e57038e143fd' alt='Git-Hub-README-Button-2x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>Contributions, issues & feature requests</td>
+  </tr>
+</table>
+
 ## Star History

 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
--- a/README_KR.md
+++ b/README_KR.md
@ -4,7 +4,7 @@
  <a href="https://cloud.dify.ai">Dify 클라우드</a> ·
  <a href="https://docs.dify.ai/getting-started/install-self-hosted">셀프-호스팅</a> ·
  <a href="https://docs.dify.ai">문서</a> ·
-  <a href="https://udify.app/chat/22L1zSxg6yW1cWQg">기업 문의 (영어만 가능)</a>
+  <a href="https://cal.com/guchenhe/60-min-meeting">기업 문의</a>
 </p>

 <p align="center">
@ -35,10 +35,8 @@
  <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
  <a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
  <a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
-  <a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
-  <a href="./README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
+  <a href="./README_KR.md"><img alt="한국어 README" src="https://img.shields.io/badge/한국어-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>

@ -151,7 +149,7 @@
  추가 참조 및 더 심층적인 지침은 [문서](https://docs.dify.ai)를 사용하세요.

 - **기업 / 조직을 위한 Dify</br>**
-  우리는 추가적인 기업 중심 기능을 제공합니다. 잡거나  [이메일 보내기](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)를 통해 기업 요구 사항을 논의하십시오. </br>
+  우리는 추가적인 기업 중심 기능을 제공합니다. 당사와 [미팅일정](https://cal.com/guchenhe/30min)을 잡거나  [이메일 보내기](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)를 통해 기업 요구 사항을 논의하십시오. </br>
  > AWS를 사용하는 스타트업 및 중소기업의 경우 [AWS Marketplace에서 Dify Premium](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6)을 확인하고 한 번의 클릭으로 자체 AWS VPC에 배포하십시오. 맞춤형 로고와 브랜딩이 포함된 앱을 생성할 수 있는 옵션이 포함된 저렴한 AMI 제품입니다.


@ -220,6 +218,22 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했
 * [디스코드](https://discord.gg/FngNHpbcY7). 애플리케이션 공유 및 커뮤니티와 소통하기에 적합합니다.
 * [트위터](https://twitter.com/dify_ai). 애플리케이션 공유 및 커뮤니티와 소통하기에 적합합니다.

+또는 팀원과 직접 미팅을 예약하세요:
+
+<table>
+  <tr>
+    <th>연락처</th>
+    <th>목적</th>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/guchenhe/15min' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/9ebcd111-1205-4d71-83d5-948d70b809f5' alt='Git-Hub-README-Button-3x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>비즈니스 문의 및 제품 피드백</td>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/pinkbanana' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/d1edd00a-d7e4-4513-be6c-e57038e143fd' alt='Git-Hub-README-Button-2x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>기여, 이슈 및 기능 요청</td>
+  </tr>
+</table>

 ## Star 히스토리

--- a/README_TR.md
+++ b/README_TR.md
@ -4,7 +4,7 @@
  <a href="https://cloud.dify.ai">Dify Bulut</a> ·
  <a href="https://docs.dify.ai/getting-started/install-self-hosted">Kendi Sunucunuzda Barındırma</a> ·
  <a href="https://docs.dify.ai">Dokümantasyon</a> ·
-  <a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Yalnızca İngilizce: Kurumsal Sorgulama</a>
+  <a href="https://cal.com/guchenhe/60-min-meeting">Kurumsal Sorgu</a>
 </p>

 <p align="center">
@ -38,7 +38,6 @@
  <a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
  <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>


@ -156,7 +155,7 @@ Bu [başlangıç kılavuzu](#quick-start) ile Dify'ı kendi ortamınızda hızl
 Daha fazla referans ve detaylı talimatlar için [dokümantasyonumuzu](https://docs.dify.ai) kullanın.

 - **Kurumlar / organizasyonlar için Dify</br>**
-Ek kurumsal odaklı özellikler sunuyoruz. Kurumsal ihtiyaçları görüşmek için [bize bir e-posta gönderin](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry). </br>
+Ek kurumsal odaklı özellikler sunuyoruz. Kurumsal ihtiyaçları görüşmek için [bizimle bir toplantı planlayın](https://cal.com/guchenhe/30min) veya [bize bir e-posta gönderin](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry). </br>
  > AWS kullanan startuplar ve küçük işletmeler için, [AWS Marketplace'deki Dify Premium'a](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) göz atın ve tek tıklamayla kendi AWS VPC'nize dağıtın. Bu, özel logo ve marka ile uygulamalar oluşturma seçeneğine sahip uygun fiyatlı bir AMI teklifdir.

 ## Güncel Kalma
@ -224,6 +223,23 @@ Aynı zamanda, lütfen Dify'ı sosyal medyada, etkinliklerde ve konferanslarda p
 * [Discord](https://discord.gg/FngNHpbcY7). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.
 * [Twitter](https://twitter.com/dify_ai). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.

+Veya doğrudan bir ekip üyesiyle toplantı planlayın:
+
+<table>
+  <tr>
+    <th>İletişim Noktası</th>
+    <th>Amaç</th>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/guchenhe/15min' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/9ebcd111-1205-4d71-83d5-948d70b809f5' alt='Git-Hub-README-Button-3x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>İş sorgulamaları & ürün geri bildirimleri</td>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/pinkbanana' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/d1edd00a-d7e4-4513-be6c-e57038e143fd' alt='Git-Hub-README-Button-2x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>Katkılar, sorunlar & özellik istekleri</td>
+  </tr>
+</table>
+
 ## Star history

 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
--- a/README_VI.md
+++ b/README_VI.md
@ -1,234 +0,0 @@
-![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
-
-<p align="center">
-  <a href="https://cloud.dify.ai">Dify Cloud</a> ·
-  <a href="https://docs.dify.ai/getting-started/install-self-hosted">Tự triển khai</a> ·
-  <a href="https://docs.dify.ai">Tài liệu</a> ·
-  <a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Yêu cầu doanh nghiệp</a>
-</p>
-
-<p align="center">
-    <a href="https://dify.ai" target="_blank">
-        <img alt="Static Badge" src="https://img.shields.io/badge/Product-F04438"></a>
-    <a href="https://dify.ai/pricing" target="_blank">
-        <img alt="Static Badge" src="https://img.shields.io/badge/free-pricing?logo=free&color=%20%23155EEF&label=pricing&labelColor=%20%23528bff"></a>
-    <a href="https://discord.gg/FngNHpbcY7" target="_blank">
-        <img src="https://img.shields.io/discord/1082486657678311454?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb"
-            alt="chat trên Discord"></a>
-    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
-        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
-            alt="theo dõi trên Twitter"></a>
-    <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">
-        <img alt="Commits tháng trước" src="https://img.shields.io/github/commit-activity/m/langgenius/dify?labelColor=%20%2332b583&color=%20%2312b76a"></a>
-    <a href="https://github.com/langgenius/dify/" target="_blank">
-        <img alt="Vấn đề đã đóng" src="https://img.shields.io/github/issues-search?query=repo%3Alanggenius%2Fdify%20is%3Aclosed&label=issues%20closed&labelColor=%20%237d89b0&color=%20%235d6b98"></a>
-    <a href="https://github.com/langgenius/dify/discussions/" target="_blank">
-        <img alt="Bài thảo luận" src="https://img.shields.io/github/discussions/langgenius/dify?labelColor=%20%239b8afb&color=%20%237a5af8"></a>
-</p>
-
-<p align="center">
-  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
-  <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
-  <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
-  <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
-  <a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
-  <a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
-  <a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
-  <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>
-
-
-Dify là một nền tảng phát triển ứng dụng LLM mã nguồn mở. Giao diện trực quan kết hợp quy trình làm việc AI, mô hình RAG, khả năng tác nhân, quản lý mô hình, tính năng quan sát và hơn thế nữa, cho phép bạn nhanh chóng chuyển từ nguyên mẫu sang sản phẩm. Đây là danh sách các tính năng cốt lõi:
-</br> </br>
-
-**1. Quy trình làm việc**: 
-  Xây dựng và kiểm tra các quy trình làm việc AI mạnh mẽ trên một canvas trực quan, tận dụng tất cả các tính năng sau đây và hơn thế nữa.
-
-
-  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
-
-
-
-**2. Hỗ trợ mô hình toàn diện**: 
-  Tích hợp liền mạch với hàng trăm mô hình LLM độc quyền / mã nguồn mở từ hàng chục nhà cung cấp suy luận và giải pháp tự lưu trữ, bao gồm GPT, Mistral, Llama3, và bất kỳ mô hình tương thích API OpenAI nào. Danh sách đầy đủ các nhà cung cấp mô hình được hỗ trợ có thể được tìm thấy [tại đây](https://docs.dify.ai/getting-started/readme/model-providers).
-
-![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)
-
-
-**3. IDE Prompt**: 
-  Giao diện trực quan để tạo prompt, so sánh hiệu suất mô hình và thêm các tính năng bổ sung như chuyển văn bản thành giọng nói cho một ứng dụng dựa trên trò chuyện. 
-
-**4. Mô hình RAG**: 
-  Khả năng RAG mở rộng bao gồm mọi thứ từ nhập tài liệu đến truy xuất, với hỗ trợ sẵn có cho việc trích xuất văn bản từ PDF, PPT và các định dạng tài liệu phổ biến khác.
-
-**5. Khả năng tác nhân**: 
-  Bạn có thể định nghĩa các tác nhân dựa trên LLM Function Calling hoặc ReAct, và thêm các công cụ được xây dựng sẵn hoặc tùy chỉnh cho tác nhân. Dify cung cấp hơn 50 công cụ tích hợp sẵn cho các tác nhân AI, như Google Search, DALL·E, Stable Diffusion và WolframAlpha.
-
-**6. LLMOps**: 
-  Giám sát và phân tích nhật ký và hiệu suất ứng dụng theo thời gian. Bạn có thể liên tục cải thiện prompt, bộ dữ liệu và mô hình dựa trên dữ liệu sản xuất và chú thích.
-
-**7. Backend-as-a-Service**: 
-  Tất cả các dịch vụ của Dify đều đi kèm với các API tương ứng, vì vậy bạn có thể dễ dàng tích hợp Dify vào logic kinh doanh của riêng mình.
-
-
-## So sánh tính năng
-<table style="width: 100%;">
-  <tr>
-    <th align="center">Tính năng</th>
-    <th align="center">Dify.AI</th>
-    <th align="center">LangChain</th>
-    <th align="center">Flowise</th>
-    <th align="center">OpenAI Assistants API</th>
-  </tr>
-  <tr>
-    <td align="center">Phương pháp lập trình</td>
-    <td align="center">Hướng API + Ứng dụng</td>
-    <td align="center">Mã Python</td>
-    <td align="center">Hướng ứng dụng</td>
-    <td align="center">Hướng API</td>
-  </tr>
-  <tr>
-    <td align="center">LLMs được hỗ trợ</td>
-    <td align="center">Đa dạng phong phú</td>
-    <td align="center">Đa dạng phong phú</td>
-    <td align="center">Đa dạng phong phú</td>
-    <td align="center">Chỉ OpenAI</td>
-  </tr>
-  <tr>
-    <td align="center">RAG Engine</td>
-    <td align="center">✅</td>
-    <td align="center">✅</td>
-    <td align="center">✅</td>
-    <td align="center">✅</td>
-  </tr>
-  <tr>
-    <td align="center">Agent</td>
-    <td align="center">✅</td>
-    <td align="center">✅</td>
-    <td align="center">❌</td>
-    <td align="center">✅</td>
-  </tr>
-  <tr>
-    <td align="center">Quy trình làm việc</td>
-    <td align="center">✅</td>
-    <td align="center">❌</td>
-    <td align="center">✅</td>
-    <td align="center">❌</td>
-  </tr>
-  <tr>
-    <td align="center">Khả năng quan sát</td>
-    <td align="center">✅</td>
-    <td align="center">✅</td>
-    <td align="center">❌</td>
-    <td align="center">❌</td>
-  </tr>
-  <tr>
-    <td align="center">Tính năng doanh nghiệp (SSO/Kiểm soát truy cập)</td>
-    <td align="center">✅</td>
-    <td align="center">❌</td>
-    <td align="center">❌</td>
-    <td align="center">❌</td>
-  </tr>
-  <tr>
-    <td align="center">Triển khai cục bộ</td>
-    <td align="center">✅</td>
-    <td align="center">✅</td>
-    <td align="center">✅</td>
-    <td align="center">❌</td>
-  </tr>
-</table>
-
-## Sử dụng Dify
-
- **Cloud </br>**
-Chúng tôi lưu trữ dịch vụ [Dify Cloud](https://dify.ai) cho bất kỳ ai muốn thử mà không cần cài đặt. Nó cung cấp tất cả các khả năng của phiên bản tự triển khai và bao gồm 200 lượt gọi GPT-4 miễn phí trong gói sandbox.
-
- **Tự triển khai Dify Community Edition</br>**
-Nhanh chóng chạy Dify trong môi trường của bạn với [hướng dẫn bắt đầu](#quick-start) này.
-Sử dụng [tài liệu](https://docs.dify.ai) của chúng tôi để tham khảo thêm và nhận hướng dẫn chi tiết hơn.
-
- **Dify cho doanh nghiệp / tổ chức</br>**
-Chúng tôi cung cấp các tính năng bổ sung tập trung vào doanh nghiệp. [Ghi lại câu hỏi của bạn cho chúng tôi thông qua chatbot này](https://udify.app/chat/22L1zSxg6yW1cWQg) hoặc [gửi email cho chúng tôi](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) để thảo luận về nhu cầu doanh nghiệp. </br>
-  > Đối với các công ty khởi nghiệp và doanh nghiệp nhỏ sử dụng AWS, hãy xem [Dify Premium trên AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) và triển khai nó vào AWS VPC của riêng bạn chỉ với một cú nhấp chuột. Đây là một AMI giá cả phải chăng với tùy chọn tạo ứng dụng với logo và thương hiệu tùy chỉnh.
-
-
-## Luôn cập nhật
-
-Yêu thích Dify trên GitHub và được thông báo ngay lập tức về các bản phát hành mới.
-
-![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4)
-
-
-
-## Bắt đầu nhanh
-> Trước khi cài đặt Dify, hãy đảm bảo máy của bạn đáp ứng các yêu cầu hệ thống tối thiểu sau:
-> 
->- CPU >= 2 Core
->- RAM >= 4GB
-
-</br>
-
-Cách dễ nhất để khởi động máy chủ Dify là chạy tệp [docker-compose.yml](docker/docker-compose.yaml) của chúng tôi. Trước khi chạy lệnh cài đặt, hãy đảm bảo rằng [Docker](https://docs.docker.com/get-docker/) và [Docker Compose](https://docs.docker.com/compose/install/) đã được cài đặt trên máy của bạn:
-
-```bash
-cd docker
-cp .env.example .env
-docker compose up -d
-```
-
-Sau khi chạy, bạn có thể truy cập bảng điều khiển Dify trong trình duyệt của bạn tại [http://localhost/install](http://localhost/install) và bắt đầu quá trình khởi tạo.
-
-> Nếu bạn muốn đóng góp cho Dify hoặc phát triển thêm, hãy tham khảo [hướng dẫn triển khai từ mã nguồn](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code) của chúng tôi
-
-## Các bước tiếp theo
-
-Nếu bạn cần tùy chỉnh cấu hình, vui lòng tham khảo các nhận xét trong tệp [.env.example](docker/.env.example) của chúng tôi và cập nhật các giá trị tương ứng trong tệp `.env` của bạn. Ngoài ra, bạn có thể cần điều chỉnh tệp `docker-compose.yaml`, chẳng hạn như thay đổi phiên bản hình ảnh, ánh xạ cổng hoặc gắn kết khối lượng, dựa trên môi trường triển khai cụ thể và yêu cầu của bạn. Sau khi thực hiện bất kỳ thay đổi nào, vui lòng chạy lại `docker-compose up -d`. Bạn có thể tìm thấy danh sách đầy đủ các biến môi trường có sẵn [tại đây](https://docs.dify.ai/getting-started/install-self-hosted/environments).
-
-Nếu bạn muốn cấu hình một cài đặt có độ sẵn sàng cao, có các [Helm Charts](https://helm.sh/) và tệp YAML do cộng đồng đóng góp cho phép Dify được triển khai trên Kubernetes.
-
- [Helm Chart bởi @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
- [Helm Chart bởi @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
- [Tệp YAML bởi @Winson-030](https://github.com/Winson-030/dify-kubernetes)
-
-#### Sử dụng Terraform để Triển khai
-
-##### 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)
-
-## 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. 
-Đồng thời, vui lòng xem xét hỗ trợ Dify bằng cách chia sẻ nó trên mạng xã hội và tại các sự kiện và hội nghị.
-
-
-> Chúng tôi đang tìm kiếm người đóng góp để giúp dịch Dify sang các ngôn ngữ khác ngoài tiếng Trung hoặc tiếng Anh. Nếu bạn quan tâm đến việc giúp đỡ, vui lòng xem [README i18n](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) để biết thêm thông tin và để lại bình luận cho chúng tôi trong kênh `global-users` của [Máy chủ Cộng đồng Discord](https://discord.gg/8Tpq4AcN9c) của chúng tôi.
-
-**Người đóng góp**
-
-<a href="https://github.com/langgenius/dify/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=langgenius/dify" />
-</a>
-
-## Cộng đồng & liên hệ
-
-* [Thảo luận GitHub](https://github.com/langgenius/dify/discussions). Tốt nhất cho: chia sẻ phản hồi và đặt câu hỏi.
-* [Vấn đề GitHub](https://github.com/langgenius/dify/issues). Tốt nhất cho: lỗi bạn gặp phải khi sử dụng Dify.AI và đề xuất tính năng. Xem [Hướng dẫn Đóng góp](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) của chúng tôi.
-* [Discord](https://discord.gg/FngNHpbcY7). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng.
-* [Twitter](https://twitter.com/dify_ai). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng.
-
-## Lịch sử Yêu thích
-
-[![Biểu đồ Lịch sử Yêu thích](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
-
-## Tiết lộ bảo mật
-
-Để bảo vệ quyền riêng tư của bạn, vui lòng tránh đăng các vấn đề bảo mật trên GitHub. Thay vào đó, hãy gửi câu hỏi của bạn đến security@dify.ai và chúng tôi sẽ cung cấp cho bạn câu trả lời chi tiết hơn.
-
-## Giấy phép
-
-Kho lưu trữ này có sẵn theo [Giấy phép Mã nguồn Mở Dify](LICENSE), về cơ bản là Apache 2.0 với một vài hạn chế bổ sung.
--- a/api/.env.example
+++ b/api/.env.example
@ -130,12 +130,6 @@ TENCENT_VECTOR_DB_DATABASE=dify
 TENCENT_VECTOR_DB_SHARD=1
 TENCENT_VECTOR_DB_REPLICAS=2

-# ElasticSearch configuration
-ELASTICSEARCH_HOST=127.0.0.1
-ELASTICSEARCH_PORT=9200
-ELASTICSEARCH_USERNAME=elastic
-ELASTICSEARCH_PASSWORD=elastic
-
 # PGVECTO_RS configuration
 PGVECTO_RS_HOST=localhost
 PGVECTO_RS_PORT=5431
--- a/api/Dockerfile
+++ b/api/Dockerfile
@ -12,7 +12,6 @@ ENV POETRY_CACHE_DIR=/tmp/poetry_cache
 ENV POETRY_NO_INTERACTION=1
 ENV POETRY_VIRTUALENVS_IN_PROJECT=true
 ENV POETRY_VIRTUALENVS_CREATE=true
-ENV POETRY_REQUESTS_TIMEOUT=15

 FROM base AS packages

@ -55,9 +54,6 @@ ENV VIRTUAL_ENV=/app/api/.venv
 COPY --from=packages ${VIRTUAL_ENV} ${VIRTUAL_ENV}
 ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"

-# Download nltk data
-RUN python -c "import nltk; nltk.download('punkt')"
-
 # Copy source code
 COPY . /app/api/

--- a/api/app.py
+++ b/api/app.py
@ -1,6 +1,6 @@
 import os

-if os.environ.get("DEBUG", "false").lower() != "true":
+if os.environ.get("DEBUG", "false").lower() != 'true':
    from gevent import monkey

    monkey.patch_all()
@ -57,7 +57,7 @@ warnings.simplefilter("ignore", ResourceWarning)
 if os.name == "nt":
    os.system('tzutil /s "UTC"')
 else:
-    os.environ["TZ"] = "UTC"
+    os.environ['TZ'] = 'UTC'
    time.tzset()


@ -70,14 +70,13 @@ class DifyApp(Flask):
 # -------------


-config_type = os.getenv("EDITION", default="SELF_HOSTED")  # ce edition first
+config_type = os.getenv('EDITION', default='SELF_HOSTED')  # ce edition first


 # ----------------------------
 # Application Factory Function
 # ----------------------------

-
 def create_flask_app_with_configs() -> Flask:
    """
    create a raw flask app
@ -93,7 +92,7 @@ def create_flask_app_with_configs() -> Flask:
        elif isinstance(value, int | float | bool):
            os.environ[key] = str(value)
        elif value is None:
-            os.environ[key] = ""
+            os.environ[key] = ''

    return dify_app

@ -101,10 +100,10 @@ def create_flask_app_with_configs() -> Flask:
 def create_app() -> Flask:
    app = create_flask_app_with_configs()

-    app.secret_key = app.config["SECRET_KEY"]
+    app.secret_key = app.config['SECRET_KEY']

    log_handlers = None
-    log_file = app.config.get("LOG_FILE")
+    log_file = app.config.get('LOG_FILE')
    if log_file:
        log_dir = os.path.dirname(log_file)
        os.makedirs(log_dir, exist_ok=True)
@ -112,24 +111,23 @@ def create_app() -> Flask:
            RotatingFileHandler(
                filename=log_file,
                maxBytes=1024 * 1024 * 1024,
-                backupCount=5,
+                backupCount=5
            ),
-            logging.StreamHandler(sys.stdout),
+            logging.StreamHandler(sys.stdout)
        ]

    logging.basicConfig(
-        level=app.config.get("LOG_LEVEL"),
-        format=app.config.get("LOG_FORMAT"),
-        datefmt=app.config.get("LOG_DATEFORMAT"),
+        level=app.config.get('LOG_LEVEL'),
+        format=app.config.get('LOG_FORMAT'),
+        datefmt=app.config.get('LOG_DATEFORMAT'),
        handlers=log_handlers,
-        force=True,
+        force=True
    )
-    log_tz = app.config.get("LOG_TZ")
+    log_tz = app.config.get('LOG_TZ')
    if log_tz:
        from datetime import datetime

        import pytz
-
        timezone = pytz.timezone(log_tz)

        def time_converter(seconds):
@ -164,24 +162,24 @@ def initialize_extensions(app):
@login_manager.request_loader
 def load_user_from_request(request_from_flask_login):
    """Load user based on the request."""
-    if request.blueprint not in ["console", "inner_api"]:
+    if request.blueprint not in ['console', 'inner_api']:
        return None
    # Check if the user_id contains a dot, indicating the old format
-    auth_header = request.headers.get("Authorization", "")
+    auth_header = request.headers.get('Authorization', '')
    if not auth_header:
-        auth_token = request.args.get("_token")
+        auth_token = request.args.get('_token')
        if not auth_token:
-            raise Unauthorized("Invalid Authorization token.")
+            raise Unauthorized('Invalid Authorization token.')
    else:
-        if " " not in auth_header:
-            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
+        if ' ' not in auth_header:
+            raise Unauthorized('Invalid Authorization header format. Expected \'Bearer <api-key>\' format.')
        auth_scheme, auth_token = auth_header.split(None, 1)
        auth_scheme = auth_scheme.lower()
-        if auth_scheme != "bearer":
-            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
+        if auth_scheme != 'bearer':
+            raise Unauthorized('Invalid Authorization header format. Expected \'Bearer <api-key>\' format.')

    decoded = PassportService().verify(auth_token)
-    user_id = decoded.get("user_id")
+    user_id = decoded.get('user_id')

    account = AccountService.load_logged_in_account(account_id=user_id, token=auth_token)
    if account:
@ -192,11 +190,10 @@ def load_user_from_request(request_from_flask_login):
@login_manager.unauthorized_handler
 def unauthorized_handler():
    """Handle unauthorized requests."""
-    return Response(
-        json.dumps({"code": "unauthorized", "message": "Unauthorized."}),
-        status=401,
-        content_type="application/json",
-    )
+    return Response(json.dumps({
+        'code': 'unauthorized',
+        'message': "Unauthorized."
+    }), status=401, content_type="application/json")


 # register blueprint routers
@ -207,36 +204,38 @@ def register_blueprints(app):
    from controllers.service_api import bp as service_api_bp
    from controllers.web import bp as web_bp

-    CORS(
-        service_api_bp,
-        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-    )
+    CORS(service_api_bp,
+         allow_headers=['Content-Type', 'Authorization', 'X-App-Code'],
+         methods=['GET', 'PUT', 'POST', 'DELETE', 'OPTIONS', 'PATCH']
+         )
    app.register_blueprint(service_api_bp)

-    CORS(
-        web_bp,
-        resources={r"/*": {"origins": app.config["WEB_API_CORS_ALLOW_ORIGINS"]}},
-        supports_credentials=True,
-        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-        expose_headers=["X-Version", "X-Env"],
-    )
+    CORS(web_bp,
+         resources={
+             r"/*": {"origins": app.config['WEB_API_CORS_ALLOW_ORIGINS']}},
+         supports_credentials=True,
+         allow_headers=['Content-Type', 'Authorization', 'X-App-Code'],
+         methods=['GET', 'PUT', 'POST', 'DELETE', 'OPTIONS', 'PATCH'],
+         expose_headers=['X-Version', 'X-Env']
+         )

    app.register_blueprint(web_bp)

-    CORS(
-        console_app_bp,
-        resources={r"/*": {"origins": app.config["CONSOLE_CORS_ALLOW_ORIGINS"]}},
-        supports_credentials=True,
-        allow_headers=["Content-Type", "Authorization"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-        expose_headers=["X-Version", "X-Env"],
-    )
+    CORS(console_app_bp,
+         resources={
+             r"/*": {"origins": app.config['CONSOLE_CORS_ALLOW_ORIGINS']}},
+         supports_credentials=True,
+         allow_headers=['Content-Type', 'Authorization'],
+         methods=['GET', 'PUT', 'POST', 'DELETE', 'OPTIONS', 'PATCH'],
+         expose_headers=['X-Version', 'X-Env']
+         )

    app.register_blueprint(console_app_bp)

-    CORS(files_bp, allow_headers=["Content-Type"], methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"])
+    CORS(files_bp,
+         allow_headers=['Content-Type'],
+         methods=['GET', 'PUT', 'POST', 'DELETE', 'OPTIONS', 'PATCH']
+         )
    app.register_blueprint(files_bp)

    app.register_blueprint(inner_api_bp)
@ -246,29 +245,29 @@ def register_blueprints(app):
 app = create_app()
 celery = app.extensions["celery"]

-if app.config.get("TESTING"):
+if app.config.get('TESTING'):
    print("App is running in TESTING mode")


@app.after_request
 def after_request(response):
    """Add Version headers to the response."""
-    response.set_cookie("remember_token", "", expires=0)
-    response.headers.add("X-Version", app.config["CURRENT_VERSION"])
-    response.headers.add("X-Env", app.config["DEPLOY_ENV"])
+    response.set_cookie('remember_token', '', expires=0)
+    response.headers.add('X-Version', app.config['CURRENT_VERSION'])
+    response.headers.add('X-Env', app.config['DEPLOY_ENV'])
    return response


-@app.route("/health")
+@app.route('/health')
 def health():
-    return Response(
-        json.dumps({"pid": os.getpid(), "status": "ok", "version": app.config["CURRENT_VERSION"]}),
-        status=200,
-        content_type="application/json",
-    )
+    return Response(json.dumps({
+        'pid': os.getpid(),
+        'status': 'ok',
+        'version': app.config['CURRENT_VERSION']
+    }), status=200, content_type="application/json")


-@app.route("/threads")
+@app.route('/threads')
 def threads():
    num_threads = threading.active_count()
    threads = threading.enumerate()
@ -279,34 +278,32 @@ def threads():
        thread_id = thread.ident
        is_alive = thread.is_alive()

-        thread_list.append(
-            {
-                "name": thread_name,
-                "id": thread_id,
-                "is_alive": is_alive,
-            }
-        )
+        thread_list.append({
+            'name': thread_name,
+            'id': thread_id,
+            'is_alive': is_alive
+        })

    return {
-        "pid": os.getpid(),
-        "thread_num": num_threads,
-        "threads": thread_list,
+        'pid': os.getpid(),
+        'thread_num': num_threads,
+        'threads': thread_list
    }


-@app.route("/db-pool-stat")
+@app.route('/db-pool-stat')
 def pool_stat():
    engine = db.engine
    return {
-        "pid": os.getpid(),
-        "pool_size": engine.pool.size(),
-        "checked_in_connections": engine.pool.checkedin(),
-        "checked_out_connections": engine.pool.checkedout(),
-        "overflow_connections": engine.pool.overflow(),
-        "connection_timeout": engine.pool.timeout(),
-        "recycle_time": db.engine.pool._recycle,
+        'pid': os.getpid(),
+        'pool_size': engine.pool.size(),
+        'checked_in_connections': engine.pool.checkedin(),
+        'checked_out_connections': engine.pool.checkedout(),
+        'overflow_connections': engine.pool.overflow(),
+        'connection_timeout': engine.pool.timeout(),
+        'recycle_time': db.engine.pool._recycle
    }


-if __name__ == "__main__":
-    app.run(host="0.0.0.0", port=5001)
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=5001)
--- a/api/commands.py
+++ b/api/commands.py
@ -27,29 +27,32 @@ from models.provider import Provider, ProviderModel
 from services.account_service import RegisterService, TenantService


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

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

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

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

    # generate password salt
@ -62,87 +65,80 @@ def reset_password(email, new_password, password_confirm):
    account.password = base64_password_hashed
    account.password_salt = base64_salt
    db.session.commit()
-    click.echo(click.style("Congratulations! Password has been reset.", fg="green"))
+    click.echo(click.style('Congratulations! Password has been reset.', fg='green'))


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

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

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

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

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


-@click.command(
-    "reset-encrypt-key-pair",
-    help="Reset the asymmetric key pair of workspace for encrypt LLM credentials. "
-    "After the reset, all LLM credentials will become invalid, "
-    "requiring re-entry."
-    "Only support SELF_HOSTED mode.",
-)
-@click.confirmation_option(
-    prompt=click.style(
-        "Are you sure you want to reset encrypt key pair?" " this operation cannot be rolled back!", fg="red"
-    )
-)
+@click.command('reset-encrypt-key-pair', help='Reset the asymmetric key pair of workspace for encrypt LLM credentials. '
+                                              'After the reset, all LLM credentials will become invalid, '
+                                              'requiring re-entry.'
+                                              'Only support SELF_HOSTED mode.')
+@click.confirmation_option(prompt=click.style('Are you sure you want to reset encrypt key pair?'
+                                              ' this operation cannot be rolled back!', fg='red'))
 def reset_encrypt_key_pair():
    """
    Reset the encrypted key pair of workspace for encrypt LLM credentials.
    After the reset, all LLM credentials will become invalid, requiring re-entry.
    Only support SELF_HOSTED mode.
    """
-    if dify_config.EDITION != "SELF_HOSTED":
-        click.echo(click.style("Sorry, only support SELF_HOSTED mode.", fg="red"))
+    if dify_config.EDITION != 'SELF_HOSTED':
+        click.echo(click.style('Sorry, only support SELF_HOSTED mode.', fg='red'))
        return

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

        tenant.encrypt_public_key = generate_key_pair(tenant.id)

-        db.session.query(Provider).filter(Provider.provider_type == "custom", Provider.tenant_id == tenant.id).delete()
+        db.session.query(Provider).filter(Provider.provider_type == 'custom', Provider.tenant_id == tenant.id).delete()
        db.session.query(ProviderModel).filter(ProviderModel.tenant_id == tenant.id).delete()
        db.session.commit()

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


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


@ -150,7 +146,7 @@ def migrate_annotation_vector_database():
    """
    Migrate annotation datas to target vector database .
    """
-    click.echo(click.style("Start migrate annotation data.", fg="green"))
+    click.echo(click.style('Start migrate annotation data.', fg='green'))
    create_count = 0
    skipped_count = 0
    total_count = 0
@ -158,103 +154,98 @@ def migrate_annotation_vector_database():
    while True:
        try:
            # get apps info
-            apps = (
-                db.session.query(App)
-                .filter(App.status == "normal")
-                .order_by(App.created_at.desc())
-                .paginate(page=page, per_page=50)
-            )
+            apps = db.session.query(App).filter(
+                App.status == 'normal'
+            ).order_by(App.created_at.desc()).paginate(page=page, per_page=50)
        except NotFound:
            break

        page += 1
        for app in apps:
            total_count = total_count + 1
-            click.echo(
-                f"Processing the {total_count} app {app.id}. " + f"{create_count} created, {skipped_count} skipped."
-            )
+            click.echo(f'Processing the {total_count} app {app.id}. '
+                       + f'{create_count} created, {skipped_count} skipped.')
            try:
-                click.echo("Create app annotation index: {}".format(app.id))
-                app_annotation_setting = (
-                    db.session.query(AppAnnotationSetting).filter(AppAnnotationSetting.app_id == app.id).first()
-                )
+                click.echo('Create app annotation index: {}'.format(app.id))
+                app_annotation_setting = db.session.query(AppAnnotationSetting).filter(
+                    AppAnnotationSetting.app_id == app.id
+                ).first()

                if not app_annotation_setting:
                    skipped_count = skipped_count + 1
-                    click.echo("App annotation setting is disabled: {}".format(app.id))
+                    click.echo('App annotation setting is disabled: {}'.format(app.id))
                    continue
                # get dataset_collection_binding info
-                dataset_collection_binding = (
-                    db.session.query(DatasetCollectionBinding)
-                    .filter(DatasetCollectionBinding.id == app_annotation_setting.collection_binding_id)
-                    .first()
-                )
+                dataset_collection_binding = db.session.query(DatasetCollectionBinding).filter(
+                    DatasetCollectionBinding.id == app_annotation_setting.collection_binding_id
+                ).first()
                if not dataset_collection_binding:
-                    click.echo("App annotation collection binding is not exist: {}".format(app.id))
+                    click.echo('App annotation collection binding is not exist: {}'.format(app.id))
                    continue
                annotations = db.session.query(MessageAnnotation).filter(MessageAnnotation.app_id == app.id).all()
                dataset = Dataset(
                    id=app.id,
                    tenant_id=app.tenant_id,
-                    indexing_technique="high_quality",
+                    indexing_technique='high_quality',
                    embedding_model_provider=dataset_collection_binding.provider_name,
                    embedding_model=dataset_collection_binding.model_name,
-                    collection_binding_id=dataset_collection_binding.id,
+                    collection_binding_id=dataset_collection_binding.id
                )
                documents = []
                if annotations:
                    for annotation in annotations:
                        document = Document(
                            page_content=annotation.question,
-                            metadata={"annotation_id": annotation.id, "app_id": app.id, "doc_id": annotation.id},
+                            metadata={
+                                "annotation_id": annotation.id,
+                                "app_id": app.id,
+                                "doc_id": annotation.id
+                            }
                        )
                        documents.append(document)

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

                try:
                    vector.delete()
-                    click.echo(click.style(f"Successfully delete vector index for app: {app.id}.", fg="green"))
+                    click.echo(
+                        click.style(f'Successfully delete vector index for app: {app.id}.',
+                                    fg='green'))
                except Exception as e:
-                    click.echo(click.style(f"Failed to delete vector index for app {app.id}.", fg="red"))
+                    click.echo(
+                        click.style(f'Failed to delete vector index for app {app.id}.',
+                                    fg='red'))
                    raise e
                if documents:
                    try:
-                        click.echo(
-                            click.style(
-                                f"Start to created vector index with {len(documents)} annotations for app {app.id}.",
-                                fg="green",
-                            )
-                        )
+                        click.echo(click.style(
+                            f'Start to created vector index with {len(documents)} annotations for app {app.id}.',
+                            fg='green'))
                        vector.create(documents)
-                        click.echo(click.style(f"Successfully created vector index for app {app.id}.", fg="green"))
+                        click.echo(
+                            click.style(f'Successfully created vector index for app {app.id}.', fg='green'))
                    except Exception as e:
-                        click.echo(click.style(f"Failed to created vector index for app {app.id}.", fg="red"))
+                        click.echo(click.style(f'Failed to created vector index for app {app.id}.', fg='red'))
                        raise e
-                click.echo(f"Successfully migrated app annotation {app.id}.")
+                click.echo(f'Successfully migrated app annotation {app.id}.')
                create_count += 1
            except Exception as e:
                click.echo(
-                    click.style(
-                        "Create app annotation index error: {} {}".format(e.__class__.__name__, str(e)), fg="red"
-                    )
-                )
+                    click.style('Create app annotation index error: {} {}'.format(e.__class__.__name__, str(e)),
+                                fg='red'))
                continue

    click.echo(
-        click.style(
-            f"Congratulations! Create {create_count} app annotation indexes, and skipped {skipped_count} apps.",
-            fg="green",
-        )
-    )
+        click.style(f'Congratulations! Create {create_count} app annotation indexes, and skipped {skipped_count} apps.',
+                    fg='green'))


 def migrate_knowledge_vector_database():
    """
    Migrate vector database datas to target vector database .
    """
-    click.echo(click.style("Start migrate vector db.", fg="green"))
+    click.echo(click.style('Start migrate vector db.', fg='green'))
    create_count = 0
    skipped_count = 0
    total_count = 0
@ -262,77 +253,87 @@ def migrate_knowledge_vector_database():
    page = 1
    while True:
        try:
-            datasets = (
-                db.session.query(Dataset)
-                .filter(Dataset.indexing_technique == "high_quality")
-                .order_by(Dataset.created_at.desc())
-                .paginate(page=page, per_page=50)
-            )
+            datasets = db.session.query(Dataset).filter(Dataset.indexing_technique == 'high_quality') \
+                .order_by(Dataset.created_at.desc()).paginate(page=page, per_page=50)
        except NotFound:
            break

        page += 1
        for dataset in datasets:
            total_count = total_count + 1
-            click.echo(
-                f"Processing the {total_count} dataset {dataset.id}. "
-                + f"{create_count} created, {skipped_count} skipped."
-            )
+            click.echo(f'Processing the {total_count} dataset {dataset.id}. '
+                       + f'{create_count} created, {skipped_count} skipped.')
            try:
-                click.echo("Create dataset vdb index: {}".format(dataset.id))
+                click.echo('Create dataset vdb index: {}'.format(dataset.id))
                if dataset.index_struct_dict:
-                    if dataset.index_struct_dict["type"] == vector_type:
+                    if dataset.index_struct_dict['type'] == vector_type:
                        skipped_count = skipped_count + 1
                        continue
-                collection_name = ""
+                collection_name = ''
                if vector_type == VectorType.WEAVIATE:
                    dataset_id = dataset.id
                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.WEAVIATE, "vector_store": {"class_prefix": collection_name}}
+                    index_struct_dict = {
+                        "type": VectorType.WEAVIATE,
+                        "vector_store": {"class_prefix": collection_name}
+                    }
                    dataset.index_struct = json.dumps(index_struct_dict)
                elif vector_type == VectorType.QDRANT:
                    if dataset.collection_binding_id:
-                        dataset_collection_binding = (
-                            db.session.query(DatasetCollectionBinding)
-                            .filter(DatasetCollectionBinding.id == dataset.collection_binding_id)
-                            .one_or_none()
-                        )
+                        dataset_collection_binding = db.session.query(DatasetCollectionBinding). \
+                            filter(DatasetCollectionBinding.id == dataset.collection_binding_id). \
+                            one_or_none()
                        if dataset_collection_binding:
                            collection_name = dataset_collection_binding.collection_name
                        else:
-                            raise ValueError("Dataset Collection Bindings is not exist!")
+                            raise ValueError('Dataset Collection Bindings is not exist!')
                    else:
                        dataset_id = dataset.id
                        collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.QDRANT, "vector_store": {"class_prefix": collection_name}}
+                    index_struct_dict = {
+                        "type": VectorType.QDRANT,
+                        "vector_store": {"class_prefix": collection_name}
+                    }
                    dataset.index_struct = json.dumps(index_struct_dict)

                elif vector_type == VectorType.MILVUS:
                    dataset_id = dataset.id
                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.MILVUS, "vector_store": {"class_prefix": collection_name}}
+                    index_struct_dict = {
+                        "type": VectorType.MILVUS,
+                        "vector_store": {"class_prefix": collection_name}
+                    }
                    dataset.index_struct = json.dumps(index_struct_dict)
                elif vector_type == VectorType.RELYT:
                    dataset_id = dataset.id
                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": "relyt", "vector_store": {"class_prefix": collection_name}}
+                    index_struct_dict = {
+                        "type": 'relyt',
+                        "vector_store": {"class_prefix": collection_name}
+                    }
                    dataset.index_struct = json.dumps(index_struct_dict)
                elif vector_type == VectorType.TENCENT:
                    dataset_id = dataset.id
                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.TENCENT, "vector_store": {"class_prefix": collection_name}}
+                    index_struct_dict = {
+                        "type": VectorType.TENCENT,
+                        "vector_store": {"class_prefix": collection_name}
+                    }
                    dataset.index_struct = json.dumps(index_struct_dict)
                elif vector_type == VectorType.PGVECTOR:
                    dataset_id = dataset.id
                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.PGVECTOR, "vector_store": {"class_prefix": collection_name}}
+                    index_struct_dict = {
+                        "type": VectorType.PGVECTOR,
+                        "vector_store": {"class_prefix": collection_name}
+                    }
                    dataset.index_struct = json.dumps(index_struct_dict)
                elif vector_type == VectorType.OPENSEARCH:
                    dataset_id = dataset.id
                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
                    index_struct_dict = {
                        "type": VectorType.OPENSEARCH,
-                        "vector_store": {"class_prefix": collection_name},
+                        "vector_store": {"class_prefix": collection_name}
                    }
                    dataset.index_struct = json.dumps(index_struct_dict)
                elif vector_type == VectorType.ANALYTICDB:
@ -340,14 +341,9 @@ def migrate_knowledge_vector_database():
                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
                    index_struct_dict = {
                        "type": VectorType.ANALYTICDB,
-                        "vector_store": {"class_prefix": collection_name},
+                        "vector_store": {"class_prefix": collection_name}
                    }
                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.ELASTICSEARCH:
-                    dataset_id = dataset.id
-                    index_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": "elasticsearch", "vector_store": {"class_prefix": index_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
                else:
                    raise ValueError(f"Vector store {vector_type} is not supported.")

@ -357,41 +353,29 @@ def migrate_knowledge_vector_database():
                try:
                    vector.delete()
                    click.echo(
-                        click.style(
-                            f"Successfully delete vector index {collection_name} for dataset {dataset.id}.", fg="green"
-                        )
-                    )
+                        click.style(f'Successfully delete vector index {collection_name} for dataset {dataset.id}.',
+                                    fg='green'))
                except Exception as e:
                    click.echo(
-                        click.style(
-                            f"Failed to delete vector index {collection_name} for dataset {dataset.id}.", fg="red"
-                        )
-                    )
+                        click.style(f'Failed to delete vector index {collection_name} for dataset {dataset.id}.',
+                                    fg='red'))
                    raise e

-                dataset_documents = (
-                    db.session.query(DatasetDocument)
-                    .filter(
-                        DatasetDocument.dataset_id == dataset.id,
-                        DatasetDocument.indexing_status == "completed",
-                        DatasetDocument.enabled == True,
-                        DatasetDocument.archived == False,
-                    )
-                    .all()
-                )
+                dataset_documents = db.session.query(DatasetDocument).filter(
+                    DatasetDocument.dataset_id == dataset.id,
+                    DatasetDocument.indexing_status == 'completed',
+                    DatasetDocument.enabled == True,
+                    DatasetDocument.archived == False,
+                ).all()

                documents = []
                segments_count = 0
                for dataset_document in dataset_documents:
-                    segments = (
-                        db.session.query(DocumentSegment)
-                        .filter(
-                            DocumentSegment.document_id == dataset_document.id,
-                            DocumentSegment.status == "completed",
-                            DocumentSegment.enabled == True,
-                        )
-                        .all()
-                    )
+                    segments = db.session.query(DocumentSegment).filter(
+                        DocumentSegment.document_id == dataset_document.id,
+                        DocumentSegment.status == 'completed',
+                        DocumentSegment.enabled == True
+                    ).all()

                    for segment in segments:
                        document = Document(
@ -401,7 +385,7 @@ def migrate_knowledge_vector_database():
                                "doc_hash": segment.index_node_hash,
                                "document_id": segment.document_id,
                                "dataset_id": segment.dataset_id,
-                            },
+                            }
                        )

                        documents.append(document)
@ -409,43 +393,37 @@ def migrate_knowledge_vector_database():

                if documents:
                    try:
-                        click.echo(
-                            click.style(
-                                f"Start to created vector index with {len(documents)} documents of {segments_count} segments for dataset {dataset.id}.",
-                                fg="green",
-                            )
-                        )
+                        click.echo(click.style(
+                            f'Start to created vector index with {len(documents)} documents of {segments_count} segments for dataset {dataset.id}.',
+                            fg='green'))
                        vector.create(documents)
                        click.echo(
-                            click.style(f"Successfully created vector index for dataset {dataset.id}.", fg="green")
-                        )
+                            click.style(f'Successfully created vector index for dataset {dataset.id}.', fg='green'))
                    except Exception as e:
-                        click.echo(click.style(f"Failed to created vector index for dataset {dataset.id}.", fg="red"))
+                        click.echo(click.style(f'Failed to created vector index for dataset {dataset.id}.', fg='red'))
                        raise e
                db.session.add(dataset)
                db.session.commit()
-                click.echo(f"Successfully migrated dataset {dataset.id}.")
+                click.echo(f'Successfully migrated dataset {dataset.id}.')
                create_count += 1
            except Exception as e:
                db.session.rollback()
                click.echo(
-                    click.style("Create dataset index error: {} {}".format(e.__class__.__name__, str(e)), fg="red")
-                )
+                    click.style('Create dataset index error: {} {}'.format(e.__class__.__name__, str(e)),
+                                fg='red'))
                continue

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


-@click.command("convert-to-agent-apps", help="Convert Agent Assistant to Agent App.")
+@click.command('convert-to-agent-apps', help='Convert Agent Assistant to Agent App.')
 def convert_to_agent_apps():
    """
    Convert Agent Assistant to Agent App.
    """
-    click.echo(click.style("Start convert to agent apps.", fg="green"))
+    click.echo(click.style('Start convert to agent apps.', fg='green'))

    proceeded_app_ids = []

@ -480,7 +458,7 @@ def convert_to_agent_apps():
                break

        for app in apps:
-            click.echo("Converting app: {}".format(app.id))
+            click.echo('Converting app: {}'.format(app.id))

            try:
                app.mode = AppMode.AGENT_CHAT.value
@ -492,139 +470,137 @@ def convert_to_agent_apps():
                )

                db.session.commit()
-                click.echo(click.style("Converted app: {}".format(app.id), fg="green"))
+                click.echo(click.style('Converted app: {}'.format(app.id), fg='green'))
            except Exception as e:
-                click.echo(click.style("Convert app error: {} {}".format(e.__class__.__name__, str(e)), fg="red"))
+                click.echo(
+                    click.style('Convert app error: {} {}'.format(e.__class__.__name__,
+                                                                  str(e)), fg='red'))

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


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

    try:
        bindings = db.session.query(DatasetCollectionBinding).all()
        if not bindings:
-            click.echo(click.style("Sorry, no dataset collection bindings found.", fg="red"))
+            click.echo(click.style('Sorry, no dataset collection bindings found.', fg='red'))
            return
        import qdrant_client
        from qdrant_client.http.exceptions import UnexpectedResponse
        from qdrant_client.http.models import PayloadSchemaType

        from core.rag.datasource.vdb.qdrant.qdrant_vector import QdrantConfig
-
        for binding in bindings:
            if dify_config.QDRANT_URL is None:
-                raise ValueError("Qdrant url is required.")
+                raise ValueError('Qdrant url is required.')
            qdrant_config = QdrantConfig(
                endpoint=dify_config.QDRANT_URL,
                api_key=dify_config.QDRANT_API_KEY,
                root_path=current_app.root_path,
                timeout=dify_config.QDRANT_CLIENT_TIMEOUT,
                grpc_port=dify_config.QDRANT_GRPC_PORT,
-                prefer_grpc=dify_config.QDRANT_GRPC_ENABLED,
+                prefer_grpc=dify_config.QDRANT_GRPC_ENABLED
            )
            try:
                client = qdrant_client.QdrantClient(**qdrant_config.to_qdrant_params())
                # create payload index
-                client.create_payload_index(binding.collection_name, field, field_schema=PayloadSchemaType.KEYWORD)
+                client.create_payload_index(binding.collection_name, field,
+                                            field_schema=PayloadSchemaType.KEYWORD)
                create_count += 1
            except UnexpectedResponse as e:
                # Collection does not exist, so return
                if e.status_code == 404:
-                    click.echo(
-                        click.style(f"Collection not found, collection_name:{binding.collection_name}.", fg="red")
-                    )
+                    click.echo(click.style(f'Collection not found, collection_name:{binding.collection_name}.', fg='red'))
                    continue
                # Some other error occurred, so re-raise the exception
                else:
-                    click.echo(
-                        click.style(
-                            f"Failed to create qdrant index, collection_name:{binding.collection_name}.", fg="red"
-                        )
-                    )
+                    click.echo(click.style(f'Failed to create qdrant index, collection_name:{binding.collection_name}.', fg='red'))

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

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


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

    # Create account
    email = email.strip()

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

-    account_name = email.split("@")[0]
+    account_name = email.split('@')[0]

    if language not in languages:
-        language = "en-US"
+        language = 'en-US'

    # generate random password
    new_password = secrets.token_urlsafe(16)

    # register account
-    account = RegisterService.register(email=email, name=account_name, password=new_password, language=language)
+    account = RegisterService.register(
+        email=email,
+        name=account_name,
+        password=new_password,
+        language=language
+    )

    TenantService.create_owner_tenant_if_not_exist(account)

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


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

            # run db migration
            import flask_migrate
-
            flask_migrate.upgrade()

-            click.echo(click.style("Database migration successful!", fg="green"))
+            click.echo(click.style('Database migration successful!', fg='green'))

        except Exception as e:
-            logging.exception(f"Database migration failed, error: {e}")
+            logging.exception(f'Database migration failed, error: {e}')
        finally:
            lock.release()
    else:
-        click.echo("Database migration skipped")
+        click.echo('Database migration skipped')


-@click.command("fix-app-site-missing", help="Fix app related site missing issue.")
+@click.command('fix-app-site-missing', help='Fix app related site missing issue.')
 def fix_app_site_missing():
    """
    Fix app related site missing issue.
    """
-    click.echo(click.style("Start fix app related site missing issue.", fg="green"))
+    click.echo(click.style('Start fix app related site missing issue.', fg='green'))

    failed_app_ids = []
    while True:
@ -655,14 +631,15 @@ where sites.id is null limit 1000"""
                        app_was_created.send(app, account=account)
                except Exception as e:
                    failed_app_ids.append(app_id)
-                    click.echo(click.style("Fix app {} related site missing issue failed!".format(app_id), fg="red"))
-                    logging.exception(f"Fix app related site missing issue failed, error: {e}")
+                    click.echo(click.style('Fix app {} related site missing issue failed!'.format(app_id), fg='red'))
+                    logging.exception(f'Fix app related site missing issue failed, error: {e}')
                    continue

            if not processed_count:
                break

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


 def register_commands(app):
--- a/api/configs/app_config.py
+++ b/api/configs/app_config.py
@ -12,14 +12,19 @@ from configs.packaging import PackagingInfo
 class DifyConfig(
    # Packaging info
    PackagingInfo,
+
    # Deployment configs
    DeploymentConfig,
+
    # Feature configs
    FeatureConfig,
+
    # Middleware configs
    MiddlewareConfig,
+
    # Extra service configs
    ExtraServiceConfig,
+
    # Enterprise feature configs
    # **Before using, please contact business@dify.ai by email to inquire about licensing matters.**
    EnterpriseFeatureConfig,
@ -31,6 +36,7 @@ class DifyConfig(
        env_file='.env',
        env_file_encoding='utf-8',
        frozen=True,
+
        # ignore extra attributes
        extra='ignore',
    )
@ -61,5 +67,3 @@ class DifyConfig(
    SSRF_PROXY_HTTPS_URL: str | None = None

    MODERATION_BUFFER_SIZE: int = Field(default=300, description='The buffer size for moderation.')
-
-    MAX_VARIABLE_SIZE: int = Field(default=5 * 1024, description='The maximum size of a variable. default is 5KB.')
--- a/api/configs/packaging/init.py
+++ b/api/configs/packaging/init.py
@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):

    CURRENT_VERSION: str = Field(
        description='Dify version',
-        default='0.7.1',
+        default='0.6.16',
    )

    COMMIT_SHA: str = Field(
--- a/api/constants/init.py
+++ b/api/constants/init.py
@ -1 +1,2 @@
-HIDDEN_VALUE = "[__HIDDEN__]"
+# TODO: Update all string in code to use this constant
+HIDDEN_VALUE = '[__HIDDEN__]'
--- a/api/constants/languages.py
+++ b/api/constants/languages.py
@ -1,22 +1,21 @@
 language_timezone_mapping = {
-    "en-US": "America/New_York",
-    "zh-Hans": "Asia/Shanghai",
-    "zh-Hant": "Asia/Taipei",
-    "pt-BR": "America/Sao_Paulo",
-    "es-ES": "Europe/Madrid",
-    "fr-FR": "Europe/Paris",
-    "de-DE": "Europe/Berlin",
-    "ja-JP": "Asia/Tokyo",
-    "ko-KR": "Asia/Seoul",
-    "ru-RU": "Europe/Moscow",
-    "it-IT": "Europe/Rome",
-    "uk-UA": "Europe/Kyiv",
-    "vi-VN": "Asia/Ho_Chi_Minh",
-    "ro-RO": "Europe/Bucharest",
-    "pl-PL": "Europe/Warsaw",
-    "hi-IN": "Asia/Kolkata",
-    "tr-TR": "Europe/Istanbul",
-    "fa-IR": "Asia/Tehran",
+    'en-US': 'America/New_York',
+    'zh-Hans': 'Asia/Shanghai',
+    'zh-Hant': 'Asia/Taipei',
+    'pt-BR': 'America/Sao_Paulo',
+    'es-ES': 'Europe/Madrid',
+    'fr-FR': 'Europe/Paris',
+    'de-DE': 'Europe/Berlin',
+    'ja-JP': 'Asia/Tokyo',
+    'ko-KR': 'Asia/Seoul',
+    'ru-RU': 'Europe/Moscow',
+    'it-IT': 'Europe/Rome',
+    'uk-UA': 'Europe/Kyiv',
+    'vi-VN': 'Asia/Ho_Chi_Minh',
+    'ro-RO': 'Europe/Bucharest',
+    'pl-PL': 'Europe/Warsaw',
+    'hi-IN': 'Asia/Kolkata',
+    'tr-TR': 'Europe/Istanbul',
 }

 languages = list(language_timezone_mapping.keys())
@ -26,5 +25,6 @@ def supported_language(lang):
    if lang in languages:
        return lang

-    error = "{lang} is not a valid language.".format(lang=lang)
+    error = ('{lang} is not a valid language.'
+             .format(lang=lang))
    raise ValueError(error)
--- a/api/constants/model_template.py
+++ b/api/constants/model_template.py
@ -5,79 +5,82 @@ from models.model import AppMode
 default_app_templates = {
    # workflow default mode
    AppMode.WORKFLOW: {
-        "app": {
-            "mode": AppMode.WORKFLOW.value,
-            "enable_site": True,
-            "enable_api": True,
+        'app': {
+            'mode': AppMode.WORKFLOW.value,
+            'enable_site': True,
+            'enable_api': True
        }
    },
+
    # completion default mode
    AppMode.COMPLETION: {
-        "app": {
-            "mode": AppMode.COMPLETION.value,
-            "enable_site": True,
-            "enable_api": True,
+        'app': {
+            'mode': AppMode.COMPLETION.value,
+            'enable_site': True,
+            'enable_api': True
        },
-        "model_config": {
-            "model": {
+        'model_config': {
+            'model': {
                "provider": "openai",
                "name": "gpt-4o",
                "mode": "chat",
-                "completion_params": {},
+                "completion_params": {}
            },
-            "user_input_form": json.dumps(
-                [
-                    {
-                        "paragraph": {
-                            "label": "Query",
-                            "variable": "query",
-                            "required": True,
-                            "default": "",
-                        },
-                    },
-                ]
-            ),
-            "pre_prompt": "{{query}}",
+            'user_input_form': json.dumps([
+                {
+                    "paragraph": {
+                        "label": "Query",
+                        "variable": "query",
+                        "required": True,
+                        "default": ""
+                    }
+                }
+            ]),
+            'pre_prompt': '{{query}}'
        },
+
    },
+
    # chat default mode
    AppMode.CHAT: {
-        "app": {
-            "mode": AppMode.CHAT.value,
-            "enable_site": True,
-            "enable_api": True,
+        'app': {
+            'mode': AppMode.CHAT.value,
+            'enable_site': True,
+            'enable_api': True
        },
-        "model_config": {
-            "model": {
+        'model_config': {
+            'model': {
                "provider": "openai",
                "name": "gpt-4o",
                "mode": "chat",
-                "completion_params": {},
-            },
-        },
+                "completion_params": {}
+            }
+        }
    },
+
    # advanced-chat default mode
    AppMode.ADVANCED_CHAT: {
-        "app": {
-            "mode": AppMode.ADVANCED_CHAT.value,
-            "enable_site": True,
-            "enable_api": True,
-        },
+        'app': {
+            'mode': AppMode.ADVANCED_CHAT.value,
+            'enable_site': True,
+            'enable_api': True
+        }
    },
+
    # agent-chat default mode
    AppMode.AGENT_CHAT: {
-        "app": {
-            "mode": AppMode.AGENT_CHAT.value,
-            "enable_site": True,
-            "enable_api": True,
+        'app': {
+            'mode': AppMode.AGENT_CHAT.value,
+            'enable_site': True,
+            'enable_api': True
        },
-        "model_config": {
-            "model": {
+        'model_config': {
+            'model': {
                "provider": "openai",
                "name": "gpt-4o",
                "mode": "chat",
-                "completion_params": {},
-            },
-        },
-    },
+                "completion_params": {}
+            }
+        }
+    }
 }
--- a/api/contexts/init.py
+++ b/api/contexts/init.py
@ -1,7 +1,3 @@
 from contextvars import ContextVar

-from core.workflow.entities.variable_pool import VariablePool
-
-tenant_id: ContextVar[str] = ContextVar("tenant_id")
-
-workflow_variable_pool: ContextVar[VariablePool] = ContextVar("workflow_variable_pool")
+tenant_id: ContextVar[str] = ContextVar('tenant_id')
--- a/api/controllers/console/init.py
+++ b/api/controllers/console/init.py
@ -17,7 +17,6 @@ from .app import (
    audio,
    completion,
    conversation,
-    conversation_variables,
    generator,
    message,
    model_config,
--- a/api/controllers/console/app/app.py
+++ b/api/controllers/console/app/app.py
@ -61,7 +61,6 @@ class AppListApi(Resource):
        parser.add_argument('name', type=str, required=True, location='json')
        parser.add_argument('description', type=str, location='json')
        parser.add_argument('mode', type=str, choices=ALLOW_CREATE_APP_MODES, location='json')
-        parser.add_argument('icon_type', type=str, location='json')
        parser.add_argument('icon', type=str, location='json')
        parser.add_argument('icon_background', type=str, location='json')
        args = parser.parse_args()
@ -95,7 +94,6 @@ class AppImportApi(Resource):
        parser.add_argument('data', type=str, required=True, nullable=False, location='json')
        parser.add_argument('name', type=str, location='json')
        parser.add_argument('description', type=str, location='json')
-        parser.add_argument('icon_type', type=str, location='json')
        parser.add_argument('icon', type=str, location='json')
        parser.add_argument('icon_background', type=str, location='json')
        args = parser.parse_args()
@ -169,7 +167,6 @@ class AppApi(Resource):
        parser = reqparse.RequestParser()
        parser.add_argument('name', type=str, required=True, nullable=False, location='json')
        parser.add_argument('description', type=str, location='json')
-        parser.add_argument('icon_type', type=str, location='json')
        parser.add_argument('icon', type=str, location='json')
        parser.add_argument('icon_background', type=str, location='json')
        parser.add_argument('max_active_requests', type=int, location='json')
@ -211,7 +208,6 @@ class AppCopyApi(Resource):
        parser = reqparse.RequestParser()
        parser.add_argument('name', type=str, location='json')
        parser.add_argument('description', type=str, location='json')
-        parser.add_argument('icon_type', type=str, location='json')
        parser.add_argument('icon', type=str, location='json')
        parser.add_argument('icon_background', type=str, location='json')
        args = parser.parse_args()
--- a/api/controllers/console/app/conversation.py
+++ b/api/controllers/console/app/conversation.py
@ -33,7 +33,7 @@ class CompletionConversationApi(Resource):
    @get_app_model(mode=AppMode.COMPLETION)
    @marshal_with(conversation_pagination_fields)
    def get(self, app_model):
-        if not current_user.is_editor:
+        if not current_user.is_admin_or_owner:
            raise Forbidden()
        parser = reqparse.RequestParser()
        parser.add_argument('keyword', type=str, location='args')
@ -108,7 +108,7 @@ class CompletionConversationDetailApi(Resource):
    @get_app_model(mode=AppMode.COMPLETION)
    @marshal_with(conversation_message_detail_fields)
    def get(self, app_model, conversation_id):
-        if not current_user.is_editor:
+        if not current_user.is_admin_or_owner:
            raise Forbidden()
        conversation_id = str(conversation_id)

@ -119,7 +119,7 @@ class CompletionConversationDetailApi(Resource):
    @account_initialization_required
    @get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT])
    def delete(self, app_model, conversation_id):
-        if not current_user.is_editor:
+        if not current_user.is_admin_or_owner:
            raise Forbidden()
        conversation_id = str(conversation_id)

@ -256,7 +256,7 @@ class ChatConversationDetailApi(Resource):
    @get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT])
    @account_initialization_required
    def delete(self, app_model, conversation_id):
-        if not current_user.is_editor:
+        if not current_user.is_admin_or_owner:
            raise Forbidden()
        conversation_id = str(conversation_id)

--- a/api/controllers/console/app/conversation_variables.py
+++ b/api/controllers/console/app/conversation_variables.py
@ -1,61 +0,0 @@
-from flask_restful import Resource, marshal_with, reqparse
-from sqlalchemy import select
-from sqlalchemy.orm import Session
-
-from controllers.console import api
-from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
-from extensions.ext_database import db
-from fields.conversation_variable_fields import paginated_conversation_variable_fields
-from libs.login import login_required
-from models import ConversationVariable
-from models.model import AppMode
-
-
-class ConversationVariablesApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    @get_app_model(mode=AppMode.ADVANCED_CHAT)
-    @marshal_with(paginated_conversation_variable_fields)
-    def get(self, app_model):
-        parser = reqparse.RequestParser()
-        parser.add_argument('conversation_id', type=str, location='args')
-        args = parser.parse_args()
-
-        stmt = (
-            select(ConversationVariable)
-            .where(ConversationVariable.app_id == app_model.id)
-            .order_by(ConversationVariable.created_at)
-        )
-        if args['conversation_id']:
-            stmt = stmt.where(ConversationVariable.conversation_id == args['conversation_id'])
-        else:
-            raise ValueError('conversation_id is required')
-
-        # NOTE: This is a temporary solution to avoid performance issues.
-        page = 1
-        page_size = 100
-        stmt = stmt.limit(page_size).offset((page - 1) * page_size)
-
-        with Session(db.engine) as session:
-            rows = session.scalars(stmt).all()
-
-        return {
-            'page': page,
-            'limit': page_size,
-            'total': len(rows),
-            'has_more': False,
-            'data': [
-                {
-                    'created_at': row.created_at,
-                    'updated_at': row.updated_at,
-                    **row.to_variable().model_dump(),
-                }
-                for row in rows
-            ],
-        }
-
-
-api.add_resource(ConversationVariablesApi, '/apps/<uuid:app_id>/conversation-variables')
--- a/api/controllers/console/app/site.py
+++ b/api/controllers/console/app/site.py
@ -16,7 +16,6 @@ from models.model import Site
 def parse_app_site_args():
    parser = reqparse.RequestParser()
    parser.add_argument('title', type=str, required=False, location='json')
-    parser.add_argument('icon_type', type=str, required=False, location='json')
    parser.add_argument('icon', type=str, required=False, location='json')
    parser.add_argument('icon_background', type=str, required=False, location='json')
    parser.add_argument('description', type=str, required=False, location='json')
@ -54,7 +53,6 @@ class AppSite(Resource):

        for attr_name in [
            'title',
-            'icon_type',
            'icon',
            'icon_background',
            'description',
--- a/api/controllers/console/app/workflow.py
+++ b/api/controllers/console/app/workflow.py
@ -74,7 +74,6 @@ class DraftWorkflowApi(Resource):
            parser.add_argument('hash', type=str, required=False, location='json')
            # TODO: set this to required=True after frontend is updated
            parser.add_argument('environment_variables', type=list, required=False, location='json')
-            parser.add_argument('conversation_variables', type=list, required=False, location='json')
            args = parser.parse_args()
        elif 'text/plain' in content_type:
            try:
@ -89,8 +88,7 @@ class DraftWorkflowApi(Resource):
                    'graph': data.get('graph'),
                    'features': data.get('features'),
                    'hash': data.get('hash'),
-                    'environment_variables': data.get('environment_variables'),
-                    'conversation_variables': data.get('conversation_variables'),
+                    'environment_variables': data.get('environment_variables')
                }
            except json.JSONDecodeError:
                return {'message': 'Invalid JSON data'}, 400
@ -102,8 +100,6 @@ class DraftWorkflowApi(Resource):
        try:
            environment_variables_list = args.get('environment_variables') or []
            environment_variables = [factory.build_variable_from_mapping(obj) for obj in environment_variables_list]
-            conversation_variables_list = args.get('conversation_variables') or []
-            conversation_variables = [factory.build_variable_from_mapping(obj) for obj in conversation_variables_list]
            workflow = workflow_service.sync_draft_workflow(
                app_model=app_model,
                graph=args['graph'],
@ -111,7 +107,6 @@ class DraftWorkflowApi(Resource):
                unique_hash=args.get('hash'),
                account=current_user,
                environment_variables=environment_variables,
-                conversation_variables=conversation_variables,
            )
        except WorkflowHashNotEqualError:
            raise DraftWorkflowNotSync()
@ -459,7 +454,6 @@ class ConvertToWorkflowApi(Resource):
        if request.data:
            parser = reqparse.RequestParser()
            parser.add_argument('name', type=str, required=False, nullable=True, location='json')
-            parser.add_argument('icon_type', type=str, required=False, nullable=True, location='json')
            parser.add_argument('icon', type=str, required=False, nullable=True, location='json')
            parser.add_argument('icon_background', type=str, required=False, nullable=True, location='json')
            args = parser.parse_args()
--- a/api/controllers/console/datasets/datasets.py
+++ b/api/controllers/console/datasets/datasets.py
@ -555,7 +555,7 @@ class DatasetRetrievalSettingApi(Resource):
                        RetrievalMethod.SEMANTIC_SEARCH.value
                    ]
                }
-            case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH | VectorType.ANALYTICDB | VectorType.MYSCALE | VectorType.ORACLE | VectorType.ELASTICSEARCH:
+            case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH | VectorType.ANALYTICDB | VectorType.MYSCALE | VectorType.ORACLE:
                return {
                    'retrieval_method': [
                        RetrievalMethod.SEMANTIC_SEARCH.value,
@ -579,7 +579,7 @@ class DatasetRetrievalSettingMockApi(Resource):
                        RetrievalMethod.SEMANTIC_SEARCH.value
                    ]
                }
-            case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH| VectorType.ANALYTICDB | VectorType.MYSCALE | VectorType.ORACLE | VectorType.ELASTICSEARCH:
+            case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH| VectorType.ANALYTICDB | VectorType.MYSCALE | VectorType.ORACLE:
                return {
                    'retrieval_method': [
                        RetrievalMethod.SEMANTIC_SEARCH.value,
--- a/api/controllers/console/datasets/datasets_document.py
+++ b/api/controllers/console/datasets/datasets_document.py
@ -178,20 +178,11 @@ class DatasetDocumentListApi(Resource):
                .subquery()

            query = query.outerjoin(sub_query, sub_query.c.document_id == Document.id) \
-                .order_by(
-                    sort_logic(db.func.coalesce(sub_query.c.total_hit_count, 0)),
-                    sort_logic(Document.position),
-                )
+                .order_by(sort_logic(db.func.coalesce(sub_query.c.total_hit_count, 0)))
        elif sort == 'created_at':
-            query = query.order_by(
-                sort_logic(Document.created_at),
-                sort_logic(Document.position),
-            )
+            query = query.order_by(sort_logic(Document.created_at))
        else:
-            query = query.order_by(
-                desc(Document.created_at),
-                desc(Document.position),
-            )
+            query = query.order_by(desc(Document.created_at))

        paginated_documents = query.paginate(
            page=page, per_page=limit, max_per_page=100, error_out=False)
--- a/api/controllers/console/extension.py
+++ b/api/controllers/console/extension.py
@ -1,7 +1,6 @@
 from flask_login import current_user
 from flask_restful import Resource, marshal_with, reqparse

-from constants import HIDDEN_VALUE
 from controllers.console import api
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
@ -90,7 +89,7 @@ class APIBasedExtensionDetailAPI(Resource):
        extension_data_from_db.name = args['name']
        extension_data_from_db.api_endpoint = args['api_endpoint']

-        if args['api_key'] != HIDDEN_VALUE:
+        if args['api_key'] != '[__HIDDEN__]':
            extension_data_from_db.api_key = args['api_key']

        return APIBasedExtensionService.save(extension_data_from_db)
--- a/api/controllers/service_api/app/message.py
+++ b/api/controllers/service_api/app/message.py
@ -131,7 +131,7 @@ class MessageSuggestedApi(Resource):
        except services.errors.message.MessageNotExistsError:
            raise NotFound("Message Not Exists.")
        except SuggestedQuestionsAfterAnswerDisabledError:
-            raise BadRequest("Suggested Questions Is Disabled.")
+            raise BadRequest("Message Not Exists.")
        except Exception:
            logging.exception("internal server error.")
            raise InternalServerError()
--- a/api/controllers/service_api/dataset/segment.py
+++ b/api/controllers/service_api/dataset/segment.py
@ -53,22 +53,19 @@ class SegmentApi(DatasetApiResource):
                raise ProviderNotInitializeError(
                    "No Embedding Model available. Please configure a valid provider "
                    "in the Settings -> Model Provider.")
-            except ProviderTokenNotInitError as ex:   
+            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
        # validate args
        parser = reqparse.RequestParser()
        parser.add_argument('segments', type=list, required=False, nullable=True, location='json')
        args = parser.parse_args()
-        if args['segments'] is not None:
-            for args_item in args['segments']:
-                SegmentService.segment_create_args_validate(args_item, document)
-            segments = SegmentService.multi_create_segment(args['segments'], document, dataset)
-            return {
-                'data': marshal(segments, segment_fields),
-                'doc_form': document.doc_form
-            }, 200
-        else:
-            return {"error": "Segemtns is required"}, 400
+        for args_item in args['segments']:
+            SegmentService.segment_create_args_validate(args_item, document)
+        segments = SegmentService.multi_create_segment(args['segments'], document, dataset)
+        return {
+            'data': marshal(segments, segment_fields),
+            'doc_form': document.doc_form
+        }, 200

    def get(self, tenant_id, dataset_id, document_id):
        """Create single segment."""
--- a/api/controllers/web/site.py
+++ b/api/controllers/web/site.py
@ -6,7 +6,6 @@ from configs import dify_config
 from controllers.web import api
 from controllers.web.wraps import WebApiResource
 from extensions.ext_database import db
-from libs.helper import AppIconUrlField
 from models.account import TenantStatus
 from models.model import Site
 from services.feature_service import FeatureService
@ -29,10 +28,8 @@ class AppSiteApi(WebApiResource):
        'title': fields.String,
        'chat_color_theme': fields.String,
        'chat_color_theme_inverted': fields.Boolean,
-        'icon_type': fields.String,
        'icon': fields.String,
        'icon_background': fields.String,
-        'icon_url': AppIconUrlField,
        'description': fields.String,
        'copyright': fields.String,
        'privacy_policy': fields.String,
--- a/api/core/agent/base_agent_runner.py
+++ b/api/core/agent/base_agent_runner.py
@ -64,19 +64,15 @@ class BaseAgentRunner(AppRunner):
        """
        Agent runner
        :param tenant_id: tenant id
-        :param application_generate_entity: application generate entity
-        :param conversation: conversation
        :param app_config: app generate entity
        :param model_config: model config
        :param config: dataset config
        :param queue_manager: queue manager
        :param message: message
        :param user_id: user id
+        :param agent_llm_callback: agent llm callback
+        :param callback: callback
        :param memory: memory
-        :param prompt_messages: prompt messages
-        :param variables_pool: variables pool
-        :param db_variables: db variables
-        :param model_instance: model instance
        """
        self.tenant_id = tenant_id
        self.application_generate_entity = application_generate_entity
@ -449,7 +445,7 @@ class BaseAgentRunner(AppRunner):
                        try:
                            tool_responses = json.loads(agent_thought.observation)
                        except Exception as e:
-                            tool_responses = dict.fromkeys(tools, agent_thought.observation)
+                            tool_responses = { tool: agent_thought.observation for tool in tools }

                        for tool in tools:
                            # generate a uuid for tool call
--- a/api/core/agent/cot_agent_runner.py
+++ b/api/core/agent/cot_agent_runner.py
@ -292,8 +292,6 @@ class CotAgentRunner(BaseAgentRunner, ABC):
        handle invoke action
        :param action: action
        :param tool_instances: tool instances
-        :param message_file_ids: message file ids
-        :param trace_manager: trace manager
        :return: observation, meta
        """
        # action is tool call, invoke tool
--- a/api/core/app/app_config/easy_ui_based_app/dataset/manager.py
+++ b/api/core/app/app_config/easy_ui_based_app/dataset/manager.py
@ -93,7 +93,6 @@ class DatasetConfigManager:
                    reranking_model=dataset_configs.get('reranking_model'),
                    weights=dataset_configs.get('weights'),
                    reranking_enabled=dataset_configs.get('reranking_enabled', True),
-                    rerank_mode=dataset_configs["reranking_mode"],
                )
            )

--- a/api/core/app/app_config/entities.py
+++ b/api/core/app/app_config/entities.py
@ -3,9 +3,8 @@ from typing import Any, Optional

 from pydantic import BaseModel

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


 class ModelConfigEntity(BaseModel):
@ -201,6 +200,11 @@ class TracingConfigEntity(BaseModel):
    tracing_provider: str


+class FileExtraConfig(BaseModel):
+    """
+    File Upload Entity.
+    """
+    image_config: Optional[dict[str, Any]] = None


 class AppAdditionalFeatures(BaseModel):
--- a/api/core/app/app_config/features/file_upload/manager.py
+++ b/api/core/app/app_config/features/file_upload/manager.py
@ -1,7 +1,7 @@
 from collections.abc import Mapping
 from typing import Any, Optional

-from core.file.file_obj import FileExtraConfig
+from core.app.app_config.entities import FileExtraConfig


 class FileUploadConfigManager:
--- a/api/core/app/apps/advanced_chat/app_generator.py
+++ b/api/core/app/apps/advanced_chat/app_generator.py
@ -8,8 +8,6 @@ from typing import Union

 from flask import Flask, current_app
 from pydantic import ValidationError
-from sqlalchemy import select
-from sqlalchemy.orm import Session

 import contexts
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
@ -20,20 +18,15 @@ from core.app.apps.advanced_chat.generate_task_pipeline import AdvancedChatAppGe
 from core.app.apps.base_app_queue_manager import AppQueueManager, GenerateTaskStoppedException, PublishFrom
 from core.app.apps.message_based_app_generator import MessageBasedAppGenerator
 from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueManager
-from core.app.entities.app_invoke_entities import (
-    AdvancedChatAppGenerateEntity,
-    InvokeFrom,
-)
+from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity, InvokeFrom
 from core.app.entities.task_entities import ChatbotAppBlockingResponse, ChatbotAppStreamResponse
 from core.file.message_file_parser import MessageFileParser
 from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
 from core.ops.ops_trace_manager import TraceQueueManager
-from core.workflow.entities.variable_pool import VariablePool
-from core.workflow.enums import SystemVariable
 from extensions.ext_database import db
 from models.account import Account
 from models.model import App, Conversation, EndUser, Message
-from models.workflow import ConversationVariable, Workflow
+from models.workflow import Workflow

 logger = logging.getLogger(__name__)

@ -96,8 +89,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
        )

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

        if invoke_from == InvokeFrom.DEBUGGER:
            # always enable retriever resource in debugger mode
@ -120,6 +112,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
        contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)

        return self._generate(
+            app_model=app_model,
            workflow=workflow,
            user=user,
            invoke_from=invoke_from,
@ -127,7 +120,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
            conversation=conversation,
            stream=stream
        )
-
+    
    def single_iteration_generate(self, app_model: App,
                                  workflow: Workflow,
                                  node_id: str,
@ -147,10 +140,10 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
        """
        if not node_id:
            raise ValueError('node_id is required')
-
+        
        if args.get('inputs') is None:
            raise ValueError('inputs is required')
-
+        
        extras = {
            "auto_generate_conversation_name": False
        }
@ -186,6 +179,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
        contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)

        return self._generate(
+            app_model=app_model,
            workflow=workflow,
            user=user,
            invoke_from=InvokeFrom.DEBUGGER,
@ -194,12 +188,12 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
            stream=stream
        )

-    def _generate(self, *,
+    def _generate(self, app_model: App,
                 workflow: Workflow,
                 user: Union[Account, EndUser],
                 invoke_from: InvokeFrom,
                 application_generate_entity: AdvancedChatAppGenerateEntity,
-                 conversation: Conversation | None = None,
+                 conversation: Conversation = None,
                 stream: bool = True) \
            -> Union[dict, Generator[dict, None, None]]:
        is_first_conversation = False
@ -216,7 +210,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
            # update conversation features
            conversation.override_model_configs = workflow.features
            db.session.commit()
-            # db.session.refresh(conversation)
+            db.session.refresh(conversation)

        # init queue manager
        queue_manager = MessageBasedAppQueueManager(
@ -228,69 +222,15 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
            message_id=message.id
        )

-        # Init conversation variables
-        stmt = select(ConversationVariable).where(
-            ConversationVariable.app_id == conversation.app_id, ConversationVariable.conversation_id == conversation.id
-        )
-        with Session(db.engine) as session:
-            conversation_variables = session.scalars(stmt).all()
-            if not conversation_variables:
-                # Create conversation variables if they don't exist.
-                conversation_variables = [
-                    ConversationVariable.from_variable(
-                        app_id=conversation.app_id, conversation_id=conversation.id, variable=variable
-                    )
-                    for variable in workflow.conversation_variables
-                ]
-                session.add_all(conversation_variables)
-            # Convert database entities to variables.
-            conversation_variables = [item.to_variable() for item in conversation_variables]
-
-            session.commit()
-
-            # Increment dialogue count.
-            conversation.dialogue_count += 1
-
-            conversation_id = conversation.id
-            conversation_dialogue_count = conversation.dialogue_count
-            db.session.commit()
-            db.session.refresh(conversation)
-
-        inputs = application_generate_entity.inputs
-        query = application_generate_entity.query
-        files = application_generate_entity.files
-
-        user_id = None
-        if application_generate_entity.invoke_from in [InvokeFrom.WEB_APP, InvokeFrom.SERVICE_API]:
-            end_user = db.session.query(EndUser).filter(EndUser.id == application_generate_entity.user_id).first()
-            if end_user:
-                user_id = end_user.session_id
-        else:
-            user_id = application_generate_entity.user_id
-
-        # Create a variable pool.
-        system_inputs = {
-            SystemVariable.QUERY: query,
-            SystemVariable.FILES: files,
-            SystemVariable.CONVERSATION_ID: conversation_id,
-            SystemVariable.USER_ID: user_id,
-            SystemVariable.DIALOGUE_COUNT: conversation_dialogue_count,
-        }
-        variable_pool = VariablePool(
-            system_variables=system_inputs,
-            user_inputs=inputs,
-            environment_variables=workflow.environment_variables,
-            conversation_variables=conversation_variables,
-        )
-        contexts.workflow_variable_pool.set(variable_pool)
-
        # new thread
        worker_thread = threading.Thread(target=self._generate_worker, kwargs={
            'flask_app': current_app._get_current_object(),
            'application_generate_entity': application_generate_entity,
            'queue_manager': queue_manager,
+            'conversation_id': conversation.id,
            'message_id': message.id,
-            'context': contextvars.copy_context(),
+            'user': user,
+            'context': contextvars.copy_context()
        })

        worker_thread.start()
@ -303,7 +243,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
            conversation=conversation,
            message=message,
            user=user,
-            stream=stream,
+            stream=stream
        )

        return AdvancedChatAppGenerateResponseConverter.convert(
@ -314,7 +254,9 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
    def _generate_worker(self, flask_app: Flask,
                         application_generate_entity: AdvancedChatAppGenerateEntity,
                         queue_manager: AppQueueManager,
+                         conversation_id: str,
                         message_id: str,
+                         user: Account,
                         context: contextvars.Context) -> None:
        """
        Generate worker in a new thread.
@ -341,7 +283,8 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
                        user_id=application_generate_entity.user_id
                    )
                else:
-                    # get message
+                    # get conversation and message
+                    conversation = self._get_conversation(conversation_id)
                    message = self._get_message(message_id)

                    # chatbot app
@ -349,6 +292,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
                    runner.run(
                        application_generate_entity=application_generate_entity,
                        queue_manager=queue_manager,
+                        conversation=conversation,
                        message=message
                    )
            except GenerateTaskStoppedException:
@ -371,17 +315,14 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
            finally:
                db.session.close()

-    def _handle_advanced_chat_response(
-        self,
-        *,
-        application_generate_entity: AdvancedChatAppGenerateEntity,
-        workflow: Workflow,
-        queue_manager: AppQueueManager,
-        conversation: Conversation,
-        message: Message,
-        user: Union[Account, EndUser],
-        stream: bool = False,
-    ) -> Union[ChatbotAppBlockingResponse, Generator[ChatbotAppStreamResponse, None, None]]:
+    def _handle_advanced_chat_response(self, application_generate_entity: AdvancedChatAppGenerateEntity,
+                                       workflow: Workflow,
+                                       queue_manager: AppQueueManager,
+                                       conversation: Conversation,
+                                       message: Message,
+                                       user: Union[Account, EndUser],
+                                       stream: bool = False) \
+            -> Union[ChatbotAppBlockingResponse, Generator[ChatbotAppStreamResponse, None, None]]:
        """
        Handle response.
        :param application_generate_entity: application generate entity
@ -401,7 +342,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
            conversation=conversation,
            message=message,
            user=user,
-            stream=stream,
+            stream=stream
        )

        try:
--- a/api/core/app/apps/advanced_chat/app_runner.py
+++ b/api/core/app/apps/advanced_chat/app_runner.py
@ -16,10 +16,12 @@ from core.app.entities.app_invoke_entities import (
 from core.app.entities.queue_entities import QueueAnnotationReplyEvent, QueueStopEvent, QueueTextChunkEvent
 from core.moderation.base import ModerationException
 from core.workflow.callbacks.base_workflow_callback import WorkflowCallback
+from core.workflow.entities.node_entities import SystemVariable
 from core.workflow.nodes.base_node import UserFrom
 from core.workflow.workflow_engine_manager import WorkflowEngineManager
 from extensions.ext_database import db
-from models import App, Message, Workflow
+from models.model import App, Conversation, EndUser, Message
+from models.workflow import Workflow

 logger = logging.getLogger(__name__)

@ -29,12 +31,10 @@ class AdvancedChatAppRunner(AppRunner):
    AdvancedChat Application Runner
    """

-    def run(
-        self,
-        application_generate_entity: AdvancedChatAppGenerateEntity,
-        queue_manager: AppQueueManager,
-        message: Message,
-    ) -> None:
+    def run(self, application_generate_entity: AdvancedChatAppGenerateEntity,
+            queue_manager: AppQueueManager,
+            conversation: Conversation,
+            message: Message) -> None:
        """
        Run application
        :param application_generate_entity: application generate entity
@ -48,43 +48,53 @@ class AdvancedChatAppRunner(AppRunner):

        app_record = db.session.query(App).filter(App.id == app_config.app_id).first()
        if not app_record:
-            raise ValueError('App not found')
+            raise ValueError("App not found")

        workflow = self.get_workflow(app_model=app_record, workflow_id=app_config.workflow_id)
        if not workflow:
-            raise ValueError('Workflow not initialized')
+            raise ValueError("Workflow not initialized")

        inputs = application_generate_entity.inputs
        query = application_generate_entity.query
+        files = application_generate_entity.files
+
+        user_id = None
+        if application_generate_entity.invoke_from in [InvokeFrom.WEB_APP, InvokeFrom.SERVICE_API]:
+            end_user = db.session.query(EndUser).filter(EndUser.id == application_generate_entity.user_id).first()
+            if end_user:
+                user_id = end_user.session_id
+        else:
+            user_id = application_generate_entity.user_id

        # moderation
        if self.handle_input_moderation(
-            queue_manager=queue_manager,
-            app_record=app_record,
-            app_generate_entity=application_generate_entity,
-            inputs=inputs,
-            query=query,
-            message_id=message.id,
+                queue_manager=queue_manager,
+                app_record=app_record,
+                app_generate_entity=application_generate_entity,
+                inputs=inputs,
+                query=query,
+                message_id=message.id
        ):
            return

        # annotation reply
        if self.handle_annotation_reply(
-            app_record=app_record,
-            message=message,
-            query=query,
-            queue_manager=queue_manager,
-            app_generate_entity=application_generate_entity,
+                app_record=app_record,
+                message=message,
+                query=query,
+                queue_manager=queue_manager,
+                app_generate_entity=application_generate_entity
        ):
            return

        db.session.close()

-        workflow_callbacks: list[WorkflowCallback] = [
-            WorkflowEventTriggerCallback(queue_manager=queue_manager, workflow=workflow)
-        ]
+        workflow_callbacks: list[WorkflowCallback] = [WorkflowEventTriggerCallback(
+            queue_manager=queue_manager,
+            workflow=workflow
+        )]

-        if bool(os.environ.get('DEBUG', 'False').lower() == 'true'):
+        if bool(os.environ.get("DEBUG", 'False').lower() == 'true'):
            workflow_callbacks.append(WorkflowLoggingCallback())

        # RUN WORKFLOW
@ -96,29 +106,43 @@ class AdvancedChatAppRunner(AppRunner):
            if application_generate_entity.invoke_from in [InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER]
            else UserFrom.END_USER,
            invoke_from=application_generate_entity.invoke_from,
+            user_inputs=inputs,
+            system_inputs={
+                SystemVariable.QUERY: query,
+                SystemVariable.FILES: files,
+                SystemVariable.CONVERSATION_ID: conversation.id,
+                SystemVariable.USER_ID: user_id
+            },
            callbacks=workflow_callbacks,
-            call_depth=application_generate_entity.call_depth,
+            call_depth=application_generate_entity.call_depth
        )

-    def single_iteration_run(
-        self, app_id: str, workflow_id: str, queue_manager: AppQueueManager, inputs: dict, node_id: str, user_id: str
-    ) -> None:
+    def single_iteration_run(self, app_id: str, workflow_id: str,
+                             queue_manager: AppQueueManager,
+                             inputs: dict, node_id: str, user_id: str) -> None:
        """
        Single iteration run
        """
-        app_record = db.session.query(App).filter(App.id == app_id).first()
+        app_record: App = db.session.query(App).filter(App.id == app_id).first()
        if not app_record:
-            raise ValueError('App not found')
-
+            raise ValueError("App not found")
+        
        workflow = self.get_workflow(app_model=app_record, workflow_id=workflow_id)
        if not workflow:
-            raise ValueError('Workflow not initialized')
-
-        workflow_callbacks = [WorkflowEventTriggerCallback(queue_manager=queue_manager, workflow=workflow)]
+            raise ValueError("Workflow not initialized")
+        
+        workflow_callbacks = [WorkflowEventTriggerCallback(
+            queue_manager=queue_manager,
+            workflow=workflow
+        )]

        workflow_engine_manager = WorkflowEngineManager()
        workflow_engine_manager.single_step_run_iteration_workflow_node(
-            workflow=workflow, node_id=node_id, user_id=user_id, user_inputs=inputs, callbacks=workflow_callbacks
+            workflow=workflow,
+            node_id=node_id,
+            user_id=user_id,
+            user_inputs=inputs,
+            callbacks=workflow_callbacks
        )

    def get_workflow(self, app_model: App, workflow_id: str) -> Optional[Workflow]:
@ -126,25 +150,22 @@ class AdvancedChatAppRunner(AppRunner):
        Get workflow
        """
        # fetch workflow by workflow_id
-        workflow = (
-            db.session.query(Workflow)
-            .filter(
-                Workflow.tenant_id == app_model.tenant_id, Workflow.app_id == app_model.id, Workflow.id == workflow_id
-            )
-            .first()
-        )
+        workflow = db.session.query(Workflow).filter(
+            Workflow.tenant_id == app_model.tenant_id,
+            Workflow.app_id == app_model.id,
+            Workflow.id == workflow_id
+        ).first()

        # return workflow
        return workflow

    def handle_input_moderation(
-        self,
-        queue_manager: AppQueueManager,
-        app_record: App,
-        app_generate_entity: AdvancedChatAppGenerateEntity,
-        inputs: Mapping[str, Any],
-        query: str,
-        message_id: str,
+            self, queue_manager: AppQueueManager,
+            app_record: App,
+            app_generate_entity: AdvancedChatAppGenerateEntity,
+            inputs: Mapping[str, Any],
+            query: str,
+            message_id: str
    ) -> bool:
        """
        Handle input moderation
@ -171,20 +192,17 @@ class AdvancedChatAppRunner(AppRunner):
                queue_manager=queue_manager,
                text=str(e),
                stream=app_generate_entity.stream,
-                stopped_by=QueueStopEvent.StopBy.INPUT_MODERATION,
+                stopped_by=QueueStopEvent.StopBy.INPUT_MODERATION
            )
            return True

        return False

-    def handle_annotation_reply(
-        self,
-        app_record: App,
-        message: Message,
-        query: str,
-        queue_manager: AppQueueManager,
-        app_generate_entity: AdvancedChatAppGenerateEntity,
-    ) -> bool:
+    def handle_annotation_reply(self, app_record: App,
+                                message: Message,
+                                query: str,
+                                queue_manager: AppQueueManager,
+                                app_generate_entity: AdvancedChatAppGenerateEntity) -> bool:
        """
        Handle annotation reply
        :param app_record: app record
@ -199,27 +217,29 @@ class AdvancedChatAppRunner(AppRunner):
            message=message,
            query=query,
            user_id=app_generate_entity.user_id,
-            invoke_from=app_generate_entity.invoke_from,
+            invoke_from=app_generate_entity.invoke_from
        )

        if annotation_reply:
            queue_manager.publish(
-                QueueAnnotationReplyEvent(message_annotation_id=annotation_reply.id), PublishFrom.APPLICATION_MANAGER
+                QueueAnnotationReplyEvent(message_annotation_id=annotation_reply.id),
+                PublishFrom.APPLICATION_MANAGER
            )

            self._stream_output(
                queue_manager=queue_manager,
                text=annotation_reply.content,
                stream=app_generate_entity.stream,
-                stopped_by=QueueStopEvent.StopBy.ANNOTATION_REPLY,
+                stopped_by=QueueStopEvent.StopBy.ANNOTATION_REPLY
            )
            return True

        return False

-    def _stream_output(
-        self, queue_manager: AppQueueManager, text: str, stream: bool, stopped_by: QueueStopEvent.StopBy
-    ) -> None:
+    def _stream_output(self, queue_manager: AppQueueManager,
+                       text: str,
+                       stream: bool,
+                       stopped_by: QueueStopEvent.StopBy) -> None:
        """
        Direct output
        :param queue_manager: application queue manager
@ -230,10 +250,21 @@ class AdvancedChatAppRunner(AppRunner):
        if stream:
            index = 0
            for token in text:
-                queue_manager.publish(QueueTextChunkEvent(text=token), PublishFrom.APPLICATION_MANAGER)
+                queue_manager.publish(
+                    QueueTextChunkEvent(
+                        text=token
+                    ), PublishFrom.APPLICATION_MANAGER
+                )
                index += 1
                time.sleep(0.01)
        else:
-            queue_manager.publish(QueueTextChunkEvent(text=text), PublishFrom.APPLICATION_MANAGER)
+            queue_manager.publish(
+                QueueTextChunkEvent(
+                    text=text
+                ), PublishFrom.APPLICATION_MANAGER
+            )

-        queue_manager.publish(QueueStopEvent(stopped_by=stopped_by), PublishFrom.APPLICATION_MANAGER)
+        queue_manager.publish(
+            QueueStopEvent(stopped_by=stopped_by),
+            PublishFrom.APPLICATION_MANAGER
+        )
--- a/api/core/app/apps/advanced_chat/generate_task_pipeline.py
+++ b/api/core/app/apps/advanced_chat/generate_task_pipeline.py
@ -4,7 +4,6 @@ import time
 from collections.abc import Generator
 from typing import Any, Optional, Union, cast

-import contexts
 from constants.tts_auto_play_timeout import TTS_AUTO_PLAY_TIMEOUT, TTS_AUTO_PLAY_YIELD_CPU_TIME
 from core.app.apps.advanced_chat.app_generator_tts_publisher import AppGeneratorTTSPublisher, AudioTrunk
 from core.app.apps.base_app_queue_manager import AppQueueManager, PublishFrom
@ -48,8 +47,7 @@ from core.file.file_obj import FileVar
 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.entities.node_entities import NodeType
-from core.workflow.enums import SystemVariable
+from core.workflow.entities.node_entities import NodeType, SystemVariable
 from core.workflow.nodes.answer.answer_node import AnswerNode
 from core.workflow.nodes.answer.entities import TextGenerateRouteChunk, VarGenerateRouteChunk
 from events.message_event import message_was_created
@ -73,7 +71,6 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
    _application_generate_entity: AdvancedChatAppGenerateEntity
    _workflow: Workflow
    _user: Union[Account, EndUser]
-    # Deprecated
    _workflow_system_variables: dict[SystemVariable, Any]
    _iteration_nested_relations: dict[str, list[str]]

@ -84,7 +81,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
            conversation: Conversation,
            message: Message,
            user: Union[Account, EndUser],
-            stream: bool,
+            stream: bool
    ) -> None:
        """
        Initialize AdvancedChatAppGenerateTaskPipeline.
@ -106,12 +103,11 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
        self._workflow = workflow
        self._conversation = conversation
        self._message = message
-        # Deprecated
        self._workflow_system_variables = {
            SystemVariable.QUERY: message.query,
            SystemVariable.FILES: application_generate_entity.files,
            SystemVariable.CONVERSATION_ID: conversation.id,
-            SystemVariable.USER_ID: user_id,
+            SystemVariable.USER_ID: user_id
        }

        self._task_state = AdvancedChatTaskState(
@ -248,10 +244,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
        :return:
        """
        for message in self._queue_manager.listen():
-            if (message.event
-                    and getattr(message.event, 'metadata', None)
-                    and message.event.metadata.get('is_answer_previous_node', False)
-                    and publisher):
+            if hasattr(message.event, 'metadata') and message.event.metadata.get('is_answer_previous_node', False) and publisher:
                publisher.publish(message=message)
            elif (hasattr(message.event, 'execution_metadata')
                  and message.event.execution_metadata
@ -616,9 +609,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc

                if route_chunk_node_id == 'sys':
                    # system variable
-                    value = contexts.workflow_variable_pool.get().get(value_selector)
-                    if value:
-                        value = value.text
+                    value = self._workflow_system_variables.get(SystemVariable.value_of(value_selector[1]))
                elif route_chunk_node_id in self._iteration_nested_relations:
                    # it's a iteration variable
                    if not self._iteration_state or route_chunk_node_id not in self._iteration_state.current_iterations:
--- a/api/core/app/apps/base_app_runner.py
+++ b/api/core/app/apps/base_app_runner.py
@ -1,6 +1,6 @@
 import time
 from collections.abc import Generator
-from typing import TYPE_CHECKING, Optional, Union
+from typing import Optional, Union

 from core.app.app_config.entities import ExternalDataVariableEntity, PromptTemplateEntity
 from core.app.apps.base_app_queue_manager import AppQueueManager, PublishFrom
@ -14,6 +14,7 @@ from core.app.entities.queue_entities import QueueAgentMessageEvent, QueueLLMChu
 from core.app.features.annotation_reply.annotation_reply import AnnotationReplyFeature
 from core.app.features.hosting_moderation.hosting_moderation import HostingModerationFeature
 from core.external_data_tool.external_data_fetch import ExternalDataFetch
+from core.file.file_obj import FileVar
 from core.memory.token_buffer_memory import TokenBufferMemory
 from core.model_manager import ModelInstance
 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
@ -26,16 +27,13 @@ from core.prompt.entities.advanced_prompt_entities import ChatModelMessage, Comp
 from core.prompt.simple_prompt_transform import ModelMode, SimplePromptTransform
 from models.model import App, AppMode, Message, MessageAnnotation

-if TYPE_CHECKING:
-    from core.file.file_obj import FileVar
-

 class AppRunner:
    def get_pre_calculate_rest_tokens(self, app_record: App,
                                      model_config: ModelConfigWithCredentialsEntity,
                                      prompt_template_entity: PromptTemplateEntity,
                                      inputs: dict[str, str],
-                                      files: list["FileVar"],
+                                      files: list[FileVar],
                                      query: Optional[str] = None) -> int:
        """
        Get pre calculate rest tokens
@ -128,7 +126,7 @@ class AppRunner:
                                 model_config: ModelConfigWithCredentialsEntity,
                                 prompt_template_entity: PromptTemplateEntity,
                                 inputs: dict[str, str],
-                                 files: list["FileVar"],
+                                 files: list[FileVar],
                                 query: Optional[str] = None,
                                 context: Optional[str] = None,
                                 memory: Optional[TokenBufferMemory] = None) \
@ -256,7 +254,6 @@ class AppRunner:
        :param invoke_result: invoke result
        :param queue_manager: application queue manager
        :param stream: stream
-        :param agent: agent
        :return:
        """
        if not stream:
@ -279,7 +276,6 @@ class AppRunner:
        Handle invoke result direct
        :param invoke_result: invoke result
        :param queue_manager: application queue manager
-        :param agent: agent
        :return:
        """
        queue_manager.publish(
@ -295,7 +291,6 @@ class AppRunner:
        Handle invoke result
        :param invoke_result: invoke result
        :param queue_manager: application queue manager
-        :param agent: agent
        :return:
        """
        model = None
@ -371,7 +366,7 @@ class AppRunner:
            message_id=message_id,
            trace_manager=app_generate_entity.trace_manager
        )
-
+    
    def check_hosting_moderation(self, application_generate_entity: EasyUIBasedAppGenerateEntity,
                                 queue_manager: AppQueueManager,
                                 prompt_messages: list[PromptMessage]) -> bool:
@ -423,7 +418,7 @@ class AppRunner:
            inputs=inputs,
            query=query
        )
-
+    
    def query_app_annotations_to_reply(self, app_record: App,
                                       message: Message,
                                       query: str,
--- a/api/core/app/apps/message_based_app_generator.py
+++ b/api/core/app/apps/message_based_app_generator.py
@ -138,7 +138,6 @@ class MessageBasedAppGenerator(BaseAppGenerator):
        """
        Initialize generate records
        :param application_generate_entity: application generate entity
-        :conversation conversation
        :return:
        """
        app_config = application_generate_entity.app_config
@ -259,7 +258,7 @@ class MessageBasedAppGenerator(BaseAppGenerator):

        return introduction

-    def _get_conversation(self, conversation_id: str):
+    def _get_conversation(self, conversation_id: str) -> Conversation:
        """
        Get conversation by conversation id
        :param conversation_id: conversation id
@ -271,9 +270,6 @@ class MessageBasedAppGenerator(BaseAppGenerator):
            .first()
        )

-        if not conversation:
-            raise ConversationNotExistsError()
-
        return conversation

    def _get_message(self, message_id: str) -> Message:
--- a/api/core/app/apps/workflow/app_runner.py
+++ b/api/core/app/apps/workflow/app_runner.py
@ -11,8 +11,7 @@ from core.app.entities.app_invoke_entities import (
    WorkflowAppGenerateEntity,
 )
 from core.workflow.callbacks.base_workflow_callback import WorkflowCallback
-from core.workflow.entities.variable_pool import VariablePool
-from core.workflow.enums import SystemVariable
+from core.workflow.entities.node_entities import SystemVariable
 from core.workflow.nodes.base_node import UserFrom
 from core.workflow.workflow_engine_manager import WorkflowEngineManager
 from extensions.ext_database import db
@ -27,7 +26,8 @@ class WorkflowAppRunner:
    Workflow Application Runner
    """

-    def run(self, application_generate_entity: WorkflowAppGenerateEntity, queue_manager: AppQueueManager) -> None:
+    def run(self, application_generate_entity: WorkflowAppGenerateEntity,
+            queue_manager: AppQueueManager) -> None:
        """
        Run application
        :param application_generate_entity: application generate entity
@ -47,36 +47,25 @@ class WorkflowAppRunner:

        app_record = db.session.query(App).filter(App.id == app_config.app_id).first()
        if not app_record:
-            raise ValueError('App not found')
+            raise ValueError("App not found")

        workflow = self.get_workflow(app_model=app_record, workflow_id=app_config.workflow_id)
        if not workflow:
-            raise ValueError('Workflow not initialized')
+            raise ValueError("Workflow not initialized")

        inputs = application_generate_entity.inputs
        files = application_generate_entity.files

        db.session.close()

-        workflow_callbacks: list[WorkflowCallback] = [
-            WorkflowEventTriggerCallback(queue_manager=queue_manager, workflow=workflow)
-        ]
+        workflow_callbacks: list[WorkflowCallback] = [WorkflowEventTriggerCallback(
+            queue_manager=queue_manager,
+            workflow=workflow
+        )]

-        if bool(os.environ.get('DEBUG', 'False').lower() == 'true'):
+        if bool(os.environ.get("DEBUG", 'False').lower() == 'true'):
            workflow_callbacks.append(WorkflowLoggingCallback())

-        # Create a variable pool.
-        system_inputs = {
-            SystemVariable.FILES: files,
-            SystemVariable.USER_ID: user_id,
-        }
-        variable_pool = VariablePool(
-            system_variables=system_inputs,
-            user_inputs=inputs,
-            environment_variables=workflow.environment_variables,
-            conversation_variables=[],
-        )
-
        # RUN WORKFLOW
        workflow_engine_manager = WorkflowEngineManager()
        workflow_engine_manager.run_workflow(
@ -86,33 +75,44 @@ class WorkflowAppRunner:
            if application_generate_entity.invoke_from in [InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER]
            else UserFrom.END_USER,
            invoke_from=application_generate_entity.invoke_from,
+            user_inputs=inputs,
+            system_inputs={
+                SystemVariable.FILES: files,
+                SystemVariable.USER_ID: user_id
+            },
            callbacks=workflow_callbacks,
-            call_depth=application_generate_entity.call_depth,
-            variable_pool=variable_pool,
+            call_depth=application_generate_entity.call_depth
        )

-    def single_iteration_run(
-        self, app_id: str, workflow_id: str, queue_manager: AppQueueManager, inputs: dict, node_id: str, user_id: str
-    ) -> None:
+    def single_iteration_run(self, app_id: str, workflow_id: str,
+                             queue_manager: AppQueueManager,
+                             inputs: dict, node_id: str, user_id: str) -> None:
        """
        Single iteration run
        """
-        app_record = db.session.query(App).filter(App.id == app_id).first()
+        app_record: App = db.session.query(App).filter(App.id == app_id).first()
        if not app_record:
-            raise ValueError('App not found')
-
+            raise ValueError("App not found")
+        
        if not app_record.workflow_id:
-            raise ValueError('Workflow not initialized')
+            raise ValueError("Workflow not initialized")

        workflow = self.get_workflow(app_model=app_record, workflow_id=workflow_id)
        if not workflow:
-            raise ValueError('Workflow not initialized')
-
-        workflow_callbacks = [WorkflowEventTriggerCallback(queue_manager=queue_manager, workflow=workflow)]
+            raise ValueError("Workflow not initialized")
+        
+        workflow_callbacks = [WorkflowEventTriggerCallback(
+            queue_manager=queue_manager,
+            workflow=workflow
+        )]

        workflow_engine_manager = WorkflowEngineManager()
        workflow_engine_manager.single_step_run_iteration_workflow_node(
-            workflow=workflow, node_id=node_id, user_id=user_id, user_inputs=inputs, callbacks=workflow_callbacks
+            workflow=workflow,
+            node_id=node_id,
+            user_id=user_id,
+            user_inputs=inputs,
+            callbacks=workflow_callbacks
        )

    def get_workflow(self, app_model: App, workflow_id: str) -> Optional[Workflow]:
@ -120,13 +120,11 @@ class WorkflowAppRunner:
        Get workflow
        """
        # fetch workflow by workflow_id
-        workflow = (
-            db.session.query(Workflow)
-            .filter(
-                Workflow.tenant_id == app_model.tenant_id, Workflow.app_id == app_model.id, Workflow.id == workflow_id
-            )
-            .first()
-        )
+        workflow = db.session.query(Workflow).filter(
+            Workflow.tenant_id == app_model.tenant_id,
+            Workflow.app_id == app_model.id,
+            Workflow.id == workflow_id
+        ).first()

        # return workflow
        return workflow
--- a/api/core/app/apps/workflow/generate_task_pipeline.py
+++ b/api/core/app/apps/workflow/generate_task_pipeline.py
@ -42,8 +42,7 @@ from core.app.entities.task_entities import (
 from core.app.task_pipeline.based_generate_task_pipeline import BasedGenerateTaskPipeline
 from core.app.task_pipeline.workflow_cycle_manage import WorkflowCycleManage
 from core.ops.ops_trace_manager import TraceQueueManager
-from core.workflow.entities.node_entities import NodeType
-from core.workflow.enums import SystemVariable
+from core.workflow.entities.node_entities import NodeType, SystemVariable
 from core.workflow.nodes.end.end_node import EndNode
 from extensions.ext_database import db
 from models.account import Account
@ -520,7 +519,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
        """
        nodes = graph.get('nodes')

-        iteration_ids = [node.get('id') for node in nodes
+        iteration_ids = [node.get('id') for node in nodes 
                         if node.get('data', {}).get('type') in [
                             NodeType.ITERATION.value,
                             NodeType.LOOP.value,
@ -531,3 +530,4 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
                node.get('id') for node in nodes if node.get('data', {}).get('iteration_id') == iteration_id
            ] for iteration_id in iteration_ids
        }
+    
--- a/api/core/app/entities/app_invoke_entities.py
+++ b/api/core/app/entities/app_invoke_entities.py
@ -166,4 +166,4 @@ class WorkflowAppGenerateEntity(AppGenerateEntity):
        node_id: str
        inputs: dict

-    single_iteration_run: Optional[SingleIterationRunEntity] = None
+    single_iteration_run: Optional[SingleIterationRunEntity] = None
--- a/api/core/app/segments/init.py
+++ b/api/core/app/segments/init.py
@ -1,7 +1,7 @@
 from .segment_group import SegmentGroup
 from .segments import (
    ArrayAnySegment,
-    ArraySegment,
+    FileSegment,
    FloatSegment,
    IntegerSegment,
    NoneSegment,
@ -12,9 +12,11 @@ from .segments import (
 from .types import SegmentType
 from .variables import (
    ArrayAnyVariable,
+    ArrayFileVariable,
    ArrayNumberVariable,
    ArrayObjectVariable,
    ArrayStringVariable,
+    FileVariable,
    FloatVariable,
    IntegerVariable,
    NoneVariable,
@ -29,6 +31,7 @@ __all__ = [
    'FloatVariable',
    'ObjectVariable',
    'SecretVariable',
+    'FileVariable',
    'StringVariable',
    'ArrayAnyVariable',
    'Variable',
@ -41,9 +44,10 @@ __all__ = [
    'FloatSegment',
    'ObjectSegment',
    'ArrayAnySegment',
+    'FileSegment',
    'StringSegment',
    'ArrayStringVariable',
    'ArrayNumberVariable',
    'ArrayObjectVariable',
-    'ArraySegment',
+    'ArrayFileVariable',
 ]
--- a/api/core/app/segments/exc.py
+++ b/api/core/app/segments/exc.py
@ -1,2 +0,0 @@
-class VariableError(Exception):
-    pass
--- a/api/core/app/segments/factory.py
+++ b/api/core/app/segments/factory.py
@ -1,11 +1,11 @@
 from collections.abc import Mapping
 from typing import Any

-from configs import dify_config
+from core.file.file_obj import FileVar

-from .exc import VariableError
 from .segments import (
    ArrayAnySegment,
+    FileSegment,
    FloatSegment,
    IntegerSegment,
    NoneSegment,
@ -15,9 +15,11 @@ from .segments import (
 )
 from .types import SegmentType
 from .variables import (
+    ArrayFileVariable,
    ArrayNumberVariable,
    ArrayObjectVariable,
    ArrayStringVariable,
+    FileVariable,
    FloatVariable,
    IntegerVariable,
    ObjectVariable,
@ -27,37 +29,39 @@ from .variables import (
 )


-def build_variable_from_mapping(mapping: Mapping[str, Any], /) -> Variable:
-    if (value_type := mapping.get('value_type')) is None:
-        raise VariableError('missing value type')
-    if not mapping.get('name'):
-        raise VariableError('missing name')
-    if (value := mapping.get('value')) is None:
-        raise VariableError('missing value')
+def build_variable_from_mapping(m: Mapping[str, Any], /) -> Variable:
+    if (value_type := m.get('value_type')) is None:
+        raise ValueError('missing value type')
+    if not m.get('name'):
+        raise ValueError('missing name')
+    if (value := m.get('value')) is None:
+        raise ValueError('missing value')
    match value_type:
        case SegmentType.STRING:
-            result = StringVariable.model_validate(mapping)
+            return StringVariable.model_validate(m)
        case SegmentType.SECRET:
-            result = SecretVariable.model_validate(mapping)
+            return SecretVariable.model_validate(m)
        case SegmentType.NUMBER if isinstance(value, int):
-            result = IntegerVariable.model_validate(mapping)
+            return IntegerVariable.model_validate(m)
        case SegmentType.NUMBER if isinstance(value, float):
-            result = FloatVariable.model_validate(mapping)
+            return FloatVariable.model_validate(m)
        case SegmentType.NUMBER if not isinstance(value, float | int):
-            raise VariableError(f'invalid number value {value}')
+            raise ValueError(f'invalid number value {value}')
+        case SegmentType.FILE:
+            return FileVariable.model_validate(m)
        case SegmentType.OBJECT if isinstance(value, dict):
-            result = ObjectVariable.model_validate(mapping)
+            return ObjectVariable.model_validate(
+                {**m, 'value': {k: build_variable_from_mapping(v) for k, v in value.items()}}
+            )
        case SegmentType.ARRAY_STRING if isinstance(value, list):
-            result = ArrayStringVariable.model_validate(mapping)
+            return ArrayStringVariable.model_validate({**m, 'value': [build_variable_from_mapping(v) for v in value]})
        case SegmentType.ARRAY_NUMBER if isinstance(value, list):
-            result = ArrayNumberVariable.model_validate(mapping)
+            return ArrayNumberVariable.model_validate({**m, 'value': [build_variable_from_mapping(v) for v in value]})
        case SegmentType.ARRAY_OBJECT if isinstance(value, list):
-            result = ArrayObjectVariable.model_validate(mapping)
-        case _:
-            raise VariableError(f'not supported value type {value_type}')
-    if result.size > dify_config.MAX_VARIABLE_SIZE:
-        raise VariableError(f'variable size {result.size} exceeds limit {dify_config.MAX_VARIABLE_SIZE}')
-    return result
+            return ArrayObjectVariable.model_validate({**m, 'value': [build_variable_from_mapping(v) for v in value]})
+        case SegmentType.ARRAY_FILE if isinstance(value, list):
+            return ArrayFileVariable.model_validate({**m, 'value': [build_variable_from_mapping(v) for v in value]})
+    raise ValueError(f'not supported value type {value_type}')


 def build_segment(value: Any, /) -> Segment:
@ -70,7 +74,13 @@ def build_segment(value: Any, /) -> Segment:
    if isinstance(value, float):
        return FloatSegment(value=value)
    if isinstance(value, dict):
-        return ObjectSegment(value=value)
+        # TODO: Limit the depth of the object
+        obj = {k: build_segment(v) for k, v in value.items()}
+        return ObjectSegment(value=obj)
    if isinstance(value, list):
-        return ArrayAnySegment(value=value)
+        # TODO: Limit the depth of the array
+        elements = [build_segment(v) for v in value]
+        return ArrayAnySegment(value=elements)
+    if isinstance(value, FileVar):
+        return FileSegment(value=value)
    raise ValueError(f'not supported value {value}')
--- a/api/core/app/segments/segments.py
+++ b/api/core/app/segments/segments.py
@ -1,10 +1,11 @@
 import json
-import sys
 from collections.abc import Mapping, Sequence
 from typing import Any

 from pydantic import BaseModel, ConfigDict, field_validator

+from core.file.file_obj import FileVar
+
 from .types import SegmentType


@ -36,10 +37,6 @@ class Segment(BaseModel):
    def markdown(self) -> str:
        return str(self.value)

-    @property
-    def size(self) -> int:
-        return sys.getsizeof(self.value)
-
    def to_object(self) -> Any:
        return self.value

@ -76,54 +73,68 @@ class IntegerSegment(Segment):
    value: int


+class FileSegment(Segment):
+    value_type: SegmentType = SegmentType.FILE
+    # TODO: embed FileVar in this model.
+    value: FileVar

+    @property
+    def markdown(self) -> str:
+        return self.value.to_markdown()


 class ObjectSegment(Segment):
    value_type: SegmentType = SegmentType.OBJECT
-    value: Mapping[str, Any]
+    value: Mapping[str, Segment]

    @property
    def text(self) -> str:
+        # TODO: Process variables.
        return json.dumps(self.model_dump()['value'], ensure_ascii=False)

    @property
    def log(self) -> str:
+        # TODO: Process variables.
        return json.dumps(self.model_dump()['value'], ensure_ascii=False, indent=2)

    @property
    def markdown(self) -> str:
+        # TODO: Use markdown code block
        return json.dumps(self.model_dump()['value'], ensure_ascii=False, indent=2)

+    def to_object(self):
+        return {k: v.to_object() for k, v in self.value.items()}
+

 class ArraySegment(Segment):
    @property
    def markdown(self) -> str:
-        items = []
-        for item in self.value:
-            if hasattr(item, 'to_markdown'):
-                items.append(item.to_markdown())
-            else:
-                items.append(str(item))
-        return '\n'.join(items)
+        return '\n'.join(['- ' + item.markdown for item in self.value])
+
+    def to_object(self):
+        return [v.to_object() for v in self.value]


 class ArrayAnySegment(ArraySegment):
    value_type: SegmentType = SegmentType.ARRAY_ANY
-    value: Sequence[Any]
+    value: Sequence[Segment]


 class ArrayStringSegment(ArraySegment):
    value_type: SegmentType = SegmentType.ARRAY_STRING
-    value: Sequence[str]
+    value: Sequence[StringSegment]


 class ArrayNumberSegment(ArraySegment):
    value_type: SegmentType = SegmentType.ARRAY_NUMBER
-    value: Sequence[float | int]
+    value: Sequence[FloatSegment | IntegerSegment]


 class ArrayObjectSegment(ArraySegment):
    value_type: SegmentType = SegmentType.ARRAY_OBJECT
-    value: Sequence[Mapping[str, Any]]
+    value: Sequence[ObjectSegment]

+
+class ArrayFileSegment(ArraySegment):
+    value_type: SegmentType = SegmentType.ARRAY_FILE
+    value: Sequence[FileSegment]
--- a/api/core/app/segments/types.py
+++ b/api/core/app/segments/types.py
@ -10,6 +10,8 @@ class SegmentType(str, Enum):
    ARRAY_STRING = 'array[string]'
    ARRAY_NUMBER = 'array[number]'
    ARRAY_OBJECT = 'array[object]'
+    ARRAY_FILE = 'array[file]'
    OBJECT = 'object'
+    FILE = 'file'

    GROUP = 'group'
--- a/api/core/app/segments/variables.py
+++ b/api/core/app/segments/variables.py
@ -4,9 +4,11 @@ from core.helper import encrypter

 from .segments import (
    ArrayAnySegment,
+    ArrayFileSegment,
    ArrayNumberSegment,
    ArrayObjectSegment,
    ArrayStringSegment,
+    FileSegment,
    FloatSegment,
    IntegerSegment,
    NoneSegment,
@ -42,6 +44,10 @@ class IntegerVariable(IntegerSegment, Variable):
    pass


+class FileVariable(FileSegment, Variable):
+    pass
+
+
 class ObjectVariable(ObjectSegment, Variable):
    pass

@ -62,6 +68,9 @@ class ArrayObjectVariable(ArrayObjectSegment, Variable):
    pass


+class ArrayFileVariable(ArrayFileSegment, Variable):
+    pass
+

 class SecretVariable(StringVariable):
    value_type: SegmentType = SegmentType.SECRET
--- a/api/core/app/task_pipeline/easy_ui_based_generate_task_pipeline.py
+++ b/api/core/app/task_pipeline/easy_ui_based_generate_task_pipeline.py
@ -48,8 +48,7 @@ from core.model_runtime.entities.message_entities import (
 )
 from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
 from core.model_runtime.utils.encoders import jsonable_encoder
-from core.ops.entities.trace_entity import TraceTaskName
-from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
+from core.ops.ops_trace_manager import TraceQueueManager, TraceTask, TraceTaskName
 from core.prompt.utils.prompt_message_util import PromptMessageUtil
 from core.prompt.utils.prompt_template_parser import PromptTemplateParser
 from events.message_event import message_was_created
--- a/api/core/app/task_pipeline/workflow_cycle_manage.py
+++ b/api/core/app/task_pipeline/workflow_cycle_manage.py
@ -22,8 +22,7 @@ from core.app.entities.task_entities import (
 from core.app.task_pipeline.workflow_iteration_cycle_manage import WorkflowIterationCycleManage
 from core.file.file_obj import FileVar
 from core.model_runtime.utils.encoders import jsonable_encoder
-from core.ops.entities.trace_entity import TraceTaskName
-from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
+from core.ops.ops_trace_manager import TraceQueueManager, TraceTask, TraceTaskName
 from core.tools.tool_manager import ToolManager
 from core.workflow.entities.node_entities import NodeRunMetadataKey, NodeType
 from core.workflow.nodes.tool.entities import ToolNodeData
@ -41,7 +40,6 @@ from models.workflow import (
    WorkflowRunStatus,
    WorkflowRunTriggeredFrom,
 )
-from services.workflow_service import WorkflowService


 class WorkflowCycleManage(WorkflowIterationCycleManage):
@ -99,6 +97,7 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):

    def _workflow_run_success(
        self, workflow_run: WorkflowRun,
+        start_at: float,
        total_tokens: int,
        total_steps: int,
        outputs: Optional[str] = None,
@ -108,6 +107,7 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):
        """
        Workflow run success
        :param workflow_run: workflow run
+        :param start_at: start time
        :param total_tokens: total tokens
        :param total_steps: total steps
        :param outputs: outputs
@ -116,7 +116,7 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):
        """
        workflow_run.status = WorkflowRunStatus.SUCCEEDED.value
        workflow_run.outputs = outputs
-        workflow_run.elapsed_time = WorkflowService.get_elapsed_time(workflow_run_id=workflow_run.id)
+        workflow_run.elapsed_time = time.perf_counter() - start_at
        workflow_run.total_tokens = total_tokens
        workflow_run.total_steps = total_steps
        workflow_run.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
@ -139,6 +139,7 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):

    def _workflow_run_failed(
        self, workflow_run: WorkflowRun,
+        start_at: float,
        total_tokens: int,
        total_steps: int,
        status: WorkflowRunStatus,
@ -149,6 +150,7 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):
        """
        Workflow run failed
        :param workflow_run: workflow run
+        :param start_at: start time
        :param total_tokens: total tokens
        :param total_steps: total steps
        :param status: status
@ -157,7 +159,7 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):
        """
        workflow_run.status = status.value
        workflow_run.error = error
-        workflow_run.elapsed_time = WorkflowService.get_elapsed_time(workflow_run_id=workflow_run.id)
+        workflow_run.elapsed_time = time.perf_counter() - start_at
        workflow_run.total_tokens = total_tokens
        workflow_run.total_steps = total_steps
        workflow_run.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
@ -540,6 +542,7 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):
        if isinstance(event, QueueStopEvent):
            workflow_run = self._workflow_run_failed(
                workflow_run=workflow_run,
+                start_at=self._task_state.start_at,
                total_tokens=self._task_state.total_tokens,
                total_steps=self._task_state.total_steps,
                status=WorkflowRunStatus.STOPPED,
@ -562,6 +565,7 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):
        elif isinstance(event, QueueWorkflowFailedEvent):
            workflow_run = self._workflow_run_failed(
                workflow_run=workflow_run,
+                start_at=self._task_state.start_at,
                total_tokens=self._task_state.total_tokens,
                total_steps=self._task_state.total_steps,
                status=WorkflowRunStatus.FAILED,
@ -579,6 +583,7 @@ class WorkflowCycleManage(WorkflowIterationCycleManage):

            workflow_run = self._workflow_run_success(
                workflow_run=workflow_run,
+                start_at=self._task_state.start_at,
                total_tokens=self._task_state.total_tokens,
                total_steps=self._task_state.total_steps,
                outputs=outputs,
--- a/api/core/app/task_pipeline/workflow_cycle_state_manager.py
+++ b/api/core/app/task_pipeline/workflow_cycle_state_manager.py
@ -2,7 +2,7 @@ from typing import Any, Union

 from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity, WorkflowAppGenerateEntity
 from core.app.entities.task_entities import AdvancedChatTaskState, WorkflowTaskState
-from core.workflow.enums import SystemVariable
+from core.workflow.entities.node_entities import SystemVariable
 from models.account import Account
 from models.model import EndUser
 from models.workflow import Workflow
@ -13,4 +13,4 @@ class WorkflowCycleStateManager:
    _workflow: Workflow
    _user: Union[Account, EndUser]
    _task_state: Union[AdvancedChatTaskState, WorkflowTaskState]
-    _workflow_system_variables: dict[SystemVariable, Any]
+    _workflow_system_variables: dict[SystemVariable, Any]
--- a/api/core/callback_handler/agent_tool_callback_handler.py
+++ b/api/core/callback_handler/agent_tool_callback_handler.py
@ -4,8 +4,7 @@ from typing import Any, Optional, TextIO, Union

 from pydantic import BaseModel

-from core.ops.entities.trace_entity import TraceTaskName
-from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
+from core.ops.ops_trace_manager import TraceQueueManager, TraceTask, TraceTaskName
 from core.tools.entities.tool_entities import ToolInvokeMessage

 _TEXT_COLOR_MAPPING = {
--- a/api/core/entities/provider_configuration.py
+++ b/api/core/entities/provider_configuration.py
@ -8,7 +8,6 @@ from typing import Optional

 from pydantic import BaseModel, ConfigDict

-from constants import HIDDEN_VALUE
 from core.entities.model_entities import ModelStatus, ModelWithProviderEntity, SimpleModelProviderEntity
 from core.entities.provider_entities import (
    CustomConfiguration,
@ -203,7 +202,7 @@ class ProviderConfiguration(BaseModel):
            for key, value in credentials.items():
                if key in provider_credential_secret_variables:
                    # if send [__HIDDEN__] in secret input, it will be same as original value
-                    if value == HIDDEN_VALUE and key in original_credentials:
+                    if value == '[__HIDDEN__]' and key in original_credentials:
                        credentials[key] = encrypter.decrypt_token(self.tenant_id, original_credentials[key])

        credentials = model_provider_factory.provider_credentials_validate(
@ -346,7 +345,7 @@ class ProviderConfiguration(BaseModel):
            for key, value in credentials.items():
                if key in provider_credential_secret_variables:
                    # if send [__HIDDEN__] in secret input, it will be same as original value
-                    if value == HIDDEN_VALUE and key in original_credentials:
+                    if value == '[__HIDDEN__]' and key in original_credentials:
                        credentials[key] = encrypter.decrypt_token(self.tenant_id, original_credentials[key])

        credentials = model_provider_factory.model_credentials_validate(
--- a/api/core/file/file_obj.py
+++ b/api/core/file/file_obj.py
@ -1,19 +1,14 @@
 import enum
-from typing import Any, Optional
+from typing import Optional

 from pydantic import BaseModel

+from core.app.app_config.entities import FileExtraConfig
 from core.file.tool_file_parser import ToolFileParser
 from core.file.upload_file_parser import UploadFileParser
 from core.model_runtime.entities.message_entities import ImagePromptMessageContent
 from extensions.ext_database import db
-
-
-class FileExtraConfig(BaseModel):
-    """
-    File Upload Entity.
-    """
-    image_config: Optional[dict[str, Any]] = None
+from models.model import UploadFile


 class FileType(enum.Enum):
@ -119,7 +114,6 @@ class FileVar(BaseModel):
            )

    def _get_data(self, force_url: bool = False) -> Optional[str]:
-        from models.model import UploadFile
        if self.type == FileType.IMAGE:
            if self.transfer_method == FileTransferMethod.REMOTE_URL:
                return self.url
--- a/api/core/file/message_file_parser.py
+++ b/api/core/file/message_file_parser.py
@ -1,11 +1,10 @@
-import re
 from collections.abc import Mapping, Sequence
 from typing import Any, Union
-from urllib.parse import parse_qs, urlparse

 import requests

-from core.file.file_obj import FileBelongsTo, FileExtraConfig, FileTransferMethod, FileType, FileVar
+from core.app.app_config.entities import FileExtraConfig
+from core.file.file_obj import FileBelongsTo, FileTransferMethod, FileType, FileVar
 from extensions.ext_database import db
 from models.account import Account
 from models.model import EndUser, MessageFile, UploadFile
@ -99,7 +98,7 @@ class MessageFileParser:
        # return all file objs
        return new_files

-    def transform_message_files(self, files: list[MessageFile], file_extra_config: FileExtraConfig):
+    def transform_message_files(self, files: list[MessageFile], file_extra_config: FileExtraConfig) -> list[FileVar]:
        """
        transform message files

@ -144,7 +143,7 @@ class MessageFileParser:

        return type_file_objs

-    def _to_file_obj(self, file: Union[dict, MessageFile], file_extra_config: FileExtraConfig):
+    def _to_file_obj(self, file: Union[dict, MessageFile], file_extra_config: FileExtraConfig) -> FileVar:
        """
        transform file to file obj

@ -187,30 +186,6 @@ class MessageFileParser:
                "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
            }

-            def is_s3_presigned_url(url):
-                try:
-                    parsed_url = urlparse(url)
-                    if 'amazonaws.com' not in parsed_url.netloc:
-                        return False
-                    query_params = parse_qs(parsed_url.query)
-                    required_params = ['Signature', 'Expires']
-                    for param in required_params:
-                        if param not in query_params:
-                            return False
-                    if not query_params['Expires'][0].isdigit():
-                        return False
-                    signature = query_params['Signature'][0]
-                    if not re.match(r'^[A-Za-z0-9+/]+={0,2}$', signature):
-                        return False
-                    return True
-                except Exception:
-                    return False
-
-            if is_s3_presigned_url(url):
-                response = requests.get(url, headers=headers, allow_redirects=True)
-                if response.status_code in {200, 304}:
-                    return True, ""
-
            response = requests.head(url, headers=headers, allow_redirects=True)
            if response.status_code in {200, 304}:
                return True, ""
--- a/api/core/helper/encrypter.py
+++ b/api/core/helper/encrypter.py
@ -2,6 +2,7 @@ import base64

 from extensions.ext_database import db
 from libs import rsa
+from models.account import Tenant


 def obfuscated_token(token: str):
@ -13,7 +14,6 @@ def obfuscated_token(token: str):


 def encrypt_token(tenant_id: str, token: str):
-    from models.account import Tenant
    if not (tenant := db.session.query(Tenant).filter(Tenant.id == tenant_id).first()):
        raise ValueError(f'Tenant with id {tenant_id} not found')
    encrypted_token = rsa.encrypt(token, tenant.encrypt_public_key)
--- a/api/core/llm_generator/llm_generator.py
+++ b/api/core/llm_generator/llm_generator.py
@ -14,8 +14,7 @@ from core.model_manager import ModelManager
 from core.model_runtime.entities.message_entities import SystemPromptMessage, UserPromptMessage
 from core.model_runtime.entities.model_entities import ModelType
 from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
-from core.ops.entities.trace_entity import TraceTaskName
-from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
+from core.ops.ops_trace_manager import TraceQueueManager, TraceTask, TraceTaskName
 from core.ops.utils import measure_time
 from core.prompt.utils.prompt_template_parser import PromptTemplateParser

--- a/api/core/model_manager.py
+++ b/api/core/model_manager.py
@ -271,8 +271,9 @@ class ModelInstance:

        :param content_text: text content to be translated
        :param tenant_id: user tenant id
-        :param voice: model timbre
        :param user: unique user id
+        :param voice: model timbre
+        :param streaming: output is streaming
        :return: text for given audio file
        """
        if not isinstance(self.model_type_instance, TTSModel):
@ -400,10 +401,6 @@ class LBModelManager:
                 managed_credentials: Optional[dict] = None) -> None:
        """
        Load balancing model manager
-        :param tenant_id: tenant_id
-        :param provider: provider
-        :param model_type: model_type
-        :param model: model name
        :param load_balancing_configs: all load balancing configurations
        :param managed_credentials: credentials if load balancing configuration name is __inherit__
        """
--- a/api/core/model_runtime/entities/defaults.py
+++ b/api/core/model_runtime/entities/defaults.py
@ -1,3 +1,4 @@
+
 from core.model_runtime.entities.model_entities import DefaultParameterName

 PARAMETER_RULE_TEMPLATE: dict[DefaultParameterName, dict] = {
@ -93,16 +94,5 @@ PARAMETER_RULE_TEMPLATE: dict[DefaultParameterName, dict] = {
        },
        'required': False,
        'options': ['JSON', 'XML'],
-    },
-    DefaultParameterName.JSON_SCHEMA: {
-        'label': {
-            'en_US': 'JSON Schema',
-        },
-        'type': 'text',
-        'help': {
-            'en_US': 'Set a response json schema will ensure LLM to adhere it.',
-            'zh_Hans': '设置返回的json schema，llm将按照它返回',
-        },
-        'required': False,
-    },
-}
+    }
+}
--- a/api/core/model_runtime/entities/model_entities.py
+++ b/api/core/model_runtime/entities/model_entities.py
@ -95,7 +95,6 @@ class DefaultParameterName(Enum):
    FREQUENCY_PENALTY = "frequency_penalty"
    MAX_TOKENS = "max_tokens"
    RESPONSE_FORMAT = "response_format"
-    JSON_SCHEMA = "json_schema"

    @classmethod
    def value_of(cls, value: Any) -> 'DefaultParameterName':
@ -119,7 +118,6 @@ class ParameterType(Enum):
    INT = "int"
    STRING = "string"
    BOOLEAN = "boolean"
-    TEXT = "text"


 class ModelPropertyKey(Enum):
--- a/api/core/model_runtime/model_providers/__base/large_language_model.py
+++ b/api/core/model_runtime/model_providers/__base/large_language_model.py
@ -185,7 +185,7 @@ if you are not sure about the structure.
                stream=stream,
                user=user
            )
-
+        
        model_parameters.pop("response_format")
        stop = stop or []
        stop.extend(["\n```", "```\n"])
@ -249,10 +249,10 @@ if you are not sure about the structure.
                    prompt_messages=prompt_messages,
                    input_generator=new_generator()
                )
-
+            
        return response

-    def _code_block_mode_stream_processor(self, model: str, prompt_messages: list[PromptMessage],
+    def _code_block_mode_stream_processor(self, model: str, prompt_messages: list[PromptMessage], 
                                          input_generator: Generator[LLMResultChunk, None, None]
                                        ) -> Generator[LLMResultChunk, None, None]:
        """
@ -310,7 +310,7 @@ if you are not sure about the structure.
                    )
                )

-    def _code_block_mode_stream_processor_with_backtick(self, model: str, prompt_messages: list,
+    def _code_block_mode_stream_processor_with_backtick(self, model: str, prompt_messages: list, 
                                        input_generator:  Generator[LLMResultChunk, None, None]) \
                                    ->  Generator[LLMResultChunk, None, None]:
        """
@ -470,7 +470,7 @@ if you are not sure about the structure.
        :return: full response or stream response chunk generator result
        """
        raise NotImplementedError
-
+    
    @abstractmethod
    def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
                       tools: Optional[list[PromptMessageTool]] = None) -> int:
@ -792,13 +792,6 @@ if you are not sure about the structure.
                if not isinstance(parameter_value, str):
                    raise ValueError(f"Model Parameter {parameter_name} should be string.")

-                # validate options
-                if parameter_rule.options and parameter_value not in parameter_rule.options:
-                    raise ValueError(f"Model Parameter {parameter_name} should be one of {parameter_rule.options}.")
-            elif parameter_rule.type == ParameterType.TEXT:
-                if not isinstance(parameter_value, str):
-                    raise ValueError(f"Model Parameter {parameter_name} should be text.")
-
                # validate options
                if parameter_rule.options and parameter_value not in parameter_rule.options:
                    raise ValueError(f"Model Parameter {parameter_name} should be one of {parameter_rule.options}.")
--- a/api/core/model_runtime/model_providers/_position.yaml
+++ b/api/core/model_runtime/model_providers/_position.yaml
@ -36,4 +36,3 @@
 - hunyuan
 - siliconflow
 - perfxcloud
- zhinao
--- a/api/core/model_runtime/model_providers/bedrock/llm/llm.py
+++ b/api/core/model_runtime/model_providers/bedrock/llm/llm.py
@ -379,12 +379,8 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
                        if not message_content.data.startswith("data:"):
                            # fetch image data from url
                            try:
-                                url = message_content.data
-                                image_content = requests.get(url).content
-                                if '?' in url:
-                                    url = url.split('?')[0]
-                                mime_type, _ = mimetypes.guess_type(url)
-                                base64_data = base64.b64encode(image_content).decode('utf-8')
+                                image_content = requests.get(message_content.data).content
+                                mime_type, _ = mimetypes.guess_type(message_content.data)
                            except Exception as ex:
                                raise ValueError(f"Failed to fetch image data from url {message_content.data}, {ex}")
                        else:
--- a/api/core/model_runtime/model_providers/huggingface_tei/init.py
+++ b/api/core/model_runtime/model_providers/huggingface_tei/init.py
--- a/api/core/model_runtime/model_providers/huggingface_tei/huggingface_tei.py
+++ b/api/core/model_runtime/model_providers/huggingface_tei/huggingface_tei.py
@ -1,11 +0,0 @@
-import logging
-
-from core.model_runtime.model_providers.__base.model_provider import ModelProvider
-
-logger = logging.getLogger(__name__)
-
-
-class HuggingfaceTeiProvider(ModelProvider):
-
-    def validate_provider_credentials(self, credentials: dict) -> None:
-        pass
--- a/api/core/model_runtime/model_providers/huggingface_tei/huggingface_tei.yaml
+++ b/api/core/model_runtime/model_providers/huggingface_tei/huggingface_tei.yaml
@ -1,36 +0,0 @@
-provider: huggingface_tei
-label:
-  en_US: Text Embedding Inference
-description:
-  en_US: A blazing fast inference solution for text embeddings models.
-  zh_Hans: 用于文本嵌入模型的超快速推理解决方案。
-background: "#FFF8DC"
-help:
-  title:
-    en_US: How to deploy Text Embedding Inference
-    zh_Hans: 如何部署 Text Embedding Inference
-  url:
-    en_US: https://github.com/huggingface/text-embeddings-inference
-supported_model_types:
-  - text-embedding
-  - rerank
-configurate_methods:
-  - customizable-model
-model_credential_schema:
-  model:
-    label:
-      en_US: Model Name
-      zh_Hans: 模型名称
-    placeholder:
-      en_US: Enter your model name
-      zh_Hans: 输入模型名称
-  credential_form_schemas:
-    - variable: server_url
-      label:
-        zh_Hans: 服务器URL
-        en_US: Server url
-      type: secret-input
-      required: true
-      placeholder:
-        zh_Hans: 在此输入Text Embedding Inference的服务器地址，如 http://192.168.1.100:8080
-        en_US: Enter the url of your Text Embedding Inference, e.g. http://192.168.1.100:8080
--- a/api/core/model_runtime/model_providers/huggingface_tei/rerank/init.py
+++ b/api/core/model_runtime/model_providers/huggingface_tei/rerank/init.py
--- a/api/core/model_runtime/model_providers/huggingface_tei/rerank/rerank.py
+++ b/api/core/model_runtime/model_providers/huggingface_tei/rerank/rerank.py
@ -1,137 +0,0 @@
-from typing import Optional
-
-import httpx
-
-from core.model_runtime.entities.common_entities import I18nObject
-from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType
-from core.model_runtime.entities.rerank_entities import RerankDocument, RerankResult
-from core.model_runtime.errors.invoke import (
-    InvokeAuthorizationError,
-    InvokeBadRequestError,
-    InvokeConnectionError,
-    InvokeError,
-    InvokeRateLimitError,
-    InvokeServerUnavailableError,
-)
-from core.model_runtime.errors.validate import CredentialsValidateFailedError
-from core.model_runtime.model_providers.__base.rerank_model import RerankModel
-from core.model_runtime.model_providers.huggingface_tei.tei_helper import TeiHelper
-
-
-class HuggingfaceTeiRerankModel(RerankModel):
-    """
-    Model class for Text Embedding Inference rerank model.
-    """
-
-    def _invoke(
-        self,
-        model: str,
-        credentials: dict,
-        query: str,
-        docs: list[str],
-        score_threshold: Optional[float] = None,
-        top_n: Optional[int] = None,
-        user: Optional[str] = None,
-    ) -> RerankResult:
-        """
-        Invoke rerank model
-
-        :param model: model name
-        :param credentials: model credentials
-        :param query: search query
-        :param docs: docs for reranking
-        :param score_threshold: score threshold
-        :param top_n: top n
-        :param user: unique user id
-        :return: rerank result
-        """
-        if len(docs) == 0:
-            return RerankResult(model=model, docs=[])
-        server_url = credentials['server_url']
-
-        if server_url.endswith('/'):
-            server_url = server_url[:-1]
-
-        try:
-            results = TeiHelper.invoke_rerank(server_url, query, docs)
-
-            rerank_documents = []
-            for result in results:  
-                rerank_document = RerankDocument(
-                    index=result['index'],
-                    text=result['text'],
-                    score=result['score'],
-                )
-                if score_threshold is None or result['score'] >= score_threshold:
-                    rerank_documents.append(rerank_document)
-                if top_n is not None and len(rerank_documents) >= top_n:
-                    break
-
-            return RerankResult(model=model, docs=rerank_documents)
-        except httpx.HTTPStatusError as e:
-            raise InvokeServerUnavailableError(str(e))  
-
-    def validate_credentials(self, model: str, credentials: dict) -> None:
-        """
-        Validate model credentials
-
-        :param model: model name
-        :param credentials: model credentials
-        :return:
-        """
-        try:
-            server_url = credentials['server_url']
-            extra_args = TeiHelper.get_tei_extra_parameter(server_url, model)
-            if extra_args.model_type != 'reranker':
-                raise CredentialsValidateFailedError('Current model is not a rerank model')
-
-            credentials['context_size'] = extra_args.max_input_length
-
-            self.invoke(
-                model=model,
-                credentials=credentials,
-                query='Whose kasumi',
-                docs=[
-                    'Kasumi is a girl\'s name of Japanese origin meaning "mist".',
-                    'Her music is a kawaii bass, a mix of future bass, pop, and kawaii music ',
-                    'and she leads a team named PopiParty.',
-                ],
-                score_threshold=0.8,
-            )
-        except Exception as ex:
-            raise CredentialsValidateFailedError(str(ex))
-
-    @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
-        """
-        return {
-            InvokeConnectionError: [InvokeConnectionError],
-            InvokeServerUnavailableError: [InvokeServerUnavailableError],
-            InvokeRateLimitError: [InvokeRateLimitError],
-            InvokeAuthorizationError: [InvokeAuthorizationError],
-            InvokeBadRequestError: [InvokeBadRequestError, KeyError, ValueError],
-        }
-
-    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.RERANK,
-            model_properties={
-                ModelPropertyKey.CONTEXT_SIZE: int(credentials.get('context_size', 512)),
-            },
-            parameter_rules=[],
-        )
-
-        return entity
--- a/api/core/model_runtime/model_providers/huggingface_tei/tei_helper.py
+++ b/api/core/model_runtime/model_providers/huggingface_tei/tei_helper.py
@ -1,183 +0,0 @@
-from threading import Lock
-from time import time
-from typing import Optional
-
-import httpx
-from requests.adapters import HTTPAdapter
-from requests.exceptions import ConnectionError, MissingSchema, Timeout
-from requests.sessions import Session
-from yarl import URL
-
-
-class TeiModelExtraParameter:
-    model_type: str
-    max_input_length: int
-    max_client_batch_size: int
-
-    def __init__(self, model_type: str, max_input_length: int, max_client_batch_size: Optional[int] = None) -> None:
-        self.model_type = model_type
-        self.max_input_length = max_input_length
-        self.max_client_batch_size = max_client_batch_size
-
-
-cache = {}
-cache_lock = Lock()
-
-
-class TeiHelper:
-    @staticmethod
-    def get_tei_extra_parameter(server_url: str, model_name: str) -> TeiModelExtraParameter:
-        TeiHelper._clean_cache()
-        with cache_lock:
-            if model_name not in cache:
-                cache[model_name] = {
-                    'expires': time() + 300,
-                    'value': TeiHelper._get_tei_extra_parameter(server_url),
-                }
-            return cache[model_name]['value']
-
-    @staticmethod
-    def _clean_cache() -> None:
-        try:
-            with cache_lock:
-                expired_keys = [model_uid for model_uid, model in cache.items() if model['expires'] < time()]
-                for model_uid in expired_keys:
-                    del cache[model_uid]
-        except RuntimeError as e:
-            pass
-
-    @staticmethod
-    def _get_tei_extra_parameter(server_url: str) -> TeiModelExtraParameter:
-        """
-        get tei model extra parameter like model_type, max_input_length, max_batch_requests
-        """
-
-        url = str(URL(server_url) / 'info')
-
-        # this method is surrounded by a lock, and default requests may hang forever, so we just set a Adapter with max_retries=3
-        session = Session()
-        session.mount('http://', HTTPAdapter(max_retries=3))
-        session.mount('https://', HTTPAdapter(max_retries=3))
-
-        try:
-            response = session.get(url, timeout=10)
-        except (MissingSchema, ConnectionError, Timeout) as e:
-            raise RuntimeError(f'get tei model extra parameter failed, url: {url}, error: {e}')
-        if response.status_code != 200:
-            raise RuntimeError(
-                f'get tei model extra parameter failed, status code: {response.status_code}, response: {response.text}'
-            )
-
-        response_json = response.json()
-
-        model_type = response_json.get('model_type', {})
-        if len(model_type.keys()) < 1:
-            raise RuntimeError('model_type is empty')
-        model_type = list(model_type.keys())[0]
-        if model_type not in ['embedding', 'reranker']:
-            raise RuntimeError(f'invalid model_type: {model_type}')
-        
-        max_input_length = response_json.get('max_input_length', 512)
-        max_client_batch_size = response_json.get('max_client_batch_size', 1)
-
-        return TeiModelExtraParameter(
-            model_type=model_type,
-            max_input_length=max_input_length,
-            max_client_batch_size=max_client_batch_size
-        )
-    
-    @staticmethod
-    def invoke_tokenize(server_url: str, texts: list[str]) -> list[list[dict]]:
-        """
-        Invoke tokenize endpoint
-
-        Example response:
-        [
-            [
-                {
-                    "id": 0,
-                    "text": "<s>",
-                    "special": true,
-                    "start": null,
-                    "stop": null
-                },
-                {
-                    "id": 7704,
-                    "text": "str",
-                    "special": false,
-                    "start": 0,
-                    "stop": 3
-                },
-                < MORE TOKENS >
-            ]
-        ]
-
-        :param server_url: server url
-        :param texts: texts to tokenize
-        """
-        resp = httpx.post(
-            f'{server_url}/tokenize',
-            json={'inputs': texts},
-        )
-        resp.raise_for_status()
-        return resp.json()
-    
-    @staticmethod
-    def invoke_embeddings(server_url: str, texts: list[str]) -> dict:
-        """
-        Invoke embeddings endpoint
-
-        Example response:
-        {
-            "object": "list",
-            "data": [
-                {
-                    "object": "embedding",
-                    "embedding": [...],
-                    "index": 0
-                }
-            ],
-            "model": "MODEL_NAME",
-            "usage": {
-                "prompt_tokens": 3,
-                "total_tokens": 3
-            }
-        }
-
-        :param server_url: server url
-        :param texts: texts to embed
-        """
-        # Use OpenAI compatible API here, which has usage tracking
-        resp = httpx.post(
-            f'{server_url}/v1/embeddings',
-            json={'input': texts},
-        )
-        resp.raise_for_status()
-        return resp.json()
-
-    @staticmethod
-    def invoke_rerank(server_url: str, query: str, docs: list[str]) -> list[dict]:
-        """
-        Invoke rerank endpoint
-
-        Example response:
-        [
-            {
-                "index": 0,
-                "text": "Deep Learning is ...",
-                "score": 0.9950755
-            }
-        ]
-
-        :param server_url: server url
-        :param texts: texts to rerank
-        :param candidates: candidates to rerank
-        """
-        params = {'query': query, 'texts': docs, 'return_text': True}
-
-        response = httpx.post(
-            server_url + '/rerank',
-            json=params,
-        )
-        response.raise_for_status() 
-        return response.json()
--- a/api/core/model_runtime/model_providers/huggingface_tei/text_embedding/init.py
+++ b/api/core/model_runtime/model_providers/huggingface_tei/text_embedding/init.py
--- a/api/core/model_runtime/model_providers/huggingface_tei/text_embedding/text_embedding.py
+++ b/api/core/model_runtime/model_providers/huggingface_tei/text_embedding/text_embedding.py
@ -1,204 +0,0 @@
-import time
-from typing import Optional
-
-from core.model_runtime.entities.common_entities import I18nObject
-from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType, PriceType
-from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
-from core.model_runtime.errors.invoke import (
-    InvokeAuthorizationError,
-    InvokeBadRequestError,
-    InvokeConnectionError,
-    InvokeError,
-    InvokeRateLimitError,
-    InvokeServerUnavailableError,
-)
-from core.model_runtime.errors.validate import CredentialsValidateFailedError
-from core.model_runtime.model_providers.__base.text_embedding_model import TextEmbeddingModel
-from core.model_runtime.model_providers.huggingface_tei.tei_helper import TeiHelper
-
-
-class HuggingfaceTeiTextEmbeddingModel(TextEmbeddingModel):
-    """
-    Model class for Text Embedding Inference text embedding model.
-    """
-
-    def _invoke(
-        self, model: str, credentials: dict, texts: list[str], user: Optional[str] = None
-    ) -> TextEmbeddingResult:
-        """
-        Invoke text embedding model
-
-        credentials should be like:
-        {
-            'server_url': 'server url',
-            'model_uid': 'model uid',
-        }
-
-        :param model: model name
-        :param credentials: model credentials
-        :param texts: texts to embed
-        :param user: unique user id
-        :return: embeddings result
-        """
-        server_url = credentials['server_url']
-
-        if server_url.endswith('/'):
-            server_url = server_url[:-1]
-
-
-        # get model properties
-        context_size = self._get_context_size(model, credentials)
-        max_chunks = self._get_max_chunks(model, credentials)
-
-        inputs = []
-        indices = []
-        used_tokens = 0
-
-        # get tokenized results from TEI
-        batched_tokenize_result = TeiHelper.invoke_tokenize(server_url, texts)
-
-        for i, (text, tokenize_result) in enumerate(zip(texts, batched_tokenize_result)):
-
-            # Check if the number of tokens is larger than the context size
-            num_tokens = len(tokenize_result)
-
-            if num_tokens >= context_size:
-                # Find the best cutoff point
-                pre_special_token_count = 0
-                for token in tokenize_result:
-                    if token['special']:
-                        pre_special_token_count += 1
-                    else:
-                        break
-                rest_special_token_count = len([token for token in tokenize_result if token['special']]) - pre_special_token_count
-
-                # Calculate the cutoff point, leave 20 extra space to avoid exceeding the limit
-                token_cutoff = context_size - rest_special_token_count - 20
-
-                # Find the cutoff index
-                cutpoint_token = tokenize_result[token_cutoff]
-                cutoff = cutpoint_token['start']
-
-                inputs.append(text[0: cutoff])
-            else:
-                inputs.append(text)
-            indices += [i]
-
-        batched_embeddings = []
-        _iter = range(0, len(inputs), max_chunks)
-
-        try:
-            used_tokens = 0
-            for i in _iter:
-                iter_texts = inputs[i : i + max_chunks]
-                results = TeiHelper.invoke_embeddings(server_url, iter_texts)
-                embeddings = results['data']
-                embeddings = [embedding['embedding'] for embedding in embeddings]
-                batched_embeddings.extend(embeddings)
-
-                usage = results['usage']
-                used_tokens += usage['total_tokens']
-        except RuntimeError as e:
-            raise InvokeServerUnavailableError(str(e))
-
-        usage = self._calc_response_usage(model=model, credentials=credentials, tokens=used_tokens)
-
-        result = TextEmbeddingResult(model=model, embeddings=batched_embeddings, usage=usage)
-
-        return result
-
-    def get_num_tokens(self, model: str, credentials: dict, texts: list[str]) -> int:
-        """
-        Get number of tokens for given prompt messages
-
-        :param model: model name
-        :param credentials: model credentials
-        :param texts: texts to embed
-        :return:
-        """
-        num_tokens = 0
-        server_url = credentials['server_url']
-
-        if server_url.endswith('/'):
-            server_url = server_url[:-1]
-
-        batch_tokens = TeiHelper.invoke_tokenize(server_url, texts)
-        num_tokens = sum(len(tokens) for tokens in batch_tokens)
-        return num_tokens
-
-    def validate_credentials(self, model: str, credentials: dict) -> None:
-        """
-        Validate model credentials
-
-        :param model: model name
-        :param credentials: model credentials
-        :return:
-        """
-        try:
-            server_url = credentials['server_url']
-            extra_args = TeiHelper.get_tei_extra_parameter(server_url, model)
-            print(extra_args)
-            if extra_args.model_type != 'embedding':
-                raise CredentialsValidateFailedError('Current model is not a embedding model')
-
-            credentials['context_size'] = extra_args.max_input_length
-            credentials['max_chunks'] = extra_args.max_client_batch_size
-            self._invoke(model=model, credentials=credentials, texts=['ping'])
-        except Exception as ex:
-            raise CredentialsValidateFailedError(str(ex))
-
-    @property
-    def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
-        return {
-            InvokeConnectionError: [InvokeConnectionError],
-            InvokeServerUnavailableError: [InvokeServerUnavailableError],
-            InvokeRateLimitError: [InvokeRateLimitError],
-            InvokeAuthorizationError: [InvokeAuthorizationError],
-            InvokeBadRequestError: [KeyError],
-        }
-
-    def _calc_response_usage(self, model: str, credentials: dict, tokens: int) -> EmbeddingUsage:
-        """
-        Calculate response usage
-
-        :param model: model name
-        :param credentials: model credentials
-        :param tokens: input tokens
-        :return: usage
-        """
-        # get input price info
-        input_price_info = self.get_price(
-            model=model, credentials=credentials, price_type=PriceType.INPUT, tokens=tokens
-        )
-
-        # transform usage
-        usage = EmbeddingUsage(
-            tokens=tokens,
-            total_tokens=tokens,
-            unit_price=input_price_info.unit_price,
-            price_unit=input_price_info.unit,
-            total_price=input_price_info.total_amount,
-            currency=input_price_info.currency,
-            latency=time.perf_counter() - self.started_at,
-        )
-
-        return usage
-
-    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.TEXT_EMBEDDING,
-            model_properties={
-                ModelPropertyKey.MAX_CHUNKS: int(credentials.get('max_chunks', 1)),
-                ModelPropertyKey.CONTEXT_SIZE: int(credentials.get('context_size', 512)),
-            },
-            parameter_rules=[],
-        )
-
-        return entity
--- a/api/core/model_runtime/model_providers/hunyuan/llm/llm.py
+++ b/api/core/model_runtime/model_providers/hunyuan/llm/llm.py
@ -214,7 +214,7 @@ class HunyuanLargeLanguageModel(LargeLanguageModel):
    def _handle_chat_response(self, credentials, model, prompt_messages, response):
        usage = self._calc_response_usage(model, credentials, response.Usage.PromptTokens,
                                          response.Usage.CompletionTokens)
-        assistant_prompt_message = AssistantPromptMessage()
+        assistant_prompt_message = PromptMessage(role="assistant")
        assistant_prompt_message.content = response.Choices[0].Message.Content
        result = LLMResult(
            model=model,
--- a/api/core/model_runtime/model_providers/jina/rerank/jina-reranker-v2-base-multilingual.yaml
+++ b/api/core/model_runtime/model_providers/jina/rerank/jina-reranker-v2-base-multilingual.yaml
@ -1,4 +1,4 @@
 model: jina-reranker-v2-base-multilingual
 model_type: rerank
 model_properties:
-  context_size: 1024
+  context_size: 8192
--- a/api/core/model_runtime/model_providers/moonshot/llm/llm.py
+++ b/api/core/model_runtime/model_providers/moonshot/llm/llm.py
@ -84,8 +84,7 @@ class MoonshotLargeLanguageModel(OAIAPICompatLargeLanguageModel):

    def _add_custom_parameters(self, credentials: dict) -> None:
        credentials['mode'] = 'chat'
-        if 'endpoint_url' not in credentials or credentials['endpoint_url'] == "":
-            credentials['endpoint_url'] = 'https://api.moonshot.cn/v1'
+        credentials['endpoint_url'] = 'https://api.moonshot.cn/v1'

    def _add_function_call(self, model: str, credentials: dict) -> None:
        model_schema = self.get_model_schema(model, credentials)
--- a/api/core/model_runtime/model_providers/moonshot/moonshot.yaml
+++ b/api/core/model_runtime/model_providers/moonshot/moonshot.yaml
@ -31,14 +31,6 @@ provider_credential_schema:
      placeholder:
        zh_Hans: 在此输入您的 API Key
        en_US: Enter your API Key
-    - variable: endpoint_url
-      label:
-        en_US: API Base
-      type: text-input
-      required: false
-      placeholder:
-        zh_Hans: Base URL, 如：https://api.moonshot.cn/v1
-        en_US: Base URL, e.g. https://api.moonshot.cn/v1
 model_credential_schema:
  model:
    label:
--- a/api/core/model_runtime/model_providers/ollama/text_embedding/text_embedding.py
+++ b/api/core/model_runtime/model_providers/ollama/text_embedding/text_embedding.py
@ -72,7 +72,7 @@ class OllamaEmbeddingModel(TextEmbeddingModel):
            num_tokens = self._get_num_tokens_by_gpt2(text)

            if num_tokens >= context_size:
-                cutoff = int(np.floor(len(text) * (context_size / num_tokens)))
+                cutoff = int(len(text) * (np.floor(context_size / num_tokens)))
                # if num tokens is larger than context length, only use the start
                inputs.append(text[0: cutoff])
            else:
--- a/api/core/model_runtime/model_providers/openai/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/openai/llm/_position.yaml
@ -1,8 +1,6 @@
 - gpt-4
 - gpt-4o
 - gpt-4o-2024-05-13
- gpt-4o-2024-08-06
- chatgpt-4o-latest
 - gpt-4o-mini
 - gpt-4o-mini-2024-07-18
 - gpt-4-turbo
--- a/api/core/model_runtime/model_providers/openai/llm/chatgpt-4o-latest.yaml
+++ b/api/core/model_runtime/model_providers/openai/llm/chatgpt-4o-latest.yaml
@ -1,44 +0,0 @@
-model: chatgpt-4o-latest
-label:
-  zh_Hans: chatgpt-4o-latest
-  en_US: chatgpt-4o-latest
-model_type: llm
-features:
-  - multi-tool-call
-  - agent-thought
-  - stream-tool-call
-  - vision
-model_properties:
-  mode: chat
-  context_size: 128000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: presence_penalty
-    use_template: presence_penalty
-  - name: frequency_penalty
-    use_template: frequency_penalty
-  - name: max_tokens
-    use_template: max_tokens
-    default: 512
-    min: 1
-    max: 16384
-  - name: response_format
-    label:
-      zh_Hans: 回复格式
-      en_US: response_format
-    type: string
-    help:
-      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
-pricing:
-  input: '2.50'
-  output: '10.00'
-  unit: '0.000001'
-  currency: USD
--- a/api/core/model_runtime/model_providers/openai/llm/gpt-4o-2024-08-06.yaml
+++ b/api/core/model_runtime/model_providers/openai/llm/gpt-4o-2024-08-06.yaml
@ -1,47 +0,0 @@
-model: gpt-4o-2024-08-06
-label:
-  zh_Hans: gpt-4o-2024-08-06
-  en_US: gpt-4o-2024-08-06
-model_type: llm
-features:
-  - multi-tool-call
-  - agent-thought
-  - stream-tool-call
-  - vision
-model_properties:
-  mode: chat
-  context_size: 128000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: presence_penalty
-    use_template: presence_penalty
-  - name: frequency_penalty
-    use_template: frequency_penalty
-  - name: max_tokens
-    use_template: max_tokens
-    default: 512
-    min: 1
-    max: 16384
-  - name: response_format
-    label:
-      zh_Hans: 回复格式
-      en_US: response_format
-    type: string
-    help:
-      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
-      - json_schema
-  - name: json_schema
-    use_template: json_schema
-pricing:
-  input: '2.50'
-  output: '10.00'
-  unit: '0.000001'
-  currency: USD
--- a/api/core/model_runtime/model_providers/openai/llm/gpt-4o-mini.yaml
+++ b/api/core/model_runtime/model_providers/openai/llm/gpt-4o-mini.yaml
@ -37,9 +37,6 @@ parameter_rules:
    options:
      - text
      - json_object
-      - json_schema
-  - name: json_schema
-    use_template: json_schema
 pricing:
  input: '0.15'
  output: '0.60'
--- a/api/core/model_runtime/model_providers/openai/llm/llm.py
+++ b/api/core/model_runtime/model_providers/openai/llm/llm.py
@ -1,4 +1,3 @@
-import json
 import logging
 from collections.abc import Generator
 from typing import Optional, Union, cast
@ -545,18 +544,13 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):

        response_format = model_parameters.get("response_format")
        if response_format:
-            if response_format == "json_schema":
-                json_schema = model_parameters.get("json_schema")
-                if not json_schema:
-                    raise ValueError("Must define JSON Schema when the response format is json_schema")
-                try:
-                    schema = json.loads(json_schema)
-                except:
-                    raise ValueError(f"not currect json_schema format: {json_schema}")
-                model_parameters.pop("json_schema")
-                model_parameters["response_format"] = {"type": "json_schema", "json_schema": schema}
+            if response_format == "json_object":
+                response_format = {"type": "json_object"}
            else:
-                model_parameters["response_format"] = {"type": response_format}
+                response_format = {"type": "text"}
+
+            model_parameters["response_format"] = response_format
+

        extra_model_kwargs = {}

@ -928,14 +922,11 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
                                  tools: Optional[list[PromptMessageTool]] = None) -> int:
        """Calculate num tokens for gpt-3.5-turbo and gpt-4 with tiktoken package.

-        Official documentation: https://github.com/openai/openai-cookbook/blob/main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb"""
+        Official documentation: https://github.com/openai/openai-cookbook/blob/
+        main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb"""
        if model.startswith('ft:'):
            model = model.split(':')[1]

-        # Currently, we can use gpt4o to calculate chatgpt-4o-latest's token.
-        if model == "chatgpt-4o-latest":
-            model = "gpt-4o"
-
        try:
            encoding = tiktoken.encoding_for_model(model)
        except KeyError:
@ -955,7 +946,7 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
            raise NotImplementedError(
                f"get_num_tokens_from_messages() is not presently implemented "
                f"for model {model}."
-                "See https://platform.openai.com/docs/advanced-usage/managing-tokens for "
+                "See https://github.com/openai/openai-python/blob/main/chatml.md for "
                "information on how messages are converted to tokens."
            )
        num_tokens = 0
--- a/api/core/model_runtime/model_providers/openai_api_compatible/openai_api_compatible.yaml
+++ b/api/core/model_runtime/model_providers/openai_api_compatible/openai_api_compatible.yaml
@ -7,7 +7,6 @@ description:
 supported_model_types:
  - llm
  - text-embedding
-  - speech2text
 configurate_methods:
  - customizable-model
 model_credential_schema:
@ -62,22 +61,6 @@ model_credential_schema:
        zh_Hans: 模型上下文长度
        en_US: Model context size
      required: true
-      show_on:
-        - variable: __model_type
-          value: llm
-      type: text-input
-      default: '4096'
-      placeholder:
-        zh_Hans: 在此输入您的模型上下文长度
-        en_US: Enter your Model context size
-    - variable: context_size
-      label:
-        zh_Hans: 模型上下文长度
-        en_US: Model context size
-      required: true
-      show_on:
-        - variable: __model_type
-          value: text-embedding
      type: text-input
      default: '4096'
      placeholder:
--- a/api/core/model_runtime/model_providers/openai_api_compatible/speech2text/init.py
+++ b/api/core/model_runtime/model_providers/openai_api_compatible/speech2text/init.py
--- a/api/core/model_runtime/model_providers/openai_api_compatible/speech2text/speech2text.py
+++ b/api/core/model_runtime/model_providers/openai_api_compatible/speech2text/speech2text.py
@ -1,63 +0,0 @@
-from typing import IO, Optional
-from urllib.parse import urljoin
-
-import requests
-
-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
-from core.model_runtime.model_providers.openai_api_compatible._common import _CommonOAI_API_Compat
-
-
-class OAICompatSpeech2TextModel(_CommonOAI_API_Compat, Speech2TextModel):
-    """
-    Model class for OpenAI Compatible Speech to text model.
-    """
-
-    def _invoke(
-            self, model: str, credentials: dict, file: IO[bytes], user: Optional[str] = None
-    ) -> str:
-        """
-        Invoke speech2text model
-
-        :param model: model name
-        :param credentials: model credentials
-        :param file: audio file
-        :param user: unique user id
-        :return: text for given audio file
-        """
-        headers = {}
-
-        api_key = credentials.get("api_key")
-        if api_key:
-            headers["Authorization"] = f"Bearer {api_key}"
-
-        endpoint_url = credentials.get("endpoint_url")
-        if not endpoint_url.endswith("/"):
-            endpoint_url += "/"
-        endpoint_url = urljoin(endpoint_url, "audio/transcriptions")
-
-        payload = {"model": model}
-        files = [("file", file)]
-        response = requests.post(endpoint_url, headers=headers, data=payload, files=files)
-
-        if response.status_code != 200:
-            raise InvokeBadRequestError(response.text)
-        response_data = response.json()
-        return response_data["text"]
-
-    def validate_credentials(self, model: str, credentials: dict) -> None:
-        """
-        Validate model credentials
-
-        :param model: model name
-        :param credentials: model credentials
-        :return:
-        """
-        try:
-            audio_file_path = self._get_demo_file_path()
-
-            with open(audio_file_path, "rb") as audio_file:
-                self._invoke(model, credentials, audio_file)
-        except Exception as ex:
-            raise CredentialsValidateFailedError(str(ex))
--- a/api/core/model_runtime/model_providers/openai_api_compatible/text_embedding/text_embedding.py
+++ b/api/core/model_runtime/model_providers/openai_api_compatible/text_embedding/text_embedding.py
@ -76,7 +76,7 @@ class OAICompatEmbeddingModel(_CommonOAI_API_Compat, TextEmbeddingModel):
            num_tokens = self._get_num_tokens_by_gpt2(text)

            if num_tokens >= context_size:
-                cutoff = int(np.floor(len(text) * (context_size / num_tokens)))
+                cutoff = int(len(text) * (np.floor(context_size / num_tokens)))
                # if num tokens is larger than context length, only use the start
                inputs.append(text[0: cutoff])
            else:
--- a/api/core/model_runtime/model_providers/openrouter/llm/gpt-4o-2024-08-06.yaml
+++ b/api/core/model_runtime/model_providers/openrouter/llm/gpt-4o-2024-08-06.yaml
@ -1,44 +0,0 @@
-model: gpt-4o-2024-08-06
-label:
-  zh_Hans: gpt-4o-2024-08-06
-  en_US: gpt-4o-2024-08-06
-model_type: llm
-features:
-  - multi-tool-call
-  - agent-thought
-  - stream-tool-call
-  - vision
-model_properties:
-  mode: chat
-  context_size: 128000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: presence_penalty
-    use_template: presence_penalty
-  - name: frequency_penalty
-    use_template: frequency_penalty
-  - name: max_tokens
-    use_template: max_tokens
-    default: 512
-    min: 1
-    max: 16384
-  - name: response_format
-    label:
-      zh_Hans: 回复格式
-      en_US: response_format
-    type: string
-    help:
-      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
-pricing:
-  input: '2.50'
-  output: '10.00'
-  unit: '0.000001'
-  currency: USD
--- a/api/core/model_runtime/model_providers/perfxcloud/llm/Llama3-Chinese_v2.yaml
+++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Llama3-Chinese_v2.yaml
@ -1,61 +0,0 @@
-model: Llama3-Chinese_v2
-label:
-  en_US: Llama3-Chinese_v2
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 8192
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    type: float
-    default: 0.5
-    min: 0.0
-    max: 2.0
-    help:
-      zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
-      en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
-  - name: max_tokens
-    use_template: max_tokens
-    type: int
-    default: 600
-    min: 1
-    max: 1248
-    help:
-      zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
-      en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
-  - name: top_p
-    use_template: top_p
-    type: float
-    default: 0.8
-    min: 0.1
-    max: 0.9
-    help:
-      zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
-      en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
-  - name: top_k
-    type: int
-    min: 0
-    max: 99
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    help:
-      zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
-      en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
-  - name: repetition_penalty
-    required: false
-    type: float
-    default: 1.1
-    label:
-      en_US: Repetition penalty
-    help:
-      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
-      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-pricing:
-  input: "0.000"
-  output: "0.000"
-  unit: "0.000"
-  currency: RMB
--- a/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3-70B-Instruct-GPTQ-Int4.yaml
+++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3-70B-Instruct-GPTQ-Int4.yaml
@ -1,61 +0,0 @@
-model: Meta-Llama-3-70B-Instruct-GPTQ-Int4
-label:
-  en_US: Meta-Llama-3-70B-Instruct-GPTQ-Int4
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 1024
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    type: float
-    default: 0.5
-    min: 0.0
-    max: 2.0
-    help:
-      zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
-      en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
-  - name: max_tokens
-    use_template: max_tokens
-    type: int
-    default: 600
-    min: 1
-    max: 1248
-    help:
-      zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
-      en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
-  - name: top_p
-    use_template: top_p
-    type: float
-    default: 0.8
-    min: 0.1
-    max: 0.9
-    help:
-      zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
-      en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
-  - name: top_k
-    type: int
-    min: 0
-    max: 99
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    help:
-      zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
-      en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
-  - name: repetition_penalty
-    required: false
-    type: float
-    default: 1.1
-    label:
-      en_US: Repetition penalty
-    help:
-      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
-      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-pricing:
-  input: "0.000"
-  output: "0.000"
-  unit: "0.000"
-  currency: RMB
--- a/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3-8B-Instruct.yaml
+++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3-8B-Instruct.yaml
@ -1,61 +0,0 @@
-model: Meta-Llama-3-8B-Instruct
-label:
-  en_US: Meta-Llama-3-8B-Instruct
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 8192
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    type: float
-    default: 0.5
-    min: 0.0
-    max: 2.0
-    help:
-      zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
-      en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
-  - name: max_tokens
-    use_template: max_tokens
-    type: int
-    default: 600
-    min: 1
-    max: 1248
-    help:
-      zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
-      en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
-  - name: top_p
-    use_template: top_p
-    type: float
-    default: 0.8
-    min: 0.1
-    max: 0.9
-    help:
-      zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
-      en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
-  - name: top_k
-    type: int
-    min: 0
-    max: 99
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    help:
-      zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
-      en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
-  - name: repetition_penalty
-    required: false
-    type: float
-    default: 1.1
-    label:
-      en_US: Repetition penalty
-    help:
-      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
-      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-pricing:
-  input: "0.000"
-  output: "0.000"
-  unit: "0.000"
-  currency: RMB
--- a/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3.1-405B-Instruct-AWQ-INT4.yaml
+++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3.1-405B-Instruct-AWQ-INT4.yaml
@ -1,61 +0,0 @@
-model: Meta-Llama-3.1-405B-Instruct-AWQ-INT4
-label:
-  en_US: Meta-Llama-3.1-405B-Instruct-AWQ-INT4
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 410960
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    type: float
-    default: 0.5
-    min: 0.0
-    max: 2.0
-    help:
-      zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
-      en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
-  - name: max_tokens
-    use_template: max_tokens
-    type: int
-    default: 600
-    min: 1
-    max: 1248
-    help:
-      zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
-      en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
-  - name: top_p
-    use_template: top_p
-    type: float
-    default: 0.8
-    min: 0.1
-    max: 0.9
-    help:
-      zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
-      en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
-  - name: top_k
-    type: int
-    min: 0
-    max: 99
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    help:
-      zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
-      en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
-  - name: repetition_penalty
-    required: false
-    type: float
-    default: 1.1
-    label:
-      en_US: Repetition penalty
-    help:
-      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
-      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-pricing:
-  input: "0.000"
-  output: "0.000"
-  unit: "0.000"
-  currency: RMB
--- a/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3.1-8B-Instruct.yaml
+++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Meta-Llama-3.1-8B-Instruct.yaml
@ -1,61 +0,0 @@
-model: Meta-Llama-3.1-8B-Instruct
-label:
-  en_US: Meta-Llama-3.1-8B-Instruct
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 4096
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    type: float
-    default: 0.1
-    min: 0.0
-    max: 2.0
-    help:
-      zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
-      en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
-  - name: max_tokens
-    use_template: max_tokens
-    type: int
-    default: 600
-    min: 1
-    max: 1248
-    help:
-      zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
-      en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
-  - name: top_p
-    use_template: top_p
-    type: float
-    default: 0.8
-    min: 0.1
-    max: 0.9
-    help:
-      zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
-      en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
-  - name: top_k
-    type: int
-    min: 0
-    max: 99
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    help:
-      zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
-      en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
-  - name: repetition_penalty
-    required: false
-    type: float
-    default: 1.1
-    label:
-      en_US: Repetition penalty
-    help:
-      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
-      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-pricing:
-  input: "0.000"
-  output: "0.000"
-  unit: "0.000"
-  currency: RMB
--- a/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen-14B-Chat-Int4.yaml
+++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen-14B-Chat-Int4.yaml
@ -55,8 +55,7 @@ parameter_rules:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
 pricing:
-  input: "0.000"
-  output: "0.000"
-  unit: "0.000"
+  input: '0.000'
+  output: '0.000'
+  unit: '0.000'
  currency: RMB
-deprecated: true
--- a/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen1.5-110B-Chat-GPTQ-Int4.yaml
+++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen1.5-110B-Chat-GPTQ-Int4.yaml
@ -55,8 +55,7 @@ parameter_rules:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
 pricing:
-  input: "0.000"
-  output: "0.000"
-  unit: "0.000"
+  input: '0.000'
+  output: '0.000'
+  unit: '0.000'
  currency: RMB
-deprecated: true
--- a/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen1.5-72B-Chat-GPTQ-Int4.yaml
+++ b/api/core/model_runtime/model_providers/perfxcloud/llm/Qwen1.5-72B-Chat-GPTQ-Int4.yaml
@ -6,7 +6,7 @@ features:
  - agent-thought
 model_properties:
  mode: chat
-  context_size: 2048
+  context_size: 8192
 parameter_rules:
  - name: temperature
    use_template: temperature
@ -55,7 +55,7 @@ parameter_rules:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
 pricing:
-  input: "0.000"
-  output: "0.000"
-  unit: "0.000"
+  input: '0.000'
+  output: '0.000'
+  unit: '0.000'
  currency: RMB
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
jyong	2ab04bb933	fix Reranking mode is null	2024-08-06 19:03:32 +08:00
jyong	a3c2ab9a6e	fix Reranking mode is null	2024-08-06 18:34:07 +08:00