version to 0.6.6 (#4050 )

test: remove explicit env settings for CI pytests (#4041 )
chore(deps): bump semver from 5.7.1 to 5.7.2 in /web (#4022 )
2026-01-20 22:14:01 +00:00 · 2024-05-02 16:06:40 +08:00 · 2024-05-02 00:49:39 +08:00 · 2024-04-30 18:47:05 +08:00 · 2024-04-30 18:39:02 +08:00 · 2024-04-30 18:11:49 +08:00
588 changed files with 15047 additions and 3887 deletions
--- a/.devcontainer/devcontainer.json
+++ b/.devcontainer/devcontainer.json
@@ -32,8 +32,8 @@
 			]
 		}
 	},
-	"postStartCommand": "cd api && pip install -r requirements.txt",
-	"postCreateCommand": "cd web && npm install"
+	"postStartCommand": "./.devcontainer/post_start_command.sh",
+	"postCreateCommand": "./.devcontainer/post_create_command.sh"

 	// Features to add to the dev container. More info: https://containers.dev/features.
 	// "features": {},
--- a/.devcontainer/post_create_command.sh
+++ b/.devcontainer/post_create_command.sh
@@ -0,0 +1,10 @@
+#!/bin/bash
+
+cd web && npm install
+
+echo 'alias start-api="cd /workspaces/dify/api && flask run --host 0.0.0.0 --port=5001 --debug"' >> ~/.bashrc
+echo 'alias start-worker="cd /workspaces/dify/api && celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail"' >> ~/.bashrc
+echo 'alias start-web="cd /workspaces/dify/web && npm run dev"' >> ~/.bashrc
+echo 'alias start-containers="cd /workspaces/dify/docker && docker-compose -f docker-compose.middleware.yaml -p dify up -d"' >> ~/.bashrc
+
+source /home/vscode/.bashrc
--- a/.devcontainer/post_start_command.sh
+++ b/.devcontainer/post_start_command.sh
@@ -0,0 +1,3 @@
+#!/bin/bash
+
+cd api && pip install -r requirements.txt
--- a/.github/workflows/api-tests.yml
+++ b/.github/workflows/api-tests.yml
@@ -8,39 +8,20 @@ on:
 jobs:
  test:
    runs-on: ubuntu-latest
-
-    env:
-      OPENAI_API_KEY: sk-IamNotARealKeyJustForMockTestKawaiiiiiiiiii
-      AZURE_OPENAI_API_BASE: https://difyai-openai.openai.azure.com
-      AZURE_OPENAI_API_KEY: xxxxb1707exxxxxxxxxxaaxxxxxf94
-      ANTHROPIC_API_KEY: sk-ant-api11-IamNotARealKeyJustForMockTestKawaiiiiiiiiii-NotBaka-ASkksz
-      CHATGLM_API_BASE: http://a.abc.com:11451
-      XINFERENCE_SERVER_URL: http://a.abc.com:11451
-      XINFERENCE_GENERATION_MODEL_UID: generate
-      XINFERENCE_CHAT_MODEL_UID: chat
-      XINFERENCE_EMBEDDINGS_MODEL_UID: embedding
-      XINFERENCE_RERANK_MODEL_UID: rerank
-      GOOGLE_API_KEY: abcdefghijklmnopqrstuvwxyz
-      HUGGINGFACE_API_KEY: hf-awuwuwuwuwuwuwuwuwuwuwuwuwuwuwuwuwu
-      HUGGINGFACE_TEXT_GEN_ENDPOINT_URL: a
-      HUGGINGFACE_TEXT2TEXT_GEN_ENDPOINT_URL: b
-      HUGGINGFACE_EMBEDDINGS_ENDPOINT_URL: c
-      MOCK_SWITCH: true
-      CODE_MAX_STRING_LENGTH: 80000
+    strategy:
+      matrix:
+        python-version:
+          - "3.10"
+          - "3.11"

    steps:
      - name: Checkout code
        uses: actions/checkout@v4

-      - name: Install APT packages
-        uses: awalsh128/cache-apt-pkgs-action@v1
-        with:
-          packages: ffmpeg
-
-      - name: Set up Python
+      - name: Set up Python ${{ matrix.python-version }}
        uses: actions/setup-python@v5
        with:
-          python-version: '3.10'
+          python-version: ${{ matrix.python-version }}
          cache: 'pip'
          cache-dependency-path: |
            ./api/requirements.txt
@@ -49,11 +30,33 @@ jobs:
      - name: Install dependencies
        run: pip install -r ./api/requirements.txt -r ./api/requirements-dev.txt

+      - name: Run Unit tests
+        run: dev/pytest/pytest_unit_tests.sh
+
      - name: Run ModelRuntime
-        run: pytest api/tests/integration_tests/model_runtime/anthropic api/tests/integration_tests/model_runtime/azure_openai api/tests/integration_tests/model_runtime/openai api/tests/integration_tests/model_runtime/chatglm api/tests/integration_tests/model_runtime/google api/tests/integration_tests/model_runtime/xinference api/tests/integration_tests/model_runtime/huggingface_hub/test_llm.py
+        run: dev/pytest/pytest_model_runtime.sh

      - name: Run Tool
-        run: pytest api/tests/integration_tests/tools/test_all_provider.py
+        run: dev/pytest/pytest_tools.sh

      - name: Run Workflow
-        run: pytest api/tests/integration_tests/workflow
+        run: dev/pytest/pytest_workflow.sh
+
+      - name: Set up Vector Stores (Weaviate, Qdrant, Milvus, PgVecto-RS)
+        uses: hoverkraft-tech/compose-action@v2.0.0
+        with:
+          compose-file: |
+            docker/docker-compose.middleware.yaml
+            docker/docker-compose.qdrant.yaml
+            docker/docker-compose.milvus.yaml
+            docker/docker-compose.pgvecto-rs.yaml
+          services: |
+            weaviate
+            qdrant
+            etcd
+            minio
+            milvus-standalone
+            pgvecto-rs
+
+      - name: Test Vector Stores
+        run: dev/pytest/pytest_vdb.sh
--- a/.github/workflows/style.yml
+++ b/.github/workflows/style.yml
@@ -24,11 +24,14 @@ jobs:
          python-version: '3.10'

      - name: Python dependencies
-        run: pip install ruff
+        run: pip install ruff dotenv-linter

      - name: Ruff check
        run: ruff check ./api

+      - name: Dotenv check
+        run: dotenv-linter ./api/.env.example ./web/.env.example
+
      - name: Lint hints
        if: failure()
        run: echo "Please run 'dev/reformat' to fix the fixable linting errors."
--- a/README.md
+++ b/README.md
@@ -29,12 +29,12 @@
 </p>

 <p align="center">
-  <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.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>
 </p>

 #
@@ -54,7 +54,7 @@ Dify is an open-source LLM app development platform. Its intuitive interface com


 **2. Comprehensive model support**: 
-  Seamless integration with hundreds of proprietary / open-source LLMs from dozens of inference providers and self-hosted solutions, covering GPT, Mistral, Llama2, and any OpenAI API-compatible models. A full list of supported model providers can be found [here](https://docs.dify.ai/getting-started/readme/model-providers).
+  Seamless integration with hundreds of proprietary / open-source LLMs from dozens of inference providers and self-hosted solutions, covering GPT, Mistral, Llama3, and any OpenAI API-compatible models. A full list of supported model providers can be found [here](https://docs.dify.ai/getting-started/readme/model-providers).

 ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)

--- a/README_CN.md
+++ b/README_CN.md
@@ -44,11 +44,11 @@
  <a href="https://trendshift.io/repositories/2152" target="_blank"><img src="https://trendshift.io/api/badge/repositories/2152" alt="langgenius%2Fdify | 趋势转变" style="width: 250px; height: 55px;" width="250" height="55"/></a>
 </div>

-Dify 是一个开源的LLM应用开发平台。其直观的界面结合了AI工作流程、RAG管道、代理功能、模型管理、可观察性功能等，让您可以快速从原型到生产。以下是其核心功能列表：
+Dify 是一个开源的 LLM 应用开发平台。其直观的界面结合了 AI 工作流、RAG 管道、Agent、模型管理、可观测性功能等，让您可以快速从原型到生产。以下是其核心功能列表：
 </br> </br>

 **1. 工作流**: 
-  在视觉画布上构建和测试功能强大的AI工作流程，利用以下所有功能以及更多功能。
+  在画布上构建和测试功能强大的 AI 工作流程，利用以下所有功能以及更多功能。


  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
@@ -56,7 +56,7 @@ Dify 是一个开源的LLM应用开发平台。其直观的界面结合了AI工


 **2. 全面的模型支持**: 
-  与数百种专有/开源LLMs以及数十种推理提供商和自托管解决方案无缝集成，涵盖GPT、Mistral、Llama2以及任何与OpenAI API兼容的模型。完整的支持模型提供商列表可在[此处](https://docs.dify.ai/getting-started/readme/model-providers)找到。
+  与数百种专有/开源 LLMs 以及数十种推理提供商和自托管解决方案无缝集成，涵盖 GPT、Mistral、Llama3 以及任何与 OpenAI API 兼容的模型。完整的支持模型提供商列表可在[此处](https://docs.dify.ai/getting-started/readme/model-providers)找到。

 ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)

@@ -65,16 +65,16 @@ Dify 是一个开源的LLM应用开发平台。其直观的界面结合了AI工
  用于制作提示、比较模型性能以及向基于聊天的应用程序添加其他功能（如文本转语音）的直观界面。

 **4. RAG Pipeline**: 
-  广泛的RAG功能，涵盖从文档摄入到检索的所有内容，支持从PDF、PPT和其他常见文档格式中提取文本的开箱即用的支持。
+  广泛的 RAG 功能，涵盖从文档摄入到检索的所有内容，支持从 PDF、PPT 和其他常见文档格式中提取文本的开箱即用的支持。

 **5. Agent 智能体**: 
-  您可以基于LLM函数调用或ReAct定义代理，并为代理添加预构建或自定义工具。Dify为AI代理提供了50多种内置工具，如谷歌搜索、DELL·E、稳定扩散和WolframAlpha等。
+  您可以基于 LLM 函数调用或 ReAct 定义 Agent，并为 Agent 添加预构建或自定义工具。Dify 为 AI Agent 提供了50多种内置工具，如谷歌搜索、DELL·E、Stable Diffusion 和 WolframAlpha 等。

 **6. LLMOps**: 
-  随时间监视和分析应用程序日志和性能。您可以根据生产数据和注释持续改进提示、数据集和模型。
+  随时间监视和分析应用程序日志和性能。您可以根据生产数据和标注持续改进提示、数据集和模型。

 **7. 后端即服务**: 
-  所有Dify的功能都带有相应的API，因此您可以轻松地将Dify集成到自己的业务逻辑中。
+  所有 Dify 的功能都带有相应的 API，因此您可以轻松地将 Dify 集成到自己的业务逻辑中。


 ## 功能比较
@@ -84,21 +84,21 @@ Dify 是一个开源的LLM应用开发平台。其直观的界面结合了AI工
    <th align="center">Dify.AI</th>
    <th align="center">LangChain</th>
    <th align="center">Flowise</th>
-    <th align="center">OpenAI助理API</th>
+    <th align="center">OpenAI Assistant API</th>
  </tr>
  <tr>
    <td align="center">编程方法</td>
    <td align="center">API + 应用程序导向</td>
-    <td align="center">Python代码</td>
+    <td align="center">Python 代码</td>
    <td align="center">应用程序导向</td>
-    <td align="center">API导向</td>
+    <td align="center">API 导向</td>
  </tr>
  <tr>
-    <td align="center">支持的LLMs</td>
+    <td align="center">支持的 LLMs</td>
    <td align="center">丰富多样</td>
    <td align="center">丰富多样</td>
    <td align="center">丰富多样</td>
-    <td align="center">仅限OpenAI</td>
+    <td align="center">仅限 OpenAI</td>
  </tr>
  <tr>
    <td align="center">RAG引擎</td>
@@ -108,21 +108,21 @@ Dify 是一个开源的LLM应用开发平台。其直观的界面结合了AI工
    <td align="center">✅</td>
  </tr>
  <tr>
-    <td align="center">代理</td>
+    <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">工作流程</td>
+    <td align="center">工作流</td>
    <td align="center">✅</td>
    <td align="center">❌</td>
    <td align="center">✅</td>
    <td align="center">❌</td>
  </tr>
  <tr>
-    <td align="center">可观察性</td>
+    <td align="center">可观测性</td>
    <td align="center">✅</td>
    <td align="center">✅</td>
    <td align="center">❌</td>
@@ -202,7 +202,7 @@ docker compose up -d
 ## Contributing

 对于那些想要贡献代码的人，请参阅我们的[贡献指南](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)。
-同时，请考虑通过社交媒体、活动和会议来支持Dify的分享。
+同时，请考虑通过社交媒体、活动和会议来支持 Dify 的分享。

 > 我们正在寻找贡献者来帮助将Dify翻译成除了中文和英文之外的其他语言。如果您有兴趣帮助，请参阅我们的[i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md)获取更多信息，并在我们的[Discord社区服务器](https://discord.gg/8Tpq4AcN9c)的`global-users`频道中留言。

--- a/README_ES.md
+++ b/README_ES.md
@@ -54,7 +54,7 @@ Dify es una plataforma de desarrollo de aplicaciones de LLM de código abierto.


 **2. Soporte de modelos completo**: 
-  Integración perfecta con cientos de LLMs propietarios / de código abierto de docenas de proveedores de inferencia y soluciones auto-alojadas, que cubren GPT, Mistral, Llama2 y cualquier modelo compatible con la API de OpenAI. Se puede encontrar una lista completa de proveedores de modelos admitidos [aquí](https://docs.dify.ai/getting-started/readme/model-providers).
+  Integración perfecta con cientos de LLMs propietarios / de código abierto de docenas de proveedores de inferencia y soluciones auto-alojadas, que cubren GPT, Mistral, Llama3 y cualquier modelo compatible con la API de OpenAI. Se puede encontrar una lista completa de proveedores de modelos admitidos [aquí](https://docs.dify.ai/getting-started/readme/model-providers).

 ![proveedores-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)

--- a/README_FR.md
+++ b/README_FR.md
@@ -54,7 +54,7 @@ Dify est une plateforme de développement d'applications LLM open source. Son in


 **2. Prise en charge complète des modèles**: 
-  Intégration transparente avec des centaines de LLM propriétaires / open source provenant de dizaines de fournisseurs d'inférence et de solutions auto-hébergées, couvrant GPT, Mistral, Llama2, et tous les modèles compatibles avec l'API OpenAI. Une liste complète des fournisseurs de modèles pris en charge se trouve [ici](https://docs.dify.ai/getting-started/readme/model-providers).
+  Intégration transparente avec des centaines de LLM propriétaires / open source provenant de dizaines de fournisseurs d'inférence et de solutions auto-hébergées, couvrant GPT, Mistral, Llama3, et tous les modèles compatibles avec l'API OpenAI. Une liste complète des fournisseurs de modèles pris en charge se trouve [ici](https://docs.dify.ai/getting-started/readme/model-providers).

 ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)

--- a/README_JA.md
+++ b/README_JA.md
@@ -55,9 +55,7 @@ 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


 **2. 網羅的なモデルサポート**: 
-  数百のプロプライエタリ/オープンソースのLLMと、数十の推論プロバイダーおよびセルフホスティングソリューションとのシームレスな統合を提供します。GPT、Mistral、Llama2、およびOpenAI API互換のモデルをカバーします。サポートされているモデルプロバイダーの完全なリストは[こちら](https://docs
-
-.dify.ai/getting-started/readme/model-providers)をご覧ください。
+  数百のプロプライエタリ/オープンソースのLLMと、数十の推論プロバイダーおよびセルフホスティングソリューションとのシームレスな統合を提供します。GPT、Mistral、Llama3、およびOpenAI API互換のモデルをカバーします。サポートされているモデルプロバイダーの完全なリストは[こちら](https://docs.dify.ai/getting-started/readme/model-providers)をご覧ください。

 ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)

@@ -155,9 +153,7 @@ 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
 さらなる参照や詳細な手順については、[ドキュメント](https://docs.dify.ai)をご覧ください。

 - **エンタープライズ/組織向けのDify</br>**
-追加のエンタープライズ向け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)してエンタープライズのニーズについて相談してください。 </br>
+追加のエンタープライズ向け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)してエンタープライズ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、ワンクリックで独自のAWS VPCにデプロイできます。カスタムロゴとブランディングでアプリを作成するオプションを備えた手頃な価格のAMIオファリングです。


--- a/README_KL.md
+++ b/README_KL.md
@@ -54,7 +54,7 @@ Dify is an open-source LLM app development platform. Its intuitive interface com


 **2. Comprehensive model support**: 
-  Seamless integration with hundreds of proprietary / open-source LLMs from dozens of inference providers and self-hosted solutions, covering GPT, Mistral, Llama2, and any OpenAI API-compatible models. A full list of supported model providers can be found [here](https://docs.dify.ai/getting-started/readme/model-providers).
+  Seamless integration with hundreds of proprietary / open-source LLMs from dozens of inference providers and self-hosted solutions, covering GPT, Mistral, Llama3, and any OpenAI API-compatible models. A full list of supported model providers can be found [here](https://docs.dify.ai/getting-started/readme/model-providers).

 ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)

--- a/api/.env.example
+++ b/api/.env.example
@@ -1,6 +1,3 @@
-# Server Edition
-EDITION=SELF_HOSTED
-
 # Your App secret key will be used for securely signing the session cookie
 # Make sure you are changing this key for your deployment with a strong key.
 # You can generate a strong key using `openssl rand -base64 42`.
@@ -52,12 +49,20 @@ AZURE_BLOB_ACCOUNT_NAME=your-account-name
 AZURE_BLOB_ACCOUNT_KEY=your-account-key
 AZURE_BLOB_CONTAINER_NAME=yout-container-name
 AZURE_BLOB_ACCOUNT_URL=https://<your_account_name>.blob.core.windows.net
+# Aliyun oss Storage configuration
+ALIYUN_OSS_BUCKET_NAME=your-bucket-name
+ALIYUN_OSS_ACCESS_KEY=your-access-key
+ALIYUN_OSS_SECRET_KEY=your-secret-key
+ALIYUN_OSS_ENDPOINT=your-endpoint
+# Google Storage configuration
+GOOGLE_STORAGE_BUCKET_NAME=yout-bucket-name
+GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON=your-google-service-account-json-base64-string

 # CORS configuration
 WEB_API_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 CONSOLE_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*

-# Vector database configuration, support: weaviate, qdrant, milvus, relyt
+# Vector database configuration, support: weaviate, qdrant, milvus, relyt, pgvecto_rs
 VECTOR_STORE=weaviate

 # Weaviate configuration
@@ -70,6 +75,8 @@ WEAVIATE_BATCH_SIZE=100
 QDRANT_URL=http://localhost:6333
 QDRANT_API_KEY=difyai123456
 QDRANT_CLIENT_TIMEOUT=20
+QDRANT_GRPC_ENABLED=false
+QDRANT_GRPC_PORT=6334

 # Milvus configuration
 MILVUS_HOST=127.0.0.1
@@ -85,6 +92,13 @@ RELYT_USER=postgres
 RELYT_PASSWORD=postgres
 RELYT_DATABASE=postgres

+# PGVECTO_RS configuration
+PGVECTO_RS_HOST=localhost
+PGVECTO_RS_PORT=5431
+PGVECTO_RS_USER=postgres
+PGVECTO_RS_PASSWORD=difyai123456
+PGVECTO_RS_DATABASE=postgres
+
 # Upload configuration
 UPLOAD_FILE_SIZE_LIMIT=15
 UPLOAD_FILE_BATCH_LIMIT=5
@@ -118,25 +132,6 @@ NOTION_CLIENT_SECRET=you-client-secret
 NOTION_CLIENT_ID=you-client-id
 NOTION_INTERNAL_SECRET=you-internal-secret

-# Hosted Model Credentials
-HOSTED_OPENAI_API_KEY=
-HOSTED_OPENAI_API_BASE=
-HOSTED_OPENAI_API_ORGANIZATION=
-HOSTED_OPENAI_TRIAL_ENABLED=false
-HOSTED_OPENAI_QUOTA_LIMIT=200
-HOSTED_OPENAI_PAID_ENABLED=false
-
-HOSTED_AZURE_OPENAI_ENABLED=false
-HOSTED_AZURE_OPENAI_API_KEY=
-HOSTED_AZURE_OPENAI_API_BASE=
-HOSTED_AZURE_OPENAI_QUOTA_LIMIT=200
-
-HOSTED_ANTHROPIC_API_BASE=
-HOSTED_ANTHROPIC_API_KEY=
-HOSTED_ANTHROPIC_TRIAL_ENABLED=false
-HOSTED_ANTHROPIC_QUOTA_LIMIT=600000
-HOSTED_ANTHROPIC_PAID_ENABLED=false
-
 ETL_TYPE=dify
 UNSTRUCTURED_API_URL=

@@ -160,3 +155,11 @@ CODE_MAX_NUMBER_ARRAY_LENGTH=1000
 # API Tool configuration
 API_TOOL_DEFAULT_CONNECT_TIMEOUT=10
 API_TOOL_DEFAULT_READ_TIMEOUT=60
+
+# HTTP Node configuration
+HTTP_REQUEST_MAX_CONNECT_TIMEOUT=300
+HTTP_REQUEST_MAX_READ_TIMEOUT=600
+HTTP_REQUEST_MAX_WRITE_TIMEOUT=600
+
+# Log file path
+LOG_FILE=
--- a/api/README.md
+++ b/api/README.md
@@ -55,3 +55,16 @@
 9. If you need to debug local async processing, please start the worker service by running 
 `celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail`.
 The started celery app handles the async tasks, e.g. dataset importing and documents indexing.
+
+
+## Testing
+
+1. Install dependencies for both the backend and the test environment
+   ```bash
+   pip install -r requirements.txt -r requirements-dev.txt
+   ``` 
+   
+2. Run the tests locally with mocked system environment variables in `tool.pytest_env` section in `pyproject.toml`
+   ```bash
+   dev/pytest/pytest_all_tests.sh
+   ```
--- a/api/app.py
+++ b/api/app.py
@@ -4,23 +4,28 @@ if not os.environ.get("DEBUG") or os.environ.get("DEBUG").lower() != 'true':
    from gevent import monkey

    monkey.patch_all()
-    # if os.environ.get("VECTOR_STORE") == 'milvus':
+
    import grpc.experimental.gevent

    grpc.experimental.gevent.init_gevent()

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

 from flask import Flask, Response, request
 from flask_cors import CORS
-
 from werkzeug.exceptions import Unauthorized
+
 from commands import register_commands
-from config import CloudEditionConfig, Config
+from config import Config
+
+# DO NOT REMOVE BELOW
+from events import event_handlers
 from extensions import (
    ext_celery,
    ext_code_based_extension,
@@ -37,11 +42,8 @@ from extensions import (
 from extensions.ext_database import db
 from extensions.ext_login import login_manager
 from libs.passport import PassportService
-from services.account_service import AccountService
-
-# DO NOT REMOVE BELOW
-from events import event_handlers
 from models import account, dataset, model, source, task, tool, tools, web
+from services.account_service import AccountService

 # DO NOT REMOVE ABOVE

@@ -73,20 +75,32 @@ config_type = os.getenv('EDITION', default='SELF_HOSTED')  # ce edition first
 # ----------------------------


-def create_app(test_config=None) -> Flask:
+def create_app() -> Flask:
    app = DifyApp(__name__)
-
-    if test_config:
-        app.config.from_object(test_config)
-    else:
-        if config_type == "CLOUD":
-            app.config.from_object(CloudEditionConfig())
-        else:
-            app.config.from_object(Config())
+    app.config.from_object(Config())

    app.secret_key = app.config['SECRET_KEY']

-    logging.basicConfig(level=app.config.get('LOG_LEVEL', 'INFO'))
+    log_handlers = None
+    log_file = app.config.get('LOG_FILE')
+    if log_file:
+        log_dir = os.path.dirname(log_file)
+        os.makedirs(log_dir, exist_ok=True)
+        log_handlers = [
+            RotatingFileHandler(
+                filename=log_file,
+                maxBytes=1024 * 1024 * 1024,
+                backupCount=5
+            ),
+            logging.StreamHandler(sys.stdout)
+        ]
+
+    logging.basicConfig(
+        level=app.config.get('LOG_LEVEL'),
+        format=app.config.get('LOG_FORMAT'),
+        datefmt=app.config.get('LOG_DATEFORMAT'),
+        handlers=log_handlers
+    )

    initialize_extensions(app)
    register_blueprints(app)
@@ -115,7 +129,7 @@ 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 == 'console':
+    if request.blueprint in ['console', 'inner_api']:
        # Check if the user_id contains a dot, indicating the old format
        auth_header = request.headers.get('Authorization', '')
        if not auth_header:
@@ -151,6 +165,7 @@ def unauthorized_handler():
 def register_blueprints(app):
    from controllers.console import bp as console_app_bp
    from controllers.files import bp as files_bp
+    from controllers.inner_api import bp as inner_api_bp
    from controllers.service_api import bp as service_api_bp
    from controllers.web import bp as web_bp

@@ -188,6 +203,8 @@ def register_blueprints(app):
         )
    app.register_blueprint(files_bp)

+    app.register_blueprint(inner_api_bp)
+

 # create app
 app = create_app()
--- a/api/config.py
+++ b/api/config.py
@@ -5,6 +5,7 @@ import dotenv
 dotenv.load_dotenv()

 DEFAULTS = {
+    'EDITION': 'SELF_HOSTED',
    'DB_USERNAME': 'postgres',
    'DB_PASSWORD': '',
    'DB_HOST': 'localhost',
@@ -36,8 +37,13 @@ DEFAULTS = {
    'WEAVIATE_GRPC_ENABLED': 'True',
    'WEAVIATE_BATCH_SIZE': 100,
    'QDRANT_CLIENT_TIMEOUT': 20,
+    'QDRANT_GRPC_ENABLED': 'False',
+    'QDRANT_GRPC_PORT': '6334',
    'CELERY_BACKEND': 'database',
    'LOG_LEVEL': 'INFO',
+    'LOG_FILE': '',
+    'LOG_FORMAT': '%(asctime)s.%(msecs)03d %(levelname)s [%(threadName)s] [%(filename)s:%(lineno)d] - %(message)s',
+    'LOG_DATEFORMAT': '%Y-%m-%d %H:%M:%S',
    'HOSTED_OPENAI_QUOTA_LIMIT': 200,
    'HOSTED_OPENAI_TRIAL_ENABLED': 'False',
    'HOSTED_OPENAI_TRIAL_MODELS': 'gpt-3.5-turbo,gpt-3.5-turbo-1106,gpt-3.5-turbo-instruct,gpt-3.5-turbo-16k,gpt-3.5-turbo-16k-0613,gpt-3.5-turbo-0613,gpt-3.5-turbo-0125,text-davinci-003',
@@ -69,6 +75,8 @@ DEFAULTS = {
    'TOOL_ICON_CACHE_MAX_AGE': 3600,
    'MILVUS_DATABASE': 'default',
    'KEYWORD_DATA_SOURCE_TYPE': 'database',
+    'INNER_API': 'False',
+    'ENTERPRISE_ENABLED': 'False',
 }


@@ -99,12 +107,15 @@ class Config:
        # ------------------------
        # General Configurations.
        # ------------------------
-        self.CURRENT_VERSION = "0.6.3"
+        self.CURRENT_VERSION = "0.6.6"
        self.COMMIT_SHA = get_env('COMMIT_SHA')
-        self.EDITION = "SELF_HOSTED"
+        self.EDITION = get_env('EDITION')
        self.DEPLOY_ENV = get_env('DEPLOY_ENV')
        self.TESTING = False
        self.LOG_LEVEL = get_env('LOG_LEVEL')
+        self.LOG_FILE = get_env('LOG_FILE')
+        self.LOG_FORMAT = get_env('LOG_FORMAT')
+        self.LOG_DATEFORMAT = get_env('LOG_DATEFORMAT')

        # The backend URL prefix of the console API.
        # used to concatenate the login authorization callback or notion integration callback.
@@ -133,6 +144,11 @@ class Config:
        # Alternatively you can set it with `SECRET_KEY` environment variable.
        self.SECRET_KEY = get_env('SECRET_KEY')

+        # Enable or disable the inner API.
+        self.INNER_API = get_bool_env('INNER_API')
+        # The inner API key is used to authenticate the inner API.
+        self.INNER_API_KEY = get_env('INNER_API_KEY')
+
        # cors settings
        self.CONSOLE_CORS_ALLOW_ORIGINS = get_cors_allow_origins(
            'CONSOLE_CORS_ALLOW_ORIGINS', self.CONSOLE_WEB_URL)
@@ -195,6 +211,12 @@ class Config:
        self.AZURE_BLOB_ACCOUNT_KEY = get_env('AZURE_BLOB_ACCOUNT_KEY')
        self.AZURE_BLOB_CONTAINER_NAME = get_env('AZURE_BLOB_CONTAINER_NAME')
        self.AZURE_BLOB_ACCOUNT_URL = get_env('AZURE_BLOB_ACCOUNT_URL')
+        self.ALIYUN_OSS_BUCKET_NAME=get_env('ALIYUN_OSS_BUCKET_NAME')
+        self.ALIYUN_OSS_ACCESS_KEY=get_env('ALIYUN_OSS_ACCESS_KEY')
+        self.ALIYUN_OSS_SECRET_KEY=get_env('ALIYUN_OSS_SECRET_KEY')
+        self.ALIYUN_OSS_ENDPOINT=get_env('ALIYUN_OSS_ENDPOINT')
+        self.GOOGLE_STORAGE_BUCKET_NAME = get_env('GOOGLE_STORAGE_BUCKET_NAME')
+        self.GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64 = get_env('GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64')

        # ------------------------
        # Vector Store Configurations.
@@ -206,6 +228,8 @@ class Config:
        self.QDRANT_URL = get_env('QDRANT_URL')
        self.QDRANT_API_KEY = get_env('QDRANT_API_KEY')
        self.QDRANT_CLIENT_TIMEOUT = get_env('QDRANT_CLIENT_TIMEOUT')
+        self.QDRANT_GRPC_ENABLED = get_env('QDRANT_GRPC_ENABLED')
+        self.QDRANT_GRPC_PORT = get_env('QDRANT_GRPC_PORT')

        # milvus / zilliz setting
        self.MILVUS_HOST = get_env('MILVUS_HOST')
@@ -228,6 +252,13 @@ class Config:
        self.RELYT_PASSWORD = get_env('RELYT_PASSWORD')
        self.RELYT_DATABASE = get_env('RELYT_DATABASE')

+        # pgvecto rs settings
+        self.PGVECTO_RS_HOST = get_env('PGVECTO_RS_HOST')
+        self.PGVECTO_RS_PORT = get_env('PGVECTO_RS_PORT')
+        self.PGVECTO_RS_USER = get_env('PGVECTO_RS_USER')
+        self.PGVECTO_RS_PASSWORD = get_env('PGVECTO_RS_PASSWORD')
+        self.PGVECTO_RS_DATABASE = get_env('PGVECTO_RS_DATABASE')
+
        # ------------------------
        # Mail Configurations.
        # ------------------------
@@ -243,7 +274,7 @@ class Config:
        self.SMTP_USE_TLS = get_bool_env('SMTP_USE_TLS')
        
        # ------------------------
-        # Workpace Configurations.
+        # Workspace Configurations.
        # ------------------------
        self.INVITE_EXPIRY_HOURS = int(get_env('INVITE_EXPIRY_HOURS'))

@@ -282,6 +313,12 @@ class Config:
        # ------------------------
        # Platform Configurations.
        # ------------------------
+        self.GITHUB_CLIENT_ID = get_env('GITHUB_CLIENT_ID')
+        self.GITHUB_CLIENT_SECRET = get_env('GITHUB_CLIENT_SECRET')
+        self.GOOGLE_CLIENT_ID = get_env('GOOGLE_CLIENT_ID')
+        self.GOOGLE_CLIENT_SECRET = get_env('GOOGLE_CLIENT_SECRET')
+        self.OAUTH_REDIRECT_PATH = get_env('OAUTH_REDIRECT_PATH')
+
        self.HOSTED_OPENAI_API_KEY = get_env('HOSTED_OPENAI_API_KEY')
        self.HOSTED_OPENAI_API_BASE = get_env('HOSTED_OPENAI_API_BASE')
        self.HOSTED_OPENAI_API_ORGANIZATION = get_env('HOSTED_OPENAI_API_ORGANIZATION')
@@ -327,16 +364,4 @@ class Config:
        self.TOOL_ICON_CACHE_MAX_AGE = get_env('TOOL_ICON_CACHE_MAX_AGE')

        self.KEYWORD_DATA_SOURCE_TYPE = get_env('KEYWORD_DATA_SOURCE_TYPE')
-
-class CloudEditionConfig(Config):
-
-    def __init__(self):
-        super().__init__()
-
-        self.EDITION = "CLOUD"
-
-        self.GITHUB_CLIENT_ID = get_env('GITHUB_CLIENT_ID')
-        self.GITHUB_CLIENT_SECRET = get_env('GITHUB_CLIENT_SECRET')
-        self.GOOGLE_CLIENT_ID = get_env('GOOGLE_CLIENT_ID')
-        self.GOOGLE_CLIENT_SECRET = get_env('GOOGLE_CLIENT_SECRET')
-        self.OAUTH_REDIRECT_PATH = get_env('OAUTH_REDIRECT_PATH')
+        self.ENTERPRISE_ENABLED = get_bool_env('ENTERPRISE_ENABLED')
--- a/api/constants/languages.py
+++ b/api/constants/languages.py
@@ -1,10 +1,11 @@


-languages = ['en-US', 'zh-Hans', 'pt-BR', 'es-ES', 'fr-FR', 'de-DE', 'ja-JP', 'ko-KR', 'ru-RU', 'it-IT', 'uk-UA', 'vi-VN']
+languages = ['en-US', 'zh-Hans', 'zh-Hant', 'pt-BR', 'es-ES', 'fr-FR', 'de-DE', 'ja-JP', 'ko-KR', 'ru-RU', 'it-IT', 'uk-UA', 'vi-VN']

 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',
--- a/api/controllers/init.py
+++ b/api/controllers/init.py
@@ -1,4 +1,3 @@
-# -*- coding:utf-8 -*-



--- a/api/controllers/console/init.py
+++ b/api/controllers/console/init.py
@@ -1,22 +1,60 @@
 from flask import Blueprint
+
 from libs.external_api import ExternalApi

 bp = Blueprint('console', __name__, url_prefix='/console/api')
 api = ExternalApi(bp)

 # Import other controllers
-from . import admin, apikey, extension, feature, setup, version, ping
+from . import admin, apikey, extension, feature, ping, setup, version
+
 # Import app controllers
-from .app import (advanced_prompt_template, annotation, app, audio, completion, conversation, generator, message,
-                  model_config, site, statistic, workflow, workflow_run, workflow_app_log, workflow_statistic, agent)
+from .app import (
+    advanced_prompt_template,
+    agent,
+    annotation,
+    app,
+    audio,
+    completion,
+    conversation,
+    generator,
+    message,
+    model_config,
+    site,
+    statistic,
+    workflow,
+    workflow_app_log,
+    workflow_run,
+    workflow_statistic,
+)
+
 # Import auth controllers
 from .auth import activate, data_source_oauth, login, oauth
+
 # Import billing controllers
 from .billing import billing
+
 # Import datasets controllers
 from .datasets import data_source, datasets, datasets_document, datasets_segments, file, hit_testing
+
+# Import enterprise controllers
+from .enterprise import enterprise_sso
+
 # Import explore controllers
-from .explore import (audio, completion, conversation, installed_app, message, parameter, recommended_app,
-                      saved_message, workflow)
+from .explore import (
+    audio,
+    completion,
+    conversation,
+    installed_app,
+    message,
+    parameter,
+    recommended_app,
+    saved_message,
+    workflow,
+)
+
+# Import tag controllers
+from .tag import tags
+
 # Import workspace controllers
-from .workspace import account, members, model_providers, models, tool_providers, workspace
+from .workspace import account, members, model_providers, models, tool_providers, workspace
--- a/api/controllers/console/app/app.py
+++ b/api/controllers/console/app/app.py
@@ -1,26 +1,25 @@
 import json
+import uuid

 from flask_login import current_user
-from flask_restful import Resource, inputs, marshal_with, reqparse
-from werkzeug.exceptions import Forbidden, BadRequest
+from flask_restful import Resource, inputs, marshal, marshal_with, reqparse
+from werkzeug.exceptions import BadRequest, Forbidden, abort

 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, cloud_edition_billing_resource_check
-from core.agent.entities import AgentToolEntity
-from extensions.ext_database import db
+from core.tools.tool_manager import ToolManager
+from core.tools.utils.configuration import ToolParameterConfigurationManager
 from fields.app_fields import (
    app_detail_fields,
    app_detail_fields_with_site,
    app_pagination_fields,
 )
 from libs.login import login_required
+from models.model import App, AppMode, AppModelConfig
 from services.app_service import AppService
-from models.model import App, AppModelConfig, AppMode
-from core.tools.utils.configuration import ToolParameterConfigurationManager
-from core.tools.tool_manager import ToolManager
-
+from services.tag_service import TagService

 ALLOW_CREATE_APP_MODES = ['chat', 'agent-chat', 'advanced-chat', 'workflow', 'completion']

@@ -30,21 +29,29 @@ class AppListApi(Resource):
    @setup_required
    @login_required
    @account_initialization_required
-    @marshal_with(app_pagination_fields)
    def get(self):
        """Get app list"""
+        def uuid_list(value):
+            try:
+                return [str(uuid.UUID(v)) for v in value.split(',')]
+            except ValueError:
+                abort(400, message="Invalid UUID format in tag_ids.")
        parser = reqparse.RequestParser()
        parser.add_argument('page', type=inputs.int_range(1, 99999), required=False, default=1, location='args')
        parser.add_argument('limit', type=inputs.int_range(1, 100), required=False, default=20, location='args')
        parser.add_argument('mode', type=str, choices=['chat', 'workflow', 'agent-chat', 'channel', 'all'], default='all', location='args', required=False)
        parser.add_argument('name', type=str, location='args', required=False)
+        parser.add_argument('tag_ids', type=uuid_list, location='args', required=False)
+
        args = parser.parse_args()

        # get app list
        app_service = AppService()
        app_pagination = app_service.get_paginate_apps(current_user.current_tenant_id, args)
+        if not app_pagination:
+            return {'data': [], 'total': 0, 'page': 1, 'limit': 20, 'has_more': False}

-        return app_pagination
+        return marshal(app_pagination, app_pagination_fields)

    @setup_required
    @login_required
@@ -109,43 +116,9 @@ class AppApi(Resource):
    @marshal_with(app_detail_fields_with_site)
    def get(self, app_model):
        """Get app detail"""
-        # get original app model config
-        if app_model.mode == AppMode.AGENT_CHAT.value or app_model.is_agent:
-            model_config: AppModelConfig = app_model.app_model_config
-            agent_mode = model_config.agent_mode_dict
-            # decrypt agent tool parameters if it's secret-input
-            for tool in agent_mode.get('tools') or []:
-                if not isinstance(tool, dict) or len(tool.keys()) <= 3:
-                    continue
-                agent_tool_entity = AgentToolEntity(**tool)
-                # get tool
-                try:
-                    tool_runtime = ToolManager.get_agent_tool_runtime(
-                        tenant_id=current_user.current_tenant_id,
-                        agent_tool=agent_tool_entity,
-                    )
-                    manager = ToolParameterConfigurationManager(
-                        tenant_id=current_user.current_tenant_id,
-                        tool_runtime=tool_runtime,
-                        provider_name=agent_tool_entity.provider_id,
-                        provider_type=agent_tool_entity.provider_type,
-                    )
+        app_service = AppService()

-                    # get decrypted parameters
-                    if agent_tool_entity.tool_parameters:
-                        parameters = manager.decrypt_tool_parameters(agent_tool_entity.tool_parameters or {})
-                        masked_parameter = manager.mask_tool_parameters(parameters or {})
-                    else:
-                        masked_parameter = {}
-
-                    # override tool parameters
-                    tool['tool_parameters'] = masked_parameter
-                except Exception as e:
-                    pass
-
-            # override agent mode
-            model_config.agent_mode = json.dumps(agent_mode)
-            db.session.commit()
+        app_model = app_service.get_app(app_model)

        return app_model

--- a/api/controllers/console/app/model_config.py
+++ b/api/controllers/console/app/model_config.py
@@ -57,6 +57,7 @@ class ModelConfigResource(Resource):
                try:
                    tool_runtime = ToolManager.get_agent_tool_runtime(
                        tenant_id=current_user.current_tenant_id,
+                        app_id=app_model.id,
                        agent_tool=agent_tool_entity,
                    )
                    manager = ToolParameterConfigurationManager(
@@ -64,6 +65,7 @@ class ModelConfigResource(Resource):
                        tool_runtime=tool_runtime,
                        provider_name=agent_tool_entity.provider_id,
                        provider_type=agent_tool_entity.provider_type,
+                        identity_id=f'AGENT.{app_model.id}'
                    )
                except Exception as e:
                    continue
@@ -94,6 +96,7 @@ class ModelConfigResource(Resource):
                    try:
                        tool_runtime = ToolManager.get_agent_tool_runtime(
                            tenant_id=current_user.current_tenant_id,
+                            app_id=app_model.id,
                            agent_tool=agent_tool_entity,
                        )
                    except Exception as e:
@@ -104,6 +107,7 @@ class ModelConfigResource(Resource):
                    tool_runtime=tool_runtime,
                    provider_name=agent_tool_entity.provider_id,
                    provider_type=agent_tool_entity.provider_type,
+                    identity_id=f'AGENT.{app_model.id}'
                )
                manager.delete_tool_parameters_cache()

@@ -111,9 +115,11 @@ class ModelConfigResource(Resource):
                if agent_tool_entity.tool_parameters:
                    if key not in masked_parameter_map:
                        continue
-
-                    if agent_tool_entity.tool_parameters == masked_parameter_map[key]:
-                        agent_tool_entity.tool_parameters = parameter_map[key]
+                    
+                    for masked_key, masked_value in masked_parameter_map[key].items():
+                        if masked_key in agent_tool_entity.tool_parameters and \
+                                agent_tool_entity.tool_parameters[masked_key] == masked_value:
+                            agent_tool_entity.tool_parameters[masked_key] = parameter_map[key].get(masked_key)

                # encrypt parameters
                if agent_tool_entity.tool_parameters:
--- a/api/controllers/console/auth/login.py
+++ b/api/controllers/console/auth/login.py
@@ -26,10 +26,13 @@ class LoginApi(Resource):

        try:
            account = AccountService.authenticate(args['email'], args['password'])
-        except services.errors.account.AccountLoginError:
-            return {'code': 'unauthorized', 'message': 'Invalid email or password'}, 401
+        except services.errors.account.AccountLoginError as e:
+            return {'code': 'unauthorized', 'message': str(e)}, 401

-        TenantService.create_owner_tenant_if_not_exist(account)
+        # SELF_HOSTED only have one workspace
+        tenants = TenantService.get_join_tenants(account)
+        if len(tenants) == 0:
+            return {'result': 'fail', 'data': 'workspace not found, please contact system admin to invite you to join in a workspace'}

        AccountService.update_last_login(account, request)

--- a/api/controllers/console/datasets/datasets.py
+++ b/api/controllers/console/datasets/datasets.py
@@ -48,11 +48,14 @@ class DatasetListApi(Resource):
        limit = request.args.get('limit', default=20, type=int)
        ids = request.args.getlist('ids')
        provider = request.args.get('provider', default="vendor")
+        search = request.args.get('keyword', default=None, type=str)
+        tag_ids = request.args.getlist('tag_ids')
+
        if ids:
            datasets, total = DatasetService.get_datasets_by_ids(ids, current_user.current_tenant_id)
        else:
            datasets, total = DatasetService.get_datasets(page, limit, provider,
-                                                          current_user.current_tenant_id, current_user)
+                                                          current_user.current_tenant_id, current_user, search, tag_ids)

        # check embedding setting
        provider_manager = ProviderManager()
@@ -184,6 +187,10 @@ class DatasetApi(Resource):
                            help='Invalid indexing technique.')
        parser.add_argument('permission', type=str, location='json', choices=(
            'only_me', 'all_team_members'), help='Invalid permission.')
+        parser.add_argument('embedding_model', type=str,
+                            location='json', help='Invalid embedding model.')
+        parser.add_argument('embedding_model_provider', type=str,
+                            location='json', help='Invalid embedding model provider.')
        parser.add_argument('retrieval_model', type=dict, location='json', help='Invalid retrieval model.')
        args = parser.parse_args()

@@ -469,7 +476,7 @@ class DatasetRetrievalSettingApi(Resource):
    @account_initialization_required
    def get(self):
        vector_type = current_app.config['VECTOR_STORE']
-        if vector_type == 'milvus':
+        if vector_type == 'milvus' or vector_type == 'pgvecto_rs' or vector_type == 'relyt':
            return {
                'retrieval_method': [
                    'semantic_search'
@@ -491,7 +498,7 @@ class DatasetRetrievalSettingMockApi(Resource):
    @account_initialization_required
    def get(self, vector_type):

-        if vector_type == 'milvus':
+        if vector_type == 'milvus' or vector_type == 'relyt':
            return {
                'retrieval_method': [
                    'semantic_search'
@@ -506,10 +513,27 @@ class DatasetRetrievalSettingMockApi(Resource):
        else:
            raise ValueError("Unsupported vector db type.")

+class DatasetErrorDocs(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        results = DocumentService.get_error_documents_by_dataset_id(dataset_id_str)
+
+        return {
+            'data': [marshal(item, document_status_fields) for item in results],
+            'total': len(results)
+        }, 200
+

 api.add_resource(DatasetListApi, '/datasets')
 api.add_resource(DatasetApi, '/datasets/<uuid:dataset_id>')
 api.add_resource(DatasetQueryApi, '/datasets/<uuid:dataset_id>/queries')
+api.add_resource(DatasetErrorDocs, '/datasets/<uuid:dataset_id>/error-docs')
 api.add_resource(DatasetIndexingEstimateApi, '/datasets/indexing-estimate')
 api.add_resource(DatasetRelatedAppListApi, '/datasets/<uuid:dataset_id>/related-apps')
 api.add_resource(DatasetIndexingStatusApi, '/datasets/<uuid:dataset_id>/indexing-status')
--- a/api/controllers/console/datasets/datasets_document.py
+++ b/api/controllers/console/datasets/datasets_document.py
@@ -1,3 +1,4 @@
+import logging
 from datetime import datetime, timezone

 from flask import request
@@ -233,7 +234,7 @@ class DatasetDocumentListApi(Resource):
                            location='json')
        parser.add_argument('data_source', type=dict, required=False, location='json')
        parser.add_argument('process_rule', type=dict, required=False, location='json')
-        parser.add_argument('duplicate', type=bool, nullable=False, location='json')
+        parser.add_argument('duplicate', type=bool, default=True, nullable=False, location='json')
        parser.add_argument('original_document_id', type=str, required=False, location='json')
        parser.add_argument('doc_form', type=str, default='text_model', required=False, nullable=False, location='json')
        parser.add_argument('doc_language', type=str, default='English', required=False, nullable=False,
@@ -393,9 +394,6 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
    def get(self, dataset_id, batch):
        dataset_id = str(dataset_id)
        batch = str(batch)
-        dataset = DatasetService.get_dataset(dataset_id)
-        if dataset is None:
-            raise NotFound("Dataset not found.")
        documents = self.get_batch_documents(dataset_id, batch)
        response = {
            "tokens": 0,
@@ -883,6 +881,49 @@ class DocumentRecoverApi(DocumentResource):
        return {'result': 'success'}, 204


+class DocumentRetryApi(DocumentResource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self, dataset_id):
+        """retry document."""
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('document_ids', type=list, required=True, nullable=False,
+                            location='json')
+        args = parser.parse_args()
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        retry_documents = []
+        if not dataset:
+            raise NotFound('Dataset not found.')
+        for document_id in args['document_ids']:
+            try:
+                document_id = str(document_id)
+
+                document = DocumentService.get_document(dataset.id, document_id)
+
+                # 404 if document not found
+                if document is None:
+                    raise NotFound("Document Not Exists.")
+
+                # 403 if document is archived
+                if DocumentService.check_archived(document):
+                    raise ArchivedDocumentImmutableError()
+
+                # 400 if document is completed
+                if document.indexing_status == 'completed':
+                    raise DocumentAlreadyFinishedError()
+                retry_documents.append(document)
+            except Exception as e:
+                logging.error(f"Document {document_id} retry failed: {str(e)}")
+                continue
+        # retry document
+        DocumentService.retry_document(dataset_id, retry_documents)
+
+        return {'result': 'success'}, 204
+
+
 api.add_resource(GetProcessRuleApi, '/datasets/process-rule')
 api.add_resource(DatasetDocumentListApi,
                 '/datasets/<uuid:dataset_id>/documents')
@@ -908,3 +949,4 @@ api.add_resource(DocumentStatusApi,
                 '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/status/<string:action>')
 api.add_resource(DocumentPauseApi, '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/processing/pause')
 api.add_resource(DocumentRecoverApi, '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/processing/resume')
+api.add_resource(DocumentRetryApi, '/datasets/<uuid:dataset_id>/retry')
--- a/api/controllers/console/datasets/hit_testing.py
+++ b/api/controllers/console/datasets/hit_testing.py
@@ -12,7 +12,7 @@ from controllers.console.app.error import (
    ProviderNotInitializeError,
    ProviderQuotaExceededError,
 )
-from controllers.console.datasets.error import DatasetNotInitializedError, HighQualityDatasetOnlyError
+from controllers.console.datasets.error import DatasetNotInitializedError
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
 from core.errors.error import (
@@ -45,10 +45,6 @@ class HitTestingApi(Resource):
        except services.errors.account.NoPermissionError as e:
            raise Forbidden(str(e))

-        # only high quality dataset can be used for hit testing
-        if dataset.indexing_technique != 'high_quality':
-            raise HighQualityDatasetOnlyError()
-
        parser = reqparse.RequestParser()
        parser.add_argument('query', type=str, location='json')
        parser.add_argument('retrieval_model', type=dict, required=False, location='json')
--- a/api/tests/unit_tests/core/rag/datasource/vdb/milvus/init.py
+++ b/api/tests/unit_tests/core/rag/datasource/vdb/milvus/init.py
--- a/api/controllers/console/enterprise/enterprise_sso.py
+++ b/api/controllers/console/enterprise/enterprise_sso.py
@@ -0,0 +1,59 @@
+from flask import current_app, redirect
+from flask_restful import Resource, reqparse
+
+from controllers.console import api
+from controllers.console.setup import setup_required
+from services.enterprise.enterprise_sso_service import EnterpriseSSOService
+
+
+class EnterpriseSSOSamlLogin(Resource):
+
+    @setup_required
+    def get(self):
+        return EnterpriseSSOService.get_sso_saml_login()
+
+
+class EnterpriseSSOSamlAcs(Resource):
+
+    @setup_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument('SAMLResponse', type=str, required=True, location='form')
+        args = parser.parse_args()
+        saml_response = args['SAMLResponse']
+
+        try:
+            token = EnterpriseSSOService.post_sso_saml_acs(saml_response)
+            return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}/signin?console_token={token}')
+        except Exception as e:
+            return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}/signin?message={str(e)}')
+
+
+class EnterpriseSSOOidcLogin(Resource):
+
+    @setup_required
+    def get(self):
+        return EnterpriseSSOService.get_sso_oidc_login()
+
+
+class EnterpriseSSOOidcCallback(Resource):
+
+    @setup_required
+    def get(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument('state', type=str, required=True, location='args')
+        parser.add_argument('code', type=str, required=True, location='args')
+        parser.add_argument('oidc-state', type=str, required=True, location='cookies')
+        args = parser.parse_args()
+
+        try:
+            token = EnterpriseSSOService.get_sso_oidc_callback(args)
+            return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}/signin?console_token={token}')
+        except Exception as e:
+            return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}/signin?message={str(e)}')
+
+
+api.add_resource(EnterpriseSSOSamlLogin, '/enterprise/sso/saml/login')
+api.add_resource(EnterpriseSSOSamlAcs, '/enterprise/sso/saml/acs')
+api.add_resource(EnterpriseSSOOidcLogin, '/enterprise/sso/oidc/login')
+api.add_resource(EnterpriseSSOOidcCallback, '/enterprise/sso/oidc/callback')
--- a/api/controllers/console/feature.py
+++ b/api/controllers/console/feature.py
@@ -1,6 +1,7 @@
 from flask_login import current_user
 from flask_restful import Resource

+from services.enterprise.enterprise_feature_service import EnterpriseFeatureService
 from services.feature_service import FeatureService

 from . import api
@@ -14,4 +15,10 @@ class FeatureApi(Resource):
        return FeatureService.get_features(current_user.current_tenant_id).dict()


+class EnterpriseFeatureApi(Resource):
+    def get(self):
+        return EnterpriseFeatureService.get_enterprise_features().dict()
+
+
 api.add_resource(FeatureApi, '/features')
+api.add_resource(EnterpriseFeatureApi, '/enterprise-features')
--- a/api/controllers/console/setup.py
+++ b/api/controllers/console/setup.py
@@ -58,6 +58,8 @@ class SetupApi(Resource):
            password=args['password']
        )

+        TenantService.create_owner_tenant_if_not_exist(account)
+
        setup()
        AccountService.update_last_login(account, request)

--- a/api/controllers/console/tag/tags.py
+++ b/api/controllers/console/tag/tags.py
@@ -0,0 +1,159 @@
+from flask import request
+from flask_login import current_user
+from flask_restful import Resource, marshal_with, reqparse
+from werkzeug.exceptions import Forbidden
+
+from controllers.console import api
+from controllers.console.setup import setup_required
+from controllers.console.wraps import account_initialization_required
+from fields.tag_fields import tag_fields
+from libs.login import login_required
+from models.model import Tag
+from services.tag_service import TagService
+
+
+def _validate_name(name):
+    if not name or len(name) < 1 or len(name) > 40:
+        raise ValueError('Name must be between 1 to 50 characters.')
+    return name
+
+
+class TagListApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(tag_fields)
+    def get(self):
+        tag_type = request.args.get('type', type=str)
+        keyword = request.args.get('keyword', default=None, type=str)
+        tags = TagService.get_tags(tag_type, current_user.current_tenant_id, keyword)
+
+        return tags, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        # The role of the current user in the ta table must be admin or owner
+        if not current_user.is_admin_or_owner:
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('name', nullable=False, required=True,
+                            help='Name must be between 1 to 50 characters.',
+                            type=_validate_name)
+        parser.add_argument('type', type=str, location='json',
+                            choices=Tag.TAG_TYPE_LIST,
+                            nullable=True,
+                            help='Invalid tag type.')
+        args = parser.parse_args()
+        tag = TagService.save_tags(args)
+
+        response = {
+            'id': tag.id,
+            'name': tag.name,
+            'type': tag.type,
+            'binding_count': 0
+        }
+
+        return response, 200
+
+
+class TagUpdateDeleteApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def patch(self, tag_id):
+        tag_id = str(tag_id)
+        # The role of the current user in the ta table must be admin or owner
+        if not current_user.is_admin_or_owner:
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('name', nullable=False, required=True,
+                            help='Name must be between 1 to 50 characters.',
+                            type=_validate_name)
+        args = parser.parse_args()
+        tag = TagService.update_tags(args, tag_id)
+
+        binding_count = TagService.get_tag_binding_count(tag_id)
+
+        response = {
+            'id': tag.id,
+            'name': tag.name,
+            'type': tag.type,
+            'binding_count': binding_count
+        }
+
+        return response, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, tag_id):
+        tag_id = str(tag_id)
+        # The role of the current user in the ta table must be admin or owner
+        if not current_user.is_admin_or_owner:
+            raise Forbidden()
+
+        TagService.delete_tag(tag_id)
+
+        return 200
+
+
+class TagBindingCreateApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        # The role of the current user in the ta table must be admin or owner
+        if not current_user.is_admin_or_owner:
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('tag_ids', type=list, nullable=False, required=True, location='json',
+                            help='Tag IDs is required.')
+        parser.add_argument('target_id', type=str, nullable=False, required=True, location='json',
+                            help='Target ID is required.')
+        parser.add_argument('type', type=str, location='json',
+                            choices=Tag.TAG_TYPE_LIST,
+                            nullable=True,
+                            help='Invalid tag type.')
+        args = parser.parse_args()
+        TagService.save_tag_binding(args)
+
+        return 200
+
+
+class TagBindingDeleteApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        # The role of the current user in the ta table must be admin or owner
+        if not current_user.is_admin_or_owner:
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('tag_id', type=str, nullable=False, required=True,
+                            help='Tag ID is required.')
+        parser.add_argument('target_id', type=str, nullable=False, required=True,
+                            help='Target ID is required.')
+        parser.add_argument('type', type=str, location='json',
+                            choices=Tag.TAG_TYPE_LIST,
+                            nullable=True,
+                            help='Invalid tag type.')
+        args = parser.parse_args()
+        TagService.delete_tag_binding(args)
+
+        return 200
+
+
+api.add_resource(TagListApi, '/tags')
+api.add_resource(TagUpdateDeleteApi, '/tags/<uuid:tag_id>')
+api.add_resource(TagBindingCreateApi, '/tag-bindings/create')
+api.add_resource(TagBindingDeleteApi, '/tag-bindings/remove')
--- a/api/controllers/console/workspace/members.py
+++ b/api/controllers/console/workspace/members.py
@@ -9,7 +9,7 @@ from controllers.console.wraps import account_initialization_required, cloud_edi
 from extensions.ext_database import db
 from fields.member_fields import account_with_role_list_fields
 from libs.login import login_required
-from models.account import Account
+from models.account import Account, TenantAccountRole
 from services.account_service import RegisterService, TenantService
 from services.errors.account import AccountAlreadyInTenantError

@@ -43,7 +43,7 @@ class MemberInviteEmailApi(Resource):
        invitee_emails = args['emails']
        invitee_role = args['role']
        interface_language = args['language']
-        if invitee_role not in ['admin', 'normal']:
+        if invitee_role not in [TenantAccountRole.ADMIN, TenantAccountRole.NORMAL]:
            return {'code': 'invalid-role', 'message': 'Invalid role'}, 400

        inviter = current_user
--- a/api/controllers/console/workspace/models.py
+++ b/api/controllers/console/workspace/models.py
@@ -11,6 +11,7 @@ from core.model_runtime.entities.model_entities import ModelType
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
 from core.model_runtime.utils.encoders import jsonable_encoder
 from libs.login import login_required
+from models.account import TenantAccountRole
 from services.model_provider_service import ModelProviderService


@@ -94,7 +95,7 @@ class ModelProviderModelApi(Resource):
    @login_required
    @account_initialization_required
    def post(self, provider: str):
-        if current_user.current_tenant.current_role not in ['admin', 'owner']:
+        if not TenantAccountRole.is_privileged_role(current_user.current_tenant.current_role):
            raise Forbidden()

        tenant_id = current_user.current_tenant_id
@@ -125,7 +126,7 @@ class ModelProviderModelApi(Resource):
    @login_required
    @account_initialization_required
    def delete(self, provider: str):
-        if current_user.current_tenant.current_role not in ['admin', 'owner']:
+        if not TenantAccountRole.is_privileged_role(current_user.current_tenant.current_role):
            raise Forbidden()

        tenant_id = current_user.current_tenant_id
--- a/api/controllers/console/workspace/workspace.py
+++ b/api/controllers/console/workspace/workspace.py
@@ -3,6 +3,7 @@ import logging
 from flask import request
 from flask_login import current_user
 from flask_restful import Resource, fields, inputs, marshal, marshal_with, reqparse
+from werkzeug.exceptions import Unauthorized

 import services
 from controllers.console import api
@@ -19,7 +20,7 @@ from controllers.console.wraps import account_initialization_required, cloud_edi
 from extensions.ext_database import db
 from libs.helper import TimestampField
 from libs.login import login_required
-from models.account import Tenant
+from models.account import Tenant, TenantStatus
 from services.account_service import TenantService
 from services.file_service import FileService
 from services.workspace_service import WorkspaceService
@@ -116,6 +117,16 @@ class TenantApi(Resource):

        tenant = current_user.current_tenant

+        if tenant.status == TenantStatus.ARCHIVE:
+            tenants = TenantService.get_join_tenants(current_user)
+            # if there is any tenant, switch to the first one
+            if len(tenants) > 0:
+                TenantService.switch_tenant(current_user, tenants[0].id)
+                tenant = tenants[0]
+            # else, raise Unauthorized
+            else:
+                raise Unauthorized('workspace is archived')
+
        return WorkspaceService.get_tenant_info(tenant), 200


--- a/api/controllers/files/init.py
+++ b/api/controllers/files/init.py
@@ -1,5 +1,5 @@
-# -*- coding:utf-8 -*-
 from flask import Blueprint
+
 from libs.external_api import ExternalApi

 bp = Blueprint('files', __name__)
--- a/api/controllers/inner_api/init.py
+++ b/api/controllers/inner_api/init.py
@@ -0,0 +1,9 @@
+from flask import Blueprint
+
+from libs.external_api import ExternalApi
+
+bp = Blueprint('inner_api', __name__, url_prefix='/inner/api')
+api = ExternalApi(bp)
+
+from .workspace import workspace
+
--- a/api/controllers/inner_api/workspace/init.py
+++ b/api/controllers/inner_api/workspace/init.py
--- a/api/controllers/inner_api/workspace/workspace.py
+++ b/api/controllers/inner_api/workspace/workspace.py
@@ -0,0 +1,37 @@
+from flask_restful import Resource, reqparse
+
+from controllers.console.setup import setup_required
+from controllers.inner_api import api
+from controllers.inner_api.wraps import inner_api_only
+from events.tenant_event import tenant_was_created
+from models.account import Account
+from services.account_service import TenantService
+
+
+class EnterpriseWorkspace(Resource):
+
+    @setup_required
+    @inner_api_only
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument('name', type=str, required=True, location='json')
+        parser.add_argument('owner_email', type=str, required=True, location='json')
+        args = parser.parse_args()
+
+        account = Account.query.filter_by(email=args['owner_email']).first()
+        if account is None:
+            return {
+                'message': 'owner account not found.'
+            }, 404
+
+        tenant = TenantService.create_tenant(args['name'])
+        TenantService.create_tenant_member(tenant, account, role='owner')
+
+        tenant_was_created.send(tenant)
+
+        return {
+            'message': 'enterprise workspace created.'
+        }
+
+
+api.add_resource(EnterpriseWorkspace, '/enterprise/workspace')
--- a/api/controllers/inner_api/wraps.py
+++ b/api/controllers/inner_api/wraps.py
@@ -0,0 +1,61 @@
+from base64 import b64encode
+from functools import wraps
+from hashlib import sha1
+from hmac import new as hmac_new
+
+from flask import abort, current_app, request
+
+from extensions.ext_database import db
+from models.model import EndUser
+
+
+def inner_api_only(view):
+    @wraps(view)
+    def decorated(*args, **kwargs):
+        if not current_app.config['INNER_API']:
+            abort(404)
+
+        # get header 'X-Inner-Api-Key'
+        inner_api_key = request.headers.get('X-Inner-Api-Key')
+        if not inner_api_key or inner_api_key != current_app.config['INNER_API_KEY']:
+            abort(404)
+
+        return view(*args, **kwargs)
+
+    return decorated
+
+
+def inner_api_user_auth(view):
+    @wraps(view)
+    def decorated(*args, **kwargs):
+        if not current_app.config['INNER_API']:
+            return view(*args, **kwargs)
+
+        # get header 'X-Inner-Api-Key'
+        authorization = request.headers.get('Authorization')
+        if not authorization:
+            return view(*args, **kwargs)
+
+        parts = authorization.split(':')
+        if len(parts) != 2:
+            return view(*args, **kwargs)
+
+        user_id, token = parts
+        if ' ' in user_id:
+            user_id = user_id.split(' ')[1]
+
+        inner_api_key = request.headers.get('X-Inner-Api-Key')
+
+        data_to_sign = f'DIFY {user_id}'
+
+        signature = hmac_new(inner_api_key.encode('utf-8'), data_to_sign.encode('utf-8'), sha1)
+        signature = b64encode(signature.digest()).decode('utf-8')
+
+        if signature != token:
+            return view(*args, **kwargs)
+
+        kwargs['user'] = db.session.query(EndUser).filter(EndUser.id == user_id).first()
+
+        return view(*args, **kwargs)
+
+    return decorated
--- a/api/controllers/service_api/init.py
+++ b/api/controllers/service_api/init.py
@@ -1,5 +1,5 @@
-# -*- coding:utf-8 -*-
 from flask import Blueprint
+
 from libs.external_api import ExternalApi

 bp = Blueprint('service_api', __name__, url_prefix='/v1')
--- a/api/controllers/service_api/dataset/dataset.py
+++ b/api/controllers/service_api/dataset/dataset.py
@@ -26,8 +26,11 @@ class DatasetApi(DatasetApiResource):
        page = request.args.get('page', default=1, type=int)
        limit = request.args.get('limit', default=20, type=int)
        provider = request.args.get('provider', default="vendor")
+        search = request.args.get('keyword', default=None, type=str)
+        tag_ids = request.args.getlist('tag_ids')
+
        datasets, total = DatasetService.get_datasets(page, limit, provider,
-                                                      tenant_id, current_user)
+                                                      tenant_id, current_user, search, tag_ids)
        # check embedding setting
        provider_manager = ProviderManager()
        configurations = provider_manager.get_configurations(
--- a/api/controllers/service_api/dataset/document.py
+++ b/api/controllers/service_api/dataset/document.py
@@ -174,7 +174,7 @@ class DocumentAddByFileApi(DatasetApiResource):

        if not dataset:
            raise ValueError('Dataset is not exist.')
-        if not dataset.indexing_technique and not args['indexing_technique']:
+        if not dataset.indexing_technique and not args.get('indexing_technique'):
            raise ValueError('indexing_technique is required.')

        # save file info
--- a/api/controllers/service_api/wraps.py
+++ b/api/controllers/service_api/wraps.py
@@ -12,7 +12,7 @@ from werkzeug.exceptions import Forbidden, NotFound, Unauthorized

 from extensions.ext_database import db
 from libs.login import _get_user
-from models.account import Account, Tenant, TenantAccountJoin
+from models.account import Account, Tenant, TenantAccountJoin, TenantStatus
 from models.model import ApiToken, App, EndUser
 from services.feature_service import FeatureService

@@ -47,6 +47,10 @@ def validate_app_token(view: Optional[Callable] = None, *, fetch_user_arg: Optio
            if not app_model.enable_api:
                raise NotFound()

+            tenant = db.session.query(Tenant).filter(Tenant.id == app_model.tenant_id).first()
+            if tenant.status == TenantStatus.ARCHIVE:
+                raise NotFound()
+
            kwargs['app_model'] = app_model

            if fetch_user_arg:
@@ -137,6 +141,7 @@ def validate_dataset_token(view=None):
                .filter(Tenant.id == api_token.tenant_id) \
                .filter(TenantAccountJoin.tenant_id == Tenant.id) \
                .filter(TenantAccountJoin.role.in_(['owner'])) \
+                .filter(Tenant.status == TenantStatus.NORMAL) \
                .one_or_none() # TODO: only owner information is required, so only one is returned.
            if tenant_account_join:
                tenant, ta = tenant_account_join
--- a/api/controllers/web/init.py
+++ b/api/controllers/web/init.py
@@ -1,5 +1,5 @@
-# -*- coding:utf-8 -*-
 from flask import Blueprint
+
 from libs.external_api import ExternalApi

 bp = Blueprint('web', __name__, url_prefix='/api')
--- a/api/controllers/web/app.py
+++ b/api/controllers/web/app.py
@@ -7,7 +7,7 @@ from controllers.web import api
 from controllers.web.error import AppUnavailableError
 from controllers.web.wraps import WebApiResource
 from extensions.ext_database import db
-from models.model import App, AppModelConfig, AppMode
+from models.model import App, AppMode, AppModelConfig
 from models.tools import ApiToolProvider
 from services.app_service import AppService

--- a/api/controllers/web/site.py
+++ b/api/controllers/web/site.py
@@ -6,6 +6,7 @@ from werkzeug.exceptions import Forbidden
 from controllers.web import api
 from controllers.web.wraps import WebApiResource
 from extensions.ext_database import db
+from models.account import TenantStatus
 from models.model import Site
 from services.feature_service import FeatureService

@@ -54,6 +55,9 @@ class AppSiteApi(WebApiResource):
        if not site:
            raise Forbidden()

+        if app_model.tenant.status == TenantStatus.ARCHIVE:
+            raise Forbidden()
+
        can_replace_logo = FeatureService.get_features(app_model.tenant_id).can_replace_logo

        return AppSiteInfo(app_model.tenant, app_model, site, end_user.id, can_replace_logo)
--- a/api/core/agent/base_agent_runner.py
+++ b/api/core/agent/base_agent_runner.py
@@ -163,6 +163,7 @@ class BaseAgentRunner(AppRunner):
        """
        tool_entity = ToolManager.get_agent_tool_runtime(
            tenant_id=self.tenant_id,
+            app_id=self.app_config.app_id,
            agent_tool=tool,
        )
        tool_entity.load_variables(self.variables_pool)
--- a/api/core/app/apps/advanced_chat/app_runner.py
+++ b/api/core/app/apps/advanced_chat/app_runner.py
@@ -18,7 +18,7 @@ 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.model import App, Conversation, Message
+from models.model import App, Conversation, EndUser, Message
 from models.workflow import Workflow

 logger = logging.getLogger(__name__)
@@ -56,6 +56,14 @@ class AdvancedChatAppRunner(AppRunner):
        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,
@@ -98,7 +106,8 @@ class AdvancedChatAppRunner(AppRunner):
            system_inputs={
                SystemVariable.QUERY: query,
                SystemVariable.FILES: files,
-                SystemVariable.CONVERSATION: conversation.id,
+                SystemVariable.CONVERSATION_ID: conversation.id,
+                SystemVariable.USER_ID: user_id
            },
            callbacks=workflow_callbacks
        )
--- a/api/core/app/apps/advanced_chat/generate_task_pipeline.py
+++ b/api/core/app/apps/advanced_chat/generate_task_pipeline.py
@@ -28,9 +28,9 @@ from core.app.entities.task_entities import (
    AdvancedChatTaskState,
    ChatbotAppBlockingResponse,
    ChatbotAppStreamResponse,
+    ChatflowStreamGenerateRoute,
    ErrorStreamResponse,
    MessageEndStreamResponse,
-    StreamGenerateRoute,
    StreamResponse,
 )
 from core.app.task_pipeline.based_generate_task_pipeline import BasedGenerateTaskPipeline
@@ -84,13 +84,19 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
        """
        super().__init__(application_generate_entity, queue_manager, user, stream)

+        if isinstance(self._user, EndUser):
+            user_id = self._user.session_id
+        else:
+            user_id = self._user.id
+
        self._workflow = workflow
        self._conversation = conversation
        self._message = message
        self._workflow_system_variables = {
            SystemVariable.QUERY: message.query,
            SystemVariable.FILES: application_generate_entity.files,
-            SystemVariable.CONVERSATION: conversation.id,
+            SystemVariable.CONVERSATION_ID: conversation.id,
+            SystemVariable.USER_ID: user_id
        }

        self._task_state = AdvancedChatTaskState(
@@ -337,7 +343,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
            **extras
        )

-    def _get_stream_generate_routes(self) -> dict[str, StreamGenerateRoute]:
+    def _get_stream_generate_routes(self) -> dict[str, ChatflowStreamGenerateRoute]:
        """
        Get stream generate routes.
        :return:
@@ -360,7 +366,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
                continue

            for start_node_id in start_node_ids:
-                stream_generate_routes[start_node_id] = StreamGenerateRoute(
+                stream_generate_routes[start_node_id] = ChatflowStreamGenerateRoute(
                    answer_node_id=answer_node_id,
                    generate_route=generate_route
                )
@@ -424,15 +430,14 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
            for route_chunk in route_chunks:
                if route_chunk.type == 'text':
                    route_chunk = cast(TextGenerateRouteChunk, route_chunk)
-                    for token in route_chunk.text:
-                        # handle output moderation chunk
-                        should_direct_answer = self._handle_output_moderation_chunk(token)
-                        if should_direct_answer:
-                            continue

-                        self._task_state.answer += token
-                        yield self._message_to_stream_response(token, self._message.id)
-                        time.sleep(0.01)
+                    # handle output moderation chunk
+                    should_direct_answer = self._handle_output_moderation_chunk(route_chunk.text)
+                    if should_direct_answer:
+                        continue
+
+                    self._task_state.answer += route_chunk.text
+                    yield self._message_to_stream_response(route_chunk.text, self._message.id)
                else:
                    break

@@ -457,10 +462,8 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
        for route_chunk in route_chunks:
            if route_chunk.type == 'text':
                route_chunk = cast(TextGenerateRouteChunk, route_chunk)
-                for token in route_chunk.text:
-                    self._task_state.answer += token
-                    yield self._message_to_stream_response(token, self._message.id)
-                    time.sleep(0.01)
+                self._task_state.answer += route_chunk.text
+                yield self._message_to_stream_response(route_chunk.text, self._message.id)
            else:
                route_chunk = cast(VarGenerateRouteChunk, route_chunk)
                value_selector = route_chunk.value_selector
--- a/api/core/app/apps/base_app_generate_response_converter.py
+++ b/api/core/app/apps/base_app_generate_response_converter.py
@@ -26,7 +26,10 @@ class AppGenerateResponseConverter(ABC):
            else:
                def _generate():
                    for chunk in cls.convert_stream_full_response(response):
-                        yield f'data: {chunk}\n\n'
+                        if chunk == 'ping':
+                            yield f'event: {chunk}\n\n'
+                        else:
+                            yield f'data: {chunk}\n\n'

                return _generate()
        else:
@@ -35,7 +38,10 @@ class AppGenerateResponseConverter(ABC):
            else:
                def _generate():
                    for chunk in cls.convert_stream_simple_response(response):
-                        yield f'data: {chunk}\n\n'
+                        if chunk == 'ping':
+                            yield f'event: {chunk}\n\n'
+                        else:
+                            yield f'data: {chunk}\n\n'

                return _generate()

--- a/api/core/app/apps/base_app_generator.py
+++ b/api/core/app/apps/base_app_generator.py
@@ -23,20 +23,28 @@ class BaseAppGenerator:
            value = user_inputs[variable]

            if value:
-                if not isinstance(value, str):
+                if variable_config.type != VariableEntity.Type.NUMBER and not isinstance(value, str):
                    raise ValueError(f"{variable} in input form must be a string")
+                elif variable_config.type == VariableEntity.Type.NUMBER and isinstance(value, str):
+                    if '.' in value:
+                        value = float(value)
+                    else:
+                        value = int(value)

            if variable_config.type == VariableEntity.Type.SELECT:
                options = variable_config.options if variable_config.options is not None else []
                if value not in options:
                    raise ValueError(f"{variable} in input form must be one of the following: {options}")
-            else:
+            elif variable_config.type in [VariableEntity.Type.TEXT_INPUT, VariableEntity.Type.PARAGRAPH]:
                if variable_config.max_length is not None:
                    max_length = variable_config.max_length
                    if len(value) > max_length:
                        raise ValueError(f'{variable} in input form must be less than {max_length} characters')

-            filtered_inputs[variable] = value.replace('\x00', '') if value else None
+            if value and isinstance(value, str):
+                filtered_inputs[variable] = value.replace('\x00', '')
+            else:
+                filtered_inputs[variable] = value if value else None

        return filtered_inputs

--- a/api/core/app/apps/workflow/app_runner.py
+++ b/api/core/app/apps/workflow/app_runner.py
@@ -14,7 +14,7 @@ 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.model import App
+from models.model import App, EndUser
 from models.workflow import Workflow

 logger = logging.getLogger(__name__)
@@ -36,6 +36,14 @@ class WorkflowAppRunner:
        app_config = application_generate_entity.app_config
        app_config = cast(WorkflowAppConfig, app_config)

+        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
+
        app_record = db.session.query(App).filter(App.id == app_config.app_id).first()
        if not app_record:
            raise ValueError("App not found")
@@ -67,7 +75,8 @@ class WorkflowAppRunner:
            else UserFrom.END_USER,
            user_inputs=inputs,
            system_inputs={
-                SystemVariable.FILES: files
+                SystemVariable.FILES: files,
+                SystemVariable.USER_ID: user_id
            },
            callbacks=workflow_callbacks
        )
--- a/api/core/app/apps/workflow/generate_task_pipeline.py
+++ b/api/core/app/apps/workflow/generate_task_pipeline.py
@@ -28,11 +28,13 @@ from core.app.entities.task_entities import (
    WorkflowAppBlockingResponse,
    WorkflowAppStreamResponse,
    WorkflowFinishStreamResponse,
+    WorkflowStreamGenerateNodes,
    WorkflowTaskState,
 )
 from core.app.task_pipeline.based_generate_task_pipeline import BasedGenerateTaskPipeline
 from core.app.task_pipeline.workflow_cycle_manage import WorkflowCycleManage
-from core.workflow.entities.node_entities 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
 from models.model import EndUser
@@ -40,6 +42,7 @@ from models.workflow import (
    Workflow,
    WorkflowAppLog,
    WorkflowAppLogCreatedFrom,
+    WorkflowNodeExecution,
    WorkflowRun,
 )

@@ -71,12 +74,19 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
        """
        super().__init__(application_generate_entity, queue_manager, user, stream)

+        if isinstance(self._user, EndUser):
+            user_id = self._user.session_id
+        else:
+            user_id = self._user.id
+
        self._workflow = workflow
        self._workflow_system_variables = {
            SystemVariable.FILES: application_generate_entity.files,
+            SystemVariable.USER_ID: user_id
        }

        self._task_state = WorkflowTaskState()
+        self._stream_generate_nodes = self._get_stream_generate_nodes()

    def process(self) -> Union[WorkflowAppBlockingResponse, Generator[WorkflowAppStreamResponse, None, None]]:
        """
@@ -161,6 +171,14 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
                )
            elif isinstance(event, QueueNodeStartedEvent):
                workflow_node_execution = self._handle_node_start(event)
+
+                # search stream_generate_routes if node id is answer start at node
+                if not self._task_state.current_stream_generate_state and event.node_id in self._stream_generate_nodes:
+                    self._task_state.current_stream_generate_state = self._stream_generate_nodes[event.node_id]
+
+                    # generate stream outputs when node started
+                    yield from self._generate_stream_outputs_when_node_started()
+
                yield self._workflow_node_start_to_stream_response(
                    event=event,
                    task_id=self._application_generate_entity.task_id,
@@ -168,6 +186,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
                )
            elif isinstance(event, QueueNodeSucceededEvent | QueueNodeFailedEvent):
                workflow_node_execution = self._handle_node_finished(event)
+
                yield self._workflow_node_finish_to_stream_response(
                    task_id=self._application_generate_entity.task_id,
                    workflow_node_execution=workflow_node_execution
@@ -187,6 +206,11 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
                if delta_text is None:
                    continue

+                if not self._is_stream_out_support(
+                        event=event
+                ):
+                    continue
+
                self._task_state.answer += delta_text
                yield self._text_chunk_to_stream_response(delta_text)
            elif isinstance(event, QueueMessageReplaceEvent):
@@ -248,3 +272,142 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
            task_id=self._application_generate_entity.task_id,
            text=TextReplaceStreamResponse.Data(text=text)
        )
+
+    def _get_stream_generate_nodes(self) -> dict[str, WorkflowStreamGenerateNodes]:
+        """
+        Get stream generate nodes.
+        :return:
+        """
+        # find all answer nodes
+        graph = self._workflow.graph_dict
+        end_node_configs = [
+            node for node in graph['nodes']
+            if node.get('data', {}).get('type') == NodeType.END.value
+        ]
+
+        # parse stream output node value selectors of end nodes
+        stream_generate_routes = {}
+        for node_config in end_node_configs:
+            # get generate route for stream output
+            end_node_id = node_config['id']
+            generate_nodes = EndNode.extract_generate_nodes(graph, node_config)
+            start_node_ids = self._get_end_start_at_node_ids(graph, end_node_id)
+            if not start_node_ids:
+                continue
+
+            for start_node_id in start_node_ids:
+                stream_generate_routes[start_node_id] = WorkflowStreamGenerateNodes(
+                    end_node_id=end_node_id,
+                    stream_node_ids=generate_nodes
+                )
+
+        return stream_generate_routes
+
+    def _get_end_start_at_node_ids(self, graph: dict, target_node_id: str) \
+            -> list[str]:
+        """
+        Get end start at node id.
+        :param graph: graph
+        :param target_node_id: target node ID
+        :return:
+        """
+        nodes = graph.get('nodes')
+        edges = graph.get('edges')
+
+        # fetch all ingoing edges from source node
+        ingoing_edges = []
+        for edge in edges:
+            if edge.get('target') == target_node_id:
+                ingoing_edges.append(edge)
+
+        if not ingoing_edges:
+            return []
+
+        start_node_ids = []
+        for ingoing_edge in ingoing_edges:
+            source_node_id = ingoing_edge.get('source')
+            source_node = next((node for node in nodes if node.get('id') == source_node_id), None)
+            if not source_node:
+                continue
+
+            node_type = source_node.get('data', {}).get('type')
+            if node_type in [
+                NodeType.IF_ELSE.value,
+                NodeType.QUESTION_CLASSIFIER.value
+            ]:
+                start_node_id = target_node_id
+                start_node_ids.append(start_node_id)
+            elif node_type == NodeType.START.value:
+                start_node_id = source_node_id
+                start_node_ids.append(start_node_id)
+            else:
+                sub_start_node_ids = self._get_end_start_at_node_ids(graph, source_node_id)
+                if sub_start_node_ids:
+                    start_node_ids.extend(sub_start_node_ids)
+
+        return start_node_ids
+
+    def _generate_stream_outputs_when_node_started(self) -> Generator:
+        """
+        Generate stream outputs.
+        :return:
+        """
+        if self._task_state.current_stream_generate_state:
+            stream_node_ids = self._task_state.current_stream_generate_state.stream_node_ids
+
+            for node_id, node_execution_info in self._task_state.ran_node_execution_infos.items():
+                if node_id not in stream_node_ids:
+                    continue
+
+                node_execution_info = self._task_state.ran_node_execution_infos[node_id]
+
+                # get chunk node execution
+                route_chunk_node_execution = db.session.query(WorkflowNodeExecution).filter(
+                    WorkflowNodeExecution.id == node_execution_info.workflow_node_execution_id).first()
+
+                if not route_chunk_node_execution:
+                    continue
+
+                outputs = route_chunk_node_execution.outputs_dict
+
+                if not outputs:
+                    continue
+
+                # get value from outputs
+                text = outputs.get('text')
+
+                if text:
+                    self._task_state.answer += text
+                    yield self._text_chunk_to_stream_response(text)
+
+            db.session.close()
+
+    def _is_stream_out_support(self, event: QueueTextChunkEvent) -> bool:
+        """
+        Is stream out support
+        :param event: queue text chunk event
+        :return:
+        """
+        if not event.metadata:
+            return False
+
+        if 'node_id' not in event.metadata:
+            return False
+
+        node_id = event.metadata.get('node_id')
+        node_type = event.metadata.get('node_type')
+        stream_output_value_selector = event.metadata.get('value_selector')
+        if not stream_output_value_selector:
+            return False
+
+        if not self._task_state.current_stream_generate_state:
+            return False
+
+        if node_id not in self._task_state.current_stream_generate_state.stream_node_ids:
+            return False
+
+        if node_type != NodeType.LLM:
+            # only LLM support chunk stream output
+            return False
+
+        return True
--- a/api/core/app/apps/workflow/workflow_event_trigger_callback.py
+++ b/api/core/app/apps/workflow/workflow_event_trigger_callback.py
@@ -6,6 +6,7 @@ from core.app.entities.queue_entities import (
    QueueNodeFailedEvent,
    QueueNodeStartedEvent,
    QueueNodeSucceededEvent,
+    QueueTextChunkEvent,
    QueueWorkflowFailedEvent,
    QueueWorkflowStartedEvent,
    QueueWorkflowSucceededEvent,
@@ -119,7 +120,15 @@ class WorkflowEventTriggerCallback(BaseWorkflowCallback):
        """
        Publish text chunk
        """
-        pass
+        self._queue_manager.publish(
+            QueueTextChunkEvent(
+                text=text,
+                metadata={
+                    "node_id": node_id,
+                    **metadata
+                }
+            ), PublishFrom.APPLICATION_MANAGER
+        )

    def on_event(self, event: AppQueueEvent) -> None:
        """
--- a/api/core/app/entities/app_invoke_entities.py
+++ b/api/core/app/entities/app_invoke_entities.py
@@ -72,7 +72,7 @@ class AppGenerateEntity(BaseModel):
    # app config
    app_config: AppConfig

-    inputs: dict[str, str]
+    inputs: dict[str, Any]
    files: list[FileVar] = []
    user_id: str

--- a/api/core/app/entities/task_entities.py
+++ b/api/core/app/entities/task_entities.py
@@ -9,9 +9,17 @@ from core.workflow.entities.node_entities import NodeType
 from core.workflow.nodes.answer.entities import GenerateRouteChunk


-class StreamGenerateRoute(BaseModel):
+class WorkflowStreamGenerateNodes(BaseModel):
    """
-    StreamGenerateRoute entity
+    WorkflowStreamGenerateNodes entity
+    """
+    end_node_id: str
+    stream_node_ids: list[str]
+
+
+class ChatflowStreamGenerateRoute(BaseModel):
+    """
+    ChatflowStreamGenerateRoute entity
    """
    answer_node_id: str
    generate_route: list[GenerateRouteChunk]
@@ -55,6 +63,8 @@ class WorkflowTaskState(TaskState):
    ran_node_execution_infos: dict[str, NodeExecutionInfo] = {}
    latest_node_execution_info: Optional[NodeExecutionInfo] = None

+    current_stream_generate_state: Optional[WorkflowStreamGenerateNodes] = None
+

 class AdvancedChatTaskState(WorkflowTaskState):
    """
@@ -62,7 +72,7 @@ class AdvancedChatTaskState(WorkflowTaskState):
    """
    usage: LLMUsage

-    current_stream_generate_state: Optional[StreamGenerateRoute] = None
+    current_stream_generate_state: Optional[ChatflowStreamGenerateRoute] = None


 class StreamEvent(Enum):
--- a/api/core/app/task_pipeline/message_cycle_manage.py
+++ b/api/core/app/task_pipeline/message_cycle_manage.py
@@ -118,7 +118,8 @@ class MessageCycleManage:
        :param event: event
        :return:
        """
-        self._task_state.metadata['retriever_resources'] = event.retriever_resources
+        if self._application_generate_entity.app_config.additional_features.show_retrieve_source:
+            self._task_state.metadata['retriever_resources'] = event.retriever_resources

    def _get_response_metadata(self) -> dict:
        """
--- a/api/core/docstore/dataset_docstore.py
+++ b/api/core/docstore/dataset_docstore.py
@@ -84,7 +84,7 @@ class DatasetDocumentStore:
            if not isinstance(doc, Document):
                raise ValueError("doc must be a Document")

-            segment_document = self.get_document(doc_id=doc.metadata['doc_id'], raise_error=False)
+            segment_document = self.get_document_segment(doc_id=doc.metadata['doc_id'])

            # NOTE: doc could already exist in the store, but we overwrite it
            if not allow_update and segment_document:
--- a/api/core/helper/code_executor/code_executor.py
+++ b/api/core/helper/code_executor/code_executor.py
@@ -6,7 +6,7 @@ from yarl import URL

 from config import get_env
 from core.helper.code_executor.javascript_transformer import NodeJsTemplateTransformer
-from core.helper.code_executor.jina2_transformer import Jinja2TemplateTransformer
+from core.helper.code_executor.jinja2_transformer import Jinja2TemplateTransformer
 from core.helper.code_executor.python_transformer import PythonTemplateTransformer

 # Code Executor
@@ -30,34 +30,24 @@ class CodeExecutionResponse(BaseModel):

 class CodeExecutor:
    @classmethod
-    def execute_code(cls, language: Literal['python3', 'javascript', 'jinja2'], code: str, inputs: dict) -> dict:
+    def execute_code(cls, language: Literal['python3', 'javascript', 'jinja2'], preload: str, code: str) -> str:
        """
        Execute code
        :param language: code language
        :param code: code
-        :param inputs: inputs
        :return:
        """
-        template_transformer = None
-        if language == 'python3':
-            template_transformer = PythonTemplateTransformer
-        elif language == 'jinja2':
-            template_transformer = Jinja2TemplateTransformer
-        elif language == 'javascript':
-            template_transformer = NodeJsTemplateTransformer
-        else:
-            raise CodeExecutionException('Unsupported language')
-
-        runner, preload = template_transformer.transform_caller(code, inputs)
        url = URL(CODE_EXECUTION_ENDPOINT) / 'v1' / 'sandbox' / 'run'
+
        headers = {
            'X-Api-Key': CODE_EXECUTION_API_KEY
        }
+
        data = {
            'language': 'python3' if language == 'jinja2' else
                        'nodejs' if language == 'javascript' else
                        'python3' if language == 'python3' else None,
-            'code': runner,
+            'code': code,
            'preload': preload
        }

@@ -85,4 +75,32 @@ class CodeExecutor:
        if response.data.error:
            raise CodeExecutionException(response.data.error)
        
-        return template_transformer.transform_response(response.data.stdout)
+        return response.data.stdout
+
+    @classmethod
+    def execute_workflow_code_template(cls, language: Literal['python3', 'javascript', 'jinja2'], code: str, inputs: dict) -> dict:
+        """
+        Execute code
+        :param language: code language
+        :param code: code
+        :param inputs: inputs
+        :return:
+        """
+        template_transformer = None
+        if language == 'python3':
+            template_transformer = PythonTemplateTransformer
+        elif language == 'jinja2':
+            template_transformer = Jinja2TemplateTransformer
+        elif language == 'javascript':
+            template_transformer = NodeJsTemplateTransformer
+        else:
+            raise CodeExecutionException('Unsupported language')
+
+        runner, preload = template_transformer.transform_caller(code, inputs)
+
+        try:
+            response = cls.execute_code(language, preload, runner)
+        except CodeExecutionException as e:
+            raise e
+
+        return template_transformer.transform_response(response)
--- a/api/core/helper/code_executor/jinja2_transformer.py
+++ b/api/core/helper/code_executor/jinja2_transformer.py
@@ -1,10 +1,13 @@
 import json
 import re
+from base64 import b64encode

 from core.helper.code_executor.template_transformer import TemplateTransformer

 PYTHON_RUNNER = """
 import jinja2
+from json import loads
+from base64 import b64decode

 template = jinja2.Template('''{{code}}''')

@@ -12,7 +15,8 @@ def main(**inputs):
    return template.render(**inputs)

 # execute main function, and return the result
-output = main(**{{inputs}})
+inputs = b64decode('{{inputs}}').decode('utf-8')
+output = main(**loads(inputs))

 result = f'''<<RESULT>>{output}<<RESULT>>'''

@@ -39,6 +43,7 @@ JINJA2_PRELOAD_TEMPLATE = """{% set fruits = ['Apple'] %}

 JINJA2_PRELOAD = f"""
 import jinja2
+from base64 import b64decode

 def _jinja2_preload_():
    # prepare jinja2 environment, load template and render before to avoid sandbox issue
@@ -50,6 +55,7 @@ if __name__ == '__main__':

 """

+
 class Jinja2TemplateTransformer(TemplateTransformer):
    @classmethod
    def transform_caller(cls, code: str, inputs: dict) -> tuple[str, str]:
@@ -60,9 +66,11 @@ class Jinja2TemplateTransformer(TemplateTransformer):
        :return:
        """

+        inputs_str = b64encode(json.dumps(inputs, ensure_ascii=False).encode()).decode('utf-8')
+
        # transform jinja2 template to python code
        runner = PYTHON_RUNNER.replace('{{code}}', code)
-        runner = runner.replace('{{inputs}}', json.dumps(inputs, indent=4, ensure_ascii=False))
+        runner = runner.replace('{{inputs}}', inputs_str)

        return runner, JINJA2_PRELOAD

--- a/api/core/helper/code_executor/python_transformer.py
+++ b/api/core/helper/code_executor/python_transformer.py
@@ -1,17 +1,22 @@
 import json
 import re
+from base64 import b64encode

 from core.helper.code_executor.template_transformer import TemplateTransformer

 PYTHON_RUNNER = """# declare main function here
 {{code}}

+from json import loads, dumps
+from base64 import b64decode
+
 # execute main function, and return the result
 # inputs is a dict, and it
-output = main(**{{inputs}})
+inputs = b64decode('{{inputs}}').decode('utf-8')
+output = main(**json.loads(inputs))

 # convert output to json and print
-output = json.dumps(output, indent=4)
+output = dumps(output, indent=4)

 result = f'''<<RESULT>>
 {output}
@@ -20,8 +25,28 @@ result = f'''<<RESULT>>
 print(result)
 """

-PYTHON_PRELOAD = """"""
-
+PYTHON_PRELOAD = """
+# prepare general imports
+import json
+import datetime
+import math
+import random
+import re
+import string
+import sys
+import time
+import traceback
+import uuid
+import os
+import base64
+import hashlib
+import hmac
+import binascii
+import collections
+import functools
+import operator
+import itertools
+"""

 class PythonTemplateTransformer(TemplateTransformer):
    @classmethod
@@ -34,7 +59,7 @@ class PythonTemplateTransformer(TemplateTransformer):
        """
        
        # transform inputs to json string
-        inputs_str = json.dumps(inputs, indent=4, ensure_ascii=False)
+        inputs_str = b64encode(json.dumps(inputs, ensure_ascii=False).encode()).decode('utf-8')

        # replace code and inputs
        runner = PYTHON_RUNNER.replace('{{code}}', code)
--- a/api/core/helper/tool_parameter_cache.py
+++ b/api/core/helper/tool_parameter_cache.py
@@ -11,12 +11,13 @@ class ToolParameterCacheType(Enum):

 class ToolParameterCache:
    def __init__(self, 
-                 tenant_id: str, 
-                 provider: str, 
-                 tool_name: str, 
-                 cache_type: ToolParameterCacheType
+            tenant_id: str, 
+            provider: str, 
+            tool_name: str, 
+            cache_type: ToolParameterCacheType,
+            identity_id: str
        ):
-        self.cache_key = f"{cache_type.value}_secret:tenant_id:{tenant_id}:provider:{provider}:tool_name:{tool_name}"
+        self.cache_key = f"{cache_type.value}_secret:tenant_id:{tenant_id}:provider:{provider}:tool_name:{tool_name}:identity_id:{identity_id}"

    def get(self) -> Optional[dict]:
        """
--- a/api/core/model_runtime/entities/message_entities.py
+++ b/api/core/model_runtime/entities/message_entities.py
@@ -88,6 +88,14 @@ class PromptMessage(ABC, BaseModel):
    content: Optional[str | list[PromptMessageContent]] = None
    name: Optional[str] = None

+    def is_empty(self) -> bool:
+        """
+        Check if prompt message is empty.
+
+        :return: True if prompt message is empty, False otherwise
+        """
+        return not self.content
+

 class UserPromptMessage(PromptMessage):
    """
@@ -118,6 +126,16 @@ class AssistantPromptMessage(PromptMessage):
    role: PromptMessageRole = PromptMessageRole.ASSISTANT
    tool_calls: list[ToolCall] = []

+    def is_empty(self) -> bool:
+        """
+        Check if prompt message is empty.
+
+        :return: True if prompt message is empty, False otherwise
+        """
+        if not super().is_empty() and not self.tool_calls:
+            return False
+
+        return True

 class SystemPromptMessage(PromptMessage):
    """
@@ -132,3 +150,14 @@ class ToolPromptMessage(PromptMessage):
    """
    role: PromptMessageRole = PromptMessageRole.TOOL
    tool_call_id: str
+
+    def is_empty(self) -> bool:
+        """
+        Check if prompt message is empty.
+
+        :return: True if prompt message is empty, False otherwise
+        """
+        if not super().is_empty() and not self.tool_call_id:
+            return False
+
+        return True
--- a/api/core/model_runtime/model_providers/bedrock/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/bedrock/llm/_position.yaml
@@ -8,5 +8,10 @@
 - anthropic.claude-3-haiku-v1:0
 - cohere.command-light-text-v14
 - cohere.command-text-v14
+- meta.llama3-8b-instruct-v1:0
+- meta.llama3-70b-instruct-v1:0
 - meta.llama2-13b-chat-v1
 - meta.llama2-70b-chat-v1
+- mistral.mistral-large-2402-v1:0
+- mistral.mixtral-8x7b-instruct-v0:1
+- mistral.mistral-7b-instruct-v0:2
--- a/api/core/model_runtime/model_providers/bedrock/llm/anthropic.claude-3-opus-v1.yaml
+++ b/api/core/model_runtime/model_providers/bedrock/llm/anthropic.claude-3-opus-v1.yaml
@@ -0,0 +1,57 @@
+model: anthropic.claude-3-opus-20240229-v1:0
+label:
+  en_US: Claude 3 Opus
+model_type: llm
+features:
+  - agent-thought
+  - vision
+model_properties:
+  mode: chat
+  context_size: 200000
+# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 4096
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  # docs: https://docs.anthropic.com/claude/docs/system-prompts
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+pricing:
+  input: '0.015'
+  output: '0.075'
+  unit: '0.001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/bedrock/llm/llm.py
+++ b/api/core/model_runtime/model_providers/bedrock/llm/llm.py
@@ -370,29 +370,14 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
        :return:md = genai.GenerativeModel(model)
        """
        prefix = model.split('.')[0]
-
+        model_name = model.split('.')[1]
        if isinstance(messages, str):
            prompt = messages
        else:
-            prompt = self._convert_messages_to_prompt(messages, prefix)
+            prompt = self._convert_messages_to_prompt(messages, prefix, model_name)

        return self._get_num_tokens_by_gpt2(prompt)
    
-    def _convert_messages_to_prompt(self, model_prefix: str, messages: list[PromptMessage]) -> str:
-        """
-        Format a list of messages into a full prompt for the Google model
-
-        :param messages: List of PromptMessage to combine.
-        :return: Combined string with necessary human_prompt and ai_prompt tags.
-        """
-        messages = messages.copy()  # don't mutate the original list
-        
-        text = "".join(
-            self._convert_one_message_to_text(message, model_prefix)
-            for message in messages
-        )
-
-        return text.rstrip()

    def validate_credentials(self, model: str, credentials: dict) -> None:
        """
@@ -432,7 +417,7 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
        except Exception as ex:
            raise CredentialsValidateFailedError(str(ex))

-    def _convert_one_message_to_text(self, message: PromptMessage, model_prefix: str) -> str:
+    def _convert_one_message_to_text(self, message: PromptMessage, model_prefix: str, model_name: Optional[str] = None) -> str:
        """
        Convert a single message to a string.

@@ -446,9 +431,21 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
            ai_prompt = "\n\nAssistant:"

        elif model_prefix == "meta":
-            human_prompt_prefix = "\n[INST]"
+            # LLAMA3
+            if model_name.startswith("llama3"):
+                human_prompt_prefix = "<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n"
+                human_prompt_postfix = "<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
+                ai_prompt = "\n\nAssistant:"
+            else:
+                # LLAMA2
+                human_prompt_prefix = "\n[INST]"
+                human_prompt_postfix = "[\\INST]\n"
+                ai_prompt = ""
+
+        elif model_prefix == "mistral":
+            human_prompt_prefix = "<s>[INST]"
            human_prompt_postfix = "[\\INST]\n"
-            ai_prompt = ""
+            ai_prompt = "\n\nAssistant:"

        elif model_prefix == "amazon":
            human_prompt_prefix = "\n\nUser:"
@@ -473,11 +470,12 @@ class BedrockLargeLanguageModel(LargeLanguageModel):

        return message_text

-    def _convert_messages_to_prompt(self, messages: list[PromptMessage], model_prefix: str) -> str:
+    def _convert_messages_to_prompt(self, messages: list[PromptMessage], model_prefix: str, model_name: Optional[str] = None) -> str:
        """
        Format a list of messages into a full prompt for the Anthropic, Amazon and Llama models

        :param messages: List of PromptMessage to combine.
+        :param model_name: specific model name.Optional,just to distinguish llama2 and llama3
        :return: Combined string with necessary human_prompt and ai_prompt tags.
        """
        if not messages:
@@ -488,18 +486,20 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
            messages.append(AssistantPromptMessage(content=""))

        text = "".join(
-            self._convert_one_message_to_text(message, model_prefix)
+            self._convert_one_message_to_text(message, model_prefix, model_name)
            for message in messages
        )

        # trim off the trailing ' ' that might come from the "Assistant: "
        return text.rstrip()

-    def _create_payload(self, model_prefix: str, prompt_messages: list[PromptMessage], model_parameters: dict, stop: Optional[list[str]] = None, stream: bool = True):
+    def _create_payload(self, model: str, prompt_messages: list[PromptMessage], model_parameters: dict, stop: Optional[list[str]] = None, stream: bool = True):
        """
        Create payload for bedrock api call depending on model provider
        """
        payload = dict()
+        model_prefix = model.split('.')[0]
+        model_name = model.split('.')[1]

        if model_prefix == "amazon":
            payload["textGenerationConfig"] = { **model_parameters }
@@ -519,6 +519,13 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
                payload["frequencyPenalty"] = {model_parameters.get("frequencyPenalty")}
            if model_parameters.get("countPenalty"):
                payload["countPenalty"] = {model_parameters.get("countPenalty")}
+        
+        elif model_prefix == "mistral":
+            payload["temperature"] = model_parameters.get("temperature")
+            payload["top_p"] = model_parameters.get("top_p")
+            payload["max_tokens"] = model_parameters.get("max_tokens")
+            payload["prompt"] = self._convert_messages_to_prompt(prompt_messages, model_prefix)
+            payload["stop"] = stop[:10] if stop else []

        elif model_prefix == "anthropic":
            payload = { **model_parameters }
@@ -532,7 +539,7 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
        
        elif model_prefix == "meta":
            payload = { **model_parameters }
-            payload["prompt"] = self._convert_messages_to_prompt(prompt_messages, model_prefix)
+            payload["prompt"] = self._convert_messages_to_prompt(prompt_messages, model_prefix, model_name)

        else:
            raise ValueError(f"Got unknown model prefix {model_prefix}")
@@ -567,7 +574,7 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
        )

        model_prefix = model.split('.')[0]
-        payload = self._create_payload(model_prefix, prompt_messages, model_parameters, stop, stream)
+        payload = self._create_payload(model, prompt_messages, model_parameters, stop, stream)

        # need workaround for ai21 models which doesn't support streaming
        if stream and model_prefix != "ai21":
@@ -648,6 +655,11 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
            output = response_body.get("generation").strip('\n')
            prompt_tokens = response_body.get("prompt_token_count")
            completion_tokens = response_body.get("generation_token_count")
+        
+        elif model_prefix == "mistral":
+            output = response_body.get("outputs")[0].get("text")
+            prompt_tokens = response.get('ResponseMetadata').get('HTTPHeaders').get('x-amzn-bedrock-input-token-count')
+            completion_tokens = response.get('ResponseMetadata').get('HTTPHeaders').get('x-amzn-bedrock-output-token-count')

        else:
            raise ValueError(f"Got unknown model prefix {model_prefix} when handling block response")
@@ -731,6 +743,10 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
                content_delta = payload.get("text")
                finish_reason = payload.get("finish_reason")
            
+            elif model_prefix == "mistral":
+                content_delta = payload.get('outputs')[0].get("text")
+                finish_reason = payload.get('outputs')[0].get("stop_reason")
+
            elif model_prefix == "meta":
                content_delta = payload.get("generation").strip('\n')
                finish_reason = payload.get("stop_reason")
--- a/api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-70b-instruct-v1.yaml
+++ b/api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-70b-instruct-v1.yaml
@@ -0,0 +1,23 @@
+model: meta.llama3-70b-instruct-v1:0
+label:
+  en_US: Llama 3 Instruct 70B
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 2048
+pricing:
+  input: '0.00265'
+  output: '0.0035'
+  unit: '0.00001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-8b-instruct-v1.yaml
+++ b/api/core/model_runtime/model_providers/bedrock/llm/meta.llama3-8b-instruct-v1.yaml
@@ -0,0 +1,23 @@
+model: meta.llama3-8b-instruct-v1:0
+label:
+  en_US: Llama 3 Instruct 8B
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 2048
+pricing:
+  input: '0.0004'
+  output: '0.0006'
+  unit: '0.0001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/bedrock/llm/mistral.mistral-7b-instruct-v0.2.yaml
+++ b/api/core/model_runtime/model_providers/bedrock/llm/mistral.mistral-7b-instruct-v0.2.yaml
@@ -0,0 +1,39 @@
+model: mistral.mistral-7b-instruct-v0:2
+label:
+  en_US: Mistral 7B Instruct
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 32000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    required: false
+    default: 0.5
+  - name: top_p
+    use_template: top_p
+    required: false
+    default: 0.9
+  - name: top_k
+    use_template: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+    default: 50
+    max: 200
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 8192
+pricing:
+  input: '0.00015'
+  output: '0.0002'
+  unit: '0.00001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/bedrock/llm/mistral.mistral-large-2402-v1.0.yaml
+++ b/api/core/model_runtime/model_providers/bedrock/llm/mistral.mistral-large-2402-v1.0.yaml
@@ -0,0 +1,27 @@
+model: mistral.mistral-large-2402-v1:0
+label:
+  en_US: Mistral Large
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 32000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    required: false
+    default: 0.7
+  - name: top_p
+    use_template: top_p
+    required: false
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 4096
+pricing:
+  input: '0.008'
+  output: '0.024'
+  unit: '0.001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/bedrock/llm/mistral.mixtral-8x7b-instruct-v0.1.yaml
+++ b/api/core/model_runtime/model_providers/bedrock/llm/mistral.mixtral-8x7b-instruct-v0.1.yaml
@@ -0,0 +1,39 @@
+model: mistral.mixtral-8x7b-instruct-v0:1
+label:
+  en_US: Mixtral 8X7B Instruct
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 32000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    required: false
+    default: 0.5
+  - name: top_p
+    use_template: top_p
+    required: false
+    default: 0.9
+  - name: top_k
+    use_template: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+    default: 50
+    max: 200
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 8192
+pricing:
+  input: '0.00045'
+  output: '0.0007'
+  unit: '0.00001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/groq/groq.py
+++ b/api/core/model_runtime/model_providers/groq/groq.py
@@ -19,7 +19,7 @@ class GroqProvider(ModelProvider):
            model_instance = self.get_model_instance(ModelType.LLM)

            model_instance.validate_credentials(
-                model='llama2-70b-4096',
+                model='llama3-8b-8192',
                credentials=credentials
            )
        except CredentialsValidateFailedError as ex:
--- a/api/core/model_runtime/model_providers/groq/llm/llama3-70b-8192.yaml
+++ b/api/core/model_runtime/model_providers/groq/llm/llama3-70b-8192.yaml
@@ -0,0 +1,25 @@
+model: llama3-70b-8192
+label:
+  zh_Hans: Llama-3-70B-8192
+  en_US: Llama-3-70B-8192
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_tokens
+    use_template: max_tokens
+    default: 512
+    min: 1
+    max: 8192
+pricing:
+  input: '0.05'
+  output: '0.1'
+  unit: '0.000001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/groq/llm/llama3-8b-8192.yaml
+++ b/api/core/model_runtime/model_providers/groq/llm/llama3-8b-8192.yaml
@@ -0,0 +1,25 @@
+model: llama3-8b-8192
+label:
+  zh_Hans: Llama-3-8B-8192
+  en_US: Llama-3-8B-8192
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_tokens
+    use_template: max_tokens
+    default: 512
+    min: 1
+    max: 8192
+pricing:
+  input: '0.59'
+  output: '0.79'
+  unit: '0.000001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/minimax/llm/abab6.5-chat.yaml
+++ b/api/core/model_runtime/model_providers/minimax/llm/abab6.5-chat.yaml
@@ -0,0 +1,37 @@
+model: abab6.5-chat
+label:
+  en_US: Abab6.5-Chat
+model_type: llm
+features:
+  - agent-thought
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0.01
+    max: 1
+    default: 0.1
+  - name: top_p
+    use_template: top_p
+    min: 0.01
+    max: 1
+    default: 0.95
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 2048
+    min: 1
+    max: 8192
+  - name: presence_penalty
+    use_template: presence_penalty
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '0.03'
+  output: '0.03'
+  unit: '0.001'
+  currency: RMB
--- a/api/core/model_runtime/model_providers/minimax/llm/abab6.5s-chat.yaml
+++ b/api/core/model_runtime/model_providers/minimax/llm/abab6.5s-chat.yaml
@@ -0,0 +1,37 @@
+model: abab6.5s-chat
+label:
+  en_US: Abab6.5s-Chat
+model_type: llm
+features:
+  - agent-thought
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 245760
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0.01
+    max: 1
+    default: 0.1
+  - name: top_p
+    use_template: top_p
+    min: 0.01
+    max: 1
+    default: 0.95
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 2048
+    min: 1
+    max: 245760
+  - name: presence_penalty
+    use_template: presence_penalty
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '0.01'
+  output: '0.01'
+  unit: '0.001'
+  currency: RMB
--- a/api/core/model_runtime/model_providers/mistralai/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/mistralai/llm/_position.yaml
@@ -1,5 +1,6 @@
 - open-mistral-7b
 - open-mixtral-8x7b
+- open-mixtral-8x22b
 - mistral-small-latest
 - mistral-medium-latest
 - mistral-large-latest
--- a/api/core/model_runtime/model_providers/mistralai/llm/mistral-large-latest.yaml
+++ b/api/core/model_runtime/model_providers/mistralai/llm/mistral-large-latest.yaml
@@ -6,6 +6,7 @@ model_type: llm
 features:
  - agent-thought
 model_properties:
+  mode: chat
  context_size: 32000
 parameter_rules:
  - name: temperature
--- a/api/core/model_runtime/model_providers/mistralai/llm/mistral-medium-latest.yaml
+++ b/api/core/model_runtime/model_providers/mistralai/llm/mistral-medium-latest.yaml
@@ -6,6 +6,7 @@ model_type: llm
 features:
  - agent-thought
 model_properties:
+  mode: chat
  context_size: 32000
 parameter_rules:
  - name: temperature
--- a/api/core/model_runtime/model_providers/mistralai/llm/mistral-small-latest.yaml
+++ b/api/core/model_runtime/model_providers/mistralai/llm/mistral-small-latest.yaml
@@ -6,6 +6,7 @@ model_type: llm
 features:
  - agent-thought
 model_properties:
+  mode: chat
  context_size: 32000
 parameter_rules:
  - name: temperature
--- a/api/core/model_runtime/model_providers/mistralai/llm/open-mistral-7b.yaml
+++ b/api/core/model_runtime/model_providers/mistralai/llm/open-mistral-7b.yaml
@@ -6,6 +6,7 @@ model_type: llm
 features:
  - agent-thought
 model_properties:
+  mode: chat
  context_size: 8000
 parameter_rules:
  - name: temperature
--- a/api/core/model_runtime/model_providers/mistralai/llm/open-mixtral-8x22b.yaml
+++ b/api/core/model_runtime/model_providers/mistralai/llm/open-mixtral-8x22b.yaml
@@ -0,0 +1,51 @@
+model: open-mixtral-8x22b
+label:
+  zh_Hans: open-mixtral-8x22b
+  en_US: open-mixtral-8x22b
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 64000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.7
+    min: 0
+    max: 1
+  - name: top_p
+    use_template: top_p
+    default: 1
+    min: 0
+    max: 1
+  - name: max_tokens
+    use_template: max_tokens
+    default: 1024
+    min: 1
+    max: 8000
+  - name: safe_prompt
+    default: false
+    type: boolean
+    help:
+      en_US: Whether to inject a safety prompt before all conversations.
+      zh_Hans: 是否开启提示词审查
+    label:
+      en_US: SafePrompt
+      zh_Hans: 提示词审查
+  - name: random_seed
+    type: int
+    help:
+      en_US: The seed to use for random sampling. If set, different calls will generate deterministic results.
+      zh_Hans: 当开启随机数种子以后，你可以通过指定一个固定的种子来使得回答结果更加稳定
+    label:
+      en_US: RandomSeed
+      zh_Hans: 随机数种子
+    default: 0
+    min: 0
+    max: 2147483647
+pricing:
+  input: '0.002'
+  output: '0.006'
+  unit: '0.001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/mistralai/llm/open-mixtral-8x7b.yaml
+++ b/api/core/model_runtime/model_providers/mistralai/llm/open-mixtral-8x7b.yaml
@@ -6,6 +6,7 @@ model_type: llm
 features:
  - agent-thought
 model_properties:
+  mode: chat
  context_size: 32000
 parameter_rules:
  - name: temperature
--- a/api/core/model_runtime/model_providers/moonshot/llm/moonshot-v1-128k.yaml
+++ b/api/core/model_runtime/model_providers/moonshot/llm/moonshot-v1-128k.yaml
@@ -5,6 +5,9 @@ label:
 model_type: llm
 features:
  - agent-thought
+  - tool-call
+  - multi-tool-call
+  - stream-tool-call
 model_properties:
  mode: chat
  context_size: 128000
--- a/api/core/model_runtime/model_providers/moonshot/llm/moonshot-v1-32k.yaml
+++ b/api/core/model_runtime/model_providers/moonshot/llm/moonshot-v1-32k.yaml
@@ -5,6 +5,9 @@ label:
 model_type: llm
 features:
  - agent-thought
+  - tool-call
+  - multi-tool-call
+  - stream-tool-call
 model_properties:
  mode: chat
  context_size: 32000
--- a/api/core/model_runtime/model_providers/moonshot/llm/moonshot-v1-8k.yaml
+++ b/api/core/model_runtime/model_providers/moonshot/llm/moonshot-v1-8k.yaml
@@ -5,6 +5,9 @@ label:
 model_type: llm
 features:
  - agent-thought
+  - tool-call
+  - multi-tool-call
+  - stream-tool-call
 model_properties:
  mode: chat
  context_size: 8192
--- a/api/core/model_runtime/model_providers/nvidia/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/nvidia/llm/_position.yaml
@@ -1,5 +1,7 @@
 - google/gemma-7b
 - google/codegemma-7b
 - meta/llama2-70b
+- meta/llama3-8b-instruct
+- meta/llama3-70b-instruct
 - mistralai/mixtral-8x7b-instruct-v0.1
 - fuyu-8b
--- a/api/core/model_runtime/model_providers/nvidia/llm/codegemma-7b.yaml
+++ b/api/core/model_runtime/model_providers/nvidia/llm/codegemma-7b.yaml
@@ -11,13 +11,19 @@ model_properties:
 parameter_rules:
  - name: temperature
    use_template: temperature
+    min: 0
+    max: 1
+    default: 0.5
  - name: top_p
    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
  - name: max_tokens
    use_template: max_tokens
-    default: 1024
    min: 1
    max: 1024
+    default: 1024
  - name: frequency_penalty
    use_template: frequency_penalty
    min: -2
--- a/api/core/model_runtime/model_providers/nvidia/llm/fuyu-8b.yaml
+++ b/api/core/model_runtime/model_providers/nvidia/llm/fuyu-8b.yaml
@@ -22,6 +22,6 @@ parameter_rules:
    max: 1
  - name: max_tokens
    use_template: max_tokens
-    default: 512
+    default: 1024
    min: 1
    max: 1024
--- a/api/core/model_runtime/model_providers/nvidia/llm/gemma-7b.yaml
+++ b/api/core/model_runtime/model_providers/nvidia/llm/gemma-7b.yaml
@@ -11,13 +11,19 @@ model_properties:
 parameter_rules:
  - name: temperature
    use_template: temperature
+    min: 0
+    max: 1
+    default: 0.5
  - name: top_p
    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
  - name: max_tokens
    use_template: max_tokens
-    default: 512
    min: 1
    max: 1024
+    default: 1024
  - name: frequency_penalty
    use_template: frequency_penalty
    min: -2
--- a/api/core/model_runtime/model_providers/nvidia/llm/llama2-70b.yaml
+++ b/api/core/model_runtime/model_providers/nvidia/llm/llama2-70b.yaml
@@ -7,17 +7,23 @@ features:
  - agent-thought
 model_properties:
  mode: chat
-  context_size: 32768
+  context_size: 4096
 parameter_rules:
  - name: temperature
    use_template: temperature
+    min: 0
+    max: 1
+    default: 0.5
  - name: top_p
    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
  - name: max_tokens
    use_template: max_tokens
-    default: 512
    min: 1
    max: 1024
+    default: 1024
  - name: frequency_penalty
    use_template: frequency_penalty
    min: -2
--- a/api/core/model_runtime/model_providers/nvidia/llm/llama3-70b.yaml
+++ b/api/core/model_runtime/model_providers/nvidia/llm/llama3-70b.yaml
@@ -0,0 +1,36 @@
+model: meta/llama3-70b-instruct
+label:
+  zh_Hans: meta/llama3-70b-instruct
+  en_US: meta/llama3-70b-instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 1
+    default: 0.5
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 1024
+    default: 1024
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
--- a/api/core/model_runtime/model_providers/nvidia/llm/llama3-8b.yaml
+++ b/api/core/model_runtime/model_providers/nvidia/llm/llama3-8b.yaml
@@ -0,0 +1,36 @@
+model: meta/llama3-8b-instruct
+label:
+  zh_Hans: meta/llama3-8b-instruct
+  en_US: meta/llama3-8b-instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0
+    max: 1
+    default: 0.5
+  - name: top_p
+    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    min: 1
+    max: 1024
+    default: 1024
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    min: -2
+    max: 2
+    default: 0
+  - name: presence_penalty
+    use_template: presence_penalty
+    min: -2
+    max: 2
+    default: 0
--- a/api/core/model_runtime/model_providers/nvidia/llm/llm.py
+++ b/api/core/model_runtime/model_providers/nvidia/llm/llm.py
@@ -25,7 +25,10 @@ class NVIDIALargeLanguageModel(OAIAPICompatLargeLanguageModel):
        'mistralai/mixtral-8x7b-instruct-v0.1': '',
        'google/gemma-7b': '',
        'google/codegemma-7b': '',
-        'meta/llama2-70b': ''
+        'meta/llama2-70b': '',
+        'meta/llama3-8b-instruct': '',
+        'meta/llama3-70b-instruct': ''
+        
    }

    def _invoke(self, model: str, credentials: dict,
@@ -131,7 +134,7 @@ class NVIDIALargeLanguageModel(OAIAPICompatLargeLanguageModel):
                endpoint_url,
                headers=headers,
                json=data,
-                timeout=(10, 60)
+                timeout=(10, 300)
            )

            if response.status_code != 200:
@@ -232,7 +235,7 @@ class NVIDIALargeLanguageModel(OAIAPICompatLargeLanguageModel):
            endpoint_url,
            headers=headers,
            json=data,
-            timeout=(10, 60),
+            timeout=(10, 300),
            stream=stream
        )

--- a/api/core/model_runtime/model_providers/nvidia/llm/mistralai_mixtral-8x7b-instruct-v0.1.yaml
+++ b/api/core/model_runtime/model_providers/nvidia/llm/mistralai_mixtral-8x7b-instruct-v0.1.yaml
@@ -11,13 +11,19 @@ model_properties:
 parameter_rules:
  - name: temperature
    use_template: temperature
+    min: 0
+    max: 1
+    default: 0.5
  - name: top_p
    use_template: top_p
+    min: 0
+    max: 1
+    default: 1
  - name: max_tokens
    use_template: max_tokens
-    default: 512
    min: 1
    max: 1024
+    default: 1024
  - name: frequency_penalty
    use_template: frequency_penalty
    min: -2
--- a/api/core/model_runtime/model_providers/nvidia/nvidia.yaml
+++ b/api/core/model_runtime/model_providers/nvidia/nvidia.yaml
@@ -1,6 +1,9 @@
 provider: nvidia
 label:
  en_US: API Catalog
+description:
+  en_US: API Catalog
+  zh_Hans: API Catalog
 icon_small:
  en_US: icon_s_en.svg
 icon_large:
--- a/api/core/model_runtime/model_providers/ollama/llm/llm.py
+++ b/api/core/model_runtime/model_providers/ollama/llm/llm.py
@@ -201,7 +201,7 @@ class OllamaLargeLanguageModel(LargeLanguageModel):
            endpoint_url,
            headers=headers,
            json=data,
-            timeout=(10, 60),
+            timeout=(10, 300),
            stream=stream
        )

--- a/api/core/model_runtime/model_providers/openai_api_compatible/llm/llm.py
+++ b/api/core/model_runtime/model_providers/openai_api_compatible/llm/llm.py
@@ -138,7 +138,7 @@ class OAIAPICompatLargeLanguageModel(_CommonOAI_API_Compat, LargeLanguageModel):
                endpoint_url,
                headers=headers,
                json=data,
-                timeout=(10, 60)
+                timeout=(10, 300)
            )

            if response.status_code != 200:
@@ -154,7 +154,7 @@ class OAIAPICompatLargeLanguageModel(_CommonOAI_API_Compat, LargeLanguageModel):
                json_result['object'] = 'chat.completion'
            elif (completion_type is LLMMode.COMPLETION and json_result['object'] == ''):
                json_result['object'] = 'text_completion'
-                
+
            if (completion_type is LLMMode.CHAT
                    and ('object' not in json_result or json_result['object'] != 'chat.completion')):
                raise CredentialsValidateFailedError(
@@ -334,7 +334,7 @@ class OAIAPICompatLargeLanguageModel(_CommonOAI_API_Compat, LargeLanguageModel):
            endpoint_url,
            headers=headers,
            json=data,
-            timeout=(10, 60),
+            timeout=(10, 300),
            stream=stream
        )

@@ -425,6 +425,7 @@ class OAIAPICompatLargeLanguageModel(_CommonOAI_API_Compat, LargeLanguageModel):
        finish_reason = 'Unknown'

        for chunk in response.iter_lines(decode_unicode=True, delimiter=delimiter):
+            chunk = chunk.strip()
            if chunk:
                # ignore sse comments
                if chunk.startswith(':'):
--- a/api/core/model_runtime/model_providers/openrouter/openrouter.yaml
+++ b/api/core/model_runtime/model_providers/openrouter/openrouter.yaml
@@ -73,3 +73,22 @@ model_credential_schema:
          value: llm
      default: "4096"
      type: text-input
+    - variable: vision_support
+      show_on:
+        - variable: __model_type
+          value: llm
+      label:
+        zh_Hans: 是否支持 Vision
+        en_US: Vision Support
+      type: radio
+      required: false
+      default: 'no_support'
+      options:
+        - value: 'support'
+          label:
+            en_US: 'Yes'
+            zh_Hans: 是
+        - value: 'no_support'
+          label:
+            en_US: 'No'
+            zh_Hans: 否
--- a/api/core/model_runtime/model_providers/replicate/llm/llm.py
+++ b/api/core/model_runtime/model_providers/replicate/llm/llm.py
@@ -33,11 +33,17 @@ class ReplicateLargeLanguageModel(_CommonReplicate, LargeLanguageModel):
                tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None, stream: bool = True,
                user: Optional[str] = None) -> Union[LLMResult, Generator]:

-        version = credentials['model_version']
+        model_version = ''
+        if 'model_version' in credentials:
+            model_version = credentials['model_version']

        client = ReplicateClient(api_token=credentials['replicate_api_token'], timeout=30)
        model_info = client.models.get(model)
-        model_info_version = model_info.versions.get(version)
+
+        if model_version:
+            model_info_version = model_info.versions.get(model_version)
+        else:
+            model_info_version = model_info.latest_version

        inputs = {**model_parameters}

@@ -65,29 +71,35 @@ class ReplicateLargeLanguageModel(_CommonReplicate, LargeLanguageModel):
        if 'replicate_api_token' not in credentials:
            raise CredentialsValidateFailedError('Replicate Access Token must be provided.')

-        if 'model_version' not in credentials:
-            raise CredentialsValidateFailedError('Replicate Model Version must be provided.')
+        model_version = ''
+        if 'model_version' in credentials:
+            model_version = credentials['model_version']

        if model.count("/") != 1:
            raise CredentialsValidateFailedError('Replicate Model Name must be provided, '
                                                 'format: {user_name}/{model_name}')

-        version = credentials['model_version']
-
        try:
            client = ReplicateClient(api_token=credentials['replicate_api_token'], timeout=30)
            model_info = client.models.get(model)
-            model_info_version = model_info.versions.get(version)

-            self._check_text_generation_model(model_info_version, model, version)
+            if model_version:
+                model_info_version = model_info.versions.get(model_version)
+            else:
+                model_info_version = model_info.latest_version
+
+            self._check_text_generation_model(model_info_version, model, model_version, model_info.description)
        except ReplicateError as e:
            raise CredentialsValidateFailedError(
-                f"Model {model}:{version} not exists, cause: {e.__class__.__name__}:{str(e)}")
+                f"Model {model}:{model_version} not exists, cause: {e.__class__.__name__}:{str(e)}")
        except Exception as e:
            raise CredentialsValidateFailedError(str(e))

    @staticmethod
-    def _check_text_generation_model(model_info_version, model_name, version):
+    def _check_text_generation_model(model_info_version, model_name, version, description):
+        if 'language model' in description.lower():
+            return
+
        if 'temperature' not in model_info_version.openapi_schema['components']['schemas']['Input']['properties'] \
                or 'top_p' not in model_info_version.openapi_schema['components']['schemas']['Input']['properties'] \
                or 'top_k' not in model_info_version.openapi_schema['components']['schemas']['Input']['properties']:
@@ -113,11 +125,17 @@ class ReplicateLargeLanguageModel(_CommonReplicate, LargeLanguageModel):

    @classmethod
    def _get_customizable_model_parameter_rules(cls, model: str, credentials: dict) -> list[ParameterRule]:
-        version = credentials['model_version']
+        model_version = ''
+        if 'model_version' in credentials:
+            model_version = credentials['model_version']

        client = ReplicateClient(api_token=credentials['replicate_api_token'], timeout=30)
        model_info = client.models.get(model)
-        model_info_version = model_info.versions.get(version)
+
+        if model_version:
+            model_info_version = model_info.versions.get(model_version)
+        else:
+            model_info_version = model_info.latest_version

        parameter_rules = []

--- a/api/core/model_runtime/model_providers/replicate/replicate.yaml
+++ b/api/core/model_runtime/model_providers/replicate/replicate.yaml
@@ -35,7 +35,7 @@ model_credential_schema:
      label:
        en_US: Model Version
      type: text-input
-      required: true
+      required: false
      placeholder:
-        zh_Hans: 在此输入您的模型版本
-        en_US: Enter your model version
+        zh_Hans: 在此输入您的模型版本，默认为最新版本
+        en_US: Enter your model version, default to the latest version
--- a/api/core/model_runtime/model_providers/replicate/text_embedding/text_embedding.py
+++ b/api/core/model_runtime/model_providers/replicate/text_embedding/text_embedding.py
@@ -17,9 +17,16 @@ class ReplicateEmbeddingModel(_CommonReplicate, TextEmbeddingModel):
                user: Optional[str] = None) -> TextEmbeddingResult:

        client = ReplicateClient(api_token=credentials['replicate_api_token'], timeout=30)
-        replicate_model_version = f'{model}:{credentials["model_version"]}'

-        text_input_key = self._get_text_input_key(model, credentials['model_version'], client)
+        if 'model_version' in credentials:
+            model_version = credentials['model_version']
+        else:
+            model_info = client.models.get(model)
+            model_version = model_info.latest_version.id
+
+        replicate_model_version = f'{model}:{model_version}'
+
+        text_input_key = self._get_text_input_key(model, model_version, client)

        embeddings = self._generate_embeddings_by_text_input_key(client, replicate_model_version, text_input_key,
                                                                 texts)
@@ -43,14 +50,18 @@ class ReplicateEmbeddingModel(_CommonReplicate, TextEmbeddingModel):
        if 'replicate_api_token' not in credentials:
            raise CredentialsValidateFailedError('Replicate Access Token must be provided.')

-        if 'model_version' not in credentials:
-            raise CredentialsValidateFailedError('Replicate Model Version must be provided.')
-
        try:
            client = ReplicateClient(api_token=credentials['replicate_api_token'], timeout=30)
-            replicate_model_version = f'{model}:{credentials["model_version"]}'

-            text_input_key = self._get_text_input_key(model, credentials['model_version'], client)
+            if 'model_version' in credentials:
+                model_version = credentials['model_version']
+            else:
+                model_info = client.models.get(model)
+                model_version = model_info.latest_version.id
+
+            replicate_model_version = f'{model}:{model_version}'
+
+            text_input_key = self._get_text_input_key(model, model_version, client)

            self._generate_embeddings_by_text_input_key(client, replicate_model_version, text_input_key,
                                                        ['Hello worlds!'])
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
takatost	93393e005e	version to 0.6.6 (#4050 )	2024-05-02 16:06:40 +08:00
Bowen Liang	4ea2755fce	test: remove explicit env settings for CI pytests (#4041 )	2024-05-02 00:49:39 +08:00
dependabot[bot]	ecb51a83d4	chore(deps): bump semver from 5.7.1 to 5.7.2 in /web (#4022 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-04-30 18:47:05 +08:00
Bowen Liang	093b5c0e63	fix: typo of jinja2 (#4019 )	2024-04-30 18:39:02 +08:00
Joel	bf42b0ae44	fix: lodash version has warning (#4020 ) Co-authored-by: nite-knite <nkCoding@gmail.com>	2024-04-30 18:11:49 +08:00
dependabot[bot]	342b4fd19d	chore(deps): bump word-wrap from 1.2.3 to 1.2.5 in /web Bumps [word-wrap](https://github.com/jonschlinkert/word-wrap) from 1.2.3 to 1.2.5. - [Release notes](https://github.com/jonschlinkert/word-wrap/releases) - [Commits](https://github.com/jonschlinkert/word-wrap/compare/1.2.3...1.2.5) --- updated-dependencies: - dependency-name: word-wrap dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com>	2024-04-30 09:39:10 +00:00
orangeclk	cbdb861ee4	add glm-3-turbo max_tokens parameter setting (#4017 ) Co-authored-by: 陈力坤 <likunchen@caixin.com>	2024-04-30 17:08:04 +08:00
sino	da5a8b9a59	feat: support question classifier node output (#4000 )	2024-04-30 17:07:29 +08:00
Weaxs	1e6e8b446d	feat: support minimax abab6.5, abab6.5s (#4012 )	2024-04-30 17:02:01 +08:00
Joel	c1fdaa6ae0	fix: prompt undefined caused match problem (#4010 )	2024-04-30 16:31:36 +08:00
Bowen Liang	142814d451	chore: skip deprecated field_schema param in creating payload index on Qdrant (#3903 )	2024-04-30 16:16:10 +08:00
crazywoola	704755d005	fix: submitCodeExecutionTask (#4006 )	2024-04-30 16:01:03 +08:00
Richards Tu	d1263700c0	Update the description and labels in Judge0ce tool (#3990 ) Co-authored-by: crazywoola <427733928@qq.com>	2024-04-30 14:58:29 +08:00
Rhon Joe	0704fe9695	fix(web): copy button visible at chat page normally (#4005 ) Co-authored-by: rongjun.qiu <qiurj@hengtonggroup.com.cn>	2024-04-30 14:55:57 +08:00
Kei YAMAZAKI	1d3f1d88ef	Enabled Notion integration setup in Docker Compose Deployment (#3919 )	2024-04-30 14:48:39 +08:00
zxhlyh	8b3edac091	fix: prompt editor insert quickly (#4004 )	2024-04-30 14:25:21 +08:00
zxhlyh	05cab85579	fix: workflow disable shortcuts when feature panel occured (#4001 )	2024-04-30 13:35:49 +08:00
Yeuoly	b72fbe200d	chore: add sandbox tag (#3997 )	2024-04-30 12:35:19 +08:00
crazywoola	b1194da6a5	fix: ci (#3983 )	2024-04-29 18:59:37 +08:00
Jyong	338e4669e5	add storage factory (#3922 )	2024-04-29 18:22:03 +08:00
crazywoola	c5e2659771	Feat/install process refinement (#3982 )	2024-04-29 17:55:52 +08:00
Jyong	1d432728ac	add default value for QDRANT_GRPC_PORT (#3976 )	2024-04-29 15:28:34 +08:00
KVOJJJin	2fd702a319	Fix: password check in page of install (#3978 )	2024-04-29 15:27:45 +08:00
Richards Tu	f26ad16af7	Add new tool: Firecrawl (#3819 ) Co-authored-by: crazywoola <427733928@qq.com> Co-authored-by: Yeuoly <admin@srmxy.cn>	2024-04-29 14:20:36 +08:00
majian	8f2ae51fe5	feat: add support for request timeout settings in the HTTP request node. (#3854 ) Co-authored-by: Yeuoly <admin@srmxy.cn>	2024-04-29 13:59:07 +08:00
Joshua	2f84d00300	fix-nvidia-llama3 (#3973 )	2024-04-29 13:41:15 +08:00
takatost	b82a2d97ef	fix: db connections not being released during workflow execution (#3971 )	2024-04-29 12:42:09 +08:00
Jyong	3e9dbe3e0a	add pgvecto_rs support and upgrade SQLAlchemy (#3833 )	2024-04-29 11:58:17 +08:00
羊羽	975b2fb79e	delete duplicate check get_dataset (#3966 ) Co-authored-by: baxiang <baxiang@lixiang.com>	2024-04-29 11:57:26 +08:00
Joel	fa509ce64e	feat: rename var name sync to used jinjia code (#3964 )	2024-04-29 11:34:30 +08:00
TinsFox	99292edd46	chore: update `@types/react` (#3939 )	2024-04-28 19:01:09 +08:00
Joel	3e992cb23c	feat: code transform node editor support insert var by add slash or left brace (#3946 ) Co-authored-by: StyleZhang <jasonapring2015@outlook.com>	2024-04-28 17:51:58 +08:00
Yeuoly	e7b4d024ee	optimize: code node has a bad error message (#3949 )	2024-04-28 17:40:29 +08:00
takatost	ff67a6d338	feat: llm text stream support for workflow app (#3798 ) Co-authored-by: JzoNg <jzongcode@gmail.com>	2024-04-28 17:37:00 +08:00
zxhlyh	8e4989ed03	feat: workflow remove preview mode (#3941 )	2024-04-28 17:09:56 +08:00
呆萌闷油瓶	0940f01634	enhancement:support Qdrant gRPC mode (#3929 )	2024-04-28 15:33:32 +08:00
majian	9d1cb1bc92	improvement: Optimizing the experience of the app list page (#3885 )	2024-04-28 13:52:45 +08:00
Pascal M	0ca4e30b19	feat: add start commands to devcontainer (#3902 )	2024-04-28 12:30:56 +08:00
Joel	ba88f8a6f0	fix: code full screen in web app cause error (#3935 )	2024-04-28 11:59:57 +08:00
studyinglover	aefe0cbf51	fix: api doc example error (#3925 )	2024-04-28 10:18:07 +08:00
miendinh	9ad489d133	feat: Add google storage support (#3887 ) Co-authored-by: miendinh <miendinh@users.noreply.github.com>	2024-04-27 18:26:52 +08:00
Bowen Liang	661b30784e	chore: skip warning messages when pytest auto-collecting the vdb test class by removing `Test` prefix (#3906 )	2024-04-27 16:36:09 +08:00
longzhihun	43a5ba9415	feat: add support for Bedrock LLAMA3 (#3890 )	2024-04-27 13:13:09 +08:00
TinsFox	08a65d74d5	fix: hydration warning (#3897 )	2024-04-26 21:34:29 +08:00
Garfield Dai	cefe156811	feat: replicate supports default version. (#3884 )	2024-04-26 21:16:22 +08:00
yongjer	3b5b4d628b	Add support for Traditional Chinese language (#3899 ) Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com> Co-authored-by: crazywoola <427733928@qq.com>	2024-04-26 21:10:23 +08:00
TinsFox	8746e48df0	chore: integrate code-inspector-plugin (#3900 )	2024-04-26 21:00:29 +08:00
Jyong	0ec8b57825	add together ai model setting (#3895 )	2024-04-26 20:43:17 +08:00
Bowen Liang	045827043d	test: improve vector store tests (#3855 )	2024-04-26 19:18:42 +08:00
yalei	4d66a86579	fix: fetch page name of notion wiki (#3847 )	2024-04-26 18:04:37 +08:00
miendinh	2a8881d0e8	fix: tool webscraper - too many redirects in case target url does not… (#3831 ) Co-authored-by: miendinh <miendinh@users.noreply.github.com>	2024-04-26 17:58:46 +08:00
akou	ffc60bb917	add the comment in entrypoint.sh (#3882 )	2024-04-26 17:19:49 +08:00
Ever	2e454c770b	fix: copy invite link for HTTPS has deplicate origin (#3877 )	2024-04-26 15:19:30 +08:00
Joel	7d711135bc	fix: full screen editor not follow panel width (#3876 )	2024-04-26 14:23:13 +08:00
Charlie.Wei	f62b2b5b45	optimize the knowledge failed documents query (#3870 ) Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM> Co-authored-by: crazywoola <427733928@qq.com> Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>	2024-04-26 11:47:23 +08:00
Bowen Liang	7919596a21	fix: UP031 style rule violation (#3866 )	2024-04-26 11:24:08 +08:00
Joel	9b4898efeb	fix: chat api doc not show title in english vision (#3864 )	2024-04-26 10:32:45 +08:00
Bowen Liang	45dd1683fd	test: add tests covering all methods of vector store (#3849 )	2024-04-25 22:27:30 +08:00
takatost	8bca908f15	refactor: config file (#3852 )	2024-04-25 22:26:45 +08:00
Garfield Dai	9cbb8ddd7f	fix: billing tenant account role. (#3850 )	2024-04-25 21:55:08 +08:00
Jingpan Xiong	1be222af2e	fix: using api can not execute relyt vector database (#3766 ) Co-authored-by: jingsi <jingsi@leadincloud.com>	2024-04-25 19:46:20 +08:00
Richards Tu	bf9fc8fef4	Reduce tool redundancy for [Judge0 CE] (#3837 ) Co-authored-by: crazywoola <427733928@qq.com>	2024-04-25 19:20:54 +08:00
Bowen Liang	86e7330fa2	test: refactor vdb tests by visitor design pattern (#3838 )	2024-04-25 18:55:49 +08:00
takatost	34bfb715e1	fix: citations always appear in the chatflow app (#3844 )	2024-04-25 18:31:38 +08:00
Joel	019d7069f8	fix: debug run not show total right tokens (#3843 )	2024-04-25 18:22:30 +08:00
Bowen Liang	c54fcfb45d	extract enum type for tenant account role (#3788 )	2024-04-25 18:20:08 +08:00
zxhlyh	cde87cb225	fix: model parameter default value (#3841 )	2024-04-25 18:04:37 +08:00
takatost	12435774ca	feat: query prompt template support in chatflow (#3791 ) Co-authored-by: Joel <iamjoel007@gmail.com>	2024-04-25 18:01:53 +08:00
Henrybit	80b9507e7a	feat: add aliyun oss storage (#3690 ) Co-authored-by: henrybit <qipenghui3056@sina.com>	2024-04-25 16:57:19 +08:00
takatost	0ac0f0ffd0	version to 0.6.5 (#3834 )	2024-04-25 16:50:37 +08:00
KVOJJJin	3d14aba4b4	Fix: event of click away in message-log-modal (#3828 )	2024-04-25 15:58:03 +08:00
Leon cap	64f694865c	Update EN,KL,JA,FR,ES documentation Llma2 to Llama3 model support (#3827 )	2024-04-25 15:52:00 +08:00
zxhlyh	d36b728088	fix: workflow sync data (#3824 )	2024-04-25 14:02:06 +08:00
KVOJJJin	1a7b4c42ab	fix: event of keyboard "enter" in text generator app (#3823 )	2024-04-25 13:58:06 +08:00
Joel	2a64ce740e	chore: remove anthropic pay entrance (#3822 )	2024-04-25 13:18:59 +08:00
呆萌闷油瓶	78988ed60e	fix:still enable SSL verification when using qdrant based on HTTP protocol (#3805 )	2024-04-25 13:04:31 +08:00
Yeuoly	2832adda88	fix: missing url field when searching special keywords (#3820 )	2024-04-25 12:33:58 +08:00
takatost	a4e4fb4094	fix: credentials validate failed for groqcloud model provider (#3817 )	2024-04-25 12:09:44 +08:00
YidaHu	777ec64635	feat: add log_file environment variable (#3793 )	2024-04-24 21:55:14 +08:00
Bowen Liang	9cec8c1750	test: add unit tests for vector stores of Milvus, Qdrant and Weaviate (#3688 )	2024-04-24 21:52:42 +08:00
Bowen Liang	8ca5aa1190	use pymilvus 2.3.7 (#3790 )	2024-04-24 18:37:08 +08:00
takatost	4d8f1b9ca4	feat: test all unit tests (#3787 ) Co-authored-by: Joel <iamjoel007@gmail.com>	2024-04-24 17:33:01 +08:00
takatost	3da179f77b	feat: add conversation_id and user_id in chatflow/workflow system vars (#3771 ) Co-authored-by: Joel <iamjoel007@gmail.com>	2024-04-24 17:20:01 +08:00
Bowen Liang	a34e8cb0bd	test: add test for PKCS1OAEP_Cipher with gmpy2 (#3760 )	2024-04-24 17:15:31 +08:00
KVOJJJin	b249767c5c	Fix: redirection of app remove (#3770 )	2024-04-24 17:11:51 +08:00
Joel	89a7434565	fix: handle inputs show the focus ui together in tools node (#3763 )	2024-04-24 15:53:07 +08:00
ugyuji	3b537cbdeb	fix: endpoint for 'Update a document from a file' (#3751 )	2024-04-24 15:25:53 +08:00
zxhlyh	731464f5b8	fix: workflow sync (#3756 )	2024-04-24 15:19:19 +08:00
Joel	1ad70f8721	feat: support prompt messages sorting (#3757 )	2024-04-24 15:09:01 +08:00
takatost	2ea8c73cd8	fix: type num of variable converted to str (#3758 )	2024-04-24 15:07:56 +08:00
Jyong	f257f2c396	Knowledge optimization (#3755 ) Co-authored-by: crazywoola <427733928@qq.com> Co-authored-by: JzoNg <jzongcode@gmail.com>	2024-04-24 15:02:29 +08:00
Joel	3cd8e6f5c6	fix: llm editor readonly cover error (#3752 )	2024-04-24 13:28:22 +08:00
KVOJJJin	0715db7681	chore: add selector for use app store (#3746 )	2024-04-24 13:07:20 +08:00
zxhlyh	a39de8a686	fix: workflow restore (#3750 )	2024-04-24 13:05:33 +08:00
Bowen Liang	ccaf335466	fix: rollback gmpy2 to 2.1.5 (#3745 )	2024-04-24 12:53:23 +08:00
legao	40e36e9b52	fix: toggling AppDetailNav causes unnecessary component rerenders (#3718 )	2024-04-24 12:07:28 +08:00
zxhlyh	9eebe9d54e	fix: workflow node variable (#3743 )	2024-04-24 11:41:12 +08:00
crazywoola	a23a191615	feat: add copy button to code (#3719 )	2024-04-24 09:34:51 +08:00
Leo Q	7d9c5586f9	Update "@formatjs/intl-localematcher" to version 0.5.4 in package.json (#3726 )	2024-04-24 09:06:23 +08:00
Ikko Eltociear Ashimine	f07c89bba4	Update README_JA.md (#3727 )	2024-04-24 09:04:27 +08:00
1102	59cba930e5	bedrock llm Model file name change (#3714 ) Co-authored-by: heshunchang <shuncanghe@clouditera.com> Co-authored-by: crazywoola <427733928@qq.com>	2024-04-23 18:57:34 +08:00
zxhlyh	39ae56e136	fix: workflow connection (#3713 )	2024-04-23 18:02:15 +08:00
Joel	f92130338b	feat: prompt editor support auto height by content height and fix some bugs (#3712 )	2024-04-23 17:46:59 +08:00
Bowen Liang	2867d29021	fix: milvus usage with create_collection (#3683 )	2024-04-23 17:37:40 +08:00
呆萌闷油瓶	f76ac8bdee	enhance:speedup xinference audio transcription (#3636 )	2024-04-23 17:09:30 +08:00
zxhlyh	83caffe000	fix: workflow restore (#3711 )	2024-04-23 17:02:23 +08:00
Luvian77	96160837d2	fix: cannot change file uploader method (#3710 )	2024-04-23 17:02:12 +08:00
Yeuoly	3480f1c59e	refactor: tool parameter cache (#3703 )	2024-04-23 15:22:42 +08:00
zxhlyh	65ac4f69af	fix: workflow shortcuts (#3701 )	2024-04-23 14:45:57 +08:00
Yeuoly	2c50fab3dd	fix: skip dataset icon (#3696 )	2024-04-23 12:41:41 +08:00
Carson Kahn	9525ccac4f	Localize links to localized READMEs (#3689 )	2024-04-23 09:30:32 +08:00
Richards Tu	ff76c4bd5d	Add new tool: Judge0 CE (#3684 ) Co-authored-by: crazywoola <427733928@qq.com>	2024-04-23 09:07:21 +08:00
Luvian77	5dacf77627	fix: Added prevention of click event propagation for overlay layer (#3666 ) Co-authored-by: crazywoola <427733928@qq.com>	2024-04-22 19:53:20 +08:00
Yeuoly	2a213c6af7	fix: incorrect type parser (#3682 )	2024-04-22 19:32:41 +08:00
Bowen Liang	b2535e7db6	chore: update description of code interpreter tool (#3679 ) Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>	2024-04-22 19:19:16 +08:00
longzhihun	28236147ee	feat: add support for bedrock Mistral AI model (#3676 ) Co-authored-by: Chenhe Gu <guchenhe@gmail.com>	2024-04-22 17:24:02 +08:00
Chenhe Gu	4969783383	add groq llama3 (#3673 )	2024-04-22 15:21:09 +08:00
takatost	b64080be1b	version to 0.6.4 (#3670 )	2024-04-22 12:13:31 +08:00
Bowen Liang	aadebd6d23	python 3.12 support (#3652 )	2024-04-22 11:41:13 +08:00
xin.gao	71cc0074ef	fix: delete tool parameters cache when sync draft workflow for run workflow use new parameter change in draft workflow (#3637 )	2024-04-22 11:12:00 +08:00
takatost	d77f52bf85	Optimize README_CN (#3660 )	2024-04-21 17:59:53 +08:00
Joel	b71163706b	fix: workflow_run_id not log_id in workflow api doc (#3658 )	2024-04-21 14:48:07 +08:00
saga.rey	1fb7df12d7	fix: in alembic's offline mode (db migrate with --sql option), skip data operations (#3533 )	2024-04-21 09:44:35 +08:00
rmmedia	b3996b3221	Fix problem with scroll inside chat window (#3578 )	2024-04-21 09:39:24 +08:00
YidaHu	7251748d59	fix: validate languages (#3638 )	2024-04-20 10:50:10 +08:00
liuzhenghua	73e9f35ab1	feat: add file log (#3612 ) Co-authored-by: liuzhenghua-jk <liuzhenghua-jk@360shuke.com>	2024-04-20 08:59:49 +08:00
Richards Tu	d7f0056e2d	Fix error in [Update yaml and py file in Tavily Tool] (#3465 ) Co-authored-by: Yeuoly <admin@srmxy.cn>	2024-04-19 16:51:51 +08:00
fuckqqcom	9b7b133cbc	content fix to continue (#3633 ) Co-authored-by: xiaohan <fuck@qq.com>	2024-04-19 16:51:38 +08:00
Joshua	7545e5de6c	add-llama3-for-nvidia-api-catalog (#3631 )	2024-04-19 14:51:22 +08:00
Yeuoly	a0c30702c1	feat: moonshot fc (#3629 )	2024-04-19 14:04:30 +08:00
zxhlyh	03c988388e	fix: chat rename (#3627 )	2024-04-19 13:29:25 +08:00
sqj8899	0a56c522eb	get dict key indexing_technique in DocumentAddByFileApi (#3615 ) Co-authored-by: songqijun <songqijun@qipeng.com>	2024-04-19 09:37:11 +08:00
jeessy2	646858ea08	feat: Vision switch functionality is provided on OpenRouter (#3564 )	2024-04-19 09:13:25 +08:00
Bowen Liang	d9b821cecc	chore: apply ruff rules on tests and app.py (#3605 )	2024-04-18 20:24:05 +08:00
Yeuoly	d5448e07ab	seucirty: http smuggling (#3609 )	2024-04-18 18:18:42 +08:00
Joel	3aa182e26a	fix: copy invite link has duplicated origin (#3608 )	2024-04-18 17:56:07 +08:00
Joshua	de3b490f8e	Add mixtral 8x22b (#3606 )	2024-04-18 17:44:22 +08:00
Garfield Dai	4481906be2	Feat/enterprise sso (#3602 )	2024-04-18 17:33:32 +08:00
Yeuoly	d9f1a8ce9f	feat: stable diffusion 3 (#3599 )	2024-04-18 16:54:37 +08:00
aniaan	aa6d2e3035	fix(openai_api_compatible): fixing the error when converting chunk to json (#3570 )	2024-04-18 16:54:16 +08:00
呆萌闷油瓶	4365843c20	enhance:speedup xinference embedding & rerank (#3587 )	2024-04-18 16:54:00 +08:00
Matheus Mondaini	b4d2d635f7	docs: Update README.md (#3577 )	2024-04-18 13:55:42 +08:00
Joshua	b9b28900b1	add-open-mixtral-8x22b (#3591 )	2024-04-18 13:48:32 +08:00
Bowen Liang	d463b82aba	test: add scripts for running tests on api module both locally and CI jobs (#3497 )	2024-04-18 13:43:15 +08:00
Joel	ed861ff782	fix: json in raw text sometimes changed back to key value in HTTP node (#3586 )	2024-04-18 12:08:18 +08:00
KVOJJJin	8cc1944160	Fix: use debounce for switch (#3585 )	2024-04-18 11:54:54 +08:00
Joel	80e390b906	feat: add workflow api in Node.js sdk (#3584 )	2024-04-18 11:23:18 +08:00
Yeuoly	c2acb2be60	feat: code (#3557 )	2024-04-18 08:00:02 +08:00
Siddharth Jain	8ba95c08a1	added claude 3 opus (#3545 )	2024-04-17 20:53:59 +08:00
Yeuoly	c7de51ca9a	enhance: preload general packages (#3567 )	2024-04-17 19:49:53 +08:00
liuzhenghua	e02ee3bb2e	fix event/stream ping (#3553 )	2024-04-17 18:28:24 +08:00
Jyong	394ceee141	optimize question classifier prompt and support keyword hit test (#3565 )	2024-04-17 17:40:40 +08:00
Joel	40b48510f4	feat: economical index support retrieval testing (#3563 )	2024-04-17 17:40:28 +08:00
Joel	be3b37114c	fix: tool node show output text variable type error (#3556 )	2024-04-17 15:26:18 +08:00
Yeuoly	e212a87b86	fix: json-reader-json-output (#3552 )	2024-04-17 14:09:42 +08:00
takatost	b890c11c14	feat: filter empty content messages in llm node (#3547 )	2024-04-17 13:30:33 +08:00
zxhlyh	2e27425e93	fix: workflow delete edge (#3541 )	2024-04-17 11:09:43 +08:00
Bowen Liang	6269e011db	fix: typo of PublishConfig (#3540 )	2024-04-17 10:45:26 +08:00
KVOJJJin	e70482dfc0	feat: agent log (#3537 ) Co-authored-by: jyong <718720800@qq.com>	2024-04-17 10:30:52 +08:00
takatost	9b8861e3e1	feat: increase read timeout of OpenAI Compatible API, Ollama, Nvidia LLM (#3538 )	2024-04-17 09:25:50 +08:00
LeePui	38ca3b29b5	add support for swagger object type (#3426 ) Co-authored-by: lipeikui <lipeikui@3vjia.com>	2024-04-16 19:54:17 +08:00
Bowen Liang	066076b157	chore: lint .env file templates (#3507 )	2024-04-16 19:53:54 +08:00
buu	be27ac0e69	fix: the hover style of the card-item operation button container (#3520 )	2024-04-16 18:09:06 +08:00
Jyong	9e6d4eeb92	fix the return with wrong datatype of segment (#3525 )	2024-04-16 17:09:15 +08:00