r2

Merge branch 'main' into feat/r2
2025-07-02 18:46:36 +08:00 · 2025-07-02 18:20:41 +08:00 · 2025-07-02 18:20:05 +08:00 · 2025-07-02 18:15:23 +08:00 · 2025-07-02 17:48:23 +08:00 · 2025-07-02 17:48:07 +08:00
2006 changed files with 83232 additions and 19552 deletions
@@ -1,5 +1,4 @@
 FROM mcr.microsoft.com/devcontainers/python:3.12

-# [Optional] Uncomment this section to install additional OS packages.
-# RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
-#     && apt-get -y install --no-install-recommends <your-package-list-here>
+RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
+     && apt-get -y install libgmp-dev libmpfr-dev libmpc-dev
@@ -1,12 +1,13 @@
 #!/bin/bash

-npm add -g pnpm@10.8.0
+npm add -g pnpm@10.11.1
 cd web && pnpm install
 pipx install uv

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

@@ -8,7 +8,7 @@ inputs:
  uv-version:
    description: UV version to set up
    required: true
-    default: '0.6.14'
+    default: '~=0.7.11'
  uv-lockfile:
    description: Path to the UV lockfile to restore cache from
    required: true
@@ -1,25 +1,23 @@
-# Summary
+> [!IMPORTANT]
+>
+> 1. Make sure you have read our [contribution guidelines](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)
+> 2. Ensure there is an associated issue and you have been assigned to it
+> 3. Use the correct syntax to link this PR: `Fixes #<issue number>`.

-Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change.
+## Summary

-> [!Tip]
-> Close issue syntax: `Fixes #<issue number>` or `Resolves #<issue number>`, see [documentation](https://docs.github.com/en/issues/tracking-your-work-with-issues/linking-a-pull-request-to-an-issue#linking-a-pull-request-to-an-issue-using-a-keyword) for more details.
+<!-- Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change. -->

-
-# Screenshots
+## Screenshots

 | Before | After |
 |--------|-------|
 | ...    | ...   |

-# Checklist
-
-> [!IMPORTANT]  
-> Please review the checklist below before submitting your pull request.
+## Checklist

 - [ ] This change requires a documentation update, included: [Dify Document](https://github.com/langgenius/dify-docs)
 - [x] I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
 - [x] I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
 - [x] I've updated the documentation accordingly.
 - [x] I ran `dev/reformat`(backend) and `cd web && npx lint-staged`(frontend) to appease the lint gods
-
@@ -47,15 +47,17 @@ jobs:
      - name: Run Unit tests
        run: |
          uv run --project api bash dev/pytest/pytest_unit_tests.sh
+
+      - name: Coverage Summary
+        run: |
+          set -x
          # Extract coverage percentage and create a summary
          TOTAL_COVERAGE=$(python -c 'import json; print(json.load(open("coverage.json"))["totals"]["percent_covered_display"])')

          # Create a detailed coverage summary
          echo "### Test Coverage Summary :test_tube:" >> $GITHUB_STEP_SUMMARY
          echo "Total Coverage: ${TOTAL_COVERAGE}%" >> $GITHUB_STEP_SUMMARY
-          echo "\`\`\`" >> $GITHUB_STEP_SUMMARY
-          uv run --project api coverage report >> $GITHUB_STEP_SUMMARY
-          echo "\`\`\`" >> $GITHUB_STEP_SUMMARY
+          uv run --project api coverage report --format=markdown >> $GITHUB_STEP_SUMMARY

      - name: Run dify config tests
        run: uv run --project api dev/pytest/pytest_config_tests.py
@@ -83,9 +85,15 @@ jobs:
          compose-file: |
            docker/docker-compose.middleware.yaml
          services: |
+            db
+            redis
            sandbox
            ssrf_proxy

+      - name: setup test config
+        run: |
+          cp api/tests/integration_tests/.env.example api/tests/integration_tests/.env
+
      - name: Run Workflow
        run: uv run --project api bash dev/pytest/pytest_workflow.sh

@@ -6,6 +6,7 @@ on:
      - "main"
      - "deploy/dev"
      - "deploy/enterprise"
+      - "deploy/rag-dev"
    tags:
      - "*"

@@ -4,7 +4,7 @@ on:
  workflow_run:
    workflows: ["Build and Push API & Web"]
    branches:
-      - "deploy/dev"
+      - "deploy/rag-dev"
    types:
      - completed

@@ -12,12 +12,13 @@ jobs:
  deploy:
    runs-on: ubuntu-latest
    if: |
-      github.event.workflow_run.conclusion == 'success'
+      github.event.workflow_run.conclusion == 'success' &&
+      github.event.workflow_run.head_branch == 'deploy/rag-dev'
    steps:
      - name: Deploy to server
        uses: appleboy/ssh-action@v0.1.8
        with:
-          host: ${{ secrets.SSH_HOST }}
+          host: ${{ secrets.RAG_SSH_HOST }}
          username: ${{ secrets.SSH_USER }}
          key: ${{ secrets.SSH_PRIVATE_KEY }}
          script: |
@@ -0,0 +1,28 @@
+name: Deploy RAG Dev
+
+permissions:
+  contents: read
+
+on:
+  workflow_run:
+    workflows: ["Build and Push API & Web"]
+    branches:
+      - "deploy/rag-dev"
+    types:
+      - completed
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    if: |
+      github.event.workflow_run.conclusion == 'success' &&
+      github.event.workflow_run.head_branch == 'deploy/rag-dev'
+    steps:
+      - name: Deploy to server
+        uses: appleboy/ssh-action@v0.1.8
+        with:
+          host: ${{ secrets.RAG_SSH_HOST }}
+          username: ${{ secrets.SSH_USER }}
+          key: ${{ secrets.SSH_PRIVATE_KEY }}
+          script: |
+            ${{ vars.SSH_SCRIPT || secrets.SSH_SCRIPT }}
@@ -10,6 +10,7 @@ yq eval '.services["elasticsearch"].ports += ["9200:9200"]' -i docker/docker-com
 yq eval '.services.couchbase-server.ports += ["8091-8096:8091-8096"]' -i docker/docker-compose.yaml
 yq eval '.services.couchbase-server.ports += ["11210:11210"]' -i docker/docker-compose.yaml
 yq eval '.services.tidb.ports += ["4000:4000"]' -i docker/tidb/docker-compose.yaml
+yq eval '.services.oceanbase.ports += ["2881:2881"]' -i docker/docker-compose.yaml
 yq eval '.services.opengauss.ports += ["6600:6600"]' -i docker/docker-compose.yaml

 echo "Ports exposed for sandbox, weaviate, tidb, qdrant, chroma, milvus, pgvector, pgvecto-rs, elasticsearch, couchbase, opengauss"
@@ -139,6 +139,7 @@ jobs:
      - name: Checkout code
        uses: actions/checkout@v4
        with:
+          fetch-depth: 0
          persist-credentials: false

      - name: Check changed files
@@ -31,11 +31,19 @@ jobs:
            echo "FILES_CHANGED=false" >> $GITHUB_ENV
          fi

+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 10
+          run_install: false
+
      - name: Set up Node.js
        if: env.FILES_CHANGED == 'true'
        uses: actions/setup-node@v4
        with:
          node-version: 'lts/*'
+          cache: pnpm
+          cache-dependency-path: ./web/package.json

      - name: Install dependencies
        if: env.FILES_CHANGED == 'true'
@@ -31,6 +31,13 @@ jobs:
        with:
          persist-credentials: false

+      - name: Free Disk Space
+        uses: endersonmenezes/free-disk-space@v2
+        with:
+          remove_dotnet: true
+          remove_haskell: true
+          remove_tool_cache: true
+
      - name: Setup UV and Python
        uses: ./.github/actions/setup-uv
        with:
@@ -59,7 +66,7 @@ jobs:
            tidb
            tiflash

-      - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase)
+      - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase, OceanBase)
        uses: hoverkraft-tech/compose-action@v2.0.2
        with:
          compose-file: |
@@ -75,8 +82,15 @@ jobs:
            pgvector
            chroma
            elasticsearch
+            oceanbase

-      - name: Check TiDB Ready
+      - name: setup test config
+        run: |
+          echo $(pwd)
+          ls -lah .
+          cp api/tests/integration_tests/.env.example api/tests/integration_tests/.env
+
+      - name: Check VDB Ready (TiDB)
        run: uv run --project api python api/tests/integration_tests/vdb/tidb_vector/check_tiflash_ready.py

      - name: Test Vector Stores
@@ -179,6 +179,7 @@ docker/volumes/pgvecto_rs/data/*
 docker/volumes/couchbase/*
 docker/volumes/oceanbase/*
 docker/volumes/plugin_daemon/*
+docker/volumes/matrixone/*
 !docker/volumes/oceanbase/init.d

 docker/nginx/conf.d/default.conf
@@ -192,12 +193,12 @@ sdks/python-client/dist
 sdks/python-client/dify_client.egg-info

 .vscode/*
-!.vscode/launch.json
+!.vscode/launch.json.template
+!.vscode/README.md
 pyrightconfig.json
 api/.vscode

 .idea/
-.vscode

 # pnpm
 /.pnpm-store
@@ -207,3 +208,10 @@ plugins.jsonl

 # mise
 mise.toml
+
+# Next.js build output
+.next/
+
+# AI Assistant
+.roo/
+api/.env.backup
@@ -0,0 +1,14 @@
+# Debugging with VS Code
+
+This `launch.json.template` file provides various debug configurations for the Dify project within VS Code / Cursor. To use these configurations, you should copy the contents of this file into a new file named `launch.json` in the same `.vscode` directory.
+
+## How to Use
+
+1.  **Create `launch.json`**: If you don't have one, create a file named `launch.json` inside the `.vscode` directory.
+2.  **Copy Content**: Copy the entire content from `launch.json.template` into your newly created `launch.json` file.
+3.  **Select Debug Configuration**: Go to the Run and Debug view in VS Code / Cursor (Ctrl+Shift+D or Cmd+Shift+D).
+4.  **Start Debugging**: Select the desired configuration from the dropdown menu and click the green play button.
+
+## Tips
+
+- If you need to debug with Edge browser instead of Chrome, modify the `serverReadyAction` configuration in the "Next.js: debug full stack" section, change `"debugWithChrome"` to `"debugWithEdge"` to use Microsoft Edge for debugging.
@@ -0,0 +1,68 @@
+{
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python: Flask API",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "flask",
+            "env": {
+                "FLASK_APP": "app.py",
+                "FLASK_ENV": "development",
+                "GEVENT_SUPPORT": "True"
+            },
+            "args": [
+                "run",
+                "--host=0.0.0.0",
+                "--port=5001",
+                "--no-debugger",
+                "--no-reload"
+            ],
+            "jinja": true,
+            "justMyCode": true,
+            "cwd": "${workspaceFolder}/api",
+            "python": "${workspaceFolder}/api/.venv/bin/python"
+        },
+        {
+            "name": "Python: Celery Worker (Solo)",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "celery",
+            "env": {
+                "GEVENT_SUPPORT": "True"
+            },
+            "args": [
+                "-A",
+                "app.celery",
+                "worker",
+                "-P",
+                "solo",
+                "-c",
+                "1",
+                "-Q",
+                "dataset,generation,mail,ops_trace",
+                "--loglevel",
+                "INFO"
+            ],
+            "justMyCode": false,
+            "cwd": "${workspaceFolder}/api",
+            "python": "${workspaceFolder}/api/.venv/bin/python"
+        },
+        {
+            "name": "Next.js: debug full stack",
+            "type": "node",
+            "request": "launch",
+            "program": "${workspaceFolder}/web/node_modules/next/dist/bin/next",
+            "runtimeArgs": ["--inspect"],
+            "skipFiles": ["<node_internals>/**"],
+            "serverReadyAction": {
+              "action": "debugWithChrome",
+              "killOnServerStop": true,
+              "pattern": "- Local:.+(https?://.+)",
+              "uriFormat": "%s",
+              "webRoot": "${workspaceFolder}/web"
+            },
+            "cwd": "${workspaceFolder}/web"
+          }
+    ]
+}
@@ -226,6 +226,15 @@ Deploy Dify to AWS with [CDK](https://aws.amazon.com/cdk/)

 - [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)

+#### Using Alibaba Cloud Computing Nest
+
+Quickly deploy Dify to Alibaba cloud with [Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88) 
+
+#### Using Alibaba Cloud Data Management
+
+One-Click deploy Dify to Alibaba Cloud with [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/) 
+
+
 ## Contributing

 For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
@@ -235,7 +244,7 @@ At the same time, please consider supporting Dify by sharing it on social media

 ## Community & contact

- [Github Discussion](https://github.com/langgenius/dify/discussions). Best for: sharing feedback and asking questions.
+- [GitHub Discussion](https://github.com/langgenius/dify/discussions). Best for: sharing feedback and asking questions.
 - [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
 - [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
 - [X(Twitter)](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
@@ -209,6 +209,14 @@ docker compose up -d

 - [AWS CDK بواسطة @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)

+#### استخدام Alibaba Cloud للنشر
+ [بسرعة نشر Dify إلى سحابة علي بابا مع عش الحوسبة السحابية علي بابا](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+ 
+#### استخدام Alibaba Cloud Data Management للنشر
+
+انشر Dify على علي بابا كلاود بنقرة واحدة باستخدام [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)
+
+
 ## المساهمة

 لأولئك الذين يرغبون في المساهمة، انظر إلى [دليل المساهمة](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) لدينا.
@@ -223,7 +231,7 @@ docker compose up -d
 </a>

 ## المجتمع والاتصال
- [مناقشة Github](https://github.com/langgenius/dify/discussions). الأفضل لـ: مشاركة التعليقات وطرح الأسئلة.
+- [مناقشة GitHub](https://github.com/langgenius/dify/discussions). الأفضل لـ: مشاركة التعليقات وطرح الأسئلة.
 - [المشكلات على GitHub](https://github.com/langgenius/dify/issues). الأفضل لـ: الأخطاء التي تواجهها في استخدام Dify.AI، واقتراحات الميزات. انظر [دليل المساهمة](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
 - [Discord](https://discord.gg/FngNHpbcY7). الأفضل لـ: مشاركة تطبيقاتك والترفيه مع المجتمع.
 - [تويتر](https://twitter.com/dify_ai). الأفضل لـ: مشاركة تطبيقاتك والترفيه مع المجتمع.
@@ -225,6 +225,15 @@ GitHub-এ ডিফাইকে স্টার দিয়ে রাখুন

 - [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)

+#### Alibaba Cloud ব্যবহার করে ডিপ্লয়
+
+ [Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+#### Alibaba Cloud Data Management ব্যবহার করে ডিপ্লয়
+
+ [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)
+
+
 ## Contributing

 যারা কোড অবদান রাখতে চান, তাদের জন্য আমাদের [অবদান নির্দেশিকা] দেখুন (https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)।
@@ -234,7 +243,7 @@ GitHub-এ ডিফাইকে স্টার দিয়ে রাখুন

 ## কমিউনিটি এবং যোগাযোগ

- [Github Discussion](https://github.com/langgenius/dify/discussions) ফিডব্যাক এবং প্রতিক্রিয়া জানানোর মাধ্যম।
+- [GitHub Discussion](https://github.com/langgenius/dify/discussions) ফিডব্যাক এবং প্রতিক্রিয়া জানানোর মাধ্যম।
 - [GitHub Issues](https://github.com/langgenius/dify/issues). Dify.AI ব্যবহার করে আপনি যেসব বাগের সম্মুখীন হন এবং ফিচার প্রস্তাবনা।  আমাদের [অবদান নির্দেশিকা](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) দেখুন।
 - [Discord](https://discord.gg/FngNHpbcY7) আপনার এপ্লিকেশন শেয়ার এবং কমিউনিটি আড্ডার মাধ্যম। 
 - [X(Twitter)](https://twitter.com/dify_ai) আপনার এপ্লিকেশন শেয়ার এবং কমিউনিটি আড্ডার মাধ্যম। 
@@ -221,6 +221,15 @@ docker compose up -d
 ##### AWS 
 - [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)

+#### 使用 阿里云计算巢 部署
+
+使用 [阿里云计算巢](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88) 将 Dify 一键部署到 阿里云
+
+#### 使用 阿里云数据管理DMS 部署
+
+使用 [阿里云数据管理DMS](https://help.aliyun.com/zh/dms/dify-in-invitational-preview) 将 Dify 一键部署到 阿里云
+
+
 ## Star History

 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
@@ -243,7 +252,7 @@ docker compose up -d

 我们欢迎您为 Dify 做出贡献，以帮助改善 Dify。包括：提交代码、问题、新想法，或分享您基于 Dify 创建的有趣且有用的 AI 应用程序。同时，我们也欢迎您在不同的活动、会议和社交媒体上分享 Dify。

- [Github Discussion](https://github.com/langgenius/dify/discussions). 👉：分享您的应用程序并与社区交流。
+- [GitHub Discussion](https://github.com/langgenius/dify/discussions). 👉：分享您的应用程序并与社区交流。
 - [GitHub Issues](https://github.com/langgenius/dify/issues)。👉：使用 Dify.AI 时遇到的错误和问题，请参阅[贡献指南](CONTRIBUTING.md)。
 - [电子邮件支持](mailto:hello@dify.ai?subject=[GitHub]Questions%20About%20Dify)。👉：关于使用 Dify.AI 的问题。
 - [Discord](https://discord.gg/FngNHpbcY7)。👉：分享您的应用程序并与社区交流。
@@ -221,6 +221,15 @@ Bereitstellung von Dify auf AWS mit [CDK](https://aws.amazon.com/cdk/)
 ##### AWS 
 - [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)

+#### Alibaba Cloud 
+
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+#### Alibaba Cloud Data Management
+
+Ein-Klick-Bereitstellung von Dify in der Alibaba Cloud mit [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)
+
+
 ## Contributing

 Falls Sie Code beitragen möchten, lesen Sie bitte unseren [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). Gleichzeitig bitten wir Sie, Dify zu unterstützen, indem Sie es in den sozialen Medien teilen und auf Veranstaltungen und Konferenzen präsentieren.
@@ -230,7 +239,7 @@ Falls Sie Code beitragen möchten, lesen Sie bitte unseren [Contribution Guide](

 ## Gemeinschaft & Kontakt

-* [Github Discussion](https://github.com/langgenius/dify/discussions). Am besten geeignet für: den Austausch von Feedback und das Stellen von Fragen.
+* [GitHub Discussion](https://github.com/langgenius/dify/discussions). Am besten geeignet für: den Austausch von Feedback und das Stellen von Fragen.
 * [GitHub Issues](https://github.com/langgenius/dify/issues). Am besten für: Fehler, auf die Sie bei der Verwendung von Dify.AI stoßen, und Funktionsvorschläge. Siehe unseren [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
 * [Discord](https://discord.gg/FngNHpbcY7).  Am besten geeignet für: den Austausch von Bewerbungen und den Austausch mit der Community.
 * [X(Twitter)](https://twitter.com/dify_ai). Am besten geeignet für: den Austausch von Bewerbungen und den Austausch mit der Community.
@@ -221,6 +221,15 @@ Despliegue Dify en AWS usando [CDK](https://aws.amazon.com/cdk/)
 ##### AWS 
 - [AWS CDK por @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)

+#### Alibaba Cloud
+
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+#### Alibaba Cloud Data Management
+
+Despliega Dify en Alibaba Cloud con un solo clic con [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)
+
+
 ## Contribuir

 Para aquellos que deseen contribuir con código, consulten nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
@@ -219,6 +219,15 @@ Déployez Dify sur AWS en utilisant [CDK](https://aws.amazon.com/cdk/)
 ##### AWS 
 - [AWS CDK par @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)

+#### Alibaba Cloud
+
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+#### Alibaba Cloud Data Management
+
+Déployez Dify en un clic sur Alibaba Cloud avec [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)
+
+
 ## Contribuer

 Pour ceux qui souhaitent contribuer du code, consultez notre [Guide de contribution](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
@@ -155,7 +155,7 @@ DifyはオープンソースのLLMアプリケーション開発プラットフ
 [こちら](https://dify.ai)のDify Cloudサービスを利用して、セットアップ不要で試すことができます。サンドボックスプランには、200回のGPT-4呼び出しが無料で含まれています。

 - **Dify Community Editionのセルフホスティング</br>**
-この[スタートガイド](#quick-start)を使用して、ローカル環境でDifyを簡単に実行できます。
+この[スタートガイド](#クイックスタート)を使用して、ローカル環境でDifyを簡単に実行できます。
 詳しくは[ドキュメント](https://docs.dify.ai)をご覧ください。

 - **企業/組織向けのDify</br>**
@@ -220,6 +220,13 @@ docker compose up -d
 ##### AWS
 - [@KevinZhaoによるAWS CDK](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)

+#### Alibaba Cloud
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+#### Alibaba Cloud Data Management
+[Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/) を利用して、DifyをAlibaba Cloudへワンクリックでデプロイできます
+
+
 ## 貢献

 コードに貢献したい方は、[Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)を参照してください。
@@ -236,7 +243,7 @@ docker compose up -d

 ## コミュニティ & お問い合わせ

-* [Github Discussion](https://github.com/langgenius/dify/discussions). 主に: フィードバックの共有や質問。
+* [GitHub Discussion](https://github.com/langgenius/dify/discussions). 主に: フィードバックの共有や質問。
 * [GitHub Issues](https://github.com/langgenius/dify/issues). 主に: Dify.AIを使用する際に発生するエラーや問題については、[貢献ガイド](CONTRIBUTING_JA.md)を参照してください
 * [Discord](https://discord.gg/FngNHpbcY7). 主に: アプリケーションの共有やコミュニティとの交流。
 * [X(Twitter)](https://twitter.com/dify_ai). 主に: アプリケーションの共有やコミュニティとの交流。
@@ -219,6 +219,15 @@ wa'logh nIqHom neH ghun deployment toy'wI' [CDK](https://aws.amazon.com/cdk/) lo
 ##### AWS 
 - [AWS CDK qachlot @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)

+#### Alibaba Cloud
+
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+#### Alibaba Cloud Data Management
+
+[Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)
+
+
 ## Contributing

 For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
@@ -235,7 +244,7 @@ At the same time, please consider supporting Dify by sharing it on social media

 ## Community & Contact

-* [Github Discussion](https://github.com/langgenius/dify/discussions
+* [GitHub Discussion](https://github.com/langgenius/dify/discussions

 ). Best for: sharing feedback and asking questions.
 * [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
@@ -213,6 +213,15 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했
 ##### AWS 
 - [KevinZhao의 AWS CDK](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)

+#### Alibaba Cloud
+
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+#### Alibaba Cloud Data Management
+
+[Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)를 통해 원클릭으로 Dify를 Alibaba Cloud에 배포할 수 있습니다
+
+
 ## 기여

 코드에 기여하고 싶은 분들은 [기여 가이드](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)를 참조하세요.
@@ -229,7 +238,7 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했

 ## 커뮤니티 & 연락처

-* [Github 토론](https://github.com/langgenius/dify/discussions). 피드백 공유 및 질문하기에 적합합니다.
+* [GitHub 토론](https://github.com/langgenius/dify/discussions). 피드백 공유 및 질문하기에 적합합니다.
 * [GitHub 이슈](https://github.com/langgenius/dify/issues). Dify.AI 사용 중 발견한 버그와 기능 제안에 적합합니다. [기여 가이드](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)를 참조하세요. 
 * [디스코드](https://discord.gg/FngNHpbcY7). 애플리케이션 공유 및 커뮤니티와 소통하기에 적합합니다.
 * [트위터](https://twitter.com/dify_ai). 애플리케이션 공유 및 커뮤니티와 소통하기에 적합합니다.
@@ -218,6 +218,15 @@ Implante o Dify na AWS usando [CDK](https://aws.amazon.com/cdk/)
 ##### AWS 
 - [AWS CDK por @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)

+#### Alibaba Cloud
+
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+#### Alibaba Cloud Data Management
+
+Implante o Dify na Alibaba Cloud com um clique usando o [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)
+
+
 ## Contribuindo

 Para aqueles que desejam contribuir com código, veja nosso [Guia de Contribuição](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
@@ -219,6 +219,15 @@ Uvedite Dify v AWS z uporabo [CDK](https://aws.amazon.com/cdk/)
 ##### AWS 
 - [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)

+#### Alibaba Cloud
+
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+#### Alibaba Cloud Data Management
+
+Z enim klikom namestite Dify na Alibaba Cloud z [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)
+
+
 ## Prispevam

 Za tiste, ki bi radi prispevali kodo, si oglejte naš vodnik za prispevke . Hkrati vas prosimo, da podprete Dify tako, da ga delite na družbenih medijih ter na dogodkih in konferencah. 
@@ -229,7 +238,7 @@ Za tiste, ki bi radi prispevali kodo, si oglejte naš vodnik za prispevke . Hkra

 ## Skupnost in stik

-* [Github Discussion](https://github.com/langgenius/dify/discussions). Najboljše za: izmenjavo povratnih informacij in postavljanje vprašanj.
+* [GitHub Discussion](https://github.com/langgenius/dify/discussions). Najboljše za: izmenjavo povratnih informacij in postavljanje vprašanj.
 * [GitHub Issues](https://github.com/langgenius/dify/issues). Najboljše za: hrošče, na katere naletite pri uporabi Dify.AI, in predloge funkcij. Oglejte si naš [vodnik za prispevke](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
 * [Discord](https://discord.gg/FngNHpbcY7). Najboljše za: deljenje vaših aplikacij in druženje s skupnostjo.
 * [X(Twitter)](https://twitter.com/dify_ai). Najboljše za: deljenje vaših aplikacij in druženje s skupnostjo.
@@ -212,6 +212,15 @@ Dify'ı bulut platformuna tek tıklamayla dağıtın [terraform](https://www.ter
 ##### AWS 
 - [AWS CDK tarafından @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)

+#### Alibaba Cloud
+
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+#### Alibaba Cloud Data Management
+
+[Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/) kullanarak Dify'ı tek tıkla Alibaba Cloud'a dağıtın
+
+
 ## Katkıda Bulunma

 Kod katkısında bulunmak isteyenler için [Katkı Kılavuzumuza](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) bakabilirsiniz.
@@ -227,7 +236,7 @@ Aynı zamanda, lütfen Dify'ı sosyal medyada, etkinliklerde ve konferanslarda p

 ## Topluluk & iletişim

-* [Github Tartışmaları](https://github.com/langgenius/dify/discussions). En uygun: geri bildirim paylaşmak ve soru sormak için.
+* [GitHub Tartışmaları](https://github.com/langgenius/dify/discussions). En uygun: geri bildirim paylaşmak ve soru sormak için.
 * [GitHub Sorunları](https://github.com/langgenius/dify/issues). En uygun: Dify.AI kullanırken karşılaştığınız hatalar ve özellik önerileri için. [Katkı Kılavuzumuza](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) bakın.
 * [Discord](https://discord.gg/FngNHpbcY7). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.
 * [X(Twitter)](https://twitter.com/dify_ai). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.
@@ -224,6 +224,15 @@ Dify 的所有功能都提供相應的 API，因此您可以輕鬆地將 Dify

 - [由 @KevinZhao 提供的 AWS CDK](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)

+#### 使用 阿里云计算巢進行部署
+
+[阿里云](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+#### 使用 阿里雲數據管理DMS 進行部署
+
+透過 [阿里雲數據管理DMS](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)，一鍵將 Dify 部署至阿里雲
+
+
 ## 貢獻

 對於想要貢獻程式碼的開發者，請參閱我們的[貢獻指南](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)。
@@ -233,7 +242,7 @@ Dify 的所有功能都提供相應的 API，因此您可以輕鬆地將 Dify

 ## 社群與聯絡方式

- [Github Discussion](https://github.com/langgenius/dify/discussions)：最適合分享反饋和提問。
+- [GitHub Discussion](https://github.com/langgenius/dify/discussions)：最適合分享反饋和提問。
 - [GitHub Issues](https://github.com/langgenius/dify/issues)：最適合報告使用 Dify.AI 時遇到的問題和提出功能建議。請參閱我們的[貢獻指南](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)。
 - [Discord](https://discord.gg/FngNHpbcY7)：最適合分享您的應用程式並與社群互動。
 - [X(Twitter)](https://twitter.com/dify_ai)：最適合分享您的應用程式並與社群互動。
@@ -214,6 +214,16 @@ Triển khai Dify trên AWS bằng [CDK](https://aws.amazon.com/cdk/)
 ##### AWS 
 - [AWS CDK bởi @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)

+
+#### Alibaba Cloud
+
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+#### Alibaba Cloud Data Management
+
+Triển khai Dify lên Alibaba Cloud chỉ với một cú nhấp chuột bằng [Alibaba Cloud Data Management](https://www.alibabacloud.com/help/en/dms/dify-in-invitational-preview/)
+
+
 ## Đóng góp

 Đối với những người muốn đóng góp mã, xem [Hướng dẫn Đóng góp](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) của chúng tôi. 
@@ -137,7 +137,7 @@ WEB_API_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 CONSOLE_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*

 # Vector database configuration
-# support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, couchbase, vikingdb, upstash, lindorm, oceanbase, opengauss, tablestore
+# support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, couchbase, vikingdb, upstash, lindorm, oceanbase, opengauss, tablestore, matrixone
 VECTOR_STORE=weaviate

 # Weaviate configuration
@@ -152,6 +152,7 @@ QDRANT_API_KEY=difyai123456
 QDRANT_CLIENT_TIMEOUT=20
 QDRANT_GRPC_ENABLED=false
 QDRANT_GRPC_PORT=6334
+QDRANT_REPLICATION_FACTOR=1

 #Couchbase configuration
 COUCHBASE_CONNECTION_STRING=127.0.0.1
@@ -269,6 +270,7 @@ OPENSEARCH_PORT=9200
 OPENSEARCH_USER=admin
 OPENSEARCH_PASSWORD=admin
 OPENSEARCH_SECURE=true
+OPENSEARCH_VERIFY_CERTS=true

 # Baidu configuration
 BAIDU_VECTOR_DB_ENDPOINT=http://127.0.0.1:5287
@@ -292,6 +294,13 @@ VIKINGDB_SCHEMA=http
 VIKINGDB_CONNECTION_TIMEOUT=30
 VIKINGDB_SOCKET_TIMEOUT=30

+# Matrixone configration
+MATRIXONE_HOST=127.0.0.1
+MATRIXONE_PORT=6001
+MATRIXONE_USER=dump
+MATRIXONE_PASSWORD=111
+MATRIXONE_DATABASE=dify
+
 # Lindorm configuration
 LINDORM_URL=http://ld-*******************-proxy-search-pub.lindorm.aliyuncs.com:30070
 LINDORM_USERNAME=admin
@@ -330,9 +339,11 @@ PROMPT_GENERATION_MAX_TOKENS=512
 CODE_GENERATION_MAX_TOKENS=1024
 PLUGIN_BASED_TOKEN_COUNTING_ENABLED=false

-# Mail configuration, support: resend, smtp
+# Mail configuration, support: resend, smtp, sendgrid
 MAIL_TYPE=
+# If using SendGrid, use the 'from' field for authentication if necessary.
 MAIL_DEFAULT_SEND_FROM=no-reply <no-reply@dify.ai>
+# resend configuration
 RESEND_API_KEY=
 RESEND_API_URL=https://api.resend.com
 # smtp configuration
@@ -342,12 +353,14 @@ SMTP_USERNAME=123
 SMTP_PASSWORD=abc
 SMTP_USE_TLS=true
 SMTP_OPPORTUNISTIC_TLS=false
-
+# Sendgid configuration
+SENDGRID_API_KEY=
 # Sentry configuration
 SENTRY_DSN=

 # DEBUG
 DEBUG=false
+ENABLE_REQUEST_LOGGING=False
 SQLALCHEMY_ECHO=false

 # Notion import configuration, support public and internal
@@ -488,3 +501,10 @@ OTEL_METRIC_EXPORT_TIMEOUT=30000

 # Prevent Clickjacking
 ALLOW_EMBED=false
+
+# Dataset queue monitor configuration
+QUEUE_MONITOR_THRESHOLD=200
+# You can configure multiple ones, separated by commas. eg: test1@dify.ai,test2@dify.ai
+QUEUE_MONITOR_ALERT_EMAILS=
+# Monitor interval in minutes, default is 30 minutes
+QUEUE_MONITOR_INTERVAL=30
@@ -1,6 +1,4 @@
-exclude = [
-    "migrations/*",
-]
+exclude = ["migrations/*"]
 line-length = 120

 [format]
@@ -9,14 +7,14 @@ quote-style = "double"
 [lint]
 preview = false
 select = [
-    "B", # flake8-bugbear rules
-    "C4", # flake8-comprehensions
-    "E", # pycodestyle E rules
-    "F", # pyflakes rules
-    "FURB", # refurb rules
-    "I", # isort rules
-    "N", # pep8-naming
-    "PT", # flake8-pytest-style rules
+    "B",       # flake8-bugbear rules
+    "C4",      # flake8-comprehensions
+    "E",       # pycodestyle E rules
+    "F",       # pyflakes rules
+    "FURB",    # refurb rules
+    "I",       # isort rules
+    "N",       # pep8-naming
+    "PT",      # flake8-pytest-style rules
    "PLC0208", # iteration-over-set
    "PLC0414", # useless-import-alias
    "PLE0604", # invalid-all-object
@@ -24,58 +22,60 @@ select = [
    "PLR0402", # manual-from-import
    "PLR1711", # useless-return
    "PLR1714", # repeated-equality-comparison
-    "RUF013", # implicit-optional
-    "RUF019", # unnecessary-key-check
-    "RUF100", # unused-noqa
-    "RUF101", # redirected-noqa
-    "RUF200", # invalid-pyproject-toml
-    "RUF022", # unsorted-dunder-all
-    "S506", # unsafe-yaml-load
-    "SIM", # flake8-simplify rules
-    "TRY400", # error-instead-of-exception
-    "TRY401", # verbose-log-message
-    "UP", # pyupgrade rules
-    "W191", # tab-indentation
-    "W605", # invalid-escape-sequence
+    "RUF013",  # implicit-optional
+    "RUF019",  # unnecessary-key-check
+    "RUF100",  # unused-noqa
+    "RUF101",  # redirected-noqa
+    "RUF200",  # invalid-pyproject-toml
+    "RUF022",  # unsorted-dunder-all
+    "S506",    # unsafe-yaml-load
+    "SIM",     # flake8-simplify rules
+    "TRY400",  # error-instead-of-exception
+    "TRY401",  # verbose-log-message
+    "UP",      # pyupgrade rules
+    "W191",    # tab-indentation
+    "W605",    # invalid-escape-sequence
    # security related linting rules
    # RCE proctection (sort of)
    "S102", # exec-builtin, disallow use of `exec`
    "S307", # suspicious-eval-usage, disallow use of `eval` and `ast.literal_eval`
    "S301", # suspicious-pickle-usage, disallow use of `pickle` and its wrappers.
    "S302", # suspicious-marshal-usage, disallow use of `marshal` module
+    "S311", # suspicious-non-cryptographic-random-usage
 ]

 ignore = [
-    "E402", # module-import-not-at-top-of-file
-    "E711", # none-comparison
-    "E712", # true-false-comparison
-    "E721", # type-comparison
-    "E722", # bare-except
-    "F821", # undefined-name
-    "F841", # unused-variable
+    "E402",    # module-import-not-at-top-of-file
+    "E711",    # none-comparison
+    "E712",    # true-false-comparison
+    "E721",    # type-comparison
+    "E722",    # bare-except
+    "F821",    # undefined-name
+    "F841",    # unused-variable
    "FURB113", # repeated-append
    "FURB152", # math-constant
-    "UP007", # non-pep604-annotation
-    "UP032", # f-string
-    "UP045", # non-pep604-annotation-optional
-    "B005", # strip-with-multi-characters
-    "B006", # mutable-argument-default
-    "B007", # unused-loop-control-variable
-    "B026", # star-arg-unpacking-after-keyword-arg
-    "B903", # class-as-data-structure
-    "B904", # raise-without-from-inside-except
-    "B905", # zip-without-explicit-strict
-    "N806", # non-lowercase-variable-in-function
-    "N815", # mixed-case-variable-in-class-scope
-    "PT011", # pytest-raises-too-broad
-    "SIM102", # collapsible-if
-    "SIM103", # needless-bool
-    "SIM105", # suppressible-exception
-    "SIM107", # return-in-try-except-finally
-    "SIM108", # if-else-block-instead-of-if-exp
-    "SIM113", # enumerate-for-loop
-    "SIM117", # multiple-with-statements
-    "SIM210", # if-expr-with-true-false
+    "UP007",   # non-pep604-annotation
+    "UP032",   # f-string
+    "UP045",   # non-pep604-annotation-optional
+    "B005",    # strip-with-multi-characters
+    "B006",    # mutable-argument-default
+    "B007",    # unused-loop-control-variable
+    "B026",    # star-arg-unpacking-after-keyword-arg
+    "B903",    # class-as-data-structure
+    "B904",    # raise-without-from-inside-except
+    "B905",    # zip-without-explicit-strict
+    "N806",    # non-lowercase-variable-in-function
+    "N815",    # mixed-case-variable-in-class-scope
+    "PT011",   # pytest-raises-too-broad
+    "SIM102",  # collapsible-if
+    "SIM103",  # needless-bool
+    "SIM105",  # suppressible-exception
+    "SIM107",  # return-in-try-except-finally
+    "SIM108",  # if-else-block-instead-of-if-exp
+    "SIM113",  # enumerate-for-loop
+    "SIM117",  # multiple-with-statements
+    "SIM210",  # if-expr-with-true-false
+    "UP038",   # deprecated and not recommended by Ruff, https://docs.astral.sh/ruff/rules/non-pep604-isinstance/
 ]

 [lint.per-file-ignores]
@@ -4,7 +4,7 @@ FROM python:3.12-slim-bookworm AS base
 WORKDIR /app/api

 # Install uv
-ENV UV_VERSION=0.6.14
+ENV UV_VERSION=0.7.11

 RUN pip install --no-cache-dir uv==${UV_VERSION}

@@ -1,4 +1,3 @@
-import os
 import sys


@@ -17,20 +16,20 @@ else:
    # It seems that JetBrains Python debugger does not work well with gevent,
    # so we need to disable gevent in debug mode.
    # If you are using debugpy and set GEVENT_SUPPORT=True, you can debug with gevent.
-    if (flask_debug := os.environ.get("FLASK_DEBUG", "0")) and flask_debug.lower() in {"false", "0", "no"}:
-        from gevent import monkey
+    # if (flask_debug := os.environ.get("FLASK_DEBUG", "0")) and flask_debug.lower() in {"false", "0", "no"}:
+    # from gevent import monkey
+    #
+    # # gevent
+    # monkey.patch_all()
+    #
+    # from grpc.experimental import gevent as grpc_gevent  # type: ignore
+    #
+    # # grpc gevent
+    # grpc_gevent.init_gevent()

-        # gevent
-        monkey.patch_all()
-
-        from grpc.experimental import gevent as grpc_gevent  # type: ignore
-
-        # grpc gevent
-        grpc_gevent.init_gevent()
-
-        import psycogreen.gevent  # type: ignore
-
-        psycogreen.gevent.patch_psycopg()
+    # import psycogreen.gevent  # type: ignore
+    #
+    # psycogreen.gevent.patch_psycopg()

    from app_factory import create_app

@@ -54,6 +54,7 @@ def initialize_extensions(app: DifyApp):
        ext_otel,
        ext_proxy_fix,
        ext_redis,
+        ext_request_logging,
        ext_sentry,
        ext_set_secretkey,
        ext_storage,
@@ -83,6 +84,7 @@ def initialize_extensions(app: DifyApp):
        ext_blueprints,
        ext_commands,
        ext_otel,
+        ext_request_logging,
    ]
    for ext in extensions:
        short_name = ext.__name__.split(".")[-1]
@@ -27,7 +27,7 @@ from models.dataset import Dataset, DatasetCollectionBinding, DatasetMetadata, D
 from models.dataset import Document as DatasetDocument
 from models.model import Account, App, AppAnnotationSetting, AppMode, Conversation, MessageAnnotation
 from models.provider import Provider, ProviderModel
-from services.account_service import RegisterService, TenantService
+from services.account_service import AccountService, RegisterService, TenantService
 from services.clear_free_plan_tenant_expired_logs import ClearFreePlanTenantExpiredLogs
 from services.plugin.data_migration import PluginDataMigration
 from services.plugin.plugin_migration import PluginMigration
@@ -68,6 +68,7 @@ def reset_password(email, new_password, password_confirm):
    account.password = base64_password_hashed
    account.password_salt = base64_salt
    db.session.commit()
+    AccountService.reset_login_error_rate_limit(email)
    click.echo(click.style("Password reset successfully.", fg="green"))


@@ -280,6 +281,7 @@ def migrate_knowledge_vector_database():
        VectorType.ELASTICSEARCH,
        VectorType.OPENGAUSS,
        VectorType.TABLESTORE,
+        VectorType.MATRIXONE,
    }
    lower_collection_vector_types = {
        VectorType.ANALYTICDB,
@@ -846,6 +848,9 @@ def clear_orphaned_file_records(force: bool):
        {"type": "text", "table": "workflow_node_executions", "column": "outputs"},
        {"type": "text", "table": "conversations", "column": "introduction"},
        {"type": "text", "table": "conversations", "column": "system_instruction"},
+        {"type": "text", "table": "accounts", "column": "avatar"},
+        {"type": "text", "table": "apps", "column": "icon"},
+        {"type": "text", "table": "sites", "column": "icon"},
        {"type": "json", "table": "messages", "column": "inputs"},
        {"type": "json", "table": "messages", "column": "message"},
    ]
@@ -1,8 +1,11 @@
 import logging
+from pathlib import Path
 from typing import Any

 from pydantic.fields import FieldInfo
-from pydantic_settings import BaseSettings, PydanticBaseSettingsSource, SettingsConfigDict
+from pydantic_settings import BaseSettings, PydanticBaseSettingsSource, SettingsConfigDict, TomlConfigSettingsSource
+
+from libs.file_utils import search_file_upwards

 from .deploy import DeploymentConfig
 from .enterprise import EnterpriseFeatureConfig
@@ -99,4 +102,12 @@ class DifyConfig(
            RemoteSettingsSourceFactory(settings_cls),
            dotenv_settings,
            file_secret_settings,
+            TomlConfigSettingsSource(
+                settings_cls=settings_cls,
+                toml_file=search_file_upwards(
+                    base_dir_path=Path(__file__).parent,
+                    target_file_name="pyproject.toml",
+                    max_search_parent_depth=2,
+                ),
+            ),
        )
@@ -17,6 +17,12 @@ class DeploymentConfig(BaseSettings):
        default=False,
    )

+    # Request logging configuration
+    ENABLE_REQUEST_LOGGING: bool = Field(
+        description="Enable request and response body logging",
+        default=False,
+    )
+
    EDITION: str = Field(
        description="Deployment edition of the application (e.g., 'SELF_HOSTED', 'CLOUD')",
        default="SELF_HOSTED",
@@ -609,7 +609,7 @@ class MailConfig(BaseSettings):
    """

    MAIL_TYPE: Optional[str] = Field(
-        description="Email service provider type ('smtp' or 'resend'), default to None.",
+        description="Email service provider type ('smtp' or 'resend' or 'sendGrid), default to None.",
        default=None,
    )

@@ -663,6 +663,11 @@ class MailConfig(BaseSettings):
        default=50,
    )

+    SENDGRID_API_KEY: Optional[str] = Field(
+        description="API key for SendGrid service",
+        default=None,
+    )
+

 class RagEtlConfig(BaseSettings):
    """
@@ -222,11 +222,28 @@ class HostedFetchAppTemplateConfig(BaseSettings):
    )


+class HostedFetchPipelineTemplateConfig(BaseSettings):
+    """
+    Configuration for fetching pipeline templates
+    """
+
+    HOSTED_FETCH_PIPELINE_TEMPLATES_MODE: str = Field(
+        description="Mode for fetching pipeline templates: remote, db, or builtin default to remote,",
+        default="database",
+    )
+
+    HOSTED_FETCH_PIPELINE_TEMPLATES_REMOTE_DOMAIN: str = Field(
+        description="Domain for fetching remote pipeline templates",
+        default="https://tmpl.dify.ai",
+    )
+
+
 class HostedServiceConfig(
    # place the configs in alphabet order
    HostedAnthropicConfig,
    HostedAzureOpenAiConfig,
    HostedFetchAppTemplateConfig,
+    HostedFetchPipelineTemplateConfig,
    HostedMinmaxConfig,
    HostedOpenAiConfig,
    HostedSparkConfig,
@@ -2,7 +2,7 @@ import os
 from typing import Any, Literal, Optional
 from urllib.parse import parse_qsl, quote_plus

-from pydantic import Field, NonNegativeInt, PositiveFloat, PositiveInt, computed_field
+from pydantic import Field, NonNegativeFloat, NonNegativeInt, PositiveFloat, PositiveInt, computed_field
 from pydantic_settings import BaseSettings

 from .cache.redis_config import RedisConfig
@@ -24,6 +24,7 @@ from .vdb.couchbase_config import CouchbaseConfig
 from .vdb.elasticsearch_config import ElasticsearchConfig
 from .vdb.huawei_cloud_config import HuaweiCloudConfig
 from .vdb.lindorm_config import LindormConfig
+from .vdb.matrixone_config import MatrixoneConfig
 from .vdb.milvus_config import MilvusConfig
 from .vdb.myscale_config import MyScaleConfig
 from .vdb.oceanbase_config import OceanBaseVectorConfig
@@ -222,6 +223,10 @@ class CeleryConfig(DatabaseConfig):
        default=None,
    )

+    CELERY_SENTINEL_PASSWORD: Optional[str] = Field(
+        description="Password of the Redis Sentinel master.",
+        default=None,
+    )
    CELERY_SENTINEL_SOCKET_TIMEOUT: Optional[PositiveFloat] = Field(
        description="Timeout for Redis Sentinel socket operations in seconds.",
        default=0.1,
@@ -256,6 +261,25 @@ class InternalTestConfig(BaseSettings):
    )


+class DatasetQueueMonitorConfig(BaseSettings):
+    """
+    Configuration settings for Dataset Queue Monitor
+    """
+
+    QUEUE_MONITOR_THRESHOLD: Optional[NonNegativeInt] = Field(
+        description="Threshold for dataset queue monitor",
+        default=200,
+    )
+    QUEUE_MONITOR_ALERT_EMAILS: Optional[str] = Field(
+        description="Emails for dataset queue monitor alert, separated by commas",
+        default=None,
+    )
+    QUEUE_MONITOR_INTERVAL: Optional[NonNegativeFloat] = Field(
+        description="Interval for dataset queue monitor in minutes",
+        default=30,
+    )
+
+
 class MiddlewareConfig(
    # place the configs in alphabet order
    CeleryConfig,
@@ -303,5 +327,7 @@ class MiddlewareConfig(
    BaiduVectorDBConfig,
    OpenGaussConfig,
    TableStoreConfig,
+    DatasetQueueMonitorConfig,
+    MatrixoneConfig,
 ):
    pass
@@ -1,4 +1,4 @@
-from typing import Optional
+from typing import Literal, Optional

 from pydantic import Field
 from pydantic_settings import BaseSettings
@@ -34,7 +34,7 @@ class S3StorageConfig(BaseSettings):
        default=None,
    )

-    S3_ADDRESS_STYLE: str = Field(
+    S3_ADDRESS_STYLE: Literal["auto", "virtual", "path"] = Field(
        description="S3 addressing style: 'auto', 'path', or 'virtual'",
        default="auto",
    )
@@ -0,0 +1,14 @@
+from pydantic import BaseModel, Field
+
+
+class MatrixoneConfig(BaseModel):
+    """Matrixone vector database configuration."""
+
+    MATRIXONE_HOST: str = Field(default="localhost", description="Host address of the Matrixone server")
+    MATRIXONE_PORT: int = Field(default=6001, description="Port number of the Matrixone server")
+    MATRIXONE_USER: str = Field(default="dump", description="Username for authenticating with Matrixone")
+    MATRIXONE_PASSWORD: str = Field(default="111", description="Password for authenticating with Matrixone")
+    MATRIXONE_DATABASE: str = Field(default="dify", description="Name of the Matrixone database to connect to")
+    MATRIXONE_METRIC: str = Field(
+        default="l2", description="Distance metric type for vector similarity search (cosine or l2)"
+    )
@@ -33,6 +33,11 @@ class OpenSearchConfig(BaseSettings):
        default=False,
    )

+    OPENSEARCH_VERIFY_CERTS: bool = Field(
+        description="Whether to verify SSL certificates for HTTPS connections (recommended to set True in production)",
+        default=True,
+    )
+
    OPENSEARCH_AUTH_METHOD: AuthMethod = Field(
        description="Authentication method for OpenSearch connection (default is 'basic')",
        default=AuthMethod.BASIC,
@@ -33,3 +33,8 @@ class QdrantConfig(BaseSettings):
        description="Port number for gRPC connection to Qdrant server (default is 6334)",
        default=6334,
    )
+
+    QDRANT_REPLICATION_FACTOR: PositiveInt = Field(
+        description="Replication factor for Qdrant collections (default is 1)",
+        default=1,
+    )
@@ -1,17 +1,13 @@
 from pydantic import Field
-from pydantic_settings import BaseSettings
+
+from configs.packaging.pyproject import PyProjectConfig, PyProjectTomlConfig


-class PackagingInfo(BaseSettings):
+class PackagingInfo(PyProjectTomlConfig):
    """
    Packaging build information
    """

-    CURRENT_VERSION: str = Field(
-        description="Dify version",
-        default="1.4.0",
-    )
-
    COMMIT_SHA: str = Field(
        description="SHA-1 checksum of the git commit used to build the app",
        default="",
@@ -0,0 +1,17 @@
+from pydantic import BaseModel, Field
+from pydantic_settings import BaseSettings
+
+
+class PyProjectConfig(BaseModel):
+    version: str = Field(description="Dify version", default="")
+
+
+class PyProjectTomlConfig(BaseSettings):
+    """
+    configs in api/pyproject.toml
+    """
+
+    project: PyProjectConfig = Field(
+        description="configs in the project section of pyproject.toml",
+        default=PyProjectConfig(),
+    )
@@ -60,8 +60,7 @@ class NacosHttpClient:
            sign_str = tenant + "+"
        if group:
            sign_str = sign_str + group + "+"
-        if sign_str:
-            sign_str += ts
+        sign_str += ts  # Directly concatenate ts without conditional checks, because the nacos auth header forced it.
        return sign_str

    def get_access_token(self, force_refresh=False):
@@ -3,6 +3,7 @@ from threading import Lock
 from typing import TYPE_CHECKING

 from contexts.wrapper import RecyclableContextVar
+from core.datasource.__base.datasource_provider import DatasourcePluginProviderController

 if TYPE_CHECKING:
    from core.model_runtime.entities.model_entities import AIModelEntity
@@ -11,10 +12,6 @@ if TYPE_CHECKING:
    from core.workflow.entities.variable_pool import VariablePool


-tenant_id: ContextVar[str] = ContextVar("tenant_id")
-
-workflow_variable_pool: ContextVar["VariablePool"] = ContextVar("workflow_variable_pool")
-
 """
 To avoid race-conditions caused by gunicorn thread recycling, using RecyclableContextVar to replace with
 """
@@ -37,3 +34,11 @@ plugin_model_schema_lock: RecyclableContextVar[Lock] = RecyclableContextVar(Cont
 plugin_model_schemas: RecyclableContextVar[dict[str, "AIModelEntity"]] = RecyclableContextVar(
    ContextVar("plugin_model_schemas")
 )
+
+datasource_plugin_providers: RecyclableContextVar[dict[str, "DatasourcePluginProviderController"]] = (
+    RecyclableContextVar(ContextVar("datasource_plugin_providers"))
+)
+
+datasource_plugin_providers_lock: RecyclableContextVar[Lock] = RecyclableContextVar(
+    ContextVar("datasource_plugin_providers_lock")
+)
@@ -63,6 +63,7 @@ from .app import (
    statistic,
    workflow,
    workflow_app_log,
+    workflow_draft_variable,
    workflow_run,
    workflow_statistic,
 )
@@ -75,7 +76,6 @@ from .billing import billing, compliance

 # Import datasets controllers
 from .datasets import (
-    data_source,
    datasets,
    datasets_document,
    datasets_segments,
@@ -84,6 +84,14 @@ from .datasets import (
    metadata,
    website,
 )
+from .datasets.rag_pipeline import (
+    datasource_auth,
+    datasource_content_preview,
+    rag_pipeline,
+    rag_pipeline_datasets,
+    rag_pipeline_import,
+    rag_pipeline_workflow,
+)

 # Import explore controllers
 from .explore import (
@@ -56,8 +56,7 @@ class InsertExploreAppListApi(Resource):
        parser.add_argument("position", type=int, required=True, nullable=False, location="json")
        args = parser.parse_args()

-        with Session(db.engine) as session:
-            app = session.execute(select(App).filter(App.id == args["app_id"])).scalar_one_or_none()
+        app = db.session.execute(select(App).filter(App.id == args["app_id"])).scalar_one_or_none()
        if not app:
            raise NotFound(f"App '{args['app_id']}' is not found")

@@ -78,38 +77,38 @@ class InsertExploreAppListApi(Resource):
                select(RecommendedApp).filter(RecommendedApp.app_id == args["app_id"])
            ).scalar_one_or_none()

-        if not recommended_app:
-            recommended_app = RecommendedApp(
-                app_id=app.id,
-                description=desc,
-                copyright=copy_right,
-                privacy_policy=privacy_policy,
-                custom_disclaimer=custom_disclaimer,
-                language=args["language"],
-                category=args["category"],
-                position=args["position"],
-            )
+            if not recommended_app:
+                recommended_app = RecommendedApp(
+                    app_id=app.id,
+                    description=desc,
+                    copyright=copy_right,
+                    privacy_policy=privacy_policy,
+                    custom_disclaimer=custom_disclaimer,
+                    language=args["language"],
+                    category=args["category"],
+                    position=args["position"],
+                )

-            db.session.add(recommended_app)
+                db.session.add(recommended_app)

-            app.is_public = True
-            db.session.commit()
+                app.is_public = True
+                db.session.commit()

-            return {"result": "success"}, 201
-        else:
-            recommended_app.description = desc
-            recommended_app.copyright = copy_right
-            recommended_app.privacy_policy = privacy_policy
-            recommended_app.custom_disclaimer = custom_disclaimer
-            recommended_app.language = args["language"]
-            recommended_app.category = args["category"]
-            recommended_app.position = args["position"]
+                return {"result": "success"}, 201
+            else:
+                recommended_app.description = desc
+                recommended_app.copyright = copy_right
+                recommended_app.privacy_policy = privacy_policy
+                recommended_app.custom_disclaimer = custom_disclaimer
+                recommended_app.language = args["language"]
+                recommended_app.category = args["category"]
+                recommended_app.position = args["position"]

-            app.is_public = True
+                app.is_public = True

-            db.session.commit()
+                db.session.commit()

-            return {"result": "success"}, 200
+                return {"result": "success"}, 200


 class InsertExploreAppApi(Resource):
@@ -208,7 +208,7 @@ class AnnotationBatchImportApi(Resource):
        if len(request.files) > 1:
            raise TooManyFilesError()
        # check file type
-        if not file.filename.endswith(".csv"):
+        if not file.filename or not file.filename.lower().endswith(".csv"):
            raise ValueError("Invalid file type. Only CSV files are allowed")
        return AppAnnotationService.batch_import_app_annotations(app_id, file)

@@ -17,15 +17,13 @@ from controllers.console.wraps import (
 )
 from core.ops.ops_trace_manager import OpsTraceManager
 from extensions.ext_database import db
-from fields.app_fields import (
-    app_detail_fields,
-    app_detail_fields_with_site,
-    app_pagination_fields,
-)
+from fields.app_fields import app_detail_fields, app_detail_fields_with_site, app_pagination_fields
 from libs.login import login_required
 from models import Account, App
 from services.app_dsl_service import AppDslService, ImportMode
 from services.app_service import AppService
+from services.enterprise.enterprise_service import EnterpriseService
+from services.feature_service import FeatureService

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

@@ -75,7 +73,17 @@ class AppListApi(Resource):
        if not app_pagination:
            return {"data": [], "total": 0, "page": 1, "limit": 20, "has_more": False}

-        return marshal(app_pagination, app_pagination_fields)
+        if FeatureService.get_system_features().webapp_auth.enabled:
+            app_ids = [str(app.id) for app in app_pagination.items]
+            res = EnterpriseService.WebAppAuth.batch_get_app_access_mode_by_id(app_ids=app_ids)
+            if len(res) != len(app_ids):
+                raise BadRequest("Invalid app id in webapp auth")
+
+            for app in app_pagination.items:
+                if str(app.id) in res:
+                    app.access_mode = res[str(app.id)].access_mode
+
+        return marshal(app_pagination, app_pagination_fields), 200

    @setup_required
    @login_required
@@ -119,6 +127,10 @@ class AppApi(Resource):

        app_model = app_service.get_app(app_model)

+        if FeatureService.get_system_features().webapp_auth.enabled:
+            app_setting = EnterpriseService.WebAppAuth.get_app_access_mode_by_id(app_id=str(app_model.id))
+            app_model.access_mode = app_setting.access_mode
+
        return app_model

    @setup_required
@@ -17,6 +17,8 @@ from libs.login import login_required
 from models import Account
 from models.model import App
 from services.app_dsl_service import AppDslService, ImportStatus
+from services.enterprise.enterprise_service import EnterpriseService
+from services.feature_service import FeatureService


 class AppImportApi(Resource):
@@ -60,7 +62,9 @@ class AppImportApi(Resource):
                app_id=args.get("app_id"),
            )
            session.commit()
-
+        if result.app_id and FeatureService.get_system_features().webapp_auth.enabled:
+            # update web app setting as private
+            EnterpriseService.WebAppAuth.update_app_access_mode(result.app_id, "private")
        # Return appropriate status code based on result
        status = result.status
        if status == ImportStatus.FAILED.value:
@@ -1,5 +1,6 @@
 import json
 import logging
+from collections.abc import Sequence
 from typing import cast

 from flask import abort, request
@@ -18,10 +19,12 @@ from controllers.console.app.error import (
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
 from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
+from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
+from core.file.models import File
 from extensions.ext_database import db
-from factories import variable_factory
+from factories import file_factory, variable_factory
 from fields.workflow_fields import workflow_fields, workflow_pagination_fields
 from fields.workflow_run_fields import workflow_run_node_execution_fields
 from libs import helper
@@ -30,6 +33,7 @@ from libs.login import current_user, login_required
 from models import App
 from models.account import Account
 from models.model import AppMode
+from models.workflow import Workflow
 from services.app_generate_service import AppGenerateService
 from services.errors.app import WorkflowHashNotEqualError
 from services.errors.llm import InvokeRateLimitError
@@ -38,6 +42,24 @@ from services.workflow_service import DraftWorkflowDeletionError, WorkflowInUseE
 logger = logging.getLogger(__name__)


+# TODO(QuantumGhost): Refactor existing node run API to handle file parameter parsing
+# at the controller level rather than in the workflow logic. This would improve separation
+# of concerns and make the code more maintainable.
+def _parse_file(workflow: Workflow, files: list[dict] | None = None) -> Sequence[File]:
+    files = files or []
+
+    file_extra_config = FileUploadConfigManager.convert(workflow.features_dict, is_vision=False)
+    file_objs: Sequence[File] = []
+    if file_extra_config is None:
+        return file_objs
+    file_objs = file_factory.build_from_mappings(
+        mappings=files,
+        tenant_id=workflow.tenant_id,
+        config=file_extra_config,
+    )
+    return file_objs
+
+
 class DraftWorkflowApi(Resource):
    @setup_required
    @login_required
@@ -81,8 +103,7 @@ class DraftWorkflowApi(Resource):
            parser.add_argument("graph", type=dict, required=True, nullable=False, location="json")
            parser.add_argument("features", type=dict, required=True, nullable=False, location="json")
            parser.add_argument("hash", type=str, required=False, location="json")
-            # TODO: set this to required=True after frontend is updated
-            parser.add_argument("environment_variables", type=list, required=False, location="json")
+            parser.add_argument("environment_variables", type=list, required=True, location="json")
            parser.add_argument("conversation_variables", type=list, required=False, location="json")
            args = parser.parse_args()
        elif "text/plain" in content_type:
@@ -403,15 +424,30 @@ class DraftWorkflowNodeRunApi(Resource):

        parser = reqparse.RequestParser()
        parser.add_argument("inputs", type=dict, required=True, nullable=False, location="json")
+        parser.add_argument("query", type=str, required=False, location="json", default="")
+        parser.add_argument("files", type=list, location="json", default=[])
        args = parser.parse_args()

-        inputs = args.get("inputs")
-        if inputs == None:
+        user_inputs = args.get("inputs")
+        if user_inputs is None:
            raise ValueError("missing inputs")

+        workflow_srv = WorkflowService()
+        # fetch draft workflow by app_model
+        draft_workflow = workflow_srv.get_draft_workflow(app_model=app_model)
+        if not draft_workflow:
+            raise ValueError("Workflow not initialized")
+        files = _parse_file(draft_workflow, args.get("files"))
        workflow_service = WorkflowService()
+
        workflow_node_execution = workflow_service.run_draft_workflow_node(
-            app_model=app_model, node_id=node_id, user_inputs=inputs, account=current_user
+            app_model=app_model,
+            draft_workflow=draft_workflow,
+            node_id=node_id,
+            user_inputs=user_inputs,
+            account=current_user,
+            query=args.get("query", ""),
+            files=files,
        )

        return workflow_node_execution
@@ -732,6 +768,27 @@ class WorkflowByIdApi(Resource):
        return None, 204


+class DraftWorkflowNodeLastRunApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
+    @marshal_with(workflow_run_node_execution_fields)
+    def get(self, app_model: App, node_id: str):
+        srv = WorkflowService()
+        workflow = srv.get_draft_workflow(app_model)
+        if not workflow:
+            raise NotFound("Workflow not found")
+        node_exec = srv.get_node_last_run(
+            app_model=app_model,
+            workflow=workflow,
+            node_id=node_id,
+        )
+        if node_exec is None:
+            raise NotFound("last run not found")
+        return node_exec
+
+
 api.add_resource(
    DraftWorkflowApi,
    "/apps/<uuid:app_id>/workflows/draft",
@@ -796,3 +853,7 @@ api.add_resource(
    WorkflowByIdApi,
    "/apps/<uuid:app_id>/workflows/<string:workflow_id>",
 )
+api.add_resource(
+    DraftWorkflowNodeLastRunApi,
+    "/apps/<uuid:app_id>/workflows/draft/nodes/<string:node_id>/last-run",
+)
@@ -6,12 +6,12 @@ from sqlalchemy.orm import Session
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
+from core.workflow.entities.workflow_execution import WorkflowExecutionStatus
 from extensions.ext_database import db
 from fields.workflow_app_log_fields import workflow_app_log_pagination_fields
 from libs.login import login_required
 from models import App
 from models.model import AppMode
-from models.workflow import WorkflowRunStatus
 from services.workflow_app_service import WorkflowAppService


@@ -34,11 +34,25 @@ class WorkflowAppLogApi(Resource):
        parser.add_argument(
            "created_at__after", type=str, location="args", help="Filter logs created after this timestamp"
        )
+        parser.add_argument(
+            "created_by_end_user_session_id",
+            type=str,
+            location="args",
+            required=False,
+            default=None,
+        )
+        parser.add_argument(
+            "created_by_account",
+            type=str,
+            location="args",
+            required=False,
+            default=None,
+        )
        parser.add_argument("page", type=int_range(1, 99999), default=1, location="args")
        parser.add_argument("limit", type=int_range(1, 100), default=20, location="args")
        args = parser.parse_args()

-        args.status = WorkflowRunStatus(args.status) if args.status else None
+        args.status = WorkflowExecutionStatus(args.status) if args.status else None
        if args.created_at__before:
            args.created_at__before = isoparse(args.created_at__before)

@@ -57,6 +71,8 @@ class WorkflowAppLogApi(Resource):
                created_at_after=args.created_at__after,
                page=args.page,
                limit=args.limit,
+                created_by_end_user_session_id=args.created_by_end_user_session_id,
+                created_by_account=args.created_by_account,
            )

            return workflow_app_log_pagination
@@ -0,0 +1,421 @@
+import logging
+from typing import Any, NoReturn
+
+from flask import Response
+from flask_restful import Resource, fields, inputs, marshal, marshal_with, reqparse
+from sqlalchemy.orm import Session
+from werkzeug.exceptions import Forbidden
+
+from controllers.console import api
+from controllers.console.app.error import (
+    DraftWorkflowNotExist,
+)
+from controllers.console.app.wraps import get_app_model
+from controllers.console.wraps import account_initialization_required, setup_required
+from controllers.web.error import InvalidArgumentError, NotFoundError
+from core.variables.segment_group import SegmentGroup
+from core.variables.segments import ArrayFileSegment, FileSegment, Segment
+from core.variables.types import SegmentType
+from core.workflow.constants import CONVERSATION_VARIABLE_NODE_ID, SYSTEM_VARIABLE_NODE_ID
+from factories.file_factory import build_from_mapping, build_from_mappings
+from factories.variable_factory import build_segment_with_type
+from libs.login import current_user, login_required
+from models import App, AppMode, db
+from models.workflow import WorkflowDraftVariable
+from services.workflow_draft_variable_service import WorkflowDraftVariableList, WorkflowDraftVariableService
+from services.workflow_service import WorkflowService
+
+logger = logging.getLogger(__name__)
+
+
+def _convert_values_to_json_serializable_object(value: Segment) -> Any:
+    if isinstance(value, FileSegment):
+        return value.value.model_dump()
+    elif isinstance(value, ArrayFileSegment):
+        return [i.model_dump() for i in value.value]
+    elif isinstance(value, SegmentGroup):
+        return [_convert_values_to_json_serializable_object(i) for i in value.value]
+    else:
+        return value.value
+
+
+def _serialize_var_value(variable: WorkflowDraftVariable) -> Any:
+    value = variable.get_value()
+    # create a copy of the value to avoid affecting the model cache.
+    value = value.model_copy(deep=True)
+    # Refresh the url signature before returning it to client.
+    if isinstance(value, FileSegment):
+        file = value.value
+        file.remote_url = file.generate_url()
+    elif isinstance(value, ArrayFileSegment):
+        files = value.value
+        for file in files:
+            file.remote_url = file.generate_url()
+    return _convert_values_to_json_serializable_object(value)
+
+
+def _create_pagination_parser():
+    parser = reqparse.RequestParser()
+    parser.add_argument(
+        "page",
+        type=inputs.int_range(1, 100_000),
+        required=False,
+        default=1,
+        location="args",
+        help="the page of data requested",
+    )
+    parser.add_argument("limit", type=inputs.int_range(1, 100), required=False, default=20, location="args")
+    return parser
+
+
+_WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS = {
+    "id": fields.String,
+    "type": fields.String(attribute=lambda model: model.get_variable_type()),
+    "name": fields.String,
+    "description": fields.String,
+    "selector": fields.List(fields.String, attribute=lambda model: model.get_selector()),
+    "value_type": fields.String,
+    "edited": fields.Boolean(attribute=lambda model: model.edited),
+    "visible": fields.Boolean,
+}
+
+_WORKFLOW_DRAFT_VARIABLE_FIELDS = dict(
+    _WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS,
+    value=fields.Raw(attribute=_serialize_var_value),
+)
+
+_WORKFLOW_DRAFT_ENV_VARIABLE_FIELDS = {
+    "id": fields.String,
+    "type": fields.String(attribute=lambda _: "env"),
+    "name": fields.String,
+    "description": fields.String,
+    "selector": fields.List(fields.String, attribute=lambda model: model.get_selector()),
+    "value_type": fields.String,
+    "edited": fields.Boolean(attribute=lambda model: model.edited),
+    "visible": fields.Boolean,
+}
+
+_WORKFLOW_DRAFT_ENV_VARIABLE_LIST_FIELDS = {
+    "items": fields.List(fields.Nested(_WORKFLOW_DRAFT_ENV_VARIABLE_FIELDS)),
+}
+
+
+def _get_items(var_list: WorkflowDraftVariableList) -> list[WorkflowDraftVariable]:
+    return var_list.variables
+
+
+_WORKFLOW_DRAFT_VARIABLE_LIST_WITHOUT_VALUE_FIELDS = {
+    "items": fields.List(fields.Nested(_WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS), attribute=_get_items),
+    "total": fields.Raw(),
+}
+
+_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS = {
+    "items": fields.List(fields.Nested(_WORKFLOW_DRAFT_VARIABLE_FIELDS), attribute=_get_items),
+}
+
+
+def _api_prerequisite(f):
+    """Common prerequisites for all draft workflow variable APIs.
+
+    It ensures the following conditions are satisfied:
+
+    - Dify has been property setup.
+    - The request user has logged in and initialized.
+    - The requested app is a workflow or a chat flow.
+    - The request user has the edit permission for the app.
+    """
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
+    def wrapper(*args, **kwargs):
+        if not current_user.is_editor:
+            raise Forbidden()
+        return f(*args, **kwargs)
+
+    return wrapper
+
+
+class WorkflowVariableCollectionApi(Resource):
+    @_api_prerequisite
+    @marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_WITHOUT_VALUE_FIELDS)
+    def get(self, app_model: App):
+        """
+        Get draft workflow
+        """
+        parser = _create_pagination_parser()
+        args = parser.parse_args()
+
+        # fetch draft workflow by app_model
+        workflow_service = WorkflowService()
+        workflow_exist = workflow_service.is_workflow_exist(app_model=app_model)
+        if not workflow_exist:
+            raise DraftWorkflowNotExist()
+
+        # fetch draft workflow by app_model
+        with Session(bind=db.engine, expire_on_commit=False) as session:
+            draft_var_srv = WorkflowDraftVariableService(
+                session=session,
+            )
+        workflow_vars = draft_var_srv.list_variables_without_values(
+            app_id=app_model.id,
+            page=args.page,
+            limit=args.limit,
+        )
+
+        return workflow_vars
+
+    @_api_prerequisite
+    def delete(self, app_model: App):
+        draft_var_srv = WorkflowDraftVariableService(
+            session=db.session(),
+        )
+        draft_var_srv.delete_workflow_variables(app_model.id)
+        db.session.commit()
+        return Response("", 204)
+
+
+def validate_node_id(node_id: str) -> NoReturn | None:
+    if node_id in [
+        CONVERSATION_VARIABLE_NODE_ID,
+        SYSTEM_VARIABLE_NODE_ID,
+    ]:
+        # NOTE(QuantumGhost): While we store the system and conversation variables as node variables
+        # with specific `node_id` in database, we still want to make the API separated. By disallowing
+        # accessing system and conversation variables in `WorkflowDraftNodeVariableListApi`,
+        # we mitigate the risk that user of the API depending on the implementation detail of the API.
+        #
+        # ref: [Hyrum's Law](https://www.hyrumslaw.com/)
+
+        raise InvalidArgumentError(
+            f"invalid node_id, please use correspond api for conversation and system variables, node_id={node_id}",
+        )
+    return None
+
+
+class NodeVariableCollectionApi(Resource):
+    @_api_prerequisite
+    @marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
+    def get(self, app_model: App, node_id: str):
+        validate_node_id(node_id)
+        with Session(bind=db.engine, expire_on_commit=False) as session:
+            draft_var_srv = WorkflowDraftVariableService(
+                session=session,
+            )
+            node_vars = draft_var_srv.list_node_variables(app_model.id, node_id)
+
+        return node_vars
+
+    @_api_prerequisite
+    def delete(self, app_model: App, node_id: str):
+        validate_node_id(node_id)
+        srv = WorkflowDraftVariableService(db.session())
+        srv.delete_node_variables(app_model.id, node_id)
+        db.session.commit()
+        return Response("", 204)
+
+
+class VariableApi(Resource):
+    _PATCH_NAME_FIELD = "name"
+    _PATCH_VALUE_FIELD = "value"
+
+    @_api_prerequisite
+    @marshal_with(_WORKFLOW_DRAFT_VARIABLE_FIELDS)
+    def get(self, app_model: App, variable_id: str):
+        draft_var_srv = WorkflowDraftVariableService(
+            session=db.session(),
+        )
+        variable = draft_var_srv.get_variable(variable_id=variable_id)
+        if variable is None:
+            raise NotFoundError(description=f"variable not found, id={variable_id}")
+        if variable.app_id != app_model.id:
+            raise NotFoundError(description=f"variable not found, id={variable_id}")
+        return variable
+
+    @_api_prerequisite
+    @marshal_with(_WORKFLOW_DRAFT_VARIABLE_FIELDS)
+    def patch(self, app_model: App, variable_id: str):
+        # Request payload for file types:
+        #
+        # Local File:
+        #
+        #     {
+        #         "type": "image",
+        #         "transfer_method": "local_file",
+        #         "url": "",
+        #         "upload_file_id": "daded54f-72c7-4f8e-9d18-9b0abdd9f190"
+        #     }
+        #
+        # Remote File:
+        #
+        #
+        #     {
+        #         "type": "image",
+        #         "transfer_method": "remote_url",
+        #         "url": "http://127.0.0.1:5001/files/1602650a-4fe4-423c-85a2-af76c083e3c4/file-preview?timestamp=1750041099&nonce=...&sign=...=",
+        #         "upload_file_id": "1602650a-4fe4-423c-85a2-af76c083e3c4"
+        #     }
+
+        parser = reqparse.RequestParser()
+        parser.add_argument(self._PATCH_NAME_FIELD, type=str, required=False, nullable=True, location="json")
+        # Parse 'value' field as-is to maintain its original data structure
+        parser.add_argument(self._PATCH_VALUE_FIELD, type=lambda x: x, required=False, nullable=True, location="json")
+
+        draft_var_srv = WorkflowDraftVariableService(
+            session=db.session(),
+        )
+        args = parser.parse_args(strict=True)
+
+        variable = draft_var_srv.get_variable(variable_id=variable_id)
+        if variable is None:
+            raise NotFoundError(description=f"variable not found, id={variable_id}")
+        if variable.app_id != app_model.id:
+            raise NotFoundError(description=f"variable not found, id={variable_id}")
+
+        new_name = args.get(self._PATCH_NAME_FIELD, None)
+        raw_value = args.get(self._PATCH_VALUE_FIELD, None)
+        if new_name is None and raw_value is None:
+            return variable
+
+        new_value = None
+        if raw_value is not None:
+            if variable.value_type == SegmentType.FILE:
+                if not isinstance(raw_value, dict):
+                    raise InvalidArgumentError(description=f"expected dict for file, got {type(raw_value)}")
+                raw_value = build_from_mapping(mapping=raw_value, tenant_id=app_model.tenant_id)
+            elif variable.value_type == SegmentType.ARRAY_FILE:
+                if not isinstance(raw_value, list):
+                    raise InvalidArgumentError(description=f"expected list for files, got {type(raw_value)}")
+                if len(raw_value) > 0 and not isinstance(raw_value[0], dict):
+                    raise InvalidArgumentError(description=f"expected dict for files[0], got {type(raw_value)}")
+                raw_value = build_from_mappings(mappings=raw_value, tenant_id=app_model.tenant_id)
+            new_value = build_segment_with_type(variable.value_type, raw_value)
+        draft_var_srv.update_variable(variable, name=new_name, value=new_value)
+        db.session.commit()
+        return variable
+
+    @_api_prerequisite
+    def delete(self, app_model: App, variable_id: str):
+        draft_var_srv = WorkflowDraftVariableService(
+            session=db.session(),
+        )
+        variable = draft_var_srv.get_variable(variable_id=variable_id)
+        if variable is None:
+            raise NotFoundError(description=f"variable not found, id={variable_id}")
+        if variable.app_id != app_model.id:
+            raise NotFoundError(description=f"variable not found, id={variable_id}")
+        draft_var_srv.delete_variable(variable)
+        db.session.commit()
+        return Response("", 204)
+
+
+class VariableResetApi(Resource):
+    @_api_prerequisite
+    def put(self, app_model: App, variable_id: str):
+        draft_var_srv = WorkflowDraftVariableService(
+            session=db.session(),
+        )
+
+        workflow_srv = WorkflowService()
+        draft_workflow = workflow_srv.get_draft_workflow(app_model)
+        if draft_workflow is None:
+            raise NotFoundError(
+                f"Draft workflow not found, app_id={app_model.id}",
+            )
+        variable = draft_var_srv.get_variable(variable_id=variable_id)
+        if variable is None:
+            raise NotFoundError(description=f"variable not found, id={variable_id}")
+        if variable.app_id != app_model.id:
+            raise NotFoundError(description=f"variable not found, id={variable_id}")
+
+        resetted = draft_var_srv.reset_variable(draft_workflow, variable)
+        db.session.commit()
+        if resetted is None:
+            return Response("", 204)
+        else:
+            return marshal(resetted, _WORKFLOW_DRAFT_VARIABLE_FIELDS)
+
+
+def _get_variable_list(app_model: App, node_id) -> WorkflowDraftVariableList:
+    with Session(bind=db.engine, expire_on_commit=False) as session:
+        draft_var_srv = WorkflowDraftVariableService(
+            session=session,
+        )
+        if node_id == CONVERSATION_VARIABLE_NODE_ID:
+            draft_vars = draft_var_srv.list_conversation_variables(app_model.id)
+        elif node_id == SYSTEM_VARIABLE_NODE_ID:
+            draft_vars = draft_var_srv.list_system_variables(app_model.id)
+        else:
+            draft_vars = draft_var_srv.list_node_variables(app_id=app_model.id, node_id=node_id)
+    return draft_vars
+
+
+class ConversationVariableCollectionApi(Resource):
+    @_api_prerequisite
+    @marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
+    def get(self, app_model: App):
+        # NOTE(QuantumGhost): Prefill conversation variables into the draft variables table
+        # so their IDs can be returned to the caller.
+        workflow_srv = WorkflowService()
+        draft_workflow = workflow_srv.get_draft_workflow(app_model)
+        if draft_workflow is None:
+            raise NotFoundError(description=f"draft workflow not found, id={app_model.id}")
+        draft_var_srv = WorkflowDraftVariableService(db.session())
+        draft_var_srv.prefill_conversation_variable_default_values(draft_workflow)
+        db.session.commit()
+        return _get_variable_list(app_model, CONVERSATION_VARIABLE_NODE_ID)
+
+
+class SystemVariableCollectionApi(Resource):
+    @_api_prerequisite
+    @marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
+    def get(self, app_model: App):
+        return _get_variable_list(app_model, SYSTEM_VARIABLE_NODE_ID)
+
+
+class EnvironmentVariableCollectionApi(Resource):
+    @_api_prerequisite
+    def get(self, app_model: App):
+        """
+        Get draft workflow
+        """
+        # fetch draft workflow by app_model
+        workflow_service = WorkflowService()
+        workflow = workflow_service.get_draft_workflow(app_model=app_model)
+        if workflow is None:
+            raise DraftWorkflowNotExist()
+
+        env_vars = workflow.environment_variables
+        env_vars_list = []
+        for v in env_vars:
+            env_vars_list.append(
+                {
+                    "id": v.id,
+                    "type": "env",
+                    "name": v.name,
+                    "description": v.description,
+                    "selector": v.selector,
+                    "value_type": v.value_type.value,
+                    "value": v.value,
+                    # Do not track edited for env vars.
+                    "edited": False,
+                    "visible": True,
+                    "editable": True,
+                }
+            )
+
+        return {"items": env_vars_list}
+
+
+api.add_resource(
+    WorkflowVariableCollectionApi,
+    "/apps/<uuid:app_id>/workflows/draft/variables",
+)
+api.add_resource(NodeVariableCollectionApi, "/apps/<uuid:app_id>/workflows/draft/nodes/<string:node_id>/variables")
+api.add_resource(VariableApi, "/apps/<uuid:app_id>/workflows/draft/variables/<uuid:variable_id>")
+api.add_resource(VariableResetApi, "/apps/<uuid:app_id>/workflows/draft/variables/<uuid:variable_id>/reset")
+
+api.add_resource(ConversationVariableCollectionApi, "/apps/<uuid:app_id>/workflows/draft/conversation-variables")
+api.add_resource(SystemVariableCollectionApi, "/apps/<uuid:app_id>/workflows/draft/system-variables")
+api.add_resource(EnvironmentVariableCollectionApi, "/apps/<uuid:app_id>/workflows/draft/environment-variables")
@@ -1,3 +1,6 @@
+from typing import cast
+
+from flask_login import current_user
 from flask_restful import Resource, marshal_with, reqparse
 from flask_restful.inputs import int_range

@@ -12,8 +15,7 @@ from fields.workflow_run_fields import (
 )
 from libs.helper import uuid_value
 from libs.login import login_required
-from models import App
-from models.model import AppMode
+from models import Account, App, AppMode, EndUser
 from services.workflow_run_service import WorkflowRunService


@@ -90,7 +92,12 @@ class WorkflowRunNodeExecutionListApi(Resource):
        run_id = str(run_id)

        workflow_run_service = WorkflowRunService()
-        node_executions = workflow_run_service.get_workflow_run_node_executions(app_model=app_model, run_id=run_id)
+        user = cast("Account | EndUser", current_user)
+        node_executions = workflow_run_service.get_workflow_run_node_executions(
+            app_model=app_model,
+            run_id=run_id,
+            user=user,
+        )

        return {"data": node_executions}

@@ -8,6 +8,15 @@ from libs.login import current_user
 from models import App, AppMode


+def _load_app_model(app_id: str) -> Optional[App]:
+    app_model = (
+        db.session.query(App)
+        .filter(App.id == app_id, App.tenant_id == current_user.current_tenant_id, App.status == "normal")
+        .first()
+    )
+    return app_model
+
+
 def get_app_model(view: Optional[Callable] = None, *, mode: Union[AppMode, list[AppMode], None] = None):
    def decorator(view_func):
        @wraps(view_func)
@@ -20,11 +29,7 @@ def get_app_model(view: Optional[Callable] = None, *, mode: Union[AppMode, list[

            del kwargs["app_id"]

-            app_model = (
-                db.session.query(App)
-                .filter(App.id == app_id, App.tenant_id == current_user.current_tenant_id, App.status == "normal")
-                .first()
-            )
+            app_model = _load_app_model(app_id)

            if not app_model:
                raise AppNotFoundError()
@@ -41,7 +41,7 @@ class OAuthDataSource(Resource):
            if not internal_secret:
                return ({"error": "Internal secret is not set"},)
            oauth_provider.save_internal_access_token(internal_secret)
-            return {"data": ""}
+            return {"data": "internal"}
        else:
            auth_url = oauth_provider.get_authorization_url()
            return {"data": auth_url}, 200
@@ -24,7 +24,7 @@ from libs.password import hash_password, valid_password
 from models.account import Account
 from services.account_service import AccountService, TenantService
 from services.errors.account import AccountRegisterError
-from services.errors.workspace import WorkSpaceNotAllowedCreateError
+from services.errors.workspace import WorkSpaceNotAllowedCreateError, WorkspacesLimitExceededError
 from services.feature_service import FeatureService


@@ -168,6 +168,8 @@ class ForgotPasswordResetApi(Resource):
            )
        except WorkSpaceNotAllowedCreateError:
            pass
+        except WorkspacesLimitExceededError:
+            pass
        except AccountRegisterError:
            raise AccountInFreezeError()

@@ -21,6 +21,7 @@ from controllers.console.error import (
    AccountNotFound,
    EmailSendIpLimitError,
    NotAllowedCreateWorkspace,
+    WorkspacesLimitExceeded,
 )
 from controllers.console.wraps import email_password_login_enabled, setup_required
 from events.tenant_event import tenant_was_created
@@ -30,7 +31,7 @@ from models.account import Account
 from services.account_service import AccountService, RegisterService, TenantService
 from services.billing_service import BillingService
 from services.errors.account import AccountRegisterError
-from services.errors.workspace import WorkSpaceNotAllowedCreateError
+from services.errors.workspace import WorkSpaceNotAllowedCreateError, WorkspacesLimitExceededError
 from services.feature_service import FeatureService


@@ -88,10 +89,15 @@ class LoginApi(Resource):
        # 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",
-            }
+            system_features = FeatureService.get_system_features()
+
+            if system_features.is_allow_create_workspace and not system_features.license.workspaces.is_available():
+                raise WorkspacesLimitExceeded()
+            else:
+                return {
+                    "result": "fail",
+                    "data": "workspace not found, please contact system admin to invite you to join in a workspace",
+                }

        token_pair = AccountService.login(account=account, ip_address=extract_remote_ip(request))
        AccountService.reset_login_error_rate_limit(args["email"])
@@ -196,15 +202,18 @@ class EmailCodeLoginApi(Resource):
        except AccountRegisterError as are:
            raise AccountInFreezeError()
        if account:
-            tenant = TenantService.get_join_tenants(account)
-            if not tenant:
+            tenants = TenantService.get_join_tenants(account)
+            if not tenants:
+                workspaces = FeatureService.get_system_features().license.workspaces
+                if not workspaces.is_available():
+                    raise WorkspacesLimitExceeded()
                if not FeatureService.get_system_features().is_allow_create_workspace:
                    raise NotAllowedCreateWorkspace()
                else:
-                    tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
-                    TenantService.create_tenant_member(tenant, account, role="owner")
-                    account.current_tenant = tenant
-                    tenant_was_created.send(tenant)
+                    new_tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
+                    TenantService.create_tenant_member(new_tenant, account, role="owner")
+                    account.current_tenant = new_tenant
+                    tenant_was_created.send(new_tenant)

        if account is None:
            try:
@@ -215,6 +224,8 @@ class EmailCodeLoginApi(Resource):
                return NotAllowedCreateWorkspace()
            except AccountRegisterError as are:
                raise AccountInFreezeError()
+            except WorkspacesLimitExceededError:
+                raise WorkspacesLimitExceeded()
        token_pair = AccountService.login(account, ip_address=extract_remote_ip(request))
        AccountService.reset_login_error_rate_limit(args["email"])
        return {"result": "success", "data": token_pair.model_dump()}
@@ -148,15 +148,15 @@ def _generate_account(provider: str, user_info: OAuthUserInfo):
    account = _get_account_by_openid_or_email(provider, user_info)

    if account:
-        tenant = TenantService.get_join_tenants(account)
-        if not tenant:
+        tenants = TenantService.get_join_tenants(account)
+        if not tenants:
            if not FeatureService.get_system_features().is_allow_create_workspace:
                raise WorkSpaceNotAllowedCreateError()
            else:
-                tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
-                TenantService.create_tenant_member(tenant, account, role="owner")
-                account.current_tenant = tenant
-                tenant_was_created.send(tenant)
+                new_tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
+                TenantService.create_tenant_member(new_tenant, account, role="owner")
+                account.current_tenant = new_tenant
+                tenant_was_created.send(new_tenant)

    if not account:
        if not FeatureService.get_system_features().is_allow_register:
@@ -283,6 +283,15 @@ class DatasetApi(Resource):
            location="json",
            help="Invalid external knowledge api id.",
        )
+
+        parser.add_argument(
+            "icon_info",
+            type=dict,
+            required=False,
+            nullable=True,
+            location="json",
+            help="Invalid icon info.",
+        )
        args = parser.parse_args()
        data = request.get_json()

@@ -540,9 +549,22 @@ class DatasetIndexingStatusApi(Resource):
                .filter(DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment")
                .count()
            )
-            document.completed_segments = completed_segments
-            document.total_segments = total_segments
-            documents_status.append(marshal(document, document_status_fields))
+            # Create a dictionary with document attributes and additional fields
+            document_dict = {
+                "id": document.id,
+                "indexing_status": document.indexing_status,
+                "processing_started_at": document.processing_started_at,
+                "parsing_completed_at": document.parsing_completed_at,
+                "cleaning_completed_at": document.cleaning_completed_at,
+                "splitting_completed_at": document.splitting_completed_at,
+                "completed_at": document.completed_at,
+                "paused_at": document.paused_at,
+                "error": document.error,
+                "stopped_at": document.stopped_at,
+                "completed_segments": completed_segments,
+                "total_segments": total_segments,
+            }
+            documents_status.append(marshal(document_dict, document_status_fields))
        data = {"data": documents_status}
        return data

@@ -673,6 +695,7 @@ class DatasetRetrievalSettingApi(Resource):
                | VectorType.TABLESTORE
                | VectorType.HUAWEI_CLOUD
                | VectorType.TENCENT
+                | VectorType.MATRIXONE
            ):
                return {
                    "retrieval_method": [
@@ -720,6 +743,7 @@ class DatasetRetrievalSettingMockApi(Resource):
                | VectorType.TABLESTORE
                | VectorType.TENCENT
                | VectorType.HUAWEI_CLOUD
+                | VectorType.MATRIXONE
            ):
                return {
                    "retrieval_method": [
@@ -1,3 +1,4 @@
+import json
 import logging
 from argparse import ArgumentTypeError
 from datetime import UTC, datetime
@@ -5,7 +6,7 @@ from typing import cast

 from flask import request
 from flask_login import current_user
-from flask_restful import Resource, fields, marshal, marshal_with, reqparse
+from flask_restful import Resource, marshal, marshal_with, reqparse
 from sqlalchemy import asc, desc, select
 from werkzeug.exceptions import Forbidden, NotFound

@@ -43,7 +44,6 @@ from core.model_runtime.errors.invoke import InvokeAuthorizationError
 from core.plugin.impl.exc import PluginDaemonClientSideError
 from core.rag.extractor.entity.extract_setting import ExtractSetting
 from extensions.ext_database import db
-from extensions.ext_redis import redis_client
 from fields.document_fields import (
    dataset_and_document_fields,
    document_fields,
@@ -52,10 +52,9 @@ from fields.document_fields import (
 )
 from libs.login import login_required
 from models import Dataset, DatasetProcessRule, Document, DocumentSegment, UploadFile
+from models.dataset import DocumentPipelineExecutionLog
 from services.dataset_service import DatasetService, DocumentService
 from services.entities.knowledge_entities.knowledge_entities import KnowledgeConfig
-from tasks.add_document_to_index_task import add_document_to_index_task
-from tasks.remove_document_from_index_task import remove_document_from_index_task


 class DocumentResource(Resource):
@@ -242,12 +241,10 @@ class DatasetDocumentListApi(Resource):

        return response

-    documents_and_batch_fields = {"documents": fields.List(fields.Nested(document_fields)), "batch": fields.String}
-
    @setup_required
    @login_required
    @account_initialization_required
-    @marshal_with(documents_and_batch_fields)
+    @marshal_with(dataset_and_document_fields)
    @cloud_edition_billing_resource_check("vector_space")
    @cloud_edition_billing_rate_limit_check("knowledge")
    def post(self, dataset_id):
@@ -293,6 +290,8 @@ class DatasetDocumentListApi(Resource):

        try:
            documents, batch = DocumentService.save_document_with_dataset_id(dataset, knowledge_config, current_user)
+            dataset = DatasetService.get_dataset(dataset_id)
+
        except ProviderTokenNotInitError as ex:
            raise ProviderNotInitializeError(ex.description)
        except QuotaExceededError:
@@ -300,7 +299,7 @@ class DatasetDocumentListApi(Resource):
        except ModelCurrentlyNotSupportError:
            raise ProviderModelCurrentlyNotSupportError()

-        return {"documents": documents, "batch": batch}
+        return {"dataset": dataset, "documents": documents, "batch": batch}

    @setup_required
    @login_required
@@ -583,11 +582,22 @@ class DocumentBatchIndexingStatusApi(DocumentResource):
                .filter(DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment")
                .count()
            )
-            document.completed_segments = completed_segments
-            document.total_segments = total_segments
-            if document.is_paused:
-                document.indexing_status = "paused"
-            documents_status.append(marshal(document, document_status_fields))
+            # Create a dictionary with document attributes and additional fields
+            document_dict = {
+                "id": document.id,
+                "indexing_status": "paused" if document.is_paused else document.indexing_status,
+                "processing_started_at": document.processing_started_at,
+                "parsing_completed_at": document.parsing_completed_at,
+                "cleaning_completed_at": document.cleaning_completed_at,
+                "splitting_completed_at": document.splitting_completed_at,
+                "completed_at": document.completed_at,
+                "paused_at": document.paused_at,
+                "error": document.error,
+                "stopped_at": document.stopped_at,
+                "completed_segments": completed_segments,
+                "total_segments": total_segments,
+            }
+            documents_status.append(marshal(document_dict, document_status_fields))
        data = {"data": documents_status}
        return data

@@ -616,11 +626,22 @@ class DocumentIndexingStatusApi(DocumentResource):
            .count()
        )

-        document.completed_segments = completed_segments
-        document.total_segments = total_segments
-        if document.is_paused:
-            document.indexing_status = "paused"
-        return marshal(document, document_status_fields)
+        # Create a dictionary with document attributes and additional fields
+        document_dict = {
+            "id": document.id,
+            "indexing_status": "paused" if document.is_paused else document.indexing_status,
+            "processing_started_at": document.processing_started_at,
+            "parsing_completed_at": document.parsing_completed_at,
+            "cleaning_completed_at": document.cleaning_completed_at,
+            "splitting_completed_at": document.splitting_completed_at,
+            "completed_at": document.completed_at,
+            "paused_at": document.paused_at,
+            "error": document.error,
+            "stopped_at": document.stopped_at,
+            "completed_segments": completed_segments,
+            "total_segments": total_segments,
+        }
+        return marshal(document_dict, document_status_fields)


 class DocumentDetailApi(DocumentResource):
@@ -642,7 +663,7 @@ class DocumentDetailApi(DocumentResource):
            response = {"id": document.id, "doc_type": document.doc_type, "doc_metadata": document.doc_metadata_details}
        elif metadata == "without":
            dataset_process_rules = DatasetService.get_process_rules(dataset_id)
-            document_process_rules = document.dataset_process_rule.to_dict()
+            document_process_rules = document.dataset_process_rule.to_dict() if document.dataset_process_rule else {}
            data_source_info = document.data_source_detail_dict
            response = {
                "id": document.id,
@@ -840,77 +861,16 @@ class DocumentStatusApi(DocumentResource):
        DatasetService.check_dataset_permission(dataset, current_user)

        document_ids = request.args.getlist("document_id")
-        for document_id in document_ids:
-            document = self.get_document(dataset_id, document_id)

-            indexing_cache_key = "document_{}_indexing".format(document.id)
-            cache_result = redis_client.get(indexing_cache_key)
-            if cache_result is not None:
-                raise InvalidActionError(f"Document:{document.name} is being indexed, please try again later")
+        try:
+            DocumentService.batch_update_document_status(dataset, document_ids, action, current_user)
+        except services.errors.document.DocumentIndexingError as e:
+            raise InvalidActionError(str(e))
+        except ValueError as e:
+            raise InvalidActionError(str(e))
+        except NotFound as e:
+            raise NotFound(str(e))

-            if action == "enable":
-                if document.enabled:
-                    continue
-                document.enabled = True
-                document.disabled_at = None
-                document.disabled_by = None
-                document.updated_at = datetime.now(UTC).replace(tzinfo=None)
-                db.session.commit()
-
-                # Set cache to prevent indexing the same document multiple times
-                redis_client.setex(indexing_cache_key, 600, 1)
-
-                add_document_to_index_task.delay(document_id)
-
-            elif action == "disable":
-                if not document.completed_at or document.indexing_status != "completed":
-                    raise InvalidActionError(f"Document: {document.name} is not completed.")
-                if not document.enabled:
-                    continue
-
-                document.enabled = False
-                document.disabled_at = datetime.now(UTC).replace(tzinfo=None)
-                document.disabled_by = current_user.id
-                document.updated_at = datetime.now(UTC).replace(tzinfo=None)
-                db.session.commit()
-
-                # Set cache to prevent indexing the same document multiple times
-                redis_client.setex(indexing_cache_key, 600, 1)
-
-                remove_document_from_index_task.delay(document_id)
-
-            elif action == "archive":
-                if document.archived:
-                    continue
-
-                document.archived = True
-                document.archived_at = datetime.now(UTC).replace(tzinfo=None)
-                document.archived_by = current_user.id
-                document.updated_at = datetime.now(UTC).replace(tzinfo=None)
-                db.session.commit()
-
-                if document.enabled:
-                    # Set cache to prevent indexing the same document multiple times
-                    redis_client.setex(indexing_cache_key, 600, 1)
-
-                    remove_document_from_index_task.delay(document_id)
-
-            elif action == "un_archive":
-                if not document.archived:
-                    continue
-                document.archived = False
-                document.archived_at = None
-                document.archived_by = None
-                document.updated_at = datetime.now(UTC).replace(tzinfo=None)
-                db.session.commit()
-
-                # Set cache to prevent indexing the same document multiple times
-                redis_client.setex(indexing_cache_key, 600, 1)
-
-                add_document_to_index_task.delay(document_id)
-
-            else:
-                raise InvalidActionError()
        return {"result": "success"}, 200


@@ -1070,6 +1030,41 @@ class WebsiteDocumentSyncApi(DocumentResource):
        return {"result": "success"}, 200


+class DocumentPipelineExecutionLogApi(DocumentResource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id, document_id):
+        dataset_id = str(dataset_id)
+        document_id = str(document_id)
+
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        document = DocumentService.get_document(dataset.id, document_id)
+        if not document:
+            raise NotFound("Document not found.")
+        log = (
+            db.session.query(DocumentPipelineExecutionLog)
+            .filter_by(document_id=document_id)
+            .order_by(DocumentPipelineExecutionLog.created_at.desc())
+            .first()
+        )
+        if not log:
+            return {
+                "datasource_info": None,
+                "datasource_type": None,
+                "input_data": None,
+                "datasource_node_id": None,
+            }, 200
+        return {
+            "datasource_info": json.loads(log.datasource_info),
+            "datasource_type": log.datasource_type,
+            "input_data": log.input_data,
+            "datasource_node_id": log.datasource_node_id,
+        }, 200
+
+
 api.add_resource(GetProcessRuleApi, "/datasets/process-rule")
 api.add_resource(DatasetDocumentListApi, "/datasets/<uuid:dataset_id>/documents")
 api.add_resource(DatasetInitApi, "/datasets/init")
@@ -1092,3 +1087,6 @@ api.add_resource(DocumentRetryApi, "/datasets/<uuid:dataset_id>/retry")
 api.add_resource(DocumentRenameApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/rename")

 api.add_resource(WebsiteDocumentSyncApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/website-sync")
+api.add_resource(
+    DocumentPipelineExecutionLogApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/pipeline-execution-log"
+)
@@ -374,7 +374,7 @@ class DatasetDocumentSegmentBatchImportApi(Resource):
        if len(request.files) > 1:
            raise TooManyFilesError()
        # check file type
-        if not file.filename.endswith(".csv"):
+        if not file.filename or not file.filename.lower().endswith(".csv"):
            raise ValueError("Invalid file type. Only CSV files are allowed")

        try:
@@ -101,3 +101,9 @@ class ChildChunkDeleteIndexError(BaseHTTPException):
    error_code = "child_chunk_delete_index_error"
    description = "Delete child chunk index failed: {message}"
    code = 500
+
+
+class PipelineNotFoundError(BaseHTTPException):
+    error_code = "pipeline_not_found"
+    description = "Pipeline not found."
+    code = 404
@@ -0,0 +1,197 @@
+from flask import redirect, request
+from flask_login import current_user  # type: ignore
+from flask_restful import (  # type: ignore
+    Resource,  # type: ignore
+    reqparse,
+)
+from werkzeug.exceptions import Forbidden, NotFound
+
+from configs import dify_config
+from controllers.console import api
+from controllers.console.wraps import (
+    account_initialization_required,
+    setup_required,
+)
+from core.model_runtime.errors.validate import CredentialsValidateFailedError
+from core.plugin.impl.oauth import OAuthHandler
+from extensions.ext_database import db
+from libs.login import login_required
+from models.oauth import DatasourceOauthParamConfig, DatasourceProvider
+from services.datasource_provider_service import DatasourceProviderService
+
+
+class DatasourcePluginOauthApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("provider", type=str, required=True, nullable=False, location="args")
+        parser.add_argument("plugin_id", type=str, required=True, nullable=False, location="args")
+        args = parser.parse_args()
+        provider = args["provider"]
+        plugin_id = args["plugin_id"]
+        # Check user role first
+        if not current_user.is_editor:
+            raise Forbidden()
+        # get all plugin oauth configs
+        plugin_oauth_config = (
+            db.session.query(DatasourceOauthParamConfig).filter_by(provider=provider, plugin_id=plugin_id).first()
+        )
+        if not plugin_oauth_config:
+            raise NotFound()
+        oauth_handler = OAuthHandler()
+        redirect_url = (
+            f"{dify_config.CONSOLE_WEB_URL}/oauth/datasource/callback?provider={provider}&plugin_id={plugin_id}"
+        )
+        system_credentials = plugin_oauth_config.system_credentials
+        if system_credentials:
+            system_credentials["redirect_url"] = redirect_url
+        response = oauth_handler.get_authorization_url(
+            current_user.current_tenant.id, current_user.id, plugin_id, provider, system_credentials=system_credentials
+        )
+        return response.model_dump()
+
+
+class DatasourceOauthCallback(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("provider", type=str, required=True, nullable=False, location="args")
+        parser.add_argument("plugin_id", type=str, required=True, nullable=False, location="args")
+        args = parser.parse_args()
+        provider = args["provider"]
+        plugin_id = args["plugin_id"]
+        oauth_handler = OAuthHandler()
+        plugin_oauth_config = (
+            db.session.query(DatasourceOauthParamConfig).filter_by(provider=provider, plugin_id=plugin_id).first()
+        )
+        if not plugin_oauth_config:
+            raise NotFound()
+        credentials = oauth_handler.get_credentials(
+            current_user.current_tenant.id,
+            current_user.id,
+            plugin_id,
+            provider,
+            system_credentials=plugin_oauth_config.system_credentials,
+            request=request,
+        )
+        datasource_provider = DatasourceProvider(
+            plugin_id=plugin_id, provider=provider, auth_type="oauth", encrypted_credentials=credentials
+        )
+        db.session.add(datasource_provider)
+        db.session.commit()
+        return redirect(f"{dify_config.CONSOLE_WEB_URL}")
+
+
+class DatasourceAuth(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        if not current_user.is_editor:
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("provider", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("name", type=str, required=False, nullable=False, location="json", default="test")
+        parser.add_argument("plugin_id", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("credentials", type=dict, required=True, nullable=False, location="json")
+        args = parser.parse_args()
+
+        datasource_provider_service = DatasourceProviderService()
+
+        try:
+            datasource_provider_service.datasource_provider_credentials_validate(
+                tenant_id=current_user.current_tenant_id,
+                provider=args["provider"],
+                plugin_id=args["plugin_id"],
+                credentials=args["credentials"],
+                name=args["name"],
+            )
+        except CredentialsValidateFailedError as ex:
+            raise ValueError(str(ex))
+
+        return {"result": "success"}, 201
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("provider", type=str, required=True, nullable=False, location="args")
+        parser.add_argument("plugin_id", type=str, required=True, nullable=False, location="args")
+        args = parser.parse_args()
+        datasource_provider_service = DatasourceProviderService()
+        datasources = datasource_provider_service.get_datasource_credentials(
+            tenant_id=current_user.current_tenant_id, provider=args["provider"], plugin_id=args["plugin_id"]
+        )
+        return {"result": datasources}, 200
+
+
+class DatasourceAuthUpdateDeleteApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, auth_id: str):
+        parser = reqparse.RequestParser()
+        parser.add_argument("provider", type=str, required=True, nullable=False, location="args")
+        parser.add_argument("plugin_id", type=str, required=True, nullable=False, location="args")
+        args = parser.parse_args()
+        if not current_user.is_editor:
+            raise Forbidden()
+        datasource_provider_service = DatasourceProviderService()
+        datasource_provider_service.remove_datasource_credentials(
+            tenant_id=current_user.current_tenant_id,
+            auth_id=auth_id,
+            provider=args["provider"],
+            plugin_id=args["plugin_id"],
+        )
+        return {"result": "success"}, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def patch(self, auth_id: str):
+        parser = reqparse.RequestParser()
+        parser.add_argument("provider", type=str, required=True, nullable=False, location="args")
+        parser.add_argument("plugin_id", type=str, required=True, nullable=False, location="args")
+        parser.add_argument("credentials", type=dict, required=True, nullable=False, location="json")
+        args = parser.parse_args()
+        if not current_user.is_editor:
+            raise Forbidden()
+        try:
+            datasource_provider_service = DatasourceProviderService()
+            datasource_provider_service.update_datasource_credentials(
+                tenant_id=current_user.current_tenant_id,
+                auth_id=auth_id,
+                provider=args["provider"],
+                plugin_id=args["plugin_id"],
+                credentials=args["credentials"],
+            )
+        except CredentialsValidateFailedError as ex:
+            raise ValueError(str(ex))
+
+        return {"result": "success"}, 201
+
+
+# Import Rag Pipeline
+api.add_resource(
+    DatasourcePluginOauthApi,
+    "/oauth/plugin/datasource",
+)
+api.add_resource(
+    DatasourceOauthCallback,
+    "/oauth/plugin/datasource/callback",
+)
+api.add_resource(
+    DatasourceAuth,
+    "/auth/plugin/datasource",
+)
+
+api.add_resource(
+    DatasourceAuthUpdateDeleteApi,
+    "/auth/plugin/datasource/<string:auth_id>",
+)
@@ -0,0 +1,55 @@
+from flask_restful import (  # type: ignore
+    Resource,  # type: ignore
+    reqparse,
+)
+from werkzeug.exceptions import Forbidden
+
+from controllers.console import api
+from controllers.console.datasets.wraps import get_rag_pipeline
+from controllers.console.wraps import account_initialization_required, setup_required
+from libs.login import current_user, login_required
+from models import Account
+from models.dataset import Pipeline
+from services.rag_pipeline.rag_pipeline import RagPipelineService
+
+
+class DataSourceContentPreviewApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_rag_pipeline
+    def post(self, pipeline: Pipeline, node_id: str):
+        """
+        Run datasource content preview
+        """
+        if not isinstance(current_user, Account):
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("inputs", type=dict, required=True, nullable=False, location="json")
+        parser.add_argument("datasource_type", type=str, required=True, location="json")
+        args = parser.parse_args()
+
+        inputs = args.get("inputs")
+        if inputs is None:
+            raise ValueError("missing inputs")
+        datasource_type = args.get("datasource_type")
+        if datasource_type is None:
+            raise ValueError("missing datasource_type")
+
+        rag_pipeline_service = RagPipelineService()
+        preview_content = rag_pipeline_service.run_datasource_node_preview(
+            pipeline=pipeline,
+            node_id=node_id,
+            user_inputs=inputs,
+            account=current_user,
+            datasource_type=datasource_type,
+            is_published=True,
+        )
+        return preview_content, 200
+
+
+api.add_resource(
+    DataSourceContentPreviewApi,
+    "/rag/pipelines/<uuid:pipeline_id>/workflows/published/datasource/nodes/<string:node_id>/preview",
+)
@@ -0,0 +1,162 @@
+import logging
+
+from flask import request
+from flask_restful import Resource, reqparse
+from sqlalchemy.orm import Session
+
+from controllers.console import api
+from controllers.console.wraps import (
+    account_initialization_required,
+    enterprise_license_required,
+    setup_required,
+)
+from extensions.ext_database import db
+from libs.login import login_required
+from models.dataset import PipelineCustomizedTemplate
+from services.entities.knowledge_entities.rag_pipeline_entities import PipelineTemplateInfoEntity
+from services.rag_pipeline.rag_pipeline import RagPipelineService
+
+logger = logging.getLogger(__name__)
+
+
+def _validate_name(name):
+    if not name or len(name) < 1 or len(name) > 40:
+        raise ValueError("Name must be between 1 to 40 characters.")
+    return name
+
+
+def _validate_description_length(description):
+    if len(description) > 400:
+        raise ValueError("Description cannot exceed 400 characters.")
+    return description
+
+
+class PipelineTemplateListApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @enterprise_license_required
+    def get(self):
+        type = request.args.get("type", default="built-in", type=str)
+        language = request.args.get("language", default="en-US", type=str)
+        # get pipeline templates
+        pipeline_templates = RagPipelineService.get_pipeline_templates(type, language)
+        return pipeline_templates, 200
+
+
+class PipelineTemplateDetailApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @enterprise_license_required
+    def get(self, template_id: str):
+        type = request.args.get("type", default="built-in", type=str)
+        rag_pipeline_service = RagPipelineService()
+        pipeline_template = rag_pipeline_service.get_pipeline_template_detail(template_id, type)
+        return pipeline_template, 200
+
+
+class CustomizedPipelineTemplateApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @enterprise_license_required
+    def patch(self, template_id: str):
+        parser = reqparse.RequestParser()
+        parser.add_argument(
+            "name",
+            nullable=False,
+            required=True,
+            help="Name must be between 1 to 40 characters.",
+            type=_validate_name,
+        )
+        parser.add_argument(
+            "description",
+            type=str,
+            nullable=True,
+            required=False,
+            default="",
+        )
+        parser.add_argument(
+            "icon_info",
+            type=dict,
+            location="json",
+            nullable=True,
+        )
+        args = parser.parse_args()
+        pipeline_template_info = PipelineTemplateInfoEntity(**args)
+        RagPipelineService.update_customized_pipeline_template(template_id, pipeline_template_info)
+        return 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @enterprise_license_required
+    def delete(self, template_id: str):
+        RagPipelineService.delete_customized_pipeline_template(template_id)
+        return 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @enterprise_license_required
+    def post(self, template_id: str):
+        with Session(db.engine) as session:
+            template = (
+                session.query(PipelineCustomizedTemplate).filter(PipelineCustomizedTemplate.id == template_id).first()
+            )
+            if not template:
+                raise ValueError("Customized pipeline template not found.")
+
+        return {"data": template.yaml_content}, 200
+
+
+class PublishCustomizedPipelineTemplateApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @enterprise_license_required
+    def post(self, pipeline_id: str):
+        parser = reqparse.RequestParser()
+        parser.add_argument(
+            "name",
+            nullable=False,
+            required=True,
+            help="Name must be between 1 to 40 characters.",
+            type=_validate_name,
+        )
+        parser.add_argument(
+            "description",
+            type=str,
+            nullable=True,
+            required=False,
+            default="",
+        )
+        parser.add_argument(
+            "icon_info",
+            type=dict,
+            location="json",
+            nullable=True,
+        )
+        args = parser.parse_args()
+        rag_pipeline_service = RagPipelineService()
+        rag_pipeline_service.publish_customized_pipeline_template(pipeline_id, args)
+        return {"result": "success"}
+
+
+api.add_resource(
+    PipelineTemplateListApi,
+    "/rag/pipeline/templates",
+)
+api.add_resource(
+    PipelineTemplateDetailApi,
+    "/rag/pipeline/templates/<string:template_id>",
+)
+api.add_resource(
+    CustomizedPipelineTemplateApi,
+    "/rag/pipeline/customized/templates/<string:template_id>",
+)
+api.add_resource(
+    PublishCustomizedPipelineTemplateApi,
+    "/rag/pipelines/<string:pipeline_id>/customized/publish",
+)
@@ -0,0 +1,171 @@
+from flask_login import current_user  # type: ignore  # type: ignore
+from flask_restful import Resource, marshal, reqparse  # type: ignore
+from werkzeug.exceptions import Forbidden
+
+import services
+from controllers.console import api
+from controllers.console.datasets.error import DatasetNameDuplicateError
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_rate_limit_check,
+    setup_required,
+)
+from fields.dataset_fields import dataset_detail_fields
+from libs.login import login_required
+from models.dataset import DatasetPermissionEnum
+from services.dataset_service import DatasetPermissionService, DatasetService
+from services.entities.knowledge_entities.rag_pipeline_entities import RagPipelineDatasetCreateEntity
+from services.rag_pipeline.rag_pipeline_dsl_service import RagPipelineDslService
+
+
+def _validate_name(name):
+    if not name or len(name) < 1 or len(name) > 40:
+        raise ValueError("Name must be between 1 to 40 characters.")
+    return name
+
+
+def _validate_description_length(description):
+    if len(description) > 400:
+        raise ValueError("Description cannot exceed 400 characters.")
+    return description
+
+
+class CreateRagPipelineDatasetApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @cloud_edition_billing_rate_limit_check("knowledge")
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument(
+            "name",
+            nullable=False,
+            required=True,
+            help="type is required. Name must be between 1 to 40 characters.",
+            type=_validate_name,
+        )
+        parser.add_argument(
+            "description",
+            type=str,
+            nullable=True,
+            required=False,
+            default="",
+        )
+
+        parser.add_argument(
+            "icon_info",
+            type=dict,
+            nullable=True,
+            required=False,
+            default={},
+        )
+
+        parser.add_argument(
+            "permission",
+            type=str,
+            choices=(DatasetPermissionEnum.ONLY_ME, DatasetPermissionEnum.ALL_TEAM, DatasetPermissionEnum.PARTIAL_TEAM),
+            nullable=True,
+            required=False,
+            default=DatasetPermissionEnum.ONLY_ME,
+        )
+
+        parser.add_argument(
+            "partial_member_list",
+            type=list,
+            nullable=True,
+            required=False,
+            default=[],
+        )
+
+        parser.add_argument(
+            "yaml_content",
+            type=str,
+            nullable=False,
+            required=True,
+            help="yaml_content is required.",
+        )
+
+        args = parser.parse_args()
+
+        # The role of the current user in the ta table must be admin, owner, or editor, or dataset_operator
+        if not current_user.is_dataset_editor:
+            raise Forbidden()
+        rag_pipeline_dataset_create_entity = RagPipelineDatasetCreateEntity(**args)
+        try:
+            import_info = RagPipelineDslService.create_rag_pipeline_dataset(
+                tenant_id=current_user.current_tenant_id,
+                rag_pipeline_dataset_create_entity=rag_pipeline_dataset_create_entity,
+            )
+            if rag_pipeline_dataset_create_entity.permission == "partial_members":
+                DatasetPermissionService.update_partial_member_list(
+                    current_user.current_tenant_id,
+                    import_info["dataset_id"],
+                    rag_pipeline_dataset_create_entity.partial_member_list,
+                )
+        except services.errors.dataset.DatasetNameDuplicateError:
+            raise DatasetNameDuplicateError()
+
+        return import_info, 201
+
+
+class CreateEmptyRagPipelineDatasetApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @cloud_edition_billing_rate_limit_check("knowledge")
+    def post(self):
+        # The role of the current user in the ta table must be admin, owner, or editor, or dataset_operator
+        if not current_user.is_dataset_editor:
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument(
+            "name",
+            nullable=False,
+            required=True,
+            help="type is required. Name must be between 1 to 40 characters.",
+            type=_validate_name,
+        )
+        parser.add_argument(
+            "description",
+            type=str,
+            nullable=True,
+            required=False,
+            default="",
+        )
+
+        parser.add_argument(
+            "icon_info",
+            type=dict,
+            nullable=True,
+            required=False,
+            default={},
+        )
+
+        parser.add_argument(
+            "permission",
+            type=str,
+            choices=(DatasetPermissionEnum.ONLY_ME, DatasetPermissionEnum.ALL_TEAM, DatasetPermissionEnum.PARTIAL_TEAM),
+            nullable=True,
+            required=False,
+            default=DatasetPermissionEnum.ONLY_ME,
+        )
+
+        parser.add_argument(
+            "partial_member_list",
+            type=list,
+            nullable=True,
+            required=False,
+            default=[],
+        )
+
+        args = parser.parse_args()
+        dataset = DatasetService.create_empty_rag_pipeline_dataset(
+            tenant_id=current_user.current_tenant_id,
+            rag_pipeline_dataset_create_entity=RagPipelineDatasetCreateEntity(**args),
+        )
+        return marshal(dataset, dataset_detail_fields), 201
+
+
+api.add_resource(CreateRagPipelineDatasetApi, "/rag/pipeline/dataset")
+api.add_resource(CreateEmptyRagPipelineDatasetApi, "/rag/pipeline/empty-dataset")
@@ -0,0 +1,146 @@
+from typing import cast
+
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, marshal_with, reqparse  # type: ignore
+from sqlalchemy.orm import Session
+from werkzeug.exceptions import Forbidden
+
+from controllers.console import api
+from controllers.console.datasets.wraps import get_rag_pipeline
+from controllers.console.wraps import (
+    account_initialization_required,
+    setup_required,
+)
+from extensions.ext_database import db
+from fields.rag_pipeline_fields import pipeline_import_check_dependencies_fields, pipeline_import_fields
+from libs.login import login_required
+from models import Account
+from models.dataset import Pipeline
+from services.app_dsl_service import ImportStatus
+from services.rag_pipeline.rag_pipeline_dsl_service import RagPipelineDslService
+
+
+class RagPipelineImportApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(pipeline_import_fields)
+    def post(self):
+        # Check user role first
+        if not current_user.is_editor:
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("mode", type=str, required=True, location="json")
+        parser.add_argument("yaml_content", type=str, location="json")
+        parser.add_argument("yaml_url", type=str, location="json")
+        parser.add_argument("name", type=str, location="json")
+        parser.add_argument("description", type=str, location="json")
+        parser.add_argument("icon_type", type=str, location="json")
+        parser.add_argument("icon", type=str, location="json")
+        parser.add_argument("icon_background", type=str, location="json")
+        parser.add_argument("pipeline_id", type=str, location="json")
+        args = parser.parse_args()
+
+        # Create service with session
+        with Session(db.engine) as session:
+            import_service = RagPipelineDslService(session)
+            # Import app
+            account = cast(Account, current_user)
+            result = import_service.import_rag_pipeline(
+                account=account,
+                import_mode=args["mode"],
+                yaml_content=args.get("yaml_content"),
+                yaml_url=args.get("yaml_url"),
+                pipeline_id=args.get("pipeline_id"),
+            )
+            session.commit()
+
+        # Return appropriate status code based on result
+        status = result.status
+        if status == ImportStatus.FAILED.value:
+            return result.model_dump(mode="json"), 400
+        elif status == ImportStatus.PENDING.value:
+            return result.model_dump(mode="json"), 202
+        return result.model_dump(mode="json"), 200
+
+
+class RagPipelineImportConfirmApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(pipeline_import_fields)
+    def post(self, import_id):
+        # Check user role first
+        if not current_user.is_editor:
+            raise Forbidden()
+
+        # Create service with session
+        with Session(db.engine) as session:
+            import_service = RagPipelineDslService(session)
+            # Confirm import
+            account = cast(Account, current_user)
+            result = import_service.confirm_import(import_id=import_id, account=account)
+            session.commit()
+
+        # Return appropriate status code based on result
+        if result.status == ImportStatus.FAILED.value:
+            return result.model_dump(mode="json"), 400
+        return result.model_dump(mode="json"), 200
+
+
+class RagPipelineImportCheckDependenciesApi(Resource):
+    @setup_required
+    @login_required
+    @get_rag_pipeline
+    @account_initialization_required
+    @marshal_with(pipeline_import_check_dependencies_fields)
+    def get(self, pipeline: Pipeline):
+        if not current_user.is_editor:
+            raise Forbidden()
+
+        with Session(db.engine) as session:
+            import_service = RagPipelineDslService(session)
+            result = import_service.check_dependencies(pipeline=pipeline)
+
+        return result.model_dump(mode="json"), 200
+
+
+class RagPipelineExportApi(Resource):
+    @setup_required
+    @login_required
+    @get_rag_pipeline
+    @account_initialization_required
+    def get(self, pipeline: Pipeline):
+        if not current_user.is_editor:
+            raise Forbidden()
+
+            # Add include_secret params
+        parser = reqparse.RequestParser()
+        parser.add_argument("include_secret", type=bool, default=False, location="args")
+        args = parser.parse_args()
+
+        with Session(db.engine) as session:
+            export_service = RagPipelineDslService(session)
+            result = export_service.export_rag_pipeline_dsl(pipeline=pipeline, include_secret=args["include_secret"])
+
+        return {"data": result}, 200
+
+
+# Import Rag Pipeline
+api.add_resource(
+    RagPipelineImportApi,
+    "/rag/pipelines/imports",
+)
+api.add_resource(
+    RagPipelineImportConfirmApi,
+    "/rag/pipelines/imports/<string:import_id>/confirm",
+)
+api.add_resource(
+    RagPipelineImportCheckDependenciesApi,
+    "/rag/pipelines/imports/<string:pipeline_id>/check-dependencies",
+)
+api.add_resource(
+    RagPipelineExportApi,
+    "/rag/pipelines/<string:pipeline_id>/exports",
+)
@@ -0,0 +1,43 @@
+from collections.abc import Callable
+from functools import wraps
+from typing import Optional
+
+from controllers.console.datasets.error import PipelineNotFoundError
+from extensions.ext_database import db
+from libs.login import current_user
+from models.dataset import Pipeline
+
+
+def get_rag_pipeline(
+    view: Optional[Callable] = None,
+):
+    def decorator(view_func):
+        @wraps(view_func)
+        def decorated_view(*args, **kwargs):
+            if not kwargs.get("pipeline_id"):
+                raise ValueError("missing pipeline_id in path parameters")
+
+            pipeline_id = kwargs.get("pipeline_id")
+            pipeline_id = str(pipeline_id)
+
+            del kwargs["pipeline_id"]
+
+            pipeline = (
+                db.session.query(Pipeline)
+                .filter(Pipeline.id == pipeline_id, Pipeline.tenant_id == current_user.current_tenant_id)
+                .first()
+            )
+
+            if not pipeline:
+                raise PipelineNotFoundError()
+
+            kwargs["pipeline"] = pipeline
+
+            return view_func(*args, **kwargs)
+
+        return decorated_view
+
+    if view is None:
+        return decorator
+    else:
+        return decorator(view)
@@ -46,6 +46,18 @@ class NotAllowedCreateWorkspace(BaseHTTPException):
    code = 400


+class WorkspaceMembersLimitExceeded(BaseHTTPException):
+    error_code = "limit_exceeded"
+    description = "Unable to add member because the maximum workspace's member limit was exceeded"
+    code = 400
+
+
+class WorkspacesLimitExceeded(BaseHTTPException):
+    error_code = "limit_exceeded"
+    description = "Unable to create workspace because the maximum workspace limit was exceeded"
+    code = 400
+
+
 class AccountBannedError(BaseHTTPException):
    error_code = "account_banned"
    description = "Account is banned."
@@ -23,3 +23,9 @@ class AppSuggestedQuestionsAfterAnswerDisabledError(BaseHTTPException):
    error_code = "app_suggested_questions_after_answer_disabled"
    description = "Function Suggested questions after answer disabled."
    code = 403
+
+
+class AppAccessDeniedError(BaseHTTPException):
+    error_code = "access_denied"
+    description = "App access denied."
+    code = 403
@@ -1,3 +1,4 @@
+import logging
 from datetime import UTC, datetime
 from typing import Any

@@ -15,6 +16,11 @@ from fields.installed_app_fields import installed_app_list_fields
 from libs.login import login_required
 from models import App, InstalledApp, RecommendedApp
 from services.account_service import TenantService
+from services.app_service import AppService
+from services.enterprise.enterprise_service import EnterpriseService
+from services.feature_service import FeatureService
+
+logger = logging.getLogger(__name__)


 class InstalledAppsListApi(Resource):
@@ -48,6 +54,28 @@ class InstalledAppsListApi(Resource):
            for installed_app in installed_apps
            if installed_app.app is not None
        ]
+
+        # filter out apps that user doesn't have access to
+        if FeatureService.get_system_features().webapp_auth.enabled:
+            user_id = current_user.id
+            res = []
+            app_ids = [installed_app["app"].id for installed_app in installed_app_list]
+            webapp_settings = EnterpriseService.WebAppAuth.batch_get_app_access_mode_by_id(app_ids)
+            for installed_app in installed_app_list:
+                webapp_setting = webapp_settings.get(installed_app["app"].id)
+                if not webapp_setting:
+                    continue
+                if webapp_setting.access_mode == "sso_verified":
+                    continue
+                app_code = AppService.get_app_code_by_id(str(installed_app["app"].id))
+                if EnterpriseService.WebAppAuth.is_user_allowed_to_access_webapp(
+                    user_id=user_id,
+                    app_code=app_code,
+                ):
+                    res.append(installed_app)
+            installed_app_list = res
+            logger.debug(f"installed_app_list: {installed_app_list}, user_id: {user_id}")
+
        installed_app_list.sort(
            key=lambda app: (
                -app["is_pinned"],
@@ -4,10 +4,14 @@ from flask_login import current_user
 from flask_restful import Resource
 from werkzeug.exceptions import NotFound

+from controllers.console.explore.error import AppAccessDeniedError
 from controllers.console.wraps import account_initialization_required
 from extensions.ext_database import db
 from libs.login import login_required
 from models import InstalledApp
+from services.app_service import AppService
+from services.enterprise.enterprise_service import EnterpriseService
+from services.feature_service import FeatureService


 def installed_app_required(view=None):
@@ -48,6 +52,36 @@ def installed_app_required(view=None):
    return decorator


+def user_allowed_to_access_app(view=None):
+    def decorator(view):
+        @wraps(view)
+        def decorated(installed_app: InstalledApp, *args, **kwargs):
+            feature = FeatureService.get_system_features()
+            if feature.webapp_auth.enabled:
+                app_id = installed_app.app_id
+                app_code = AppService.get_app_code_by_id(app_id)
+                res = EnterpriseService.WebAppAuth.is_user_allowed_to_access_webapp(
+                    user_id=str(current_user.id),
+                    app_code=app_code,
+                )
+                if not res:
+                    raise AppAccessDeniedError()
+
+            return view(installed_app, *args, **kwargs)
+
+        return decorated
+
+    if view:
+        return decorator(view)
+    return decorator
+
+
 class InstalledAppResource(Resource):
    # must be reversed if there are multiple decorators
-    method_decorators = [installed_app_required, account_initialization_required, login_required]
+
+    method_decorators = [
+        user_allowed_to_access_app,
+        installed_app_required,
+        account_initialization_required,
+        login_required,
+    ]
@@ -18,7 +18,7 @@ class VersionApi(Resource):
        check_update_url = dify_config.CHECK_UPDATE_URL

        result = {
-            "version": dify_config.CURRENT_VERSION,
+            "version": dify_config.project.version,
            "release_date": "",
            "release_notes": "",
            "can_auto_update": False,
@@ -15,7 +15,7 @@ class LoadBalancingCredentialsValidateApi(Resource):
    @login_required
    @account_initialization_required
    def post(self, provider: str):
-        if not TenantAccountRole.is_privileged_role(current_user.current_tenant.current_role):
+        if not TenantAccountRole.is_privileged_role(current_user.current_role):
            raise Forbidden()

        tenant_id = current_user.current_tenant_id
@@ -64,7 +64,7 @@ class LoadBalancingConfigCredentialsValidateApi(Resource):
    @login_required
    @account_initialization_required
    def post(self, provider: str, config_id: str):
-        if not TenantAccountRole.is_privileged_role(current_user.current_tenant.current_role):
+        if not TenantAccountRole.is_privileged_role(current_user.current_role):
            raise Forbidden()

        tenant_id = current_user.current_tenant_id
@@ -6,6 +6,7 @@ from flask_restful import Resource, abort, marshal_with, reqparse
 import services
 from configs import dify_config
 from controllers.console import api
+from controllers.console.error import WorkspaceMembersLimitExceeded
 from controllers.console.wraps import (
    account_initialization_required,
    cloud_edition_billing_resource_check,
@@ -17,6 +18,7 @@ from libs.login import login_required
 from models.account import Account, TenantAccountRole
 from services.account_service import RegisterService, TenantService
 from services.errors.account import AccountAlreadyInTenantError
+from services.feature_service import FeatureService


 class MemberListApi(Resource):
@@ -54,6 +56,12 @@ class MemberInviteEmailApi(Resource):
        inviter = current_user
        invitation_results = []
        console_web_url = dify_config.CONSOLE_WEB_URL
+
+        workspace_members = FeatureService.get_features(tenant_id=inviter.current_tenant.id).workspace_members
+
+        if not workspace_members.is_available(len(invitee_emails)):
+            raise WorkspaceMembersLimitExceeded()
+
        for invitee_email in invitee_emails:
            try:
                token = RegisterService.invite_new_member(
@@ -77,6 +85,7 @@ class MemberInviteEmailApi(Resource):
        return {
            "result": "success",
            "invitation_results": invitation_results,
+            "tenant_id": str(current_user.current_tenant.id),
        }, 201


@@ -102,7 +111,7 @@ class MemberCancelInviteApi(Resource):
            except Exception as e:
                raise ValueError(str(e))

-        return {"result": "success"}, 204
+        return {"result": "success", "tenant_id": str(current_user.current_tenant.id)}, 200


 class MemberUpdateRoleApi(Resource):
@@ -13,6 +13,7 @@ from core.model_runtime.utils.encoders import jsonable_encoder
 from core.plugin.impl.exc import PluginDaemonClientSideError
 from libs.login import login_required
 from models.account import TenantPluginPermission
+from services.plugin.plugin_parameter_service import PluginParameterService
 from services.plugin.plugin_permission_service import PluginPermissionService
 from services.plugin.plugin_service import PluginService

@@ -41,12 +42,16 @@ class PluginListApi(Resource):
    @account_initialization_required
    def get(self):
        tenant_id = current_user.current_tenant_id
+        parser = reqparse.RequestParser()
+        parser.add_argument("page", type=int, required=False, location="args", default=1)
+        parser.add_argument("page_size", type=int, required=False, location="args", default=256)
+        args = parser.parse_args()
        try:
-            plugins = PluginService.list(tenant_id)
+            plugins_with_total = PluginService.list_with_total(tenant_id, args["page"], args["page_size"])
        except PluginDaemonClientSideError as e:
            raise ValueError(e)

-        return jsonable_encoder({"plugins": plugins})
+        return jsonable_encoder({"plugins": plugins_with_total.list, "total": plugins_with_total.total})


 class PluginListLatestVersionsApi(Resource):
@@ -493,6 +498,42 @@ class PluginFetchPermissionApi(Resource):
        )


+class PluginFetchDynamicSelectOptionsApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+        # check if the user is admin or owner
+        if not current_user.is_admin_or_owner:
+            raise Forbidden()
+
+        tenant_id = current_user.current_tenant_id
+        user_id = current_user.id
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("plugin_id", type=str, required=True, location="args")
+        parser.add_argument("provider", type=str, required=True, location="args")
+        parser.add_argument("action", type=str, required=True, location="args")
+        parser.add_argument("parameter", type=str, required=True, location="args")
+        parser.add_argument("provider_type", type=str, required=True, location="args")
+        args = parser.parse_args()
+
+        try:
+            options = PluginParameterService.get_dynamic_select_options(
+                tenant_id,
+                user_id,
+                args["plugin_id"],
+                args["provider"],
+                args["action"],
+                args["parameter"],
+                args["provider_type"],
+            )
+        except PluginDaemonClientSideError as e:
+            raise ValueError(e)
+
+        return jsonable_encoder({"options": options})
+
+
 api.add_resource(PluginDebuggingKeyApi, "/workspaces/current/plugin/debugging-key")
 api.add_resource(PluginListApi, "/workspaces/current/plugin/list")
 api.add_resource(PluginListLatestVersionsApi, "/workspaces/current/plugin/list/latest-versions")
@@ -517,3 +558,5 @@ api.add_resource(PluginFetchMarketplacePkgApi, "/workspaces/current/plugin/marke

 api.add_resource(PluginChangePermissionApi, "/workspaces/current/plugin/permission/change")
 api.add_resource(PluginFetchPermissionApi, "/workspaces/current/plugin/permission/fetch")
+
+api.add_resource(PluginFetchDynamicSelectOptionsApi, "/workspaces/current/plugin/parameters/dynamic-options")
@@ -68,16 +68,24 @@ class TenantListApi(Resource):
    @account_initialization_required
    def get(self):
        tenants = TenantService.get_join_tenants(current_user)
+        tenant_dicts = []

        for tenant in tenants:
            features = FeatureService.get_features(tenant.id)
-            if features.billing.enabled:
-                tenant.plan = features.billing.subscription.plan
-            else:
-                tenant.plan = "sandbox"
-            if tenant.id == current_user.current_tenant_id:
-                tenant.current = True  # Set current=True for current tenant
-        return {"workspaces": marshal(tenants, tenants_fields)}, 200
+
+            # Create a dictionary with tenant attributes
+            tenant_dict = {
+                "id": tenant.id,
+                "name": tenant.name,
+                "status": tenant.status,
+                "created_at": tenant.created_at,
+                "plan": features.billing.subscription.plan if features.billing.enabled else "sandbox",
+                "current": tenant.id == current_user.current_tenant_id,
+            }
+
+            tenant_dicts.append(tenant_dict)
+
+        return {"workspaces": marshal(tenant_dicts, tenants_fields)}, 200


 class WorkspaceListApi(Resource):
@@ -44,6 +44,17 @@ def only_edition_cloud(view):
    return decorated


+def only_edition_enterprise(view):
+    @wraps(view)
+    def decorated(*args, **kwargs):
+        if not dify_config.ENTERPRISE_ENABLED:
+            abort(404)
+
+        return view(*args, **kwargs)
+
+    return decorated
+
+
 def only_edition_self_hosted(view):
    @wraps(view)
    def decorated(*args, **kwargs):
@@ -64,9 +64,24 @@ class PluginUploadFileApi(Resource):

            extension = guess_extension(tool_file.mimetype) or ".bin"
            preview_url = ToolFileManager.sign_file(tool_file_id=tool_file.id, extension=extension)
-            tool_file.mime_type = mimetype
-            tool_file.extension = extension
-            tool_file.preview_url = preview_url
+
+            # Create a dictionary with all the necessary attributes
+            result = {
+                "id": tool_file.id,
+                "user_id": tool_file.user_id,
+                "tenant_id": tool_file.tenant_id,
+                "conversation_id": tool_file.conversation_id,
+                "file_key": tool_file.file_key,
+                "mimetype": tool_file.mimetype,
+                "original_url": tool_file.original_url,
+                "name": tool_file.name,
+                "size": tool_file.size,
+                "mime_type": mimetype,
+                "extension": extension,
+                "preview_url": preview_url,
+            }
+
+            return result, 201
        except services.errors.file.FileTooLargeError as file_too_large_error:
            raise FileTooLargeError(file_too_large_error.description)
        except services.errors.file.UnsupportedFileTypeError:
@@ -5,5 +5,6 @@ from libs.external_api import ExternalApi
 bp = Blueprint("inner_api", __name__, url_prefix="/inner/api")
 api = ExternalApi(bp)

+from . import mail
 from .plugin import plugin
 from .workspace import workspace
@@ -0,0 +1,27 @@
+from flask_restful import (
+    Resource,  # type: ignore
+    reqparse,
+)
+
+from controllers.console.wraps import setup_required
+from controllers.inner_api import api
+from controllers.inner_api.wraps import enterprise_inner_api_only
+from services.enterprise.mail_service import DifyMail, EnterpriseMailService
+
+
+class EnterpriseMail(Resource):
+    @setup_required
+    @enterprise_inner_api_only
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("to", type=str, action="append", required=True)
+        parser.add_argument("subject", type=str, required=True)
+        parser.add_argument("body", type=str, required=True)
+        parser.add_argument("substitutions", type=dict, required=False)
+        args = parser.parse_args()
+
+        EnterpriseMailService.send_mail(DifyMail(**args))
+        return {"message": "success"}, 200
+
+
+api.add_resource(EnterpriseMail, "/enterprise/mail")
@@ -17,6 +17,7 @@ from core.plugin.entities.request import (
    RequestInvokeApp,
    RequestInvokeEncrypt,
    RequestInvokeLLM,
+    RequestInvokeLLMWithStructuredOutput,
    RequestInvokeModeration,
    RequestInvokeParameterExtractorNode,
    RequestInvokeQuestionClassifierNode,
@@ -29,7 +30,7 @@ from core.plugin.entities.request import (
    RequestRequestUploadFile,
 )
 from core.tools.entities.tool_entities import ToolProviderType
-from libs.helper import compact_generate_response
+from libs.helper import length_prefixed_response
 from models.account import Account, Tenant
 from models.model import EndUser

@@ -44,7 +45,22 @@ class PluginInvokeLLMApi(Resource):
            response = PluginModelBackwardsInvocation.invoke_llm(user_model.id, tenant_model, payload)
            return PluginModelBackwardsInvocation.convert_to_event_stream(response)

-        return compact_generate_response(generator())
+        return length_prefixed_response(0xF, generator())
+
+
+class PluginInvokeLLMWithStructuredOutputApi(Resource):
+    @setup_required
+    @plugin_inner_api_only
+    @get_user_tenant
+    @plugin_data(payload_type=RequestInvokeLLMWithStructuredOutput)
+    def post(self, user_model: Account | EndUser, tenant_model: Tenant, payload: RequestInvokeLLMWithStructuredOutput):
+        def generator():
+            response = PluginModelBackwardsInvocation.invoke_llm_with_structured_output(
+                user_model.id, tenant_model, payload
+            )
+            return PluginModelBackwardsInvocation.convert_to_event_stream(response)
+
+        return length_prefixed_response(0xF, generator())


 class PluginInvokeTextEmbeddingApi(Resource):
@@ -101,7 +117,7 @@ class PluginInvokeTTSApi(Resource):
            )
            return PluginModelBackwardsInvocation.convert_to_event_stream(response)

-        return compact_generate_response(generator())
+        return length_prefixed_response(0xF, generator())


 class PluginInvokeSpeech2TextApi(Resource):
@@ -162,7 +178,7 @@ class PluginInvokeToolApi(Resource):
                ),
            )

-        return compact_generate_response(generator())
+        return length_prefixed_response(0xF, generator())


 class PluginInvokeParameterExtractorNodeApi(Resource):
@@ -228,7 +244,7 @@ class PluginInvokeAppApi(Resource):
            files=payload.files,
        )

-        return compact_generate_response(PluginAppBackwardsInvocation.convert_to_event_stream(response))
+        return length_prefixed_response(0xF, PluginAppBackwardsInvocation.convert_to_event_stream(response))


 class PluginInvokeEncryptApi(Resource):
@@ -291,6 +307,7 @@ class PluginFetchAppInfoApi(Resource):


 api.add_resource(PluginInvokeLLMApi, "/invoke/llm")
+api.add_resource(PluginInvokeLLMWithStructuredOutputApi, "/invoke/llm/structured-output")
 api.add_resource(PluginInvokeTextEmbeddingApi, "/invoke/text-embedding")
 api.add_resource(PluginInvokeRerankApi, "/invoke/rerank")
 api.add_resource(PluginInvokeTTSApi, "/invoke/tts")
@@ -2,12 +2,14 @@ from collections.abc import Callable
 from functools import wraps
 from typing import Optional

-from flask import request
+from flask import current_app, request
+from flask_login import user_logged_in
 from flask_restful import reqparse
 from pydantic import BaseModel
 from sqlalchemy.orm import Session

 from extensions.ext_database import db
+from libs.login import _get_user
 from models.account import Account, Tenant
 from models.model import EndUser
 from services.account_service import AccountService
@@ -30,6 +32,7 @@ def get_user(tenant_id: str, user_id: str | None) -> Account | EndUser:
                    )
                    session.add(user_model)
                    session.commit()
+                    session.refresh(user_model)
            else:
                user_model = AccountService.load_user(user_id)
                if not user_model:
@@ -80,7 +83,12 @@ def get_user_tenant(view: Optional[Callable] = None):
                raise ValueError("tenant not found")

            kwargs["tenant_model"] = tenant_model
-            kwargs["user_model"] = get_user(tenant_id, user_id)
+
+            user = get_user(tenant_id, user_id)
+            kwargs["user_model"] = user
+
+            current_app.login_manager._update_request_context_with_user(user)  # type: ignore
+            user_logged_in.send(current_app._get_current_object(), user=_get_user())  # type: ignore

            return view_func(*args, **kwargs)

@@ -29,7 +29,19 @@ class EnterpriseWorkspace(Resource):

        tenant_was_created.send(tenant)

-        return {"message": "enterprise workspace created."}
+        resp = {
+            "id": tenant.id,
+            "name": tenant.name,
+            "plan": tenant.plan,
+            "status": tenant.status,
+            "created_at": tenant.created_at.isoformat() + "Z" if tenant.created_at else None,
+            "updated_at": tenant.updated_at.isoformat() + "Z" if tenant.updated_at else None,
+        }
+
+        return {
+            "message": "enterprise workspace created.",
+            "tenant": resp,
+        }


 class EnterpriseWorkspaceNoOwnerEmail(Resource):
@@ -3,19 +3,19 @@ from flask_restful import Resource, marshal, marshal_with, reqparse
 from werkzeug.exceptions import Forbidden

 from controllers.service_api import api
-from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
+from controllers.service_api.wraps import validate_app_token
 from extensions.ext_redis import redis_client
 from fields.annotation_fields import (
    annotation_fields,
 )
 from libs.login import current_user
-from models.model import App, EndUser
+from models.model import App
 from services.annotation_service import AppAnnotationService


 class AnnotationReplyActionApi(Resource):
-    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON))
-    def post(self, app_model: App, end_user: EndUser, action):
+    @validate_app_token
+    def post(self, app_model: App, action):
        parser = reqparse.RequestParser()
        parser.add_argument("score_threshold", required=True, type=float, location="json")
        parser.add_argument("embedding_provider_name", required=True, type=str, location="json")
@@ -31,8 +31,8 @@ class AnnotationReplyActionApi(Resource):


 class AnnotationReplyActionStatusApi(Resource):
-    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.QUERY))
-    def get(self, app_model: App, end_user: EndUser, job_id, action):
+    @validate_app_token
+    def get(self, app_model: App, job_id, action):
        job_id = str(job_id)
        app_annotation_job_key = "{}_app_annotation_job_{}".format(action, str(job_id))
        cache_result = redis_client.get(app_annotation_job_key)
@@ -49,8 +49,8 @@ class AnnotationReplyActionStatusApi(Resource):


 class AnnotationListApi(Resource):
-    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.QUERY))
-    def get(self, app_model: App, end_user: EndUser):
+    @validate_app_token
+    def get(self, app_model: App):
        page = request.args.get("page", default=1, type=int)
        limit = request.args.get("limit", default=20, type=int)
        keyword = request.args.get("keyword", default="", type=str)
@@ -65,9 +65,9 @@ class AnnotationListApi(Resource):
        }
        return response, 200

-    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON))
+    @validate_app_token
    @marshal_with(annotation_fields)
-    def post(self, app_model: App, end_user: EndUser):
+    def post(self, app_model: App):
        parser = reqparse.RequestParser()
        parser.add_argument("question", required=True, type=str, location="json")
        parser.add_argument("answer", required=True, type=str, location="json")
@@ -77,9 +77,9 @@ class AnnotationListApi(Resource):


 class AnnotationUpdateDeleteApi(Resource):
-    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON))
+    @validate_app_token
    @marshal_with(annotation_fields)
-    def put(self, app_model: App, end_user: EndUser, annotation_id):
+    def put(self, app_model: App, annotation_id):
        if not current_user.is_editor:
            raise Forbidden()

@@ -91,8 +91,8 @@ class AnnotationUpdateDeleteApi(Resource):
        annotation = AppAnnotationService.update_app_annotation_directly(args, app_model.id, annotation_id)
        return annotation

-    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.QUERY))
-    def delete(self, app_model: App, end_user: EndUser, annotation_id):
+    @validate_app_token
+    def delete(self, app_model: App, annotation_id):
        if not current_user.is_editor:
            raise Forbidden()

@@ -47,7 +47,13 @@ class AppInfoApi(Resource):
    def get(self, app_model: App):
        """Get app information"""
        tags = [tag.name for tag in app_model.tags]
-        return {"name": app_model.name, "description": app_model.description, "tags": tags, "mode": app_model.mode}
+        return {
+            "name": app_model.name,
+            "description": app_model.description,
+            "tags": tags,
+            "mode": app_model.mode,
+            "author_name": app_model.author_name,
+        }


 api.add_resource(AppParameterApi, "/parameters")
@@ -24,12 +24,13 @@ from core.errors.error import (
    QuotaExceededError,
 )
 from core.model_runtime.errors.invoke import InvokeError
+from core.workflow.entities.workflow_execution import WorkflowExecutionStatus
 from extensions.ext_database import db
 from fields.workflow_app_log_fields import workflow_app_log_pagination_fields
 from libs import helper
 from libs.helper import TimestampField
 from models.model import App, AppMode, EndUser
-from models.workflow import WorkflowRun, WorkflowRunStatus
+from models.workflow import WorkflowRun
 from services.app_generate_service import AppGenerateService
 from services.errors.llm import InvokeRateLimitError
 from services.workflow_app_service import WorkflowAppService
@@ -134,11 +135,25 @@ class WorkflowAppLogApi(Resource):
        parser.add_argument("status", type=str, choices=["succeeded", "failed", "stopped"], location="args")
        parser.add_argument("created_at__before", type=str, location="args")
        parser.add_argument("created_at__after", type=str, location="args")
+        parser.add_argument(
+            "created_by_end_user_session_id",
+            type=str,
+            location="args",
+            required=False,
+            default=None,
+        )
+        parser.add_argument(
+            "created_by_account",
+            type=str,
+            location="args",
+            required=False,
+            default=None,
+        )
        parser.add_argument("page", type=int_range(1, 99999), default=1, location="args")
        parser.add_argument("limit", type=int_range(1, 100), default=20, location="args")
        args = parser.parse_args()

-        args.status = WorkflowRunStatus(args.status) if args.status else None
+        args.status = WorkflowExecutionStatus(args.status) if args.status else None
        if args.created_at__before:
            args.created_at__before = isoparse(args.created_at__before)

@@ -157,6 +172,8 @@ class WorkflowAppLogApi(Resource):
                created_at_after=args.created_at__after,
                page=args.page,
                limit=args.limit,
+                created_by_end_user_session_id=args.created_by_end_user_session_id,
+                created_by_account=args.created_by_account,
            )

            return workflow_app_log_pagination
@@ -1,19 +1,25 @@
 from flask import request
-from flask_restful import marshal, reqparse
+from flask_restful import marshal, marshal_with, reqparse
 from werkzeug.exceptions import Forbidden, NotFound

 import services.dataset_service
 from controllers.service_api import api
-from controllers.service_api.dataset.error import DatasetInUseError, DatasetNameDuplicateError
-from controllers.service_api.wraps import DatasetApiResource
+from controllers.service_api.dataset.error import DatasetInUseError, DatasetNameDuplicateError, InvalidActionError
+from controllers.service_api.wraps import (
+    DatasetApiResource,
+    cloud_edition_billing_rate_limit_check,
+    validate_dataset_token,
+)
 from core.model_runtime.entities.model_entities import ModelType
 from core.plugin.entities.plugin import ModelProviderID
 from core.provider_manager import ProviderManager
 from fields.dataset_fields import dataset_detail_fields
+from fields.tag_fields import tag_fields
 from libs.login import current_user
 from models.dataset import Dataset, DatasetPermissionEnum
-from services.dataset_service import DatasetPermissionService, DatasetService
+from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService
 from services.entities.knowledge_entities.knowledge_entities import RetrievalModel
+from services.tag_service import TagService


 def _validate_name(name):
@@ -68,6 +74,7 @@ class DatasetListApi(DatasetApiResource):
        response = {"data": data, "has_more": len(datasets) == limit, "limit": limit, "total": total, "page": page}
        return response, 200

+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def post(self, tenant_id):
        """Resource for creating datasets."""
        parser = reqparse.RequestParser()
@@ -126,6 +133,22 @@ class DatasetListApi(DatasetApiResource):
        parser.add_argument("embedding_model_provider", type=str, required=False, nullable=True, location="json")

        args = parser.parse_args()
+
+        if args.get("embedding_model_provider"):
+            DatasetService.check_embedding_model_setting(
+                tenant_id, args.get("embedding_model_provider"), args.get("embedding_model")
+            )
+        if (
+            args.get("retrieval_model")
+            and args.get("retrieval_model").get("reranking_model")
+            and args.get("retrieval_model").get("reranking_model").get("reranking_provider_name")
+        ):
+            DatasetService.check_reranking_model_setting(
+                tenant_id,
+                args.get("retrieval_model").get("reranking_model").get("reranking_provider_name"),
+                args.get("retrieval_model").get("reranking_model").get("reranking_model_name"),
+            )
+
        try:
            dataset = DatasetService.create_empty_dataset(
                tenant_id=tenant_id,
@@ -191,6 +214,7 @@ class DatasetApi(DatasetApiResource):

        return data, 200

+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def patch(self, _, dataset_id):
        dataset_id_str = str(dataset_id)
        dataset = DatasetService.get_dataset(dataset_id_str)
@@ -257,10 +281,20 @@ class DatasetApi(DatasetApiResource):
        data = request.get_json()

        # check embedding model setting
-        if data.get("indexing_technique") == "high_quality":
+        if data.get("indexing_technique") == "high_quality" or data.get("embedding_model_provider"):
            DatasetService.check_embedding_model_setting(
                dataset.tenant_id, data.get("embedding_model_provider"), data.get("embedding_model")
            )
+        if (
+            data.get("retrieval_model")
+            and data.get("retrieval_model").get("reranking_model")
+            and data.get("retrieval_model").get("reranking_model").get("reranking_provider_name")
+        ):
+            DatasetService.check_reranking_model_setting(
+                dataset.tenant_id,
+                data.get("retrieval_model").get("reranking_model").get("reranking_provider_name"),
+                data.get("retrieval_model").get("reranking_model").get("reranking_model_name"),
+            )

        # The role of the current user in the ta table must be admin, owner, editor, or dataset_operator
        DatasetPermissionService.check_permission(
@@ -291,6 +325,7 @@ class DatasetApi(DatasetApiResource):

        return result_data, 200

+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def delete(self, _, dataset_id):
        """
        Deletes a dataset given its ID.
@@ -320,5 +355,186 @@ class DatasetApi(DatasetApiResource):
            raise DatasetInUseError()


+class DocumentStatusApi(DatasetApiResource):
+    """Resource for batch document status operations."""
+
+    def patch(self, tenant_id, dataset_id, action):
+        """
+        Batch update document status.
+
+        Args:
+            tenant_id: tenant id
+            dataset_id: dataset id
+            action: action to perform (enable, disable, archive, un_archive)
+
+        Returns:
+            dict: A dictionary with a key 'result' and a value 'success'
+            int: HTTP status code 200 indicating that the operation was successful.
+
+        Raises:
+            NotFound: If the dataset with the given ID does not exist.
+            Forbidden: If the user does not have permission.
+            InvalidActionError: If the action is invalid or cannot be performed.
+        """
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+
+        # Check user's permission
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+
+        # Check dataset model setting
+        DatasetService.check_dataset_model_setting(dataset)
+
+        # Get document IDs from request body
+        data = request.get_json()
+        document_ids = data.get("document_ids", [])
+
+        try:
+            DocumentService.batch_update_document_status(dataset, document_ids, action, current_user)
+        except services.errors.document.DocumentIndexingError as e:
+            raise InvalidActionError(str(e))
+        except ValueError as e:
+            raise InvalidActionError(str(e))
+
+        return {"result": "success"}, 200
+
+
+class DatasetTagsApi(DatasetApiResource):
+    @validate_dataset_token
+    @marshal_with(tag_fields)
+    def get(self, _, dataset_id):
+        """Get all knowledge type tags."""
+        tags = TagService.get_tags("knowledge", current_user.current_tenant_id)
+
+        return tags, 200
+
+    @validate_dataset_token
+    def post(self, _, dataset_id):
+        """Add a knowledge type tag."""
+        if not (current_user.is_editor or current_user.is_dataset_editor):
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument(
+            "name",
+            nullable=False,
+            required=True,
+            help="Name must be between 1 to 50 characters.",
+            type=DatasetTagsApi._validate_tag_name,
+        )
+
+        args = parser.parse_args()
+        args["type"] = "knowledge"
+        tag = TagService.save_tags(args)
+
+        response = {"id": tag.id, "name": tag.name, "type": tag.type, "binding_count": 0}
+
+        return response, 200
+
+    @validate_dataset_token
+    def patch(self, _, dataset_id):
+        if not (current_user.is_editor or current_user.is_dataset_editor):
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument(
+            "name",
+            nullable=False,
+            required=True,
+            help="Name must be between 1 to 50 characters.",
+            type=DatasetTagsApi._validate_tag_name,
+        )
+        parser.add_argument("tag_id", nullable=False, required=True, help="Id of a tag.", type=str)
+        args = parser.parse_args()
+        args["type"] = "knowledge"
+        tag = TagService.update_tags(args, args.get("tag_id"))
+
+        binding_count = TagService.get_tag_binding_count(args.get("tag_id"))
+
+        response = {"id": tag.id, "name": tag.name, "type": tag.type, "binding_count": binding_count}
+
+        return response, 200
+
+    @validate_dataset_token
+    def delete(self, _, dataset_id):
+        """Delete a knowledge type tag."""
+        if not current_user.is_editor:
+            raise Forbidden()
+        parser = reqparse.RequestParser()
+        parser.add_argument("tag_id", nullable=False, required=True, help="Id of a tag.", type=str)
+        args = parser.parse_args()
+        TagService.delete_tag(args.get("tag_id"))
+
+        return 204
+
+    @staticmethod
+    def _validate_tag_name(name):
+        if not name or len(name) < 1 or len(name) > 50:
+            raise ValueError("Name must be between 1 to 50 characters.")
+        return name
+
+
+class DatasetTagBindingApi(DatasetApiResource):
+    @validate_dataset_token
+    def post(self, _, dataset_id):
+        # The role of the current user in the ta table must be admin, owner, editor, or dataset_operator
+        if not (current_user.is_editor or current_user.is_dataset_editor):
+            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 Dataset ID is required."
+        )
+
+        args = parser.parse_args()
+        args["type"] = "knowledge"
+        TagService.save_tag_binding(args)
+
+        return 204
+
+
+class DatasetTagUnbindingApi(DatasetApiResource):
+    @validate_dataset_token
+    def post(self, _, dataset_id):
+        # The role of the current user in the ta table must be admin, owner, editor, or dataset_operator
+        if not (current_user.is_editor or current_user.is_dataset_editor):
+            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.")
+
+        args = parser.parse_args()
+        args["type"] = "knowledge"
+        TagService.delete_tag_binding(args)
+
+        return 204
+
+
+class DatasetTagsBindingStatusApi(DatasetApiResource):
+    @validate_dataset_token
+    def get(self, _, *args, **kwargs):
+        """Get all knowledge type tags."""
+        dataset_id = kwargs.get("dataset_id")
+        tags = TagService.get_tags_by_target_id("knowledge", current_user.current_tenant_id, str(dataset_id))
+        tags_list = [{"id": tag.id, "name": tag.name} for tag in tags]
+        response = {"data": tags_list, "total": len(tags)}
+        return response, 200
+
+
 api.add_resource(DatasetListApi, "/datasets")
 api.add_resource(DatasetApi, "/datasets/<uuid:dataset_id>")
+api.add_resource(DocumentStatusApi, "/datasets/<uuid:dataset_id>/documents/status/<string:action>")
+api.add_resource(DatasetTagsApi, "/datasets/tags")
+api.add_resource(DatasetTagBindingApi, "/datasets/tags/binding")
+api.add_resource(DatasetTagUnbindingApi, "/datasets/tags/unbinding")
+api.add_resource(DatasetTagsBindingStatusApi, "/datasets/<uuid:dataset_id>/tags")
@@ -3,7 +3,7 @@ import json
 from flask import request
 from flask_restful import marshal, reqparse
 from sqlalchemy import desc, select
-from werkzeug.exceptions import NotFound
+from werkzeug.exceptions import Forbidden, NotFound

 import services
 from controllers.common.errors import FilenameNotExistsError
@@ -18,14 +18,19 @@ from controllers.service_api.app.error import (
 from controllers.service_api.dataset.error import (
    ArchivedDocumentImmutableError,
    DocumentIndexingError,
+    InvalidMetadataError,
+)
+from controllers.service_api.wraps import (
+    DatasetApiResource,
+    cloud_edition_billing_rate_limit_check,
+    cloud_edition_billing_resource_check,
 )
-from controllers.service_api.wraps import DatasetApiResource, cloud_edition_billing_resource_check
 from core.errors.error import ProviderTokenNotInitError
 from extensions.ext_database import db
 from fields.document_fields import document_fields, document_status_fields
 from libs.login import current_user
 from models.dataset import Dataset, Document, DocumentSegment
-from services.dataset_service import DocumentService
+from services.dataset_service import DatasetService, DocumentService
 from services.entities.knowledge_entities.knowledge_entities import KnowledgeConfig
 from services.file_service import FileService

@@ -35,6 +40,7 @@ class DocumentAddByTextApi(DatasetApiResource):

    @cloud_edition_billing_resource_check("vector_space", "dataset")
    @cloud_edition_billing_resource_check("documents", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def post(self, tenant_id, dataset_id):
        """Create document by text."""
        parser = reqparse.RequestParser()
@@ -54,6 +60,7 @@ class DocumentAddByTextApi(DatasetApiResource):
        parser.add_argument("embedding_model_provider", type=str, required=False, nullable=True, location="json")

        args = parser.parse_args()
+
        dataset_id = str(dataset_id)
        tenant_id = str(tenant_id)
        dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
@@ -69,6 +76,21 @@ class DocumentAddByTextApi(DatasetApiResource):
        if text is None or name is None:
            raise ValueError("Both 'text' and 'name' must be non-null values.")

+        if args.get("embedding_model_provider"):
+            DatasetService.check_embedding_model_setting(
+                tenant_id, args.get("embedding_model_provider"), args.get("embedding_model")
+            )
+        if (
+            args.get("retrieval_model")
+            and args.get("retrieval_model").get("reranking_model")
+            and args.get("retrieval_model").get("reranking_model").get("reranking_provider_name")
+        ):
+            DatasetService.check_reranking_model_setting(
+                tenant_id,
+                args.get("retrieval_model").get("reranking_model").get("reranking_provider_name"),
+                args.get("retrieval_model").get("reranking_model").get("reranking_model_name"),
+            )
+
        upload_file = FileService.upload_text(text=str(text), text_name=str(name))
        data_source = {
            "type": "upload_file",
@@ -99,6 +121,7 @@ class DocumentUpdateByTextApi(DatasetApiResource):
    """Resource for update documents."""

    @cloud_edition_billing_resource_check("vector_space", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def post(self, tenant_id, dataset_id, document_id):
        """Update document by text."""
        parser = reqparse.RequestParser()
@@ -118,6 +141,17 @@ class DocumentUpdateByTextApi(DatasetApiResource):
        if not dataset:
            raise ValueError("Dataset does not exist.")

+        if (
+            args.get("retrieval_model")
+            and args.get("retrieval_model").get("reranking_model")
+            and args.get("retrieval_model").get("reranking_model").get("reranking_provider_name")
+        ):
+            DatasetService.check_reranking_model_setting(
+                tenant_id,
+                args.get("retrieval_model").get("reranking_model").get("reranking_provider_name"),
+                args.get("retrieval_model").get("reranking_model").get("reranking_model_name"),
+            )
+
        # indexing_technique is already set in dataset since this is an update
        args["indexing_technique"] = dataset.indexing_technique

@@ -158,6 +192,7 @@ class DocumentAddByFileApi(DatasetApiResource):

    @cloud_edition_billing_resource_check("vector_space", "dataset")
    @cloud_edition_billing_resource_check("documents", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def post(self, tenant_id, dataset_id):
        """Create document by upload file."""
        args = {}
@@ -175,8 +210,26 @@ class DocumentAddByFileApi(DatasetApiResource):

        if not dataset:
            raise ValueError("Dataset does not exist.")
-        if not dataset.indexing_technique and not args.get("indexing_technique"):
+
+        indexing_technique = args.get("indexing_technique") or dataset.indexing_technique
+        if not indexing_technique:
            raise ValueError("indexing_technique is required.")
+        args["indexing_technique"] = indexing_technique
+
+        if "embedding_model_provider" in args:
+            DatasetService.check_embedding_model_setting(
+                tenant_id, args["embedding_model_provider"], args["embedding_model"]
+            )
+        if (
+            "retrieval_model" in args
+            and args["retrieval_model"].get("reranking_model")
+            and args["retrieval_model"].get("reranking_model").get("reranking_provider_name")
+        ):
+            DatasetService.check_reranking_model_setting(
+                tenant_id,
+                args["retrieval_model"].get("reranking_model").get("reranking_provider_name"),
+                args["retrieval_model"].get("reranking_model").get("reranking_model_name"),
+            )

        # save file info
        file = request.files["file"]
@@ -206,12 +259,16 @@ class DocumentAddByFileApi(DatasetApiResource):
        knowledge_config = KnowledgeConfig(**args)
        DocumentService.document_create_args_validate(knowledge_config)

+        dataset_process_rule = dataset.latest_process_rule if "process_rule" not in args else None
+        if not knowledge_config.original_document_id and not dataset_process_rule and not knowledge_config.process_rule:
+            raise ValueError("process_rule is required.")
+
        try:
            documents, batch = DocumentService.save_document_with_dataset_id(
                dataset=dataset,
                knowledge_config=knowledge_config,
                account=dataset.created_by_account,
-                dataset_process_rule=dataset.latest_process_rule if "process_rule" not in args else None,
+                dataset_process_rule=dataset_process_rule,
                created_from="api",
            )
        except ProviderTokenNotInitError as ex:
@@ -225,6 +282,7 @@ class DocumentUpdateByFileApi(DatasetApiResource):
    """Resource for update documents."""

    @cloud_edition_billing_resource_check("vector_space", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def post(self, tenant_id, dataset_id, document_id):
        """Update document by upload file."""
        args = {}
@@ -295,6 +353,7 @@ class DocumentUpdateByFileApi(DatasetApiResource):


 class DocumentDeleteApi(DatasetApiResource):
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def delete(self, tenant_id, dataset_id, document_id):
        """Delete document."""
        document_id = str(document_id)
@@ -388,15 +447,121 @@ class DocumentIndexingStatusApi(DatasetApiResource):
                .filter(DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment")
                .count()
            )
-            document.completed_segments = completed_segments
-            document.total_segments = total_segments
-            if document.is_paused:
-                document.indexing_status = "paused"
-            documents_status.append(marshal(document, document_status_fields))
+            # Create a dictionary with document attributes and additional fields
+            document_dict = {
+                "id": document.id,
+                "indexing_status": "paused" if document.is_paused else document.indexing_status,
+                "processing_started_at": document.processing_started_at,
+                "parsing_completed_at": document.parsing_completed_at,
+                "cleaning_completed_at": document.cleaning_completed_at,
+                "splitting_completed_at": document.splitting_completed_at,
+                "completed_at": document.completed_at,
+                "paused_at": document.paused_at,
+                "error": document.error,
+                "stopped_at": document.stopped_at,
+                "completed_segments": completed_segments,
+                "total_segments": total_segments,
+            }
+            documents_status.append(marshal(document_dict, document_status_fields))
        data = {"data": documents_status}
        return data


+class DocumentDetailApi(DatasetApiResource):
+    METADATA_CHOICES = {"all", "only", "without"}
+
+    def get(self, tenant_id, dataset_id, document_id):
+        dataset_id = str(dataset_id)
+        document_id = str(document_id)
+
+        dataset = self.get_dataset(dataset_id, tenant_id)
+
+        document = DocumentService.get_document(dataset.id, document_id)
+
+        if not document:
+            raise NotFound("Document not found.")
+
+        if document.tenant_id != str(tenant_id):
+            raise Forbidden("No permission.")
+
+        metadata = request.args.get("metadata", "all")
+        if metadata not in self.METADATA_CHOICES:
+            raise InvalidMetadataError(f"Invalid metadata value: {metadata}")
+
+        if metadata == "only":
+            response = {"id": document.id, "doc_type": document.doc_type, "doc_metadata": document.doc_metadata_details}
+        elif metadata == "without":
+            dataset_process_rules = DatasetService.get_process_rules(dataset_id)
+            document_process_rules = document.dataset_process_rule.to_dict()
+            data_source_info = document.data_source_detail_dict
+            response = {
+                "id": document.id,
+                "position": document.position,
+                "data_source_type": document.data_source_type,
+                "data_source_info": data_source_info,
+                "dataset_process_rule_id": document.dataset_process_rule_id,
+                "dataset_process_rule": dataset_process_rules,
+                "document_process_rule": document_process_rules,
+                "name": document.name,
+                "created_from": document.created_from,
+                "created_by": document.created_by,
+                "created_at": document.created_at.timestamp(),
+                "tokens": document.tokens,
+                "indexing_status": document.indexing_status,
+                "completed_at": int(document.completed_at.timestamp()) if document.completed_at else None,
+                "updated_at": int(document.updated_at.timestamp()) if document.updated_at else None,
+                "indexing_latency": document.indexing_latency,
+                "error": document.error,
+                "enabled": document.enabled,
+                "disabled_at": int(document.disabled_at.timestamp()) if document.disabled_at else None,
+                "disabled_by": document.disabled_by,
+                "archived": document.archived,
+                "segment_count": document.segment_count,
+                "average_segment_length": document.average_segment_length,
+                "hit_count": document.hit_count,
+                "display_status": document.display_status,
+                "doc_form": document.doc_form,
+                "doc_language": document.doc_language,
+            }
+        else:
+            dataset_process_rules = DatasetService.get_process_rules(dataset_id)
+            document_process_rules = document.dataset_process_rule.to_dict()
+            data_source_info = document.data_source_detail_dict
+            response = {
+                "id": document.id,
+                "position": document.position,
+                "data_source_type": document.data_source_type,
+                "data_source_info": data_source_info,
+                "dataset_process_rule_id": document.dataset_process_rule_id,
+                "dataset_process_rule": dataset_process_rules,
+                "document_process_rule": document_process_rules,
+                "name": document.name,
+                "created_from": document.created_from,
+                "created_by": document.created_by,
+                "created_at": document.created_at.timestamp(),
+                "tokens": document.tokens,
+                "indexing_status": document.indexing_status,
+                "completed_at": int(document.completed_at.timestamp()) if document.completed_at else None,
+                "updated_at": int(document.updated_at.timestamp()) if document.updated_at else None,
+                "indexing_latency": document.indexing_latency,
+                "error": document.error,
+                "enabled": document.enabled,
+                "disabled_at": int(document.disabled_at.timestamp()) if document.disabled_at else None,
+                "disabled_by": document.disabled_by,
+                "archived": document.archived,
+                "doc_type": document.doc_type,
+                "doc_metadata": document.doc_metadata_details,
+                "segment_count": document.segment_count,
+                "average_segment_length": document.average_segment_length,
+                "hit_count": document.hit_count,
+                "display_status": document.display_status,
+                "doc_form": document.doc_form,
+                "doc_language": document.doc_language,
+            }
+
+        return response
+
+
 api.add_resource(
    DocumentAddByTextApi,
    "/datasets/<uuid:dataset_id>/document/create_by_text",
@@ -420,3 +585,4 @@ api.add_resource(
 api.add_resource(DocumentDeleteApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>")
 api.add_resource(DocumentListApi, "/datasets/<uuid:dataset_id>/documents")
 api.add_resource(DocumentIndexingStatusApi, "/datasets/<uuid:dataset_id>/documents/<string:batch>/indexing-status")
+api.add_resource(DocumentDetailApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>")
@@ -1,9 +1,10 @@
 from controllers.console.datasets.hit_testing_base import DatasetsHitTestingBase
 from controllers.service_api import api
-from controllers.service_api.wraps import DatasetApiResource
+from controllers.service_api.wraps import DatasetApiResource, cloud_edition_billing_rate_limit_check


 class HitTestingApi(DatasetApiResource, DatasetsHitTestingBase):
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def post(self, tenant_id, dataset_id):
        dataset_id_str = str(dataset_id)

@@ -3,7 +3,7 @@ from flask_restful import marshal, reqparse
 from werkzeug.exceptions import NotFound

 from controllers.service_api import api
-from controllers.service_api.wraps import DatasetApiResource
+from controllers.service_api.wraps import DatasetApiResource, cloud_edition_billing_rate_limit_check
 from fields.dataset_fields import dataset_metadata_fields
 from services.dataset_service import DatasetService
 from services.entities.knowledge_entities.knowledge_entities import (
@@ -14,6 +14,7 @@ from services.metadata_service import MetadataService


 class DatasetMetadataCreateServiceApi(DatasetApiResource):
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def post(self, tenant_id, dataset_id):
        parser = reqparse.RequestParser()
        parser.add_argument("type", type=str, required=True, nullable=True, location="json")
@@ -39,6 +40,7 @@ class DatasetMetadataCreateServiceApi(DatasetApiResource):


 class DatasetMetadataServiceApi(DatasetApiResource):
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def patch(self, tenant_id, dataset_id, metadata_id):
        parser = reqparse.RequestParser()
        parser.add_argument("name", type=str, required=True, nullable=True, location="json")
@@ -54,6 +56,7 @@ class DatasetMetadataServiceApi(DatasetApiResource):
        metadata = MetadataService.update_metadata_name(dataset_id_str, metadata_id_str, args.get("name"))
        return marshal(metadata, dataset_metadata_fields), 200

+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def delete(self, tenant_id, dataset_id, metadata_id):
        dataset_id_str = str(dataset_id)
        metadata_id_str = str(metadata_id)
@@ -73,6 +76,7 @@ class DatasetMetadataBuiltInFieldServiceApi(DatasetApiResource):


 class DatasetMetadataBuiltInFieldActionServiceApi(DatasetApiResource):
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def post(self, tenant_id, dataset_id, action):
        dataset_id_str = str(dataset_id)
        dataset = DatasetService.get_dataset(dataset_id_str)
@@ -88,6 +92,7 @@ class DatasetMetadataBuiltInFieldActionServiceApi(DatasetApiResource):


 class DocumentMetadataEditServiceApi(DatasetApiResource):
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def post(self, tenant_id, dataset_id):
        dataset_id_str = str(dataset_id)
        dataset = DatasetService.get_dataset(dataset_id_str)
@@ -8,6 +8,7 @@ from controllers.service_api.app.error import ProviderNotInitializeError
 from controllers.service_api.wraps import (
    DatasetApiResource,
    cloud_edition_billing_knowledge_limit_check,
+    cloud_edition_billing_rate_limit_check,
    cloud_edition_billing_resource_check,
 )
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
@@ -35,6 +36,7 @@ class SegmentApi(DatasetApiResource):

    @cloud_edition_billing_resource_check("vector_space", "dataset")
    @cloud_edition_billing_knowledge_limit_check("add_segment", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def post(self, tenant_id, dataset_id, document_id):
        """Create single segment."""
        # check dataset
@@ -139,6 +141,7 @@ class SegmentApi(DatasetApiResource):


 class DatasetSegmentApi(DatasetApiResource):
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def delete(self, tenant_id, dataset_id, document_id, segment_id):
        # check dataset
        dataset_id = str(dataset_id)
@@ -162,6 +165,7 @@ class DatasetSegmentApi(DatasetApiResource):
        return 204

    @cloud_edition_billing_resource_check("vector_space", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def post(self, tenant_id, dataset_id, document_id, segment_id):
        # check dataset
        dataset_id = str(dataset_id)
@@ -208,12 +212,35 @@ class DatasetSegmentApi(DatasetApiResource):
        )
        return {"data": marshal(updated_segment, segment_fields), "doc_form": document.doc_form}, 200

+    def get(self, tenant_id, dataset_id, document_id, segment_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset_id, document_id)
+        if not document:
+            raise NotFound("Document not found.")
+        # check segment
+        segment_id = str(segment_id)
+        segment = SegmentService.get_segment_by_id(segment_id=segment_id, tenant_id=current_user.current_tenant_id)
+        if not segment:
+            raise NotFound("Segment not found.")
+
+        return {"data": marshal(segment, segment_fields), "doc_form": document.doc_form}, 200
+

 class ChildChunkApi(DatasetApiResource):
    """Resource for child chunks."""

    @cloud_edition_billing_resource_check("vector_space", "dataset")
    @cloud_edition_billing_knowledge_limit_check("add_segment", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def post(self, tenant_id, dataset_id, document_id, segment_id):
        """Create child chunk."""
        # check dataset
@@ -310,6 +337,7 @@ class DatasetChildChunkApi(DatasetApiResource):
    """Resource for updating child chunks."""

    @cloud_edition_billing_knowledge_limit_check("add_segment", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def delete(self, tenant_id, dataset_id, document_id, segment_id, child_chunk_id):
        """Delete child chunk."""
        # check dataset
@@ -348,6 +376,7 @@ class DatasetChildChunkApi(DatasetApiResource):

    @cloud_edition_billing_resource_check("vector_space", "dataset")
    @cloud_edition_billing_knowledge_limit_check("add_segment", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
    def patch(self, tenant_id, dataset_id, document_id, segment_id, child_chunk_id):
        """Update child chunk."""
        # check dataset
@@ -9,7 +9,7 @@ class IndexApi(Resource):
        return {
            "welcome": "Dify OpenAPI",
            "api_version": "v1",
-            "server_version": dify_config.CURRENT_VERSION,
+            "server_version": dify_config.project.version,
        }


@@ -11,13 +11,13 @@ from flask_restful import Resource
 from pydantic import BaseModel
 from sqlalchemy import select, update
 from sqlalchemy.orm import Session
-from werkzeug.exceptions import Forbidden, Unauthorized
+from werkzeug.exceptions import Forbidden, NotFound, Unauthorized

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

@@ -99,7 +99,12 @@ def validate_app_token(view: Optional[Callable] = None, *, fetch_user_arg: Optio
                if user_id:
                    user_id = str(user_id)

-                kwargs["end_user"] = create_or_update_end_user_for_user_id(app_model, user_id)
+                end_user = create_or_update_end_user_for_user_id(app_model, user_id)
+                kwargs["end_user"] = end_user
+
+                # Set EndUser as current logged-in user for flask_login.current_user
+                current_app.login_manager._update_request_context_with_user(end_user)  # type: ignore
+                user_logged_in.send(current_app._get_current_object(), user=end_user)  # type: ignore

            return view_func(*args, **kwargs)

@@ -312,3 +317,11 @@ def create_or_update_end_user_for_user_id(app_model: App, user_id: Optional[str]

 class DatasetApiResource(Resource):
    method_decorators = [validate_dataset_token]
+
+    def get_dataset(self, dataset_id: str, tenant_id: str) -> Dataset:
+        dataset = db.session.query(Dataset).filter(Dataset.id == dataset_id, Dataset.tenant_id == tenant_id).first()
+
+        if not dataset:
+            raise NotFound("Dataset not found.")
+
+        return dataset
--- a/Show More
+++ b/Show More