Merge branch 'main' into fix-doc-TOC-style

.devcontainer/Dockerfile

@@ -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

.devcontainer/post_create_command.sh

@@ -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
 

.editorconfig

@@ -5,18 +5,35 @@ root = true
 
 # Unix-style newlines with a newline ending every file
 [*]
+charset = utf-8
 end_of_line = lf
 insert_final_newline = true
+trim_trailing_whitespace = true
+
+[*.py]
+indent_size = 4
+indent_style = space
+
+[*.{yml,yaml}]
+indent_style = space
+indent_size = 2
+
+[*.toml]
+indent_size = 4
+indent_style = space
+
+# Markdown and MDX are whitespace sensitive languages.
+# Do not remove trailing spaces.
+[*.{md,mdx}]
+trim_trailing_whitespace = false
 
 # Matches multiple files with brace expansion notation
 # Set default charset
 [*.{js,tsx}]
-charset = utf-8
 indent_style = space
 indent_size = 2
 
-
-# Matches the exact files either package.json or .travis.yml
-[{package.json,.travis.yml}]
+# Matches the exact files package.json
+[package.json]
 indent_style = space
 indent_size = 2

.github/actions/setup-uv/action.yml

@@ -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

.github/linters/editorconfig-checker.json

@@ -0,0 +1,22 @@
+{
+    "Verbose": false,
+    "Debug": false,
+    "IgnoreDefaults": false,
+    "SpacesAfterTabs": false,
+    "NoColor": false,
+    "Exclude": [
+        "^web/public/vs/",
+        "^web/public/pdf.worker.min.mjs$",
+        "web/app/components/base/icons/src/vender/"
+    ],
+    "AllowedContentTypes": [],
+    "PassedFiles": [],
+    "Disable": {
+        "EndOfLine": false,
+        "Indentation": false,
+        "IndentSize": true,
+        "InsertFinalNewline": false,
+        "TrimTrailingWhitespace": false,
+        "MaxLineLength": false
+    }
+}

.github/pull_request_template.md

@@ -1,25 +1,23 @@
-# Summary
-
-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.
+> [!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>`.
 
-> [!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.
+## Summary
 
+<!-- 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
-

.github/workflows/api-tests.yml

@@ -88,3 +88,6 @@ jobs:
 
       - name: Run Workflow
         run: uv run --project api bash dev/pytest/pytest_workflow.sh
+
+      - name: Run Tool
+        run: uv run --project api bash dev/pytest/pytest_tools.sh

.github/workflows/deploy-rag-dev.yml

@@ -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 }}

.github/workflows/expose_service_ports.sh

@@ -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"

.github/workflows/style.yml

@@ -9,6 +9,12 @@ concurrency:
   group: style-${{ github.head_ref || github.run_id }}
   cancel-in-progress: true
 
+permissions:
+  checks: write
+  statuses: write
+  contents: read
+
+
 jobs:
   python-style:
     name: Python Style
@@ -43,8 +49,8 @@ jobs:
         if: steps.changed-files.outputs.any_changed == 'true'
         run: |
           uv run --directory api ruff --version
-          uv run --directory api ruff check ./
-          uv run --directory api ruff format --check ./
+          uv run --directory api ruff check --diff ./
+          uv run --directory api ruff format --check --diff ./
 
       - name: Dotenv check
         if: steps.changed-files.outputs.any_changed == 'true'
@@ -133,6 +139,7 @@ jobs:
       - name: Checkout code
         uses: actions/checkout@v4
         with:
+          fetch-depth: 0
           persist-credentials: false
 
       - name: Check changed files
@@ -163,3 +170,14 @@ jobs:
           VALIDATE_DOCKERFILE_HADOLINT: true
           VALIDATE_XML: true
           VALIDATE_YAML: true
+
+      - name: EditorConfig checks
+        uses: super-linter/super-linter/slim@v7
+        env:
+          DEFAULT_BRANCH: main
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          IGNORE_GENERATED_FILES: true
+          IGNORE_GITIGNORED_FILES: true
+          # EditorConfig validation
+          VALIDATE_EDITORCONFIG: true
+          EDITORCONFIG_FILE_NAME: editorconfig-checker.json

.github/workflows/translate-i18n-base-on-english.yml

@@ -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'

.github/workflows/vdb-tests.yml

@@ -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: |
@@ -75,9 +82,12 @@ jobs:
             pgvector
             chroma
             elasticsearch
+            oceanbase
 
-      - name: Check TiDB Ready
-        run: uv run --project api python api/tests/integration_tests/vdb/tidb_vector/check_tiflash_ready.py
+      - name: Check VDB Ready (TiDB, Oceanbase)
+        run: |
+          uv run --project api python api/tests/integration_tests/vdb/tidb_vector/check_tiflash_ready.py
+          uv run --project api python api/tests/integration_tests/vdb/oceanbase/check_oceanbase_ready.py
 
       - name: Test Vector Stores
         run: uv run --project api bash dev/pytest/pytest_vdb.sh

.gitignore

@@ -192,12 +192,12 @@ 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 +207,6 @@ plugins.jsonl
 
 # mise
 mise.toml
+
+# Next.js build output
+.next/

.vscode/README.md

@@ -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.

.vscode/launch.json.template

@@ -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"
+          }
+    ]
+}

README.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+![cover-v5-optimized](./images/GitHub_README_if.png)
 
 <p align="center">
   📌 <a href="https://dify.ai/blog/introducing-dify-workflow-file-upload-a-demo-on-ai-podcast">Introducing Dify Workflow File Upload: Recreate Google NotebookLM Podcast</a>
@@ -54,7 +54,7 @@
   <a href="./README_BN.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
 </p>
 
-Dify is an open-source LLM app development platform. Its intuitive interface combines agentic AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.
+Dify is an open-source LLM app development platform. Its intuitive interface combines agentic AI workflow, RAG pipeline, agent capabilities, model management, observability features, and more, allowing you to quickly move from prototype to production.
 
 ## Quick start
 
@@ -87,8 +87,6 @@ Please refer to our [FAQ](https://docs.dify.ai/getting-started/install-self-host
 **1. Workflow**:
 Build and test powerful AI workflows on a visual canvas, leveraging all the following features and beyond.
 
-https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
-
 **2. Comprehensive model support**:
 Seamless integration with hundreds of proprietary / open-source LLMs from dozens of inference providers and self-hosted solutions, covering GPT, Mistral, Llama3, and any OpenAI API-compatible models. A full list of supported model providers can be found [here](https://docs.dify.ai/getting-started/readme/model-providers).
 
@@ -188,7 +186,7 @@ All of Dify's offerings come with corresponding APIs, so you could effortlessly
 
 - **Dify for enterprise / organizations</br>**
   We provide additional enterprise-centric features. [Log your questions for us through this chatbot](https://udify.app/chat/22L1zSxg6yW1cWQg) or [send us an email](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) to discuss enterprise needs. </br>
-  > For startups and small businesses using AWS, check out [Dify Premium on AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) and deploy it to your own AWS VPC with one-click. It's an affordable AMI offering with the option to create apps with custom logo and branding.
+  > For startups and small businesses using AWS, check out [Dify Premium on AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) and deploy it to your own AWS VPC with one click. It's an affordable AMI offering with the option to create apps with custom logo and branding.
 
 ## Staying ahead
 
@@ -233,11 +231,11 @@ Deploy Dify to AWS with [CDK](https://aws.amazon.com/cdk/)
 For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
 At the same time, please consider supporting Dify by sharing it on social media and at events and conferences.
 
-> We are looking for contributors to help with translating Dify to languages other than Mandarin or English. If you are interested in helping, please see the [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) for more information, and leave us a comment in the `global-users` channel of our [Discord Community Server](https://discord.gg/8Tpq4AcN9c).
+> We are looking for contributors to help translate Dify into languages other than Mandarin or English. If you are interested in helping, please see the [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) for more information, and leave us a comment in the `global-users` channel of our [Discord Community Server](https://discord.gg/8Tpq4AcN9c).
 
 ## 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.

README_AR.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+![cover-v5-optimized](./images/GitHub_README_if.png)
 
 <p align="center">
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
@@ -54,8 +54,6 @@
 
 **1. سير العمل**:  قم ببناء واختبار سير عمل الذكاء الاصطناعي القوي على قماش بصري، مستفيدًا من جميع الميزات التالية وأكثر.
 
-  <https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa>
-
 **2. الدعم الشامل للنماذج**: تكامل سلس مع مئات من LLMs الخاصة / مفتوحة المصدر من عشرات من موفري التحليل والحلول المستضافة ذاتيًا، مما يغطي GPT و Mistral و Llama3 وأي نماذج متوافقة مع واجهة OpenAI API. يمكن العثور على قائمة كاملة بمزودي النموذج المدعومين [هنا](https://docs.dify.ai/getting-started/readme/model-providers).
 
 ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)
@@ -225,7 +223,7 @@ 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.

README_BN.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+![cover-v5-optimized](./images/GitHub_README_if.png)
 
 <p align="center">
   📌 <a href="https://dify.ai/blog/introducing-dify-workflow-file-upload-a-demo-on-ai-podcast">ডিফাই ওয়ার্কফ্লো ফাইল আপলোড পরিচিতি: গুগল নোটবুক-এলএম পডকাস্ট পুনর্নির্মাণ</a>
@@ -84,8 +84,6 @@ docker compose up -d
 **১. ওয়ার্কফ্লো**:
     ভিজ্যুয়াল ক্যানভাসে  AI ওয়ার্কফ্লো তৈরি এবং পরীক্ষা করুন, নিম্নলিখিত সব ফিচার এবং  তার বাইরেও আরও অনেক কিছু ব্যবহার করে।
 
-  <https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa>
-
 **২.  মডেল সাপোর্ট**:
   GPT, Mistral, Llama3, এবং যেকোনো OpenAI API-সামঞ্জস্যপূর্ণ মডেলসহ, কয়েক ডজন ইনফারেন্স প্রদানকারী এবং সেল্ফ-হোস্টেড সমাধান থেকে শুরু করে প্রোপ্রাইটরি/ওপেন-সোর্স LLM-এর সাথে সহজে ইন্টিগ্রেশন। সমর্থিত মডেল প্রদানকারীদের একটি সম্পূর্ণ তালিকা পাওয়া যাবে [এখানে](https://docs.dify.ai/getting-started/readme/model-providers)।
 
@@ -236,7 +234,7 @@ 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। 

README_CN.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+![cover-v5-optimized](./images/GitHub_README_if.png)
 
 <div align="center">
   <a href="https://cloud.dify.ai">Dify 云服务</a> ·
@@ -61,11 +61,6 @@ Dify 是一个开源的 LLM 应用开发平台。其直观的界面结合了 AI
 **1. 工作流**: 
   在画布上构建和测试功能强大的 AI 工作流程，利用以下所有功能以及更多功能。
 
-
-  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
-
-
-
 **2. 全面的模型支持**: 
   与数百种专有/开源 LLMs 以及数十种推理提供商和自托管解决方案无缝集成，涵盖 GPT、Mistral、Llama3 以及任何与 OpenAI API 兼容的模型。完整的支持模型提供商列表可在[此处](https://docs.dify.ai/getting-started/readme/model-providers)找到。
 
@@ -248,7 +243,7 @@ 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。

README_DE.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+![cover-v5-optimized](./images/GitHub_README_if.png)
 
 <p align="center">
   📌 <a href="https://dify.ai/blog/introducing-dify-workflow-file-upload-a-demo-on-ai-podcast">Einführung in Dify Workflow File Upload: Google NotebookLM Podcast nachbilden</a>
@@ -83,11 +83,6 @@ Bitte beachten Sie unsere [FAQ](https://docs.dify.ai/getting-started/install-sel
 **1. Workflow**: 
   Erstellen und testen Sie leistungsstarke KI-Workflows auf einer visuellen Oberfläche, wobei Sie alle der folgenden Funktionen und darüber hinaus nutzen können.
 
-
-  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
-
-
-
 **2. Umfassende Modellunterstützung**: 
   Nahtlose Integration mit Hunderten von proprietären und Open-Source-LLMs von Dutzenden Inferenzanbietern und selbstgehosteten Lösungen, die GPT, Mistral, Llama3 und alle mit der OpenAI API kompatiblen Modelle abdecken. Eine vollständige Liste der unterstützten Modellanbieter finden Sie [hier](https://docs.dify.ai/getting-started/readme/model-providers).
 
@@ -235,7 +230,7 @@ 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.

README_ES.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+![cover-v5-optimized](./images/GitHub_README_if.png)
 
 <p align="center">
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
@@ -59,11 +59,6 @@ Dify es una plataforma de desarrollo de aplicaciones de LLM de código abierto.
 **1. Flujo de trabajo**: 
   Construye y prueba potentes flujos de trabajo de IA en un lienzo visual, aprovechando todas las siguientes características y más.
 
-
-  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
-
-
-
 **2. Soporte de modelos completo**: 
   Integración perfecta con cientos de LLMs propietarios / de código abierto de docenas de proveedores de inferencia y soluciones auto-alojadas, que cubren GPT, Mistral, Llama3 y cualquier modelo compatible con la API de OpenAI. Se puede encontrar una lista completa de proveedores de modelos admitidos [aquí](https://docs.dify.ai/getting-started/readme/model-providers).
 

README_FR.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+![cover-v5-optimized](./images/GitHub_README_if.png)
 
 <p align="center">
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
@@ -59,11 +59,6 @@ Dify est une plateforme de développement d'applications LLM open source. Son in
 **1. Flux de travail** : 
   Construisez et testez des flux de travail d'IA puissants sur un canevas visuel, en utilisant toutes les fonctionnalités suivantes et plus encore.
 
-
-  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
-
-
-
 **2. Prise en charge complète des modèles** : 
   Intégration transparente avec des centaines de LLM propriétaires / open source provenant de dizaines de fournisseurs d'inférence et de solutions auto-hébergées, couvrant GPT, Mistral, Llama3, et tous les modèles compatibles avec l'API OpenAI. Une liste complète des fournisseurs de modèles pris en charge se trouve [ici](https://docs.dify.ai/getting-started/readme/model-providers).
 

README_JA.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+![cover-v5-optimized](./images/GitHub_README_if.png)
 
 <p align="center">
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
@@ -60,11 +60,6 @@ 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
 **1. ワークフロー**:
   強力なAIワークフローをビジュアルキャンバス上で構築し、テストできます。すべての機能、および以下の機能を使用できます。
 
-
-  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
-
-
-
 **2. 総合的なモデルサポート**:
   数百ものプロプライエタリ/オープンソースのLLMと、数十もの推論プロバイダーおよびセルフホスティングソリューションとのシームレスな統合を提供します。GPT、Mistral、Llama3、OpenAI APIと互換性のあるすべてのモデルを統合されています。サポートされているモデルプロバイダーの完全なリストは[こちら](https://docs.dify.ai/getting-started/readme/model-providers)をご覧ください。
 
@@ -241,7 +236,7 @@ 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。

README_KL.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+![cover-v5-optimized](./images/GitHub_README_if.png)
 
 <p align="center">
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
@@ -59,11 +59,6 @@ Dify is an open-source LLM app development platform. Its intuitive interface com
 **1. Workflow**: 
   Build and test powerful AI workflows on a visual canvas, leveraging all the following features and beyond.
 
-
-  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
-
-
-
 **2. Comprehensive model support**: 
   Seamless integration with hundreds of proprietary / open-source LLMs from dozens of inference providers and self-hosted solutions, covering GPT, Mistral, Llama3, and any OpenAI API-compatible models. A full list of supported model providers can be found [here](https://docs.dify.ai/getting-started/readme/model-providers).
 
@@ -240,7 +235,7 @@ 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).

README_KR.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+![cover-v5-optimized](./images/GitHub_README_if.png)
 
 <p align="center">
   <a href="https://cloud.dify.ai">Dify 클라우드</a> ·
@@ -54,11 +54,6 @@
 **1. 워크플로우**:
     다음 기능들을 비롯한 다양한 기능을 활용하여 시각적 캔버스에서 강력한 AI 워크플로우를 구축하고 테스트하세요.
 
-
-  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
-
-
-
 **2. 포괄적인 모델 지원:**: 
 
 수십 개의 추론 제공업체와 자체 호스팅 솔루션에서 제공하는 수백 개의 독점 및 오픈 소스 LLM과 원활하게 통합되며, GPT, Mistral, Llama3 및 모든 OpenAI API 호환 모델을 포함합니다. 지원되는 모델 제공업체의 전체 목록은 [여기](https://docs.dify.ai/getting-started/readme/model-providers)에서 확인할 수 있습니다.
@@ -234,7 +229,7 @@ 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.

README_PT.md

@@ -1,5 +1,4 @@
-![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
-
+![cover-v5-optimized](./images/GitHub_README_if.png)
 <p align="center">
   📌 <a href="https://dify.ai/blog/introducing-dify-workflow-file-upload-a-demo-on-ai-podcast">Introduzindo o Dify Workflow com Upload de Arquivo: Recrie o Podcast Google NotebookLM</a>
 </p>
@@ -59,11 +58,6 @@ Dify é uma plataforma de desenvolvimento de aplicativos LLM de código aberto.
 **1. Workflow**: 
   Construa e teste workflows poderosos de IA em uma interface visual, aproveitando todos os recursos a seguir e muito mais.
 
-
-  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
-
-
-
 **2. Suporte abrangente a modelos**: 
   Integração perfeita com centenas de LLMs proprietários e de código aberto de diversas provedoras e soluções auto-hospedadas, abrangendo GPT, Mistral, Llama3 e qualquer modelo compatível com a API da OpenAI. A lista completa de provedores suportados pode ser encontrada [aqui](https://docs.dify.ai/getting-started/readme/model-providers).
 

README_SI.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+![cover-v5-optimized](./images/GitHub_README_if.png)
 
 <p align="center">
   📌 <a href="https://dify.ai/blog/introducing-dify-workflow-file-upload-a-demo-on-ai-podcast">Predstavljamo nalaganje datotek Dify Workflow: znova ustvarite Google NotebookLM Podcast</a>
@@ -81,11 +81,6 @@ Prosimo, glejte naša pogosta vprašanja [FAQ](https://docs.dify.ai/getting-star
 **1. Potek dela**: 
   Zgradite in preizkusite zmogljive poteke dela AI na vizualnem platnu, pri čemer izkoristite vse naslednje funkcije in več.
 
-
-  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
-
-
-
 **2. Celovita podpora za modele**: 
   Brezhibna integracija s stotinami lastniških/odprtokodnih LLM-jev ducatov ponudnikov sklepanja in samostojnih rešitev, ki pokrivajo GPT, Mistral, Llama3 in vse modele, združljive z API-jem OpenAI. Celoten seznam podprtih ponudnikov modelov najdete [tukaj](https://docs.dify.ai/getting-started/readme/model-providers).
 
@@ -234,7 +229,7 @@ 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.

README_TR.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+![cover-v5-optimized](./images/GitHub_README_if.png)
 
 <p align="center">
   <a href="https://cloud.dify.ai">Dify Bulut</a> ·
@@ -55,11 +55,6 @@ Dify, açık kaynaklı bir LLM uygulama geliştirme platformudur. Sezgisel aray
 **1. Workflow**: 
 Görsel bir arayüz üzerinde güçlü AI iş akışları oluşturun ve test edin, aşağıdaki tüm özellikleri ve daha fazlasını kullanarak.
 
-
-  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
-
-
-
 **2. Kapsamlı model desteği**:
 Çok sayıda çıkarım sağlayıcısı ve kendi kendine barındırılan çözümlerden yüzlerce özel / açık kaynaklı LLM ile sorunsuz entegrasyon sağlar. GPT, Mistral, Llama3 ve OpenAI API uyumlu tüm modelleri kapsar. Desteklenen model sağlayıcılarının tam listesine [buradan](https://docs.dify.ai/getting-started/readme/model-providers) ulaşabilirsiniz.
 
@@ -232,7 +227,7 @@ 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.

README_TW.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+![cover-v5-optimized](./images/GitHub_README_if.png)
 
 <p align="center">
   📌 <a href="https://dify.ai/blog/introducing-dify-workflow-file-upload-a-demo-on-ai-podcast">介紹 Dify 工作流程檔案上傳功能：重現 Google NotebookLM Podcast</a>
@@ -86,8 +86,6 @@ docker compose up -d
 **1. 工作流程**：
 在視覺化畫布上建立和測試強大的 AI 工作流程，利用以下所有功能及更多。
 
-https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
-
 **2. 全面的模型支援**：
 無縫整合來自數十個推理提供商和自託管解決方案的數百個專有/開源 LLM，涵蓋 GPT、Mistral、Llama3 和任何與 OpenAI API 兼容的模型。您可以在[此處](https://docs.dify.ai/getting-started/readme/model-providers)找到支援的模型提供商完整列表。
 
@@ -235,7 +233,7 @@ 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。

README_VI.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+![cover-v5-optimized](./images/GitHub_README_if.png)
 
 <p align="center">
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
@@ -55,11 +55,6 @@ Dify là một nền tảng phát triển ứng dụng LLM mã nguồn mở. Gia
 **1. Quy trình làm việc**: 
   Xây dựng và kiểm tra các quy trình làm việc AI mạnh mẽ trên một canvas trực quan, tận dụng tất cả các tính năng sau đây và hơn thế nữa.
 
-
-  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
-
-
-
 **2. Hỗ trợ mô hình toàn diện**: 
   Tích hợp liền mạch với hàng trăm mô hình LLM độc quyền / mã nguồn mở từ hàng chục nhà cung cấp suy luận và giải pháp tự lưu trữ, bao gồm GPT, Mistral, Llama3, và bất kỳ mô hình tương thích API OpenAI nào. Danh sách đầy đủ các nhà cung cấp mô hình được hỗ trợ có thể được tìm thấy [tại đây](https://docs.dify.ai/getting-started/readme/model-providers).
 

api/.env.example

@@ -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
@@ -297,6 +299,7 @@ LINDORM_URL=http://ld-*******************-proxy-search-pub.lindorm.aliyuncs.com:
 LINDORM_USERNAME=admin
 LINDORM_PASSWORD=admin
 USING_UGC_INDEX=False
+LINDORM_QUERY_TIMEOUT=1
 
 # OceanBase Vector configuration
 OCEANBASE_VECTOR_HOST=127.0.0.1
@@ -347,6 +350,7 @@ SENTRY_DSN=
 
 # DEBUG
 DEBUG=false
+ENABLE_REQUEST_LOGGING=False
 SQLALCHEMY_ECHO=false
 
 # Notion import configuration, support public and internal
@@ -475,6 +479,7 @@ LOGIN_LOCKOUT_DURATION=86400
 ENABLE_OTEL=false
 OTLP_BASE_ENDPOINT=http://localhost:4318
 OTLP_API_KEY=
+OTEL_EXPORTER_OTLP_PROTOCOL=
 OTEL_EXPORTER_TYPE=otlp
 OTEL_SAMPLING_RATE=0.1
 OTEL_BATCH_EXPORT_SCHEDULE_DELAY=5000
@@ -486,3 +491,10 @@ 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

api/.ruff.toml

@@ -43,6 +43,7 @@ select = [
     "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 = [

api/Dockerfile

@@ -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}
 

api/README.md

@@ -90,3 +90,4 @@
    ```bash
    uv run -P api bash dev/pytest/pytest_all_tests.sh
    ```
+

api/app.py

@@ -18,7 +18,7 @@ else:
     # 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  # type: ignore
+        from gevent import monkey
 
         # gevent
         monkey.patch_all()

api/app_factory.py

@@ -52,10 +52,9 @@ def initialize_extensions(app: DifyApp):
         ext_mail,
         ext_migrate,
         ext_otel,
-        ext_otel_patch,
         ext_proxy_fix,
         ext_redis,
-        ext_repositories,
+        ext_request_logging,
         ext_sentry,
         ext_set_secretkey,
         ext_storage,
@@ -76,7 +75,6 @@ def initialize_extensions(app: DifyApp):
         ext_migrate,
         ext_redis,
         ext_storage,
-        ext_repositories,
         ext_celery,
         ext_login,
         ext_mail,
@@ -85,8 +83,8 @@ def initialize_extensions(app: DifyApp):
         ext_proxy_fix,
         ext_blueprints,
         ext_commands,
-        ext_otel_patch,  # Apply patch before initializing OpenTelemetry
         ext_otel,
+        ext_request_logging,
     ]
     for ext in extensions:
         short_name = ext.__name__.split(".")[-1]

api/commands.py

@@ -6,6 +6,7 @@ from typing import Optional
 
 import click
 from flask import current_app
+from sqlalchemy import select
 from werkzeug.exceptions import NotFound
 
 from configs import dify_config
@@ -17,6 +18,7 @@ from core.rag.models.document import Document
 from events.app_event import app_was_created
 from extensions.ext_database import db
 from extensions.ext_redis import redis_client
+from extensions.ext_storage import storage
 from libs.helper import email as email_validate
 from libs.password import hash_password, password_pattern, valid_password
 from libs.rsa import generate_key_pair
@@ -25,7 +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
@@ -66,6 +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"))
 
 
@@ -271,6 +274,7 @@ def migrate_knowledge_vector_database():
     upper_collection_vector_types = {
         VectorType.MILVUS,
         VectorType.PGVECTOR,
+        VectorType.VASTBASE,
         VectorType.RELYT,
         VectorType.WEAVIATE,
         VectorType.ORACLE,
@@ -295,11 +299,11 @@ def migrate_knowledge_vector_database():
     page = 1
     while True:
         try:
-            datasets = (
-                Dataset.query.filter(Dataset.indexing_technique == "high_quality")
-                .order_by(Dataset.created_at.desc())
-                .paginate(page=page, per_page=50)
+            stmt = (
+                select(Dataset).filter(Dataset.indexing_technique == "high_quality").order_by(Dataset.created_at.desc())
             )
+
+            datasets = db.paginate(select=stmt, page=page, per_page=50, max_per_page=50, error_out=False)
         except NotFound:
             break
 
@@ -442,13 +446,13 @@ def convert_to_agent_apps():
             WHERE a.mode = 'chat'
             AND am.agent_mode is not null
             AND (
-				am.agent_mode like '%"strategy": "function_call"%'
+                am.agent_mode like '%"strategy": "function_call"%'
                 OR am.agent_mode  like '%"strategy": "react"%'
-			)
+            )
             AND (
-				am.agent_mode like '{"enabled": true%'
+                am.agent_mode like '{"enabled": true%'
                 OR am.agent_mode like '{"max_iteration": %'
-			) ORDER BY a.created_at DESC LIMIT 1000
+            ) ORDER BY a.created_at DESC LIMIT 1000
         """
 
         with db.engine.begin() as conn:
@@ -549,11 +553,12 @@ def old_metadata_migration():
     page = 1
     while True:
         try:
-            documents = (
-                DatasetDocument.query.filter(DatasetDocument.doc_metadata is not None)
+            stmt = (
+                select(DatasetDocument)
+                .filter(DatasetDocument.doc_metadata.is_not(None))
                 .order_by(DatasetDocument.created_at.desc())
-                .paginate(page=page, per_page=50)
             )
+            documents = db.paginate(select=stmt, page=page, per_page=50, max_per_page=50, error_out=False)
         except NotFound:
             break
         if not documents:
@@ -590,11 +595,15 @@ def old_metadata_migration():
                             )
                             db.session.add(dataset_metadata_binding)
                         else:
-                            dataset_metadata_binding = DatasetMetadataBinding.query.filter(
-                                DatasetMetadataBinding.dataset_id == document.dataset_id,
-                                DatasetMetadataBinding.document_id == document.id,
-                                DatasetMetadataBinding.metadata_id == dataset_metadata.id,
-                            ).first()
+                            dataset_metadata_binding = (
+                                db.session.query(DatasetMetadataBinding)  # type: ignore
+                                .filter(
+                                    DatasetMetadataBinding.dataset_id == document.dataset_id,
+                                    DatasetMetadataBinding.document_id == document.id,
+                                    DatasetMetadataBinding.metadata_id == dataset_metadata.id,
+                                )
+                                .first()
+                            )
                             if not dataset_metadata_binding:
                                 dataset_metadata_binding = DatasetMetadataBinding(
                                     tenant_id=document.tenant_id,
@@ -666,7 +675,7 @@ def upgrade_db():
             click.echo(click.style("Starting database migration.", fg="green"))
 
             # run db migration
-            import flask_migrate  # type: ignore
+            import flask_migrate
 
             flask_migrate.upgrade()
 
@@ -814,3 +823,334 @@ def clear_free_plan_tenant_expired_logs(days: int, batch: int, tenant_ids: list[
     ClearFreePlanTenantExpiredLogs.process(days, batch, tenant_ids)
 
     click.echo(click.style("Clear free plan tenant expired logs completed.", fg="green"))
+
+
+@click.option("-f", "--force", is_flag=True, help="Skip user confirmation and force the command to execute.")
+@click.command("clear-orphaned-file-records", help="Clear orphaned file records.")
+def clear_orphaned_file_records(force: bool):
+    """
+    Clear orphaned file records in the database.
+    """
+
+    # define tables and columns to process
+    files_tables = [
+        {"table": "upload_files", "id_column": "id", "key_column": "key"},
+        {"table": "tool_files", "id_column": "id", "key_column": "file_key"},
+    ]
+    ids_tables = [
+        {"type": "uuid", "table": "message_files", "column": "upload_file_id"},
+        {"type": "text", "table": "documents", "column": "data_source_info"},
+        {"type": "text", "table": "document_segments", "column": "content"},
+        {"type": "text", "table": "messages", "column": "answer"},
+        {"type": "text", "table": "workflow_node_executions", "column": "inputs"},
+        {"type": "text", "table": "workflow_node_executions", "column": "process_data"},
+        {"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"},
+    ]
+
+    # notify user and ask for confirmation
+    click.echo(
+        click.style(
+            "This command will first find and delete orphaned file records from the message_files table,", fg="yellow"
+        )
+    )
+    click.echo(
+        click.style(
+            "and then it will find and delete orphaned file records in the following tables:",
+            fg="yellow",
+        )
+    )
+    for files_table in files_tables:
+        click.echo(click.style(f"- {files_table['table']}", fg="yellow"))
+    click.echo(
+        click.style("The following tables and columns will be scanned to find orphaned file records:", fg="yellow")
+    )
+    for ids_table in ids_tables:
+        click.echo(click.style(f"- {ids_table['table']} ({ids_table['column']})", fg="yellow"))
+    click.echo("")
+
+    click.echo(click.style("!!! USE WITH CAUTION !!!", fg="red"))
+    click.echo(
+        click.style(
+            (
+                "Since not all patterns have been fully tested, "
+                "please note that this command may delete unintended file records."
+            ),
+            fg="yellow",
+        )
+    )
+    click.echo(
+        click.style("This cannot be undone. Please make sure to back up your database before proceeding.", fg="yellow")
+    )
+    click.echo(
+        click.style(
+            (
+                "It is also recommended to run this during the maintenance window, "
+                "as this may cause high load on your instance."
+            ),
+            fg="yellow",
+        )
+    )
+    if not force:
+        click.confirm("Do you want to proceed?", abort=True)
+
+    # start the cleanup process
+    click.echo(click.style("Starting orphaned file records cleanup.", fg="white"))
+
+    # clean up the orphaned records in the message_files table where message_id doesn't exist in messages table
+    try:
+        click.echo(
+            click.style("- Listing message_files records where message_id doesn't exist in messages table", fg="white")
+        )
+        query = (
+            "SELECT mf.id, mf.message_id "
+            "FROM message_files mf LEFT JOIN messages m ON mf.message_id = m.id "
+            "WHERE m.id IS NULL"
+        )
+        orphaned_message_files = []
+        with db.engine.begin() as conn:
+            rs = conn.execute(db.text(query))
+            for i in rs:
+                orphaned_message_files.append({"id": str(i[0]), "message_id": str(i[1])})
+
+        if orphaned_message_files:
+            click.echo(click.style(f"Found {len(orphaned_message_files)} orphaned message_files records:", fg="white"))
+            for record in orphaned_message_files:
+                click.echo(click.style(f"  - id: {record['id']}, message_id: {record['message_id']}", fg="black"))
+
+            if not force:
+                click.confirm(
+                    (
+                        f"Do you want to proceed "
+                        f"to delete all {len(orphaned_message_files)} orphaned message_files records?"
+                    ),
+                    abort=True,
+                )
+
+            click.echo(click.style("- Deleting orphaned message_files records", fg="white"))
+            query = "DELETE FROM message_files WHERE id IN :ids"
+            with db.engine.begin() as conn:
+                conn.execute(db.text(query), {"ids": tuple([record["id"] for record in orphaned_message_files])})
+            click.echo(
+                click.style(f"Removed {len(orphaned_message_files)} orphaned message_files records.", fg="green")
+            )
+        else:
+            click.echo(click.style("No orphaned message_files records found. There is nothing to delete.", fg="green"))
+    except Exception as e:
+        click.echo(click.style(f"Error deleting orphaned message_files records: {str(e)}", fg="red"))
+
+    # clean up the orphaned records in the rest of the *_files tables
+    try:
+        # fetch file id and keys from each table
+        all_files_in_tables = []
+        for files_table in files_tables:
+            click.echo(click.style(f"- Listing file records in table {files_table['table']}", fg="white"))
+            query = f"SELECT {files_table['id_column']}, {files_table['key_column']} FROM {files_table['table']}"
+            with db.engine.begin() as conn:
+                rs = conn.execute(db.text(query))
+            for i in rs:
+                all_files_in_tables.append({"table": files_table["table"], "id": str(i[0]), "key": i[1]})
+        click.echo(click.style(f"Found {len(all_files_in_tables)} files in tables.", fg="white"))
+
+        # fetch referred table and columns
+        guid_regexp = "[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{12}"
+        all_ids_in_tables = []
+        for ids_table in ids_tables:
+            query = ""
+            if ids_table["type"] == "uuid":
+                click.echo(
+                    click.style(
+                        f"- Listing file ids in column {ids_table['column']} in table {ids_table['table']}", fg="white"
+                    )
+                )
+                query = (
+                    f"SELECT {ids_table['column']} FROM {ids_table['table']} WHERE {ids_table['column']} IS NOT NULL"
+                )
+                with db.engine.begin() as conn:
+                    rs = conn.execute(db.text(query))
+                for i in rs:
+                    all_ids_in_tables.append({"table": ids_table["table"], "id": str(i[0])})
+            elif ids_table["type"] == "text":
+                click.echo(
+                    click.style(
+                        f"- Listing file-id-like strings in column {ids_table['column']} in table {ids_table['table']}",
+                        fg="white",
+                    )
+                )
+                query = (
+                    f"SELECT regexp_matches({ids_table['column']}, '{guid_regexp}', 'g') AS extracted_id "
+                    f"FROM {ids_table['table']}"
+                )
+                with db.engine.begin() as conn:
+                    rs = conn.execute(db.text(query))
+                for i in rs:
+                    for j in i[0]:
+                        all_ids_in_tables.append({"table": ids_table["table"], "id": j})
+            elif ids_table["type"] == "json":
+                click.echo(
+                    click.style(
+                        (
+                            f"- Listing file-id-like JSON string in column {ids_table['column']} "
+                            f"in table {ids_table['table']}"
+                        ),
+                        fg="white",
+                    )
+                )
+                query = (
+                    f"SELECT regexp_matches({ids_table['column']}::text, '{guid_regexp}', 'g') AS extracted_id "
+                    f"FROM {ids_table['table']}"
+                )
+                with db.engine.begin() as conn:
+                    rs = conn.execute(db.text(query))
+                for i in rs:
+                    for j in i[0]:
+                        all_ids_in_tables.append({"table": ids_table["table"], "id": j})
+        click.echo(click.style(f"Found {len(all_ids_in_tables)} file ids in tables.", fg="white"))
+
+    except Exception as e:
+        click.echo(click.style(f"Error fetching keys: {str(e)}", fg="red"))
+        return
+
+    # find orphaned files
+    all_files = [file["id"] for file in all_files_in_tables]
+    all_ids = [file["id"] for file in all_ids_in_tables]
+    orphaned_files = list(set(all_files) - set(all_ids))
+    if not orphaned_files:
+        click.echo(click.style("No orphaned file records found. There is nothing to delete.", fg="green"))
+        return
+    click.echo(click.style(f"Found {len(orphaned_files)} orphaned file records.", fg="white"))
+    for file in orphaned_files:
+        click.echo(click.style(f"- orphaned file id: {file}", fg="black"))
+    if not force:
+        click.confirm(f"Do you want to proceed to delete all {len(orphaned_files)} orphaned file records?", abort=True)
+
+    # delete orphaned records for each file
+    try:
+        for files_table in files_tables:
+            click.echo(click.style(f"- Deleting orphaned file records in table {files_table['table']}", fg="white"))
+            query = f"DELETE FROM {files_table['table']} WHERE {files_table['id_column']} IN :ids"
+            with db.engine.begin() as conn:
+                conn.execute(db.text(query), {"ids": tuple(orphaned_files)})
+    except Exception as e:
+        click.echo(click.style(f"Error deleting orphaned file records: {str(e)}", fg="red"))
+        return
+    click.echo(click.style(f"Removed {len(orphaned_files)} orphaned file records.", fg="green"))
+
+
+@click.option("-f", "--force", is_flag=True, help="Skip user confirmation and force the command to execute.")
+@click.command("remove-orphaned-files-on-storage", help="Remove orphaned files on the storage.")
+def remove_orphaned_files_on_storage(force: bool):
+    """
+    Remove orphaned files on the storage.
+    """
+
+    # define tables and columns to process
+    files_tables = [
+        {"table": "upload_files", "key_column": "key"},
+        {"table": "tool_files", "key_column": "file_key"},
+    ]
+    storage_paths = ["image_files", "tools", "upload_files"]
+
+    # notify user and ask for confirmation
+    click.echo(click.style("This command will find and remove orphaned files on the storage,", fg="yellow"))
+    click.echo(
+        click.style("by comparing the files on the storage with the records in the following tables:", fg="yellow")
+    )
+    for files_table in files_tables:
+        click.echo(click.style(f"- {files_table['table']}", fg="yellow"))
+    click.echo(click.style("The following paths on the storage will be scanned to find orphaned files:", fg="yellow"))
+    for storage_path in storage_paths:
+        click.echo(click.style(f"- {storage_path}", fg="yellow"))
+    click.echo("")
+
+    click.echo(click.style("!!! USE WITH CAUTION !!!", fg="red"))
+    click.echo(
+        click.style(
+            "Currently, this command will work only for opendal based storage (STORAGE_TYPE=opendal).", fg="yellow"
+        )
+    )
+    click.echo(
+        click.style(
+            "Since not all patterns have been fully tested, please note that this command may delete unintended files.",
+            fg="yellow",
+        )
+    )
+    click.echo(
+        click.style("This cannot be undone. Please make sure to back up your storage before proceeding.", fg="yellow")
+    )
+    click.echo(
+        click.style(
+            (
+                "It is also recommended to run this during the maintenance window, "
+                "as this may cause high load on your instance."
+            ),
+            fg="yellow",
+        )
+    )
+    if not force:
+        click.confirm("Do you want to proceed?", abort=True)
+
+    # start the cleanup process
+    click.echo(click.style("Starting orphaned files cleanup.", fg="white"))
+
+    # fetch file id and keys from each table
+    all_files_in_tables = []
+    try:
+        for files_table in files_tables:
+            click.echo(click.style(f"- Listing files from table {files_table['table']}", fg="white"))
+            query = f"SELECT {files_table['key_column']} FROM {files_table['table']}"
+            with db.engine.begin() as conn:
+                rs = conn.execute(db.text(query))
+            for i in rs:
+                all_files_in_tables.append(str(i[0]))
+        click.echo(click.style(f"Found {len(all_files_in_tables)} files in tables.", fg="white"))
+    except Exception as e:
+        click.echo(click.style(f"Error fetching keys: {str(e)}", fg="red"))
+
+    all_files_on_storage = []
+    for storage_path in storage_paths:
+        try:
+            click.echo(click.style(f"- Scanning files on storage path {storage_path}", fg="white"))
+            files = storage.scan(path=storage_path, files=True, directories=False)
+            all_files_on_storage.extend(files)
+        except FileNotFoundError as e:
+            click.echo(click.style(f"  -> Skipping path {storage_path} as it does not exist.", fg="yellow"))
+            continue
+        except Exception as e:
+            click.echo(click.style(f"  -> Error scanning files on storage path {storage_path}: {str(e)}", fg="red"))
+            continue
+    click.echo(click.style(f"Found {len(all_files_on_storage)} files on storage.", fg="white"))
+
+    # find orphaned files
+    orphaned_files = list(set(all_files_on_storage) - set(all_files_in_tables))
+    if not orphaned_files:
+        click.echo(click.style("No orphaned files found. There is nothing to remove.", fg="green"))
+        return
+    click.echo(click.style(f"Found {len(orphaned_files)} orphaned files.", fg="white"))
+    for file in orphaned_files:
+        click.echo(click.style(f"- orphaned file: {file}", fg="black"))
+    if not force:
+        click.confirm(f"Do you want to proceed to remove all {len(orphaned_files)} orphaned files?", abort=True)
+
+    # delete orphaned files
+    removed_files = 0
+    error_files = 0
+    for file in orphaned_files:
+        try:
+            storage.delete(file)
+            removed_files += 1
+            click.echo(click.style(f"- Removing orphaned file: {file}", fg="white"))
+        except Exception as e:
+            error_files += 1
+            click.echo(click.style(f"- Error deleting orphaned file {file}: {str(e)}", fg="red"))
+            continue
+    if error_files == 0:
+        click.echo(click.style(f"Removed {removed_files} orphaned files without errors.", fg="green"))
+    else:
+        click.echo(click.style(f"Removed {removed_files} orphaned files, with {error_files} errors.", fg="yellow"))

api/configs/deploy/__init__.py

@@ -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",

api/configs/feature/__init__.py

@@ -74,7 +74,7 @@ class CodeExecutionSandboxConfig(BaseSettings):
 
     CODE_EXECUTION_ENDPOINT: HttpUrl = Field(
         description="URL endpoint for the code execution service",
-        default="http://sandbox:8194",
+        default=HttpUrl("http://sandbox:8194"),
     )
 
     CODE_EXECUTION_API_KEY: str = Field(
@@ -145,7 +145,7 @@ class PluginConfig(BaseSettings):
 
     PLUGIN_DAEMON_URL: HttpUrl = Field(
         description="Plugin API URL",
-        default="http://localhost:5002",
+        default=HttpUrl("http://localhost:5002"),
     )
 
     PLUGIN_DAEMON_KEY: str = Field(
@@ -188,7 +188,7 @@ class MarketplaceConfig(BaseSettings):
 
     MARKETPLACE_API_URL: HttpUrl = Field(
         description="Marketplace API URL",
-        default="https://marketplace.dify.ai",
+        default=HttpUrl("https://marketplace.dify.ai"),
     )
 
 
@@ -398,6 +398,11 @@ class InnerAPIConfig(BaseSettings):
         default=False,
     )
 
+    INNER_API_KEY: Optional[str] = Field(
+        description="API key for accessing the internal API",
+        default=None,
+    )
+
 
 class LoggingConfig(BaseSettings):
     """

api/configs/middleware/__init__.py

@@ -1,8 +1,8 @@
 import os
 from typing import Any, Literal, Optional
-from urllib.parse import quote_plus
+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
@@ -39,6 +39,7 @@ from .vdb.tencent_vector_config import TencentVectorDBConfig
 from .vdb.tidb_on_qdrant_config import TidbOnQdrantConfig
 from .vdb.tidb_vector_config import TiDBVectorConfig
 from .vdb.upstash_config import UpstashConfig
+from .vdb.vastbase_vector_config import VastbaseVectorConfig
 from .vdb.vikingdb_config import VikingDBConfig
 from .vdb.weaviate_config import WeaviateConfig
 
@@ -172,17 +173,31 @@ class DatabaseConfig(BaseSettings):
 
     RETRIEVAL_SERVICE_EXECUTORS: NonNegativeInt = Field(
         description="Number of processes for the retrieval service, default to CPU cores.",
-        default=os.cpu_count(),
+        default=os.cpu_count() or 1,
     )
 
-    @computed_field
+    @computed_field  # type: ignore[misc]
+    @property
     def SQLALCHEMY_ENGINE_OPTIONS(self) -> dict[str, Any]:
+        # Parse DB_EXTRAS for 'options'
+        db_extras_dict = dict(parse_qsl(self.DB_EXTRAS))
+        options = db_extras_dict.get("options", "")
+        # Always include timezone
+        timezone_opt = "-c timezone=UTC"
+        if options:
+            # Merge user options and timezone
+            merged_options = f"{options} {timezone_opt}"
+        else:
+            merged_options = timezone_opt
+
+        connect_args = {"options": merged_options}
+
         return {
             "pool_size": self.SQLALCHEMY_POOL_SIZE,
             "max_overflow": self.SQLALCHEMY_MAX_OVERFLOW,
             "pool_recycle": self.SQLALCHEMY_POOL_RECYCLE,
             "pool_pre_ping": self.SQLALCHEMY_POOL_PRE_PING,
-            "connect_args": {"options": "-c timezone=UTC"},
+            "connect_args": connect_args,
         }
 
 
@@ -241,6 +256,25 @@ 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,
@@ -270,6 +304,7 @@ class MiddlewareConfig(
     OpenSearchConfig,
     OracleConfig,
     PGVectorConfig,
+    VastbaseVectorConfig,
     PGVectoRSConfig,
     QdrantConfig,
     RelytConfig,
@@ -287,5 +322,6 @@ class MiddlewareConfig(
     BaiduVectorDBConfig,
     OpenGaussConfig,
     TableStoreConfig,
+    DatasetQueueMonitorConfig,
 ):
     pass

api/configs/middleware/cache/redis_config.py

@@ -83,3 +83,13 @@ class RedisConfig(BaseSettings):
         description="Password for Redis Clusters authentication (if required)",
         default=None,
     )
+
+    REDIS_SERIALIZATION_PROTOCOL: int = Field(
+        description="Redis serialization protocol (RESP) version",
+        default=3,
+    )
+
+    REDIS_ENABLE_CLIENT_SIDE_CACHE: bool = Field(
+        description="Enable client side cache in redis",
+        default=False,
+    )

api/configs/middleware/storage/amazon_s3_storage_config.py

@@ -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",
     )

api/configs/middleware/vdb/lindorm_config.py

@@ -32,3 +32,4 @@ class LindormConfig(BaseSettings):
         description="Using UGC index will store the same type of Index in a single index but can retrieve separately.",
         default=False,
     )
+    LINDORM_QUERY_TIMEOUT: Optional[float] = Field(description="The lindorm search request timeout (s)", default=2.0)

api/configs/middleware/vdb/opensearch_config.py

@@ -1,4 +1,5 @@
-from typing import Optional
+import enum
+from typing import Literal, Optional
 
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
@@ -9,6 +10,14 @@ class OpenSearchConfig(BaseSettings):
     Configuration settings for OpenSearch
     """
 
+    class AuthMethod(enum.StrEnum):
+        """
+        Authentication method for OpenSearch
+        """
+
+        BASIC = "basic"
+        AWS_MANAGED_IAM = "aws_managed_iam"
+
     OPENSEARCH_HOST: Optional[str] = Field(
         description="Hostname or IP address of the OpenSearch server (e.g., 'localhost' or 'opensearch.example.com')",
         default=None,
@@ -19,6 +28,21 @@ class OpenSearchConfig(BaseSettings):
         default=9200,
     )
 
+    OPENSEARCH_SECURE: bool = Field(
+        description="Whether to use SSL/TLS encrypted connection for OpenSearch (True for HTTPS, False for HTTP)",
+        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,
+    )
+
     OPENSEARCH_USER: Optional[str] = Field(
         description="Username for authenticating with OpenSearch",
         default=None,
@@ -29,7 +53,11 @@ class OpenSearchConfig(BaseSettings):
         default=None,
     )
 
-    OPENSEARCH_SECURE: bool = Field(
-        description="Whether to use SSL/TLS encrypted connection for OpenSearch (True for HTTPS, False for HTTP)",
-        default=False,
+    OPENSEARCH_AWS_REGION: Optional[str] = Field(
+        description="AWS region for OpenSearch (e.g. 'us-west-2')",
+        default=None,
+    )
+
+    OPENSEARCH_AWS_SERVICE: Optional[Literal["es", "aoss"]] = Field(
+        description="AWS service for OpenSearch (e.g. 'aoss' for OpenSearch Serverless)", default=None
     )

api/configs/middleware/vdb/qdrant_config.py

@@ -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,
+    )

api/configs/middleware/vdb/vastbase_vector_config.py

@@ -0,0 +1,45 @@
+from typing import Optional
+
+from pydantic import Field, PositiveInt
+from pydantic_settings import BaseSettings
+
+
+class VastbaseVectorConfig(BaseSettings):
+    """
+    Configuration settings for Vector (Vastbase with vector extension)
+    """
+
+    VASTBASE_HOST: Optional[str] = Field(
+        description="Hostname or IP address of the Vastbase server with Vector extension (e.g., 'localhost')",
+        default=None,
+    )
+
+    VASTBASE_PORT: PositiveInt = Field(
+        description="Port number on which the Vastbase server is listening (default is 5432)",
+        default=5432,
+    )
+
+    VASTBASE_USER: Optional[str] = Field(
+        description="Username for authenticating with the Vastbase database",
+        default=None,
+    )
+
+    VASTBASE_PASSWORD: Optional[str] = Field(
+        description="Password for authenticating with the Vastbase database",
+        default=None,
+    )
+
+    VASTBASE_DATABASE: Optional[str] = Field(
+        description="Name of the Vastbase database to connect to",
+        default=None,
+    )
+
+    VASTBASE_MIN_CONNECTION: PositiveInt = Field(
+        description="Min connection of the Vastbase database",
+        default=1,
+    )
+
+    VASTBASE_MAX_CONNECTION: PositiveInt = Field(
+        description="Max connection of the Vastbase database",
+        default=5,
+    )

api/configs/observability/otel/otel_config.py

@@ -27,6 +27,11 @@ class OTelConfig(BaseSettings):
         default="otlp",
     )
 
+    OTEL_EXPORTER_OTLP_PROTOCOL: str = Field(
+        description="OTLP exporter protocol ('grpc' or 'http')",
+        default="http",
+    )
+
     OTEL_SAMPLING_RATE: float = Field(default=0.1, description="Sampling rate for traces (0.0 to 1.0)")
 
     OTEL_BATCH_EXPORT_SCHEDULE_DELAY: int = Field(

api/configs/packaging/__init__.py

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
 
     CURRENT_VERSION: str = Field(
         description="Dify version",
-        default="1.3.0",
+        default="1.4.3",
     )
 
     COMMIT_SHA: str = Field(

api/configs/remote_settings_sources/nacos/http_request.py

@@ -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):

api/constants/__init__.py

@@ -16,11 +16,25 @@ AUDIO_EXTENSIONS.extend([ext.upper() for ext in AUDIO_EXTENSIONS])
 
 
 if dify_config.ETL_TYPE == "Unstructured":
-    DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "mdx", "pdf", "html", "htm", "xlsx", "xls"]
+    DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "mdx", "pdf", "html", "htm", "xlsx", "xls", "vtt", "properties"]
     DOCUMENT_EXTENSIONS.extend(("doc", "docx", "csv", "eml", "msg", "pptx", "xml", "epub"))
     if dify_config.UNSTRUCTURED_API_URL:
         DOCUMENT_EXTENSIONS.append("ppt")
     DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])
 else:
-    DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "mdx", "pdf", "html", "htm", "xlsx", "xls", "docx", "csv"]
+    DOCUMENT_EXTENSIONS = [
+        "txt",
+        "markdown",
+        "md",
+        "mdx",
+        "pdf",
+        "html",
+        "htm",
+        "xlsx",
+        "xls",
+        "docx",
+        "csv",
+        "vtt",
+        "properties",
+    ]
     DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])

api/constants/mimetypes.py

@@ -0,0 +1,7 @@
+# The two constants below should keep in sync.
+# Default content type for files which have no explicit content type.
+
+DEFAULT_MIME_TYPE = "application/octet-stream"
+# Default file extension for files which have no explicit content type, should
+# correspond to the `DEFAULT_MIME_TYPE` above.
+DEFAULT_EXTENSION = ".bin"

api/contexts/__init__.py

@@ -11,10 +11,6 @@ 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
 """

api/controllers/common/fields.py

@@ -1,4 +1,6 @@
-from flask_restful import fields  # type: ignore
+from flask_restful import fields
+
+from libs.helper import AppIconUrlField
 
 parameters__system_parameters = {
     "image_file_size_limit": fields.Integer,
@@ -22,3 +24,20 @@ parameters_fields = {
     "file_upload": fields.Raw,
     "system_parameters": fields.Nested(parameters__system_parameters),
 }
+
+site_fields = {
+    "title": fields.String,
+    "chat_color_theme": fields.String,
+    "chat_color_theme_inverted": fields.Boolean,
+    "icon_type": fields.String,
+    "icon": fields.String,
+    "icon_background": fields.String,
+    "icon_url": AppIconUrlField,
+    "description": fields.String,
+    "copyright": fields.String,
+    "privacy_policy": fields.String,
+    "custom_disclaimer": fields.String,
+    "default_language": fields.String,
+    "show_workflow_steps": fields.Boolean,
+    "use_icon_as_answer_icon": fields.Boolean,
+}

api/controllers/console/admin.py

@@ -1,7 +1,7 @@
 from functools import wraps
 
 from flask import request
-from flask_restful import Resource, reqparse  # type: ignore
+from flask_restful import Resource, reqparse
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import NotFound, Unauthorized

api/controllers/console/apikey.py

@@ -1,7 +1,7 @@
 from typing import Any
 
-import flask_restful  # type: ignore
-from flask_login import current_user  # type: ignore
+import flask_restful
+from flask_login import current_user
 from flask_restful import Resource, fields, marshal_with
 from sqlalchemy import select
 from sqlalchemy.orm import Session

api/controllers/console/app/advanced_prompt_template.py

@@ -1,4 +1,4 @@
-from flask_restful import Resource, reqparse  # type: ignore
+from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.wraps import account_initialization_required, setup_required

api/controllers/console/app/agent.py

@@ -1,4 +1,4 @@
-from flask_restful import Resource, reqparse  # type: ignore
+from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model

api/controllers/console/app/annotation.py

@@ -1,6 +1,6 @@
 from flask import request
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource, marshal, marshal_with, reqparse  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource, marshal, marshal_with, reqparse
 from werkzeug.exceptions import Forbidden
 
 from controllers.console import api
@@ -186,7 +186,7 @@ class AnnotationUpdateDeleteApi(Resource):
         app_id = str(app_id)
         annotation_id = str(annotation_id)
         AppAnnotationService.delete_app_annotation(app_id, annotation_id)
-        return {"result": "success"}, 200
+        return {"result": "success"}, 204
 
 
 class AnnotationBatchImportApi(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.endswith(".csv"):
             raise ValueError("Invalid file type. Only CSV files are allowed")
         return AppAnnotationService.batch_import_app_annotations(app_id, file)
 

api/controllers/console/app/app.py

@@ -1,8 +1,8 @@
 import uuid
 from typing import cast
 
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource, inputs, marshal, marshal_with, reqparse  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource, inputs, marshal, marshal_with, reqparse
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import BadRequest, Forbidden, abort
@@ -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

api/controllers/console/app/app_import.py

@@ -1,7 +1,7 @@
 from typing import cast
 
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource, marshal_with, reqparse  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource, marshal_with, reqparse
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import Forbidden
 

api/controllers/console/app/audio.py

@@ -1,7 +1,7 @@
 import logging
 
 from flask import request
-from flask_restful import Resource, reqparse  # type: ignore
+from flask_restful import Resource, reqparse
 from werkzeug.exceptions import InternalServerError
 
 import services

api/controllers/console/app/completion.py

@@ -1,7 +1,7 @@
 import logging
 
-import flask_login  # type: ignore
-from flask_restful import Resource, reqparse  # type: ignore
+import flask_login
+from flask_restful import Resource, reqparse
 from werkzeug.exceptions import InternalServerError, NotFound
 
 import services

api/controllers/console/app/conversation.py

@@ -1,9 +1,9 @@
 from datetime import UTC, datetime
 
 import pytz  # pip install pytz
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource, marshal_with, reqparse  # type: ignore
-from flask_restful.inputs import int_range  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource, marshal_with, reqparse
+from flask_restful.inputs import int_range
 from sqlalchemy import func, or_
 from sqlalchemy.orm import joinedload
 from werkzeug.exceptions import Forbidden, NotFound

api/controllers/console/app/conversation_variables.py

@@ -1,4 +1,4 @@
-from flask_restful import Resource, marshal_with, reqparse  # type: ignore
+from flask_restful import Resource, marshal_with, reqparse
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 

api/controllers/console/app/generator.py

@@ -1,7 +1,7 @@
 import os
 
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource, reqparse  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.app.error import (

api/controllers/console/app/message.py

@@ -1,8 +1,8 @@
 import logging
 
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource, fields, marshal_with, reqparse  # type: ignore
-from flask_restful.inputs import int_range  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource, fields, marshal_with, reqparse
+from flask_restful.inputs import int_range
 from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 
 from controllers.console import api

api/controllers/console/app/model_config.py

@@ -2,8 +2,8 @@ import json
 from typing import cast
 
 from flask import request
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model

api/controllers/console/app/ops_trace.py

@@ -1,4 +1,4 @@
-from flask_restful import Resource, reqparse  # type: ignore
+from flask_restful import Resource, reqparse
 from werkzeug.exceptions import BadRequest
 
 from controllers.console import api
@@ -84,7 +84,7 @@ class TraceAppConfigApi(Resource):
             result = OpsService.delete_tracing_app_config(app_id=app_id, tracing_provider=args["tracing_provider"])
             if not result:
                 raise TracingConfigNotExist()
-            return {"result": "success"}
+            return {"result": "success"}, 204
         except Exception as e:
             raise BadRequest(str(e))
 

api/controllers/console/app/site.py

@@ -1,7 +1,7 @@
 from datetime import UTC, datetime
 
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource, marshal_with, reqparse  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource, marshal_with, reqparse
 from werkzeug.exceptions import Forbidden, NotFound
 
 from constants.languages import supported_language

api/controllers/console/app/statistic.py

@@ -3,8 +3,8 @@ from decimal import Decimal
 
 import pytz
 from flask import jsonify
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource, reqparse  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model

api/controllers/console/app/workflow.py

@@ -3,7 +3,7 @@ import logging
 from typing import cast
 
 from flask import abort, request
-from flask_restful import Resource, inputs, marshal_with, reqparse  # type: ignore
+from flask_restful import Resource, inputs, marshal_with, reqparse
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 
@@ -81,8 +81,7 @@ 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:

api/controllers/console/app/workflow_app_log.py

@@ -1,17 +1,17 @@
 from dateutil.parser import isoparse
-from flask_restful import Resource, marshal_with, reqparse  # type: ignore
-from flask_restful.inputs import int_range  # type: ignore
+from flask_restful import Resource, marshal_with, reqparse
+from flask_restful.inputs import int_range
 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
 
 
@@ -38,7 +38,7 @@ class WorkflowAppLogApi(Resource):
         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)
 

api/controllers/console/app/workflow_run.py

@@ -1,5 +1,8 @@
-from flask_restful import Resource, marshal_with, reqparse  # type: ignore
-from flask_restful.inputs import int_range  # type: ignore
+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
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
@@ -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}
 

api/controllers/console/app/workflow_statistic.py

@@ -3,8 +3,8 @@ from decimal import Decimal
 
 import pytz
 from flask import jsonify
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource, reqparse  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model

api/controllers/console/auth/activate.py

@@ -1,7 +1,7 @@
 import datetime
 
 from flask import request
-from flask_restful import Resource, reqparse  # type: ignore
+from flask_restful import Resource, reqparse
 
 from constants.languages import supported_language
 from controllers.console import api

api/controllers/console/auth/data_source_bearer_auth.py

@@ -1,5 +1,5 @@
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource, reqparse  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource, reqparse
 from werkzeug.exceptions import Forbidden
 
 from controllers.console import api
@@ -65,7 +65,7 @@ class ApiKeyAuthDataSourceBindingDelete(Resource):
 
         ApiKeyAuthService.delete_provider_auth(current_user.current_tenant_id, binding_id)
 
-        return {"result": "success"}, 200
+        return {"result": "success"}, 204
 
 
 api.add_resource(ApiKeyAuthDataSource, "/api-key-auth/data-source")

api/controllers/console/auth/data_source_oauth.py

@@ -2,8 +2,8 @@ import logging
 
 import requests
 from flask import current_app, redirect, request
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource
 from werkzeug.exceptions import Forbidden
 
 from configs import dify_config

api/controllers/console/auth/forgot_password.py

@@ -2,7 +2,7 @@ import base64
 import secrets
 
 from flask import request
-from flask_restful import Resource, reqparse  # type: ignore
+from flask_restful import Resource, reqparse
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 
@@ -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()
 

api/controllers/console/auth/login.py

@@ -1,8 +1,8 @@
 from typing import cast
 
-import flask_login  # type: ignore
+import flask_login
 from flask import request
-from flask_restful import Resource, reqparse  # type: ignore
+from flask_restful import Resource, reqparse
 
 import services
 from configs import dify_config
@@ -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()}

api/controllers/console/auth/oauth.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 import requests
 from flask import current_app, redirect, request
-from flask_restful import Resource  # type: ignore
+from flask_restful import Resource
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import Unauthorized
@@ -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:

api/controllers/console/billing/billing.py

@@ -1,5 +1,5 @@
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource, reqparse  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.wraps import account_initialization_required, only_edition_cloud, setup_required

api/controllers/console/billing/compliance.py

@@ -1,6 +1,6 @@
 from flask import request
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource, reqparse  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource, reqparse
 
 from libs.helper import extract_remote_ip
 from libs.login import login_required

api/controllers/console/datasets/data_source.py

@@ -2,8 +2,8 @@ import datetime
 import json
 
 from flask import request
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource, marshal_with, reqparse  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource, marshal_with, reqparse
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import NotFound

api/controllers/console/datasets/datasets.py

@@ -1,7 +1,7 @@
-import flask_restful  # type: ignore
+import flask_restful
 from flask import request
-from flask_login import current_user  # type: ignore  # type: ignore
-from flask_restful import Resource, marshal, marshal_with, reqparse  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource, marshal, marshal_with, reqparse
 from werkzeug.exceptions import Forbidden, NotFound
 
 import services
@@ -526,17 +526,36 @@ class DatasetIndexingStatusApi(Resource):
         )
         documents_status = []
         for document in documents:
-            completed_segments = DocumentSegment.query.filter(
-                DocumentSegment.completed_at.isnot(None),
-                DocumentSegment.document_id == str(document.id),
-                DocumentSegment.status != "re_segment",
-            ).count()
-            total_segments = DocumentSegment.query.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))
+            completed_segments = (
+                db.session.query(DocumentSegment)
+                .filter(
+                    DocumentSegment.completed_at.isnot(None),
+                    DocumentSegment.document_id == str(document.id),
+                    DocumentSegment.status != "re_segment",
+                )
+                .count()
+            )
+            total_segments = (
+                db.session.query(DocumentSegment)
+                .filter(DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment")
+                .count()
+            )
+            # 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
 
@@ -657,6 +676,7 @@ class DatasetRetrievalSettingApi(Resource):
                 | VectorType.ELASTICSEARCH
                 | VectorType.ELASTICSEARCH_JA
                 | VectorType.PGVECTOR
+                | VectorType.VASTBASE
                 | VectorType.TIDB_ON_QDRANT
                 | VectorType.LINDORM
                 | VectorType.COUCHBASE
@@ -706,6 +726,7 @@ class DatasetRetrievalSettingMockApi(Resource):
                 | VectorType.ELASTICSEARCH_JA
                 | VectorType.COUCHBASE
                 | VectorType.PGVECTOR
+                | VectorType.VASTBASE
                 | VectorType.LINDORM
                 | VectorType.OPENGAUSS
                 | VectorType.OCEANBASE

api/controllers/console/datasets/datasets_document.py

@@ -4,9 +4,9 @@ from datetime import UTC, datetime
 from typing import cast
 
 from flask import request
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource, fields, marshal, marshal_with, reqparse  # type: ignore
-from sqlalchemy import asc, desc
+from flask_login import current_user
+from flask_restful import Resource, fields, marshal, marshal_with, reqparse
+from sqlalchemy import asc, desc, select
 from werkzeug.exceptions import Forbidden, NotFound
 
 import services
@@ -40,7 +40,7 @@ from core.indexing_runner import IndexingRunner
 from core.model_manager import ModelManager
 from core.model_runtime.entities.model_entities import ModelType
 from core.model_runtime.errors.invoke import InvokeAuthorizationError
-from core.plugin.manager.exc import PluginDaemonClientSideError
+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
@@ -112,7 +112,7 @@ class GetProcessRuleApi(Resource):
         limits = DocumentService.DEFAULT_RULES["limits"]
         if document_id:
             # get the latest process rule
-            document = Document.query.get_or_404(document_id)
+            document = db.get_or_404(Document, document_id)
 
             dataset = DatasetService.get_dataset(document.dataset_id)
 
@@ -175,7 +175,7 @@ class DatasetDocumentListApi(Resource):
         except services.errors.account.NoPermissionError as e:
             raise Forbidden(str(e))
 
-        query = Document.query.filter_by(dataset_id=str(dataset_id), tenant_id=current_user.current_tenant_id)
+        query = select(Document).filter_by(dataset_id=str(dataset_id), tenant_id=current_user.current_tenant_id)
 
         if search:
             search = f"%{search}%"
@@ -209,18 +209,24 @@ class DatasetDocumentListApi(Resource):
                 desc(Document.position),
             )
 
-        paginated_documents = query.paginate(page=page, per_page=limit, max_per_page=100, error_out=False)
+        paginated_documents = db.paginate(select=query, page=page, per_page=limit, max_per_page=100, error_out=False)
         documents = paginated_documents.items
         if fetch:
             for document in documents:
-                completed_segments = DocumentSegment.query.filter(
-                    DocumentSegment.completed_at.isnot(None),
-                    DocumentSegment.document_id == str(document.id),
-                    DocumentSegment.status != "re_segment",
-                ).count()
-                total_segments = DocumentSegment.query.filter(
-                    DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment"
-                ).count()
+                completed_segments = (
+                    db.session.query(DocumentSegment)
+                    .filter(
+                        DocumentSegment.completed_at.isnot(None),
+                        DocumentSegment.document_id == str(document.id),
+                        DocumentSegment.status != "re_segment",
+                    )
+                    .count()
+                )
+                total_segments = (
+                    db.session.query(DocumentSegment)
+                    .filter(DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment")
+                    .count()
+                )
                 document.completed_segments = completed_segments
                 document.total_segments = total_segments
             data = marshal(documents, document_with_segments_fields)
@@ -563,19 +569,36 @@ class DocumentBatchIndexingStatusApi(DocumentResource):
         documents = self.get_batch_documents(dataset_id, batch)
         documents_status = []
         for document in documents:
-            completed_segments = DocumentSegment.query.filter(
-                DocumentSegment.completed_at.isnot(None),
-                DocumentSegment.document_id == str(document.id),
-                DocumentSegment.status != "re_segment",
-            ).count()
-            total_segments = DocumentSegment.query.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))
+            completed_segments = (
+                db.session.query(DocumentSegment)
+                .filter(
+                    DocumentSegment.completed_at.isnot(None),
+                    DocumentSegment.document_id == str(document.id),
+                    DocumentSegment.status != "re_segment",
+                )
+                .count()
+            )
+            total_segments = (
+                db.session.query(DocumentSegment)
+                .filter(DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment")
+                .count()
+            )
+            # 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
 
@@ -589,20 +612,37 @@ class DocumentIndexingStatusApi(DocumentResource):
         document_id = str(document_id)
         document = self.get_document(dataset_id, document_id)
 
-        completed_segments = DocumentSegment.query.filter(
-            DocumentSegment.completed_at.isnot(None),
-            DocumentSegment.document_id == str(document_id),
-            DocumentSegment.status != "re_segment",
-        ).count()
-        total_segments = DocumentSegment.query.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"
-        return marshal(document, document_status_fields)
+        completed_segments = (
+            db.session.query(DocumentSegment)
+            .filter(
+                DocumentSegment.completed_at.isnot(None),
+                DocumentSegment.document_id == str(document_id),
+                DocumentSegment.status != "re_segment",
+            )
+            .count()
+        )
+        total_segments = (
+            db.session.query(DocumentSegment)
+            .filter(DocumentSegment.document_id == str(document_id), DocumentSegment.status != "re_segment")
+            .count()
+        )
+
+        # 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):

api/controllers/console/datasets/datasets_segments.py

@@ -2,8 +2,9 @@ import uuid
 
 import pandas as pd
 from flask import request
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource, marshal, reqparse  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource, marshal, reqparse
+from sqlalchemy import select
 from werkzeug.exceptions import Forbidden, NotFound
 
 import services
@@ -26,6 +27,7 @@ from controllers.console.wraps import (
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.model_manager import ModelManager
 from core.model_runtime.entities.model_entities import ModelType
+from extensions.ext_database import db
 from extensions.ext_redis import redis_client
 from fields.segment_fields import child_chunk_fields, segment_fields
 from libs.login import login_required
@@ -74,9 +76,14 @@ class DatasetDocumentSegmentListApi(Resource):
         hit_count_gte = args["hit_count_gte"]
         keyword = args["keyword"]
 
-        query = DocumentSegment.query.filter(
-            DocumentSegment.document_id == str(document_id), DocumentSegment.tenant_id == current_user.current_tenant_id
-        ).order_by(DocumentSegment.position.asc())
+        query = (
+            select(DocumentSegment)
+            .filter(
+                DocumentSegment.document_id == str(document_id),
+                DocumentSegment.tenant_id == current_user.current_tenant_id,
+            )
+            .order_by(DocumentSegment.position.asc())
+        )
 
         if status_list:
             query = query.filter(DocumentSegment.status.in_(status_list))
@@ -93,7 +100,7 @@ class DatasetDocumentSegmentListApi(Resource):
             elif args["enabled"].lower() == "false":
                 query = query.filter(DocumentSegment.enabled == False)
 
-        segments = query.paginate(page=page, per_page=limit, max_per_page=100, error_out=False)
+        segments = db.paginate(select=query, page=page, per_page=limit, max_per_page=100, error_out=False)
 
         response = {
             "data": marshal(segments.items, segment_fields),
@@ -131,7 +138,7 @@ class DatasetDocumentSegmentListApi(Resource):
         except services.errors.account.NoPermissionError as e:
             raise Forbidden(str(e))
         SegmentService.delete_segments(segment_ids, document, dataset)
-        return {"result": "success"}, 200
+        return {"result": "success"}, 204
 
 
 class DatasetDocumentSegmentApi(Resource):
@@ -276,9 +283,11 @@ class DatasetDocumentSegmentUpdateApi(Resource):
                 raise ProviderNotInitializeError(ex.description)
             # check segment
         segment_id = str(segment_id)
-        segment = DocumentSegment.query.filter(
-            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
-        ).first()
+        segment = (
+            db.session.query(DocumentSegment)
+            .filter(DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id)
+            .first()
+        )
         if not segment:
             raise NotFound("Segment not found.")
         # The role of the current user in the ta table must be admin, owner, dataset_operator, or editor
@@ -320,9 +329,11 @@ class DatasetDocumentSegmentUpdateApi(Resource):
             raise NotFound("Document not found.")
         # check segment
         segment_id = str(segment_id)
-        segment = DocumentSegment.query.filter(
-            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
-        ).first()
+        segment = (
+            db.session.query(DocumentSegment)
+            .filter(DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id)
+            .first()
+        )
         if not segment:
             raise NotFound("Segment not found.")
         # The role of the current user in the ta table must be admin, owner, dataset_operator, or editor
@@ -333,7 +344,7 @@ class DatasetDocumentSegmentUpdateApi(Resource):
         except services.errors.account.NoPermissionError as e:
             raise Forbidden(str(e))
         SegmentService.delete_segment(segment, document, dataset)
-        return {"result": "success"}, 200
+        return {"result": "success"}, 204
 
 
 class DatasetDocumentSegmentBatchImportApi(Resource):
@@ -363,7 +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.endswith(".csv"):
             raise ValueError("Invalid file type. Only CSV files are allowed")
 
         try:
@@ -423,9 +434,11 @@ class ChildChunkAddApi(Resource):
             raise NotFound("Document not found.")
         # check segment
         segment_id = str(segment_id)
-        segment = DocumentSegment.query.filter(
-            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
-        ).first()
+        segment = (
+            db.session.query(DocumentSegment)
+            .filter(DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id)
+            .first()
+        )
         if not segment:
             raise NotFound("Segment not found.")
         if not current_user.is_dataset_editor:
@@ -478,9 +491,11 @@ class ChildChunkAddApi(Resource):
             raise NotFound("Document not found.")
         # check segment
         segment_id = str(segment_id)
-        segment = DocumentSegment.query.filter(
-            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
-        ).first()
+        segment = (
+            db.session.query(DocumentSegment)
+            .filter(DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id)
+            .first()
+        )
         if not segment:
             raise NotFound("Segment not found.")
         parser = reqparse.RequestParser()
@@ -523,9 +538,11 @@ class ChildChunkAddApi(Resource):
             raise NotFound("Document not found.")
             # check segment
         segment_id = str(segment_id)
-        segment = DocumentSegment.query.filter(
-            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
-        ).first()
+        segment = (
+            db.session.query(DocumentSegment)
+            .filter(DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id)
+            .first()
+        )
         if not segment:
             raise NotFound("Segment not found.")
         # The role of the current user in the ta table must be admin, owner, dataset_operator, or editor
@@ -567,16 +584,20 @@ class ChildChunkUpdateApi(Resource):
             raise NotFound("Document not found.")
         # check segment
         segment_id = str(segment_id)
-        segment = DocumentSegment.query.filter(
-            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
-        ).first()
+        segment = (
+            db.session.query(DocumentSegment)
+            .filter(DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id)
+            .first()
+        )
         if not segment:
             raise NotFound("Segment not found.")
         # check child chunk
         child_chunk_id = str(child_chunk_id)
-        child_chunk = ChildChunk.query.filter(
-            ChildChunk.id == str(child_chunk_id), ChildChunk.tenant_id == current_user.current_tenant_id
-        ).first()
+        child_chunk = (
+            db.session.query(ChildChunk)
+            .filter(ChildChunk.id == str(child_chunk_id), ChildChunk.tenant_id == current_user.current_tenant_id)
+            .first()
+        )
         if not child_chunk:
             raise NotFound("Child chunk not found.")
         # The role of the current user in the ta table must be admin, owner, dataset_operator, or editor
@@ -590,7 +611,7 @@ class ChildChunkUpdateApi(Resource):
             SegmentService.delete_child_chunk(child_chunk, dataset)
         except ChildChunkDeleteIndexServiceError as e:
             raise ChildChunkDeleteIndexError(str(e))
-        return {"result": "success"}, 200
+        return {"result": "success"}, 204
 
     @setup_required
     @login_required
@@ -612,16 +633,20 @@ class ChildChunkUpdateApi(Resource):
             raise NotFound("Document not found.")
             # check segment
         segment_id = str(segment_id)
-        segment = DocumentSegment.query.filter(
-            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
-        ).first()
+        segment = (
+            db.session.query(DocumentSegment)
+            .filter(DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id)
+            .first()
+        )
         if not segment:
             raise NotFound("Segment not found.")
         # check child chunk
         child_chunk_id = str(child_chunk_id)
-        child_chunk = ChildChunk.query.filter(
-            ChildChunk.id == str(child_chunk_id), ChildChunk.tenant_id == current_user.current_tenant_id
-        ).first()
+        child_chunk = (
+            db.session.query(ChildChunk)
+            .filter(ChildChunk.id == str(child_chunk_id), ChildChunk.tenant_id == current_user.current_tenant_id)
+            .first()
+        )
         if not child_chunk:
             raise NotFound("Child chunk not found.")
         # The role of the current user in the ta table must be admin, owner, dataset_operator, or editor

api/controllers/console/datasets/external.py

@@ -1,6 +1,6 @@
 from flask import request
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource, marshal, reqparse  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource, marshal, reqparse
 from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 
 import services
@@ -135,7 +135,7 @@ class ExternalApiTemplateApi(Resource):
             raise Forbidden()
 
         ExternalDatasetService.delete_external_knowledge_api(current_user.current_tenant_id, external_knowledge_api_id)
-        return {"result": "success"}, 200
+        return {"result": "success"}, 204
 
 
 class ExternalApiUseCheckApi(Resource):
@@ -209,6 +209,7 @@ class ExternalKnowledgeHitTestingApi(Resource):
         parser = reqparse.RequestParser()
         parser.add_argument("query", type=str, location="json")
         parser.add_argument("external_retrieval_model", type=dict, required=False, location="json")
+        parser.add_argument("metadata_filtering_conditions", type=dict, required=False, location="json")
         args = parser.parse_args()
 
         HitTestingService.hit_testing_args_check(args)
@@ -219,6 +220,7 @@ class ExternalKnowledgeHitTestingApi(Resource):
                 query=args["query"],
                 account=current_user,
                 external_retrieval_model=args["external_retrieval_model"],
+                metadata_filtering_conditions=args["metadata_filtering_conditions"],
             )
 
             return response

api/controllers/console/datasets/hit_testing.py

@@ -1,4 +1,4 @@
-from flask_restful import Resource  # type: ignore
+from flask_restful import Resource
 
 from controllers.console import api
 from controllers.console.datasets.hit_testing_base import DatasetsHitTestingBase

api/controllers/console/datasets/hit_testing_base.py

@@ -1,7 +1,7 @@
 import logging
 
-from flask_login import current_user  # type: ignore
-from flask_restful import marshal, reqparse  # type: ignore
+from flask_login import current_user
+from flask_restful import marshal, reqparse
 from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 
 import services.dataset_service

api/controllers/console/datasets/metadata.py

@@ -1,5 +1,5 @@
-from flask_login import current_user  # type: ignore  # type: ignore
-from flask_restful import Resource, marshal_with, reqparse  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource, marshal_with, reqparse
 from werkzeug.exceptions import NotFound
 
 from controllers.console import api
@@ -82,7 +82,7 @@ class DatasetMetadataApi(Resource):
         DatasetService.check_dataset_permission(dataset, current_user)
 
         MetadataService.delete_metadata(dataset_id_str, metadata_id_str)
-        return 200
+        return {"result": "success"}, 204
 
 
 class DatasetMetadataBuiltInFieldApi(Resource):

api/controllers/console/datasets/website.py

@@ -1,4 +1,4 @@
-from flask_restful import Resource, reqparse  # type: ignore
+from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.datasets.error import WebsiteCrawlError

api/controllers/console/error.py

@@ -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."

api/controllers/console/explore/audio.py

@@ -66,7 +66,7 @@ class ChatAudioApi(InstalledAppResource):
 
 class ChatTextApi(InstalledAppResource):
     def post(self, installed_app):
-        from flask_restful import reqparse  # type: ignore
+        from flask_restful import reqparse
 
         app_model = installed_app.app
         try:

api/controllers/console/explore/completion.py

@@ -1,8 +1,8 @@
 import logging
 from datetime import UTC, datetime
 
-from flask_login import current_user  # type: ignore
-from flask_restful import reqparse  # type: ignore
+from flask_login import current_user
+from flask_restful import reqparse
 from werkzeug.exceptions import InternalServerError, NotFound
 
 import services

api/controllers/console/explore/conversation.py

@@ -1,6 +1,6 @@
-from flask_login import current_user  # type: ignore
-from flask_restful import marshal_with, reqparse  # type: ignore
-from flask_restful.inputs import int_range  # type: ignore
+from flask_login import current_user
+from flask_restful import marshal_with, reqparse
+from flask_restful.inputs import int_range
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import NotFound
 

api/controllers/console/explore/error.py

@@ -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

api/controllers/console/explore/installed_app.py

@@ -1,9 +1,10 @@
+import logging
 from datetime import UTC, datetime
 from typing import Any
 
 from flask import request
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource, inputs, marshal_with, reqparse  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource, inputs, marshal_with, reqparse
 from sqlalchemy import and_
 from werkzeug.exceptions import BadRequest, Forbidden, NotFound
 
@@ -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"],
@@ -66,7 +94,7 @@ class InstalledAppsListApi(Resource):
         parser.add_argument("app_id", type=str, required=True, help="Invalid app_id")
         args = parser.parse_args()
 
-        recommended_app = RecommendedApp.query.filter(RecommendedApp.app_id == args["app_id"]).first()
+        recommended_app = db.session.query(RecommendedApp).filter(RecommendedApp.app_id == args["app_id"]).first()
         if recommended_app is None:
             raise NotFound("App not found")
 
@@ -79,9 +107,11 @@ class InstalledAppsListApi(Resource):
         if not app.is_public:
             raise Forbidden("You can't install a non-public app")
 
-        installed_app = InstalledApp.query.filter(
-            and_(InstalledApp.app_id == args["app_id"], InstalledApp.tenant_id == current_tenant_id)
-        ).first()
+        installed_app = (
+            db.session.query(InstalledApp)
+            .filter(and_(InstalledApp.app_id == args["app_id"], InstalledApp.tenant_id == current_tenant_id))
+            .first()
+        )
 
         if installed_app is None:
             # todo: position
@@ -113,7 +143,7 @@ class InstalledAppApi(InstalledAppResource):
         db.session.delete(installed_app)
         db.session.commit()
 
-        return {"result": "success", "message": "App uninstalled successfully"}
+        return {"result": "success", "message": "App uninstalled successfully"}, 204
 
     def patch(self, installed_app):
         parser = reqparse.RequestParser()

api/controllers/console/explore/message.py

@@ -1,8 +1,8 @@
 import logging
 
-from flask_login import current_user  # type: ignore
-from flask_restful import marshal_with, reqparse  # type: ignore
-from flask_restful.inputs import int_range  # type: ignore
+from flask_login import current_user
+from flask_restful import marshal_with, reqparse
+from flask_restful.inputs import int_range
 from werkzeug.exceptions import InternalServerError, NotFound
 
 import services

api/controllers/console/explore/parameter.py

@@ -1,4 +1,4 @@
-from flask_restful import marshal_with  # type: ignore
+from flask_restful import marshal_with
 
 from controllers.common import fields
 from controllers.console import api

api/controllers/console/explore/recommended_app.py

@@ -1,5 +1,5 @@
-from flask_login import current_user  # type: ignore
-from flask_restful import Resource, fields, marshal_with, reqparse  # type: ignore
+from flask_login import current_user
+from flask_restful import Resource, fields, marshal_with, reqparse
 
 from constants.languages import languages
 from controllers.console import api