Merge branch 'main' into chore/ssrf-config

Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>

.devcontainer/Dockerfile

@@ -1,4 +1,4 @@
-FROM mcr.microsoft.com/devcontainers/python:3.12
+FROM mcr.microsoft.com/devcontainers/python:3.12-bullseye
 
 RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
      && apt-get -y install libgmp-dev libmpfr-dev libmpc-dev

.devcontainer/post_create_command.sh

@@ -1,15 +1,16 @@
 #!/bin/bash
+WORKSPACE_ROOT=$(pwd)
 
 corepack enable
 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,plugin,workflow_storage"' >> ~/.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
+echo "alias start-api=\"cd $WORKSPACE_ROOT/api && uv run python -m flask run --host 0.0.0.0 --port=5001 --debug\"" >> ~/.bashrc
+echo "alias start-worker=\"cd $WORKSPACE_ROOT/api && uv run python -m celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail,ops_trace,app_deletion,plugin,workflow_storage\"" >> ~/.bashrc
+echo "alias start-web=\"cd $WORKSPACE_ROOT/web && pnpm dev\"" >> ~/.bashrc
+echo "alias start-web-prod=\"cd $WORKSPACE_ROOT/web && pnpm build && pnpm start\"" >> ~/.bashrc
+echo "alias start-containers=\"cd $WORKSPACE_ROOT/docker && docker-compose -f docker-compose.middleware.yaml -p dify --env-file middleware.env up -d\"" >> ~/.bashrc
+echo "alias stop-containers=\"cd $WORKSPACE_ROOT/docker && docker-compose -f docker-compose.middleware.yaml -p dify --env-file middleware.env down\"" >> ~/.bashrc
 
 source /home/vscode/.bashrc
 

.github/ISSUE_TEMPLATE/config.yml

@@ -1,5 +1,8 @@
 blank_issues_enabled: false
 contact_links:
+  - name: "\U0001F510 Security Vulnerabilities"
+    url: "https://github.com/langgenius/dify/security/advisories/new"
+    about: Report security vulnerabilities through GitHub Security Advisories to ensure responsible disclosure. 💡 Please do not report security vulnerabilities in public issues.
   - name: "\U0001F4A1 Model Providers & Plugins"
     url: "https://github.com/langgenius/dify-official-plugins/issues/new/choose"
     about: Report issues with official plugins or model providers, you will need to provide the plugin version and other relevant details.

.github/dependabot.yml

@@ -0,0 +1,12 @@
+version: 2
+updates:
+  - package-ecosystem: "npm"
+    directory: "/web"
+    schedule:
+      interval: "weekly"
+    open-pull-requests-limit: 2
+  - package-ecosystem: "uv"
+    directory: "/api"
+    schedule:
+      interval: "weekly"
+    open-pull-requests-limit: 2

.github/workflows/api-tests.yml

@@ -42,11 +42,7 @@ jobs:
       - name: Run Unit tests
         run: |
           uv run --project api bash dev/pytest/pytest_unit_tests.sh
-      - name: Run ty check
-        run: |
-          cd api
-          uv add --dev ty
-          uv run ty check || true
+
       - name: Run pyrefly check
         run: |
           cd api
@@ -66,20 +62,14 @@ jobs:
       - name: Run dify config tests
         run: uv run --project api dev/pytest/pytest_config_tests.py
 
-      - name: MyPy Cache
-        uses: actions/cache@v4
-        with:
-          path: api/.mypy_cache
-          key: mypy-${{ matrix.python-version }}-${{ runner.os }}-${{ hashFiles('api/uv.lock') }}
-
-      - name: Run MyPy Checks
-        run: dev/mypy-check
-
       - name: Set up dotenvs
         run: |
           cp docker/.env.example docker/.env
           cp docker/middleware.env.example docker/middleware.env
 
+      - name: Setup SSRF Proxy for Testing
+        run: sh docker/ssrf_proxy/setup-testing.sh
+
       - name: Expose Service Ports
         run: sh .github/workflows/expose_service_ports.sh
 

.github/workflows/autofix.yml

@@ -15,19 +15,67 @@ jobs:
       # Use uv to ensure we have the same ruff version in CI and locally.
       - uses: astral-sh/setup-uv@v6
         with:
-          python-version: "3.12"
+          python-version: "3.11"
       - run: |
           cd api
           uv sync --dev
+          # fmt first to avoid line too long
+          uv run ruff format ..
           # Fix lint errors
-          uv run ruff check --fix-only .
+          uv run ruff check --fix .
           # Format code
-          uv run ruff format .
+          uv run ruff format ..
+
       - name: ast-grep
         run: |
           uvx --from ast-grep-cli sg --pattern 'db.session.query($WHATEVER).filter($HERE)' --rewrite 'db.session.query($WHATEVER).where($HERE)' -l py --update-all
           uvx --from ast-grep-cli sg --pattern 'session.query($WHATEVER).filter($HERE)' --rewrite 'session.query($WHATEVER).where($HERE)' -l py --update-all
+          # Convert Optional[T] to T | None (ignoring quoted types)
+          cat > /tmp/optional-rule.yml << 'EOF'
+          id: convert-optional-to-union
+          language: python
+          rule:
+            kind: generic_type
+            all:
+              - has:
+                  kind: identifier
+                  pattern: Optional
+              - has:
+                  kind: type_parameter
+                  has:
+                    kind: type
+                    pattern: $T
+          fix: $T | None
+          EOF
+          uvx --from ast-grep-cli sg scan --inline-rules "$(cat /tmp/optional-rule.yml)" --update-all
+          # Fix forward references that were incorrectly converted (Python doesn't support "Type" | None syntax)
+          find . -name "*.py" -type f -exec sed -i.bak -E 's/"([^"]+)" \| None/Optional["\1"]/g; s/'"'"'([^'"'"']+)'"'"' \| None/Optional['"'"'\1'"'"']/g' {} \;
+          find . -name "*.py.bak" -type f -delete
+
       - name: mdformat
         run: |
           uvx mdformat .
+
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          package_json_file: web/package.json
+          run_install: false
+
+      - name: Setup NodeJS
+        uses: actions/setup-node@v4
+        with:
+          node-version: 22
+          cache: pnpm
+          cache-dependency-path: ./web/package.json
+
+      - name: Web dependencies
+        working-directory: ./web
+        run: pnpm install --frozen-lockfile
+
+      - name: oxlint
+        working-directory: ./web
+        run: |
+          pnpx oxlint --fix
+
       - uses: autofix-ci/action@635ffb0c9798bd160680f18fd73371e355b85f27

.github/workflows/build-push.yml

@@ -8,6 +8,7 @@ on:
       - "deploy/enterprise"
       - "build/**"
       - "release/e-*"
+      - "hotfix/**"
     tags:
       - "*"
 

.github/workflows/deploy-dev.yml

@@ -12,12 +12,13 @@ jobs:
   deploy:
     runs-on: ubuntu-latest
     if: |
-      github.event.workflow_run.conclusion == 'success'
+      github.event.workflow_run.conclusion == 'success' &&
+      github.event.workflow_run.head_branch == 'deploy/dev'
     steps:
       - name: Deploy to server
         uses: appleboy/ssh-action@v0.1.8
         with:
-          host: ${{ secrets.SSH_HOST }}
+          host: ${{ secrets.RAG_SSH_HOST }}
           username: ${{ secrets.SSH_USER }}
           key: ${{ secrets.SSH_PRIVATE_KEY }}
           script: |

.github/workflows/deploy-enterprise.yml

@@ -19,11 +19,23 @@ jobs:
       github.event.workflow_run.head_branch == 'deploy/enterprise'
 
     steps:
-      - name: Deploy to server
-        uses: appleboy/ssh-action@v0.1.8
-        with:
-          host: ${{ secrets.ENTERPRISE_SSH_HOST }}
-          username: ${{ secrets.ENTERPRISE_SSH_USER }}
-          password: ${{ secrets.ENTERPRISE_SSH_PASSWORD }}
-          script: |
-            ${{ vars.ENTERPRISE_SSH_SCRIPT || secrets.ENTERPRISE_SSH_SCRIPT }}
+      - name: trigger deployments
+        env:
+          DEV_ENV_ADDRS: ${{ vars.DEV_ENV_ADDRS }}
+          DEPLOY_SECRET: ${{ secrets.DEPLOY_SECRET }}
+        run: |
+          IFS=',' read -ra ENDPOINTS <<< "${DEV_ENV_ADDRS:-}"
+          BODY='{"project":"dify-api","tag":"deploy-enterprise"}'
+
+          for ENDPOINT in "${ENDPOINTS[@]}"; do
+            ENDPOINT="$(echo "$ENDPOINT" | xargs)"
+            [ -z "$ENDPOINT" ] && continue
+
+            API_SIGNATURE=$(printf '%s' "$BODY" | openssl dgst -sha256 -hmac "$DEPLOY_SECRET" | awk '{print "sha256="$2}')
+
+            curl -sSf -X POST \
+              -H "Content-Type: application/json" \
+              -H "X-Hub-Signature-256: $API_SIGNATURE" \
+              -d "$BODY" \
+              "$ENDPOINT"
+          done

.github/workflows/style.yml

@@ -12,7 +12,6 @@ permissions:
   statuses: write
   contents: read
 
-
 jobs:
   python-style:
     name: Python Style
@@ -44,6 +43,18 @@ jobs:
         if: steps.changed-files.outputs.any_changed == 'true'
         run: uv sync --project api --dev
 
+      - name: Run Import Linter
+        if: steps.changed-files.outputs.any_changed == 'true'
+        run: uv run --directory api --dev lint-imports
+
+      - name: Run Basedpyright Checks
+        if: steps.changed-files.outputs.any_changed == 'true'
+        run: dev/basedpyright-check
+
+      - name: Run Mypy Type Checks
+        if: steps.changed-files.outputs.any_changed == 'true'
+        run: uv --directory api run mypy --exclude-gitignore --exclude 'tests/' --exclude 'migrations/' --check-untyped-defs --disable-error-code=import-untyped .
+
       - name: Dotenv check
         if: steps.changed-files.outputs.any_changed == 'true'
         run: uv run --project api dotenv-linter ./api/.env.example ./web/.env.example
@@ -89,7 +100,8 @@ jobs:
       - name: Web style check
         if: steps.changed-files.outputs.any_changed == 'true'
         working-directory: ./web
-        run: pnpm run lint
+        run: |
+          pnpm run lint
 
   docker-compose-template:
     name: Docker Compose Template

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

@@ -67,12 +67,22 @@ jobs:
         working-directory: ./web
         run: pnpm run auto-gen-i18n ${{ env.FILE_ARGS }}
 
+      - name: Generate i18n type definitions
+        if: env.FILES_CHANGED == 'true'
+        working-directory: ./web
+        run: pnpm run gen:i18n-types
+
       - name: Create Pull Request
         if: env.FILES_CHANGED == 'true'
         uses: peter-evans/create-pull-request@v6
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
-          commit-message: Update i18n files based on en-US changes
-          title: 'chore: translate i18n files'
-          body: This PR was automatically created to update i18n files based on changes in en-US locale.
+          commit-message: Update i18n files and type definitions based on en-US changes
+          title: 'chore: translate i18n files and update type definitions'
+          body: |
+            This PR was automatically created to update i18n files and TypeScript type definitions based on changes in en-US locale.
+            
+            **Changes included:**
+            - Updated translation files for all locales
+            - Regenerated TypeScript type definitions for type safety
           branch: chore/automated-i18n-updates

.github/workflows/web-tests.yml

@@ -47,6 +47,11 @@ jobs:
         working-directory: ./web
         run: pnpm install --frozen-lockfile
 
+      - name: Check i18n types synchronization
+        if: steps.changed-files.outputs.any_changed == 'true'
+        working-directory: ./web
+        run: pnpm run check:i18n-types
+
       - name: Run tests
         if: steps.changed-files.outputs.any_changed == 'true'
         working-directory: ./web

.gitignore

@@ -123,10 +123,12 @@ venv.bak/
 # mkdocs documentation
 /site
 
-# mypy
+# type checking
 .mypy_cache/
 .dmypy.json
 dmypy.json
+pyrightconfig.json
+!api/pyrightconfig.json
 
 # Pyre type checker
 .pyre/
@@ -195,8 +197,8 @@ sdks/python-client/dify_client.egg-info
 .vscode/*
 !.vscode/launch.json.template
 !.vscode/README.md
-pyrightconfig.json
 api/.vscode
+web/.vscode
 # vscode Code History Extension
 .history
 
@@ -214,7 +216,26 @@ mise.toml
 # Next.js build output
 .next/
 
+# PWA generated files
+web/public/sw.js
+web/public/sw.js.map
+web/public/workbox-*.js
+web/public/workbox-*.js.map
+web/public/fallback-*.js
+
 # AI Assistant
 .roo/
 api/.env.backup
 /clickzetta
+
+# SSRF Proxy - ignore the conf.d directory that's created for testing/local overrides
+docker/ssrf_proxy/conf.d/
+
+# Benchmark
+scripts/stress-test/setup/config/
+scripts/stress-test/reports/
+
+# mcp
+.playwright-mcp/
+.serena/
+

AGENTS.md

@@ -1 +0,0 @@
-CLAUDE.md

AGENTS.md

@@ -0,0 +1,54 @@
+# AGENTS.md
+
+## Project Overview
+
+Dify is an open-source platform for developing LLM applications with an intuitive interface combining agentic AI workflows, RAG pipelines, agent capabilities, and model management.
+
+The codebase is split into:
+
+- **Backend API** (`/api`): Python Flask application organized with Domain-Driven Design
+- **Frontend Web** (`/web`): Next.js 15 application using TypeScript and React 19
+- **Docker deployment** (`/docker`): Containerized deployment configurations
+
+## Backend Workflow
+
+- Run backend CLI commands through `uv run --project api <command>`.
+
+- Backend QA gate requires passing `make lint`, `make type-check`, and `uv run --project api --dev dev/pytest/pytest_unit_tests.sh` before review.
+
+- Use Makefile targets for linting and formatting; `make lint` and `make type-check` cover the required checks.
+
+- Integration tests are CI-only and are not expected to run in the local environment.
+
+## Frontend Workflow
+
+```bash
+cd web
+pnpm lint
+pnpm lint:fix
+pnpm test
+```
+
+## Testing & Quality Practices
+
+- Follow TDD: red → green → refactor.
+- Use `pytest` for backend tests with Arrange-Act-Assert structure.
+- Enforce strong typing; avoid `Any` and prefer explicit type annotations.
+- Write self-documenting code; only add comments that explain intent.
+
+## Language Style
+
+- **Python**: Keep type hints on functions and attributes, and implement relevant special methods (e.g., `__repr__`, `__str__`).
+- **TypeScript**: Use the strict config, lean on ESLint + Prettier workflows, and avoid `any` types.
+
+## General Practices
+
+- Prefer editing existing files; add new documentation only when requested.
+- Inject dependencies through constructors and preserve clean architecture boundaries.
+- Handle errors with domain-specific exceptions at the correct layer.
+
+## Project Conventions
+
+- Backend architecture adheres to DDD and Clean Architecture principles.
+- Async work runs through Celery with Redis as the broker.
+- Frontend user-facing strings must use `web/i18n/en-US/`; avoid hardcoded text.

CLAUDE.md

@@ -1,89 +0,0 @@
-# CLAUDE.md
-
-This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
-
-## Project Overview
-
-Dify is an open-source platform for developing LLM applications with an intuitive interface combining agentic AI workflows, RAG pipelines, agent capabilities, and model management.
-
-The codebase consists of:
-
-- **Backend API** (`/api`): Python Flask application with Domain-Driven Design architecture
-- **Frontend Web** (`/web`): Next.js 15 application with TypeScript and React 19
-- **Docker deployment** (`/docker`): Containerized deployment configurations
-
-## Development Commands
-
-### Backend (API)
-
-All Python commands must be prefixed with `uv run --project api`:
-
-```bash
-# Start development servers
-./dev/start-api                   # Start API server
-./dev/start-worker                # Start Celery worker
-
-# Run tests
-uv run --project api pytest      # Run all tests
-uv run --project api pytest tests/unit_tests/     # Unit tests only
-uv run --project api pytest tests/integration_tests/  # Integration tests
-
-# Code quality
-./dev/reformat                    # Run all formatters and linters
-uv run --project api ruff check --fix ./    # Fix linting issues
-uv run --project api ruff format ./         # Format code
-uv run --project api mypy .                 # Type checking
-```
-
-### Frontend (Web)
-
-```bash
-cd web
-pnpm lint                         # Run ESLint
-pnpm eslint-fix                   # Fix ESLint issues
-pnpm test                         # Run Jest tests
-```
-
-## Testing Guidelines
-
-### Backend Testing
-
-- Use `pytest` for all backend tests
-- Write tests first (TDD approach)
-- Test structure: Arrange-Act-Assert
-
-## Code Style Requirements
-
-### Python
-
-- Use type hints for all functions and class attributes
-- No `Any` types unless absolutely necessary
-- Implement special methods (`__repr__`, `__str__`) appropriately
-
-### TypeScript/JavaScript
-
-- Strict TypeScript configuration
-- ESLint with Prettier integration
-- Avoid `any` type
-
-## Important Notes
-
-- **Environment Variables**: Always use UV for Python commands: `uv run --project api <command>`
-- **Comments**: Only write meaningful comments that explain "why", not "what"
-- **File Creation**: Always prefer editing existing files over creating new ones
-- **Documentation**: Don't create documentation files unless explicitly requested
-- **Code Quality**: Always run `./dev/reformat` before committing backend changes
-
-## Common Development Tasks
-
-### Adding a New API Endpoint
-
-1. Create controller in `/api/controllers/`
-1. Add service logic in `/api/services/`
-1. Update routes in controller's `__init__.py`
-1. Write tests in `/api/tests/`
-
-## Project-Specific Conventions
-
-- All async tasks use Celery with Redis as broker
-- **Internationalization**: Frontend supports multiple languages with English (`web/i18n/en-US/`) as the source. All user-facing text must use i18n keys, no hardcoded strings. Edit corresponding module files in `en-US/` directory for translations.

CLAUDE.md

@@ -0,0 +1 @@
+AGENTS.md

CONTRIBUTING/CONTRIBUTING_CN.md

@@ -6,7 +6,7 @@
 
 本指南和 Dify 一样在不断完善中。如果有任何滞后于项目实际情况的地方，恳请谅解，我们也欢迎任何改进建议。
 
-关于许可证，请花一分钟阅读我们简短的[许可和贡献者协议](./LICENSE)。同时也请遵循社区[行为准则](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md)。
+关于许可证，请花一分钟阅读我们简短的[许可和贡献者协议](../LICENSE)。同时也请遵循社区[行为准则](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md)。
 
 ## 开始之前
 

CONTRIBUTING/CONTRIBUTING_DE.md

@@ -6,7 +6,7 @@ Wir müssen wendig sein und schnell liefern, aber wir möchten auch sicherstelle
 
 Dieser Leitfaden ist, wie Dify selbst, in ständiger Entwicklung. Wir sind dankbar für Ihr Verständnis, falls er manchmal hinter dem eigentlichen Projekt zurückbleibt, und begrüßen jedes Feedback zur Verbesserung.
 
-Bitte nehmen Sie sich einen Moment Zeit, um unsere [Lizenz- und Mitwirkungsvereinbarung](./LICENSE) zu lesen. Die Community hält sich außerdem an den [Verhaltenskodex](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md).
+Bitte nehmen Sie sich einen Moment Zeit, um unsere [Lizenz- und Mitwirkungsvereinbarung](../LICENSE) zu lesen. Die Community hält sich außerdem an den [Verhaltenskodex](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md).
 
 ## Bevor Sie loslegen
 

CONTRIBUTING/CONTRIBUTING_ES.md

@@ -6,7 +6,7 @@ Necesitamos ser ágiles y enviar rápidamente dado donde estamos, pero también
 
 Esta guía, como Dify mismo, es un trabajo en constante progreso. Agradecemos mucho tu comprensión si a veces se queda atrás del proyecto real, y damos la bienvenida a cualquier comentario para que podamos mejorar.
 
-En términos de licencia, por favor tómate un minuto para leer nuestro breve [Acuerdo de Licencia y Colaborador](./LICENSE). La comunidad también se adhiere al [código de conducta](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md).
+En términos de licencia, por favor tómate un minuto para leer nuestro breve [Acuerdo de Licencia y Colaborador](../LICENSE). La comunidad también se adhiere al [código de conducta](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md).
 
 ## Antes de empezar
 

CONTRIBUTING/CONTRIBUTING_FR.md

@@ -6,7 +6,7 @@ Nous devons être agiles et livrer rapidement compte tenu de notre position, mai
 
 Ce guide, comme Dify lui-même, est un travail en constante évolution. Nous apprécions grandement votre compréhension si parfois il est en retard par rapport au projet réel, et nous accueillons tout commentaire pour nous aider à nous améliorer.
 
-En termes de licence, veuillez prendre une minute pour lire notre bref [Accord de Licence et de Contributeur](./LICENSE). La communauté adhère également au [code de conduite](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md).
+En termes de licence, veuillez prendre une minute pour lire notre bref [Accord de Licence et de Contributeur](../LICENSE). La communauté adhère également au [code de conduite](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md).
 
 ## Avant de vous lancer
 

CONTRIBUTING/CONTRIBUTING_JA.md

@@ -6,7 +6,7 @@ Difyに貢献しようとお考えですか？素晴らしいですね。私た
 
 このガイドは、Dify自体と同様に、常に進化し続けています。実際のプロジェクトの進行状況と多少のずれが生じる場合もございますが、ご理解いただけますと幸いです。改善のためのフィードバックも歓迎いたします。
 
-ライセンスについては、[ライセンスと貢献者同意書](./LICENSE)をご一読ください。また、コミュニティは[行動規範](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md)に従っています。
+ライセンスについては、[ライセンスと貢献者同意書](../LICENSE)をご一読ください。また、コミュニティは[行動規範](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md)に従っています。
 
 ## 始める前に
 

CONTRIBUTING/CONTRIBUTING_KR.md

@@ -6,7 +6,7 @@ Dify에 기여하려고 하시는군요 - 정말 멋집니다, 당신이 무엇
 
 이 가이드는 Dify 자체와 마찬가지로 끊임없이 진행 중인 작업입니다. 때로는 실제 프로젝트보다 뒤처질 수 있다는 점을 이해해 주시면 감사하겠으며, 개선을 위한 피드백은 언제든지 환영합니다.
 
-라이센스 측면에서, 간략한 [라이센스 및 기여자 동의서](./LICENSE)를 읽어보는 시간을 가져주세요. 커뮤니티는 또한 [행동 강령](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md)을 준수합니다.
+라이센스 측면에서, 간략한 [라이센스 및 기여자 동의서](../LICENSE)를 읽어보는 시간을 가져주세요. 커뮤니티는 또한 [행동 강령](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md)을 준수합니다.
 
 ## 시작하기 전에
 

CONTRIBUTING/CONTRIBUTING_PT.md

@@ -6,7 +6,7 @@ Precisamos ser ágeis e entregar rapidamente considerando onde estamos, mas tamb
 
 Este guia, como o próprio Dify, é um trabalho em constante evolução. Agradecemos muito a sua compreensão se às vezes ele ficar atrasado em relação ao projeto real, e damos as boas-vindas a qualquer feedback para que possamos melhorar.
 
-Em termos de licenciamento, por favor, dedique um minuto para ler nosso breve [Acordo de Licença e Contribuidor](./LICENSE). A comunidade também adere ao [código de conduta](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md).
+Em termos de licenciamento, por favor, dedique um minuto para ler nosso breve [Acordo de Licença e Contribuidor](../LICENSE). A comunidade também adere ao [código de conduta](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md).
 
 ## Antes de começar
 

CONTRIBUTING/CONTRIBUTING_TR.md

@@ -6,7 +6,7 @@ Bulunduğumuz noktada çevik olmamız ve hızlı hareket etmemiz gerekiyor, anca
 
 Bu rehber, Dify'ın kendisi gibi, sürekli gelişen bir çalışmadır. Bazen gerçek projenin gerisinde kalırsa anlayışınız için çok minnettarız ve gelişmemize yardımcı olacak her türlü geri bildirimi memnuniyetle karşılıyoruz.
 
-Lisanslama konusunda, lütfen kısa [Lisans ve Katkıda Bulunan Anlaşmamızı](./LICENSE) okumak için bir dakikanızı ayırın. Topluluk ayrıca [davranış kurallarına](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md) da uyar.
+Lisanslama konusunda, lütfen kısa [Lisans ve Katkıda Bulunan Anlaşmamızı](../LICENSE) okumak için bir dakikanızı ayırın. Topluluk ayrıca [davranış kurallarına](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md) da uyar.
 
 ## Başlamadan Önce
 

CONTRIBUTING/CONTRIBUTING_TW.md

@@ -6,7 +6,7 @@
 
 這份指南與 Dify 一樣，都在持續完善中。如果指南內容有落後於實際專案的情況，還請見諒，也歡迎提供改進建議。
 
-關於授權部分，請花點時間閱讀我們簡短的[授權和貢獻者協議](./LICENSE)。社群也需遵守[行為準則](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md)。
+關於授權部分，請花點時間閱讀我們簡短的[授權和貢獻者協議](../LICENSE)。社群也需遵守[行為準則](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md)。
 
 ## 開始之前
 

CONTRIBUTING/CONTRIBUTING_VI.md

@@ -6,7 +6,7 @@ Chúng tôi cần phải nhanh nhẹn và triển khai nhanh chóng, nhưng cũn
 
 Hướng dẫn này, giống như Dify, đang được phát triển liên tục. Chúng tôi rất cảm kích sự thông cảm của bạn nếu đôi khi nó chưa theo kịp dự án thực tế, và hoan nghênh mọi phản hồi để cải thiện.
 
-Về giấy phép, vui lòng dành chút thời gian đọc [Thỏa thuận Cấp phép và Người đóng góp](./LICENSE) ngắn gọn của chúng tôi. Cộng đồng cũng tuân theo [quy tắc ứng xử](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md).
+Về giấy phép, vui lòng dành chút thời gian đọc [Thỏa thuận Cấp phép và Người đóng góp](../LICENSE) ngắn gọn của chúng tôi. Cộng đồng cũng tuân theo [quy tắc ứng xử](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md).
 
 ## Trước khi bắt đầu
 

Makefile

@@ -4,6 +4,73 @@ WEB_IMAGE=$(DOCKER_REGISTRY)/dify-web
 API_IMAGE=$(DOCKER_REGISTRY)/dify-api
 VERSION=latest
 
+# Default target - show help
+.DEFAULT_GOAL := help
+
+# Backend Development Environment Setup
+.PHONY: dev-setup prepare-docker prepare-web prepare-api
+
+# Dev setup target
+dev-setup: prepare-docker prepare-web prepare-api
+	@echo "✅ Backend development environment setup complete!"
+
+# Step 1: Prepare Docker middleware
+prepare-docker:
+	@echo "🐳 Setting up Docker middleware..."
+	@cp -n docker/middleware.env.example docker/middleware.env 2>/dev/null || echo "Docker middleware.env already exists"
+	@cd docker && docker compose -f docker-compose.middleware.yaml --env-file middleware.env -p dify-middlewares-dev up -d
+	@echo "✅ Docker middleware started"
+
+# Step 2: Prepare web environment
+prepare-web:
+	@echo "🌐 Setting up web environment..."
+	@cp -n web/.env.example web/.env 2>/dev/null || echo "Web .env already exists"
+	@cd web && pnpm install
+	@cd web && pnpm build
+	@echo "✅ Web environment prepared (not started)"
+
+# Step 3: Prepare API environment
+prepare-api:
+	@echo "🔧 Setting up API environment..."
+	@cp -n api/.env.example api/.env 2>/dev/null || echo "API .env already exists"
+	@cd api && uv sync --dev
+	@cd api && uv run flask db upgrade
+	@echo "✅ API environment prepared (not started)"
+
+# Clean dev environment
+dev-clean:
+	@echo "⚠️  Stopping Docker containers..."
+	@cd docker && docker compose -f docker-compose.middleware.yaml --env-file middleware.env -p dify-middlewares-dev down
+	@echo "🗑️  Removing volumes..."
+	@rm -rf docker/volumes/db
+	@rm -rf docker/volumes/redis
+	@rm -rf docker/volumes/plugin_daemon
+	@rm -rf docker/volumes/weaviate
+	@rm -rf api/storage
+	@echo "✅ Cleanup complete"
+
+# Backend Code Quality Commands
+format:
+	@echo "🎨 Running ruff format..."
+	@uv run --project api --dev ruff format ./api
+	@echo "✅ Code formatting complete"
+
+check:
+	@echo "🔍 Running ruff check..."
+	@uv run --project api --dev ruff check ./api
+	@echo "✅ Code check complete"
+
+lint:
+	@echo "🔧 Running ruff format, check with fixes, and import linter..."
+	@uv run --project api --dev sh -c 'ruff format ./api && ruff check --fix ./api'
+	@uv run --directory api --dev lint-imports
+	@echo "✅ Linting complete"
+
+type-check:
+	@echo "📝 Running type check with basedpyright..."
+	@uv run --directory api --dev basedpyright
+	@echo "✅ Type check complete"
+
 # Build Docker images
 build-web:
 	@echo "Building web Docker image: $(WEB_IMAGE):$(VERSION)..."
@@ -39,5 +106,27 @@ build-push-web: build-web push-web
 build-push-all: build-all push-all
 	@echo "All Docker images have been built and pushed."
 
+# Help target
+help:
+	@echo "Development Setup Targets:"
+	@echo "  make dev-setup      - Run all setup steps for backend dev environment"
+	@echo "  make prepare-docker - Set up Docker middleware"
+	@echo "  make prepare-web    - Set up web environment"
+	@echo "  make prepare-api    - Set up API environment"
+	@echo "  make dev-clean      - Stop Docker middleware containers"
+	@echo ""
+	@echo "Backend Code Quality:"
+	@echo "  make format         - Format code with ruff"
+	@echo "  make check          - Check code with ruff"
+	@echo "  make lint           - Format and fix code with ruff"
+	@echo "  make type-check     - Run type checking with basedpyright"
+	@echo ""
+	@echo "Docker Build Targets:"
+	@echo "  make build-web      - Build web Docker image"
+	@echo "  make build-api      - Build API Docker image"
+	@echo "  make build-all      - Build all Docker images"
+	@echo "  make push-all       - Push all Docker images"
+	@echo "  make build-push-all - Build and push all Docker images"
+
 # Phony targets
-.PHONY: build-web build-api push-web push-api build-all push-all build-push-all
+.PHONY: build-web build-api push-web push-api build-all push-all build-push-all dev-setup prepare-docker prepare-web prepare-api dev-clean help format check lint type-check

README.md

@@ -40,18 +40,18 @@
 
 <p align="center">
   <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
-  <a href="./README_TW.md"><img alt="繁體中文文件" src="https://img.shields.io/badge/繁體中文-d9d9d9"></a>
-  <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
-  <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
-  <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
-  <a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
-  <a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
-  <a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
-  <a href="./README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
-  <a href="./README_TR.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
-  <a href="./README_VI.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
-  <a href="./README_DE.md"><img alt="README in Deutsch" src="https://img.shields.io/badge/German-d9d9d9"></a>
-  <a href="./README_BN.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
+  <a href="./README/README_TW.md"><img alt="繁體中文文件" src="https://img.shields.io/badge/繁體中文-d9d9d9"></a>
+  <a href="./README/README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="./README/README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="./README/README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
+  <a href="./README/README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
+  <a href="./README/README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
+  <a href="./README/README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
+  <a href="./README/README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
+  <a href="./README/README_TR.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
+  <a href="./README/README_VI.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
+  <a href="./README/README_DE.md"><img alt="README in Deutsch" src="https://img.shields.io/badge/German-d9d9d9"></a>
+  <a href="./README/README_BN.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
 </p>
 
 Dify is an open-source platform for developing LLM applications. Its intuitive interface combines agentic AI workflows, RAG pipelines, agent capabilities, model management, observability features, and more—allowing you to quickly move from prototype to production.

README/README_AR.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](./images/GitHub_README_if.png)
+![cover-v5-optimized](../images/GitHub_README_if.png)
 
 <p align="center">
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
@@ -35,7 +35,7 @@
 </p>
 
 <p align="center">
-  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
   <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
   <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
   <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
@@ -185,7 +185,7 @@ docker compose up -d
 
 ## الرخصة
 
-هذا المستودع متاح تحت [رخصة البرنامج الحر Dify](LICENSE)، والتي تعتبر بشكل أساسي Apache 2.0 مع بعض القيود الإضافية.
+هذا المستودع متاح تحت [رخصة البرنامج الحر Dify](../LICENSE)، والتي تعتبر بشكل أساسي Apache 2.0 مع بعض القيود الإضافية.
 
 ## الكشف عن الأمان
 
@@ -193,4 +193,4 @@ docker compose up -d
 
 ## الرخصة
 
-هذا المستودع متاح تحت [رخصة البرنامج الحر Dify](LICENSE)، والتي تعتبر بشكل أساسي Apache 2.0 مع بعض القيود الإضافية.
+هذا المستودع متاح تحت [رخصة البرنامج الحر Dify](../LICENSE)، والتي تعتبر بشكل أساسي Apache 2.0 مع بعض القيود الإضافية.

README/README_BN.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](./images/GitHub_README_if.png)
+![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>
@@ -39,7 +39,7 @@
 </p>
 
 <p align="center">
-  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
   <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
   <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
   <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
@@ -203,4 +203,4 @@ GitHub-এ ডিফাইকে স্টার দিয়ে রাখুন
 
 ## লাইসেন্স
 
-এই রিপোজিটরিটি [ডিফাই ওপেন সোর্স লাইসেন্স](LICENSE) এর অধিনে , যা মূলত অ্যাপাচি ২.০, তবে কিছু অতিরিক্ত বিধিনিষেধ রয়েছে।
+এই রিপোজিটরিটি [ডিফাই ওপেন সোর্স লাইসেন্স](../LICENSE) এর অধিনে , যা মূলত অ্যাপাচি ২.০, তবে কিছু অতিরিক্ত বিধিনিষেধ রয়েছে।

README/README_CN.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](./images/GitHub_README_if.png)
+![cover-v5-optimized](../images/GitHub_README_if.png)
 
 <div align="center">
   <a href="https://cloud.dify.ai">Dify 云服务</a> ·
@@ -35,7 +35,7 @@
 </p>
 
 <div align="center">
-  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
   <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
   <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
   <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
@@ -180,7 +180,7 @@ docker compose up -d
 
 ## Contributing
 
-对于那些想要贡献代码的人，请参阅我们的[贡献指南](https://github.com/langgenius/dify/blob/main/CONTRIBUTING_CN.md)。
+对于那些想要贡献代码的人，请参阅我们的[贡献指南](https://github.com/langgenius/dify/blob/main/CONTRIBUTING/CONTRIBUTING_CN.md)。
 同时，请考虑通过社交媒体、活动和会议来支持 Dify 的分享。
 
 > 我们正在寻找贡献者来帮助将 Dify 翻译成除了中文和英文之外的其他语言。如果您有兴趣帮助，请参阅我们的[i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md)获取更多信息，并在我们的[Discord 社区服务器](https://discord.gg/8Tpq4AcN9c)的`global-users`频道中留言。
@@ -196,7 +196,7 @@ 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 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)。
+- [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=%5BGitHub%5DQuestions%20About%20Dify)。👉：关于使用 Dify.AI 的问题。
 - [Discord](https://discord.gg/FngNHpbcY7)。👉：分享您的应用程序并与社区交流。
 - [X(Twitter)](https://twitter.com/dify_ai)。👉：分享您的应用程序并与社区交流。
@@ -208,4 +208,4 @@ docker compose up -d
 
 ## License
 
-本仓库遵循 [Dify Open Source License](LICENSE) 开源协议，该许可证本质上是 Apache 2.0，但有一些额外的限制。
+本仓库遵循 [Dify Open Source License](../LICENSE) 开源协议，该许可证本质上是 Apache 2.0，但有一些额外的限制。

README/README_DE.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](./images/GitHub_README_if.png)
+![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>
@@ -39,7 +39,7 @@
 </p>
 
 <p align="center">
-  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
   <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
   <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
   <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
@@ -173,7 +173,7 @@ Stellen Sie Dify mit einem Klick in AKS bereit, indem Sie [Azure Devops Pipeline
 
 ## Contributing
 
-Falls Sie Code beitragen möchten, lesen Sie bitte unseren [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING_DE.md). Gleichzeitig bitten wir Sie, Dify zu unterstützen, indem Sie es in den sozialen Medien teilen und auf Veranstaltungen und Konferenzen präsentieren.
+Falls Sie Code beitragen möchten, lesen Sie bitte unseren [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING/CONTRIBUTING_DE.md). Gleichzeitig bitten wir Sie, Dify zu unterstützen, indem Sie es in den sozialen Medien teilen und auf Veranstaltungen und Konferenzen präsentieren.
 
 > Wir suchen Mitwirkende, die dabei helfen, Dify in weitere Sprachen zu übersetzen – außer Mandarin oder Englisch. Wenn Sie Interesse an einer Mitarbeit haben, lesen Sie bitte die [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) für weitere Informationen und hinterlassen Sie einen Kommentar im `global-users`-Kanal unseres [Discord Community Servers](https://discord.gg/8Tpq4AcN9c).
 
@@ -200,4 +200,4 @@ Um Ihre Privatsphäre zu schützen, vermeiden Sie es bitte, Sicherheitsprobleme
 
 ## Lizenz
 
-Dieses Repository steht unter der [Dify Open Source License](LICENSE), die im Wesentlichen Apache 2.0 mit einigen zusätzlichen Einschränkungen ist.
+Dieses Repository steht unter der [Dify Open Source License](../LICENSE), die im Wesentlichen Apache 2.0 mit einigen zusätzlichen Einschränkungen ist.

README/README_ES.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](./images/GitHub_README_if.png)
+![cover-v5-optimized](../images/GitHub_README_if.png)
 
 <p align="center">
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
@@ -35,7 +35,7 @@
 </p>
 
 <p align="center">
-  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
   <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
   <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
   <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
@@ -170,7 +170,7 @@ Implementa Dify en AKS con un clic usando [Azure Devops Pipeline Helm Chart by @
 
 ## Contribuir
 
-Para aquellos que deseen contribuir con código, consulten nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING_ES.md).
+Para aquellos que deseen contribuir con código, consulten nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING/CONTRIBUTING_ES.md).
 Al mismo tiempo, considera apoyar a Dify compartiéndolo en redes sociales y en eventos y conferencias.
 
 > Estamos buscando colaboradores para ayudar con la traducción de Dify a idiomas que no sean el mandarín o el inglés. Si estás interesado en ayudar, consulta el [README de i18n](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) para obtener más información y déjanos un comentario en el canal `global-users` de nuestro [Servidor de Comunidad en Discord](https://discord.gg/8Tpq4AcN9c).
@@ -198,7 +198,7 @@ Para proteger tu privacidad, evita publicar problemas de seguridad en GitHub. En
 
 ## Licencia
 
-Este repositorio está disponible bajo la [Licencia de Código Abierto de Dify](LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales.
+Este repositorio está disponible bajo la [Licencia de Código Abierto de Dify](../LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales.
 
 ## Divulgación de Seguridad
 
@@ -206,4 +206,4 @@ Para proteger tu privacidad, evita publicar problemas de seguridad en GitHub. En
 
 ## Licencia
 
-Este repositorio está disponible bajo la [Licencia de Código Abierto de Dify](LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales.
+Este repositorio está disponible bajo la [Licencia de Código Abierto de Dify](../LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales.

README/README_FR.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](./images/GitHub_README_if.png)
+![cover-v5-optimized](../images/GitHub_README_if.png)
 
 <p align="center">
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
@@ -35,7 +35,7 @@
 </p>
 
 <p align="center">
-  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
   <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
   <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
   <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
@@ -168,7 +168,7 @@ Déployez Dify sur AKS en un clic en utilisant [Azure Devops Pipeline Helm Chart
 
 ## Contribuer
 
-Pour ceux qui souhaitent contribuer du code, consultez notre [Guide de contribution](https://github.com/langgenius/dify/blob/main/CONTRIBUTING_FR.md).
+Pour ceux qui souhaitent contribuer du code, consultez notre [Guide de contribution](https://github.com/langgenius/dify/blob/main/CONTRIBUTING/CONTRIBUTING_FR.md).
 Dans le même temps, veuillez envisager de soutenir Dify en le partageant sur les réseaux sociaux et lors d'événements et de conférences.
 
 > Nous recherchons des contributeurs pour aider à traduire Dify dans des langues autres que le mandarin ou l'anglais. Si vous êtes intéressé à aider, veuillez consulter le [README i18n](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) pour plus d'informations, et laissez-nous un commentaire dans le canal `global-users` de notre [Serveur communautaire Discord](https://discord.gg/8Tpq4AcN9c).
@@ -196,7 +196,7 @@ Pour protéger votre vie privée, veuillez éviter de publier des problèmes de
 
 ## Licence
 
-Ce référentiel est disponible sous la [Licence open source Dify](LICENSE), qui est essentiellement l'Apache 2.0 avec quelques restrictions supplémentaires.
+Ce référentiel est disponible sous la [Licence open source Dify](../LICENSE), qui est essentiellement l'Apache 2.0 avec quelques restrictions supplémentaires.
 
 ## Divulgation de sécurité
 
@@ -204,4 +204,4 @@ Pour protéger votre vie privée, veuillez éviter de publier des problèmes de
 
 ## Licence
 
-Ce référentiel est disponible sous la [Licence open source Dify](LICENSE), qui est essentiellement l'Apache 2.0 avec quelques restrictions supplémentaires.
+Ce référentiel est disponible sous la [Licence open source Dify](../LICENSE), qui est essentiellement l'Apache 2.0 avec quelques restrictions supplémentaires.

README/README_JA.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](./images/GitHub_README_if.png)
+![cover-v5-optimized](../images/GitHub_README_if.png)
 
 <p align="center">
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
@@ -35,7 +35,7 @@
 </p>
 
 <p align="center">
-  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
   <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
   <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
   <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
@@ -169,7 +169,7 @@ docker compose up -d
 
 ## 貢献
 
-コードに貢献したい方は、[Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING_JA.md)を参照してください。
+コードに貢献したい方は、[Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING/CONTRIBUTING_JA.md)を参照してください。
 同時に、DifyをSNSやイベント、カンファレンスで共有してサポートしていただけると幸いです。
 
 > Difyを英語または中国語以外の言語に翻訳してくれる貢献者を募集しています。興味がある場合は、詳細については[i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md)を参照してください。また、[Discordコミュニティサーバー](https://discord.gg/8Tpq4AcN9c)の`global-users`チャンネルにコメントを残してください。
@@ -183,10 +183,10 @@ 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 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
+- [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/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。
 
 ## ライセンス
 
-このリポジトリは、Dify Open Source License にいくつかの追加制限を加えた[Difyオープンソースライセンス](LICENSE)の下で利用可能です。
+このリポジトリは、Dify Open Source License にいくつかの追加制限を加えた[Difyオープンソースライセンス](../LICENSE)の下で利用可能です。

README/README_KL.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](./images/GitHub_README_if.png)
+![cover-v5-optimized](../images/GitHub_README_if.png)
 
 <p align="center">
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
@@ -35,7 +35,7 @@
 </p>
 
 <p align="center">
-  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
   <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
   <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
   <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
@@ -199,4 +199,4 @@ To protect your privacy, please avoid posting security issues on GitHub. Instead
 
 ## License
 
-This repository is available under the [Dify Open Source License](LICENSE), which is essentially Apache 2.0 with a few additional restrictions.
+This repository is available under the [Dify Open Source License](../LICENSE), which is essentially Apache 2.0 with a few additional restrictions.

README/README_KR.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](./images/GitHub_README_if.png)
+![cover-v5-optimized](../images/GitHub_README_if.png)
 
 <p align="center">
   <a href="https://cloud.dify.ai">Dify 클라우드</a> ·
@@ -35,7 +35,7 @@
 </p>
 
 <p align="center">
-  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
   <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
   <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
   <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
@@ -162,7 +162,7 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했
 
 ## 기여
 
-코드에 기여하고 싶은 분들은 [기여 가이드](https://github.com/langgenius/dify/blob/main/CONTRIBUTING_KR.md)를 참조하세요.
+코드에 기여하고 싶은 분들은 [기여 가이드](https://github.com/langgenius/dify/blob/main/CONTRIBUTING/CONTRIBUTING_KR.md)를 참조하세요.
 동시에 Dify를 소셜 미디어와 행사 및 컨퍼런스에 공유하여 지원하는 것을 고려해 주시기 바랍니다.
 
 > 우리는 Dify를 중국어나 영어 이외의 언어로 번역하는 데 도움을 줄 수 있는 기여자를 찾고 있습니다. 도움을 주고 싶으시다면 [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md)에서 더 많은 정보를 확인하시고 [Discord 커뮤니티 서버](https://discord.gg/8Tpq4AcN9c)의 `global-users` 채널에 댓글을 남겨주세요.
@@ -190,4 +190,4 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했
 
 ## 라이선스
 
-이 저장소는 기본적으로 몇 가지 추가 제한 사항이 있는 Apache 2.0인 [Dify 오픈 소스 라이선스](LICENSE)에 따라 사용할 수 있습니다.
+이 저장소는 기본적으로 몇 가지 추가 제한 사항이 있는 Apache 2.0인 [Dify 오픈 소스 라이선스](../LICENSE)에 따라 사용할 수 있습니다.

README/README_PT.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](./images/GitHub_README_if.png)
+![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>
@@ -39,7 +39,7 @@
 </p>
 
 <p align="center">
-  <a href="./README.md"><img alt="README em Inglês" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="../README.md"><img alt="README em Inglês" src="https://img.shields.io/badge/English-d9d9d9"></a>
   <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
   <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
   <a href="./README_ES.md"><img alt="README em Espanhol" src="https://img.shields.io/badge/Español-d9d9d9"></a>
@@ -168,7 +168,7 @@ Implante o Dify no AKS com um clique usando [Azure Devops Pipeline Helm Chart by
 
 ## Contribuindo
 
-Para aqueles que desejam contribuir com código, veja nosso [Guia de Contribuição](https://github.com/langgenius/dify/blob/main/CONTRIBUTING_PT.md).
+Para aqueles que desejam contribuir com código, veja nosso [Guia de Contribuição](https://github.com/langgenius/dify/blob/main/CONTRIBUTING/CONTRIBUTING_PT.md).
 Ao mesmo tempo, considere apoiar o Dify compartilhando-o nas redes sociais e em eventos e conferências.
 
 > Estamos buscando contribuidores para ajudar na tradução do Dify para idiomas além de Mandarim e Inglês. Se você tiver interesse em ajudar, consulte o [README i18n](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) para mais informações e deixe-nos um comentário no canal `global-users` em nosso [Servidor da Comunidade no Discord](https://discord.gg/8Tpq4AcN9c).
@@ -196,4 +196,4 @@ Para proteger sua privacidade, evite postar problemas de segurança no GitHub. E
 
 ## Licença
 
-Este repositório está disponível sob a [Licença de Código Aberto Dify](LICENSE), que é essencialmente Apache 2.0 com algumas restrições adicionais.
+Este repositório está disponível sob a [Licença de Código Aberto Dify](../LICENSE), que é essencialmente Apache 2.0 com algumas restrições adicionais.

README/README_SI.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](./images/GitHub_README_if.png)
+![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>
@@ -36,7 +36,7 @@
 </p>
 
 <p align="center">
-  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
   <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
   <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
   <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
@@ -196,4 +196,4 @@ Zaradi zaščite vaše zasebnosti se izogibajte objavljanju varnostnih vprašanj
 
 ## Licenca
 
-To skladišče je na voljo pod [odprtokodno licenco Dify](LICENSE) , ki je v bistvu Apache 2.0 z nekaj dodatnimi omejitvami.
+To skladišče je na voljo pod [odprtokodno licenco Dify](../LICENSE) , ki je v bistvu Apache 2.0 z nekaj dodatnimi omejitvami.

README/README_TR.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](./images/GitHub_README_if.png)
+![cover-v5-optimized](../images/GitHub_README_if.png)
 
 <p align="center">
   <a href="https://cloud.dify.ai">Dify Bulut</a> ·
@@ -35,7 +35,7 @@
 </p>
 
 <p align="center">
-  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
   <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
   <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
   <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
@@ -161,7 +161,7 @@ Dify'ı bulut platformuna tek tıklamayla dağıtın [terraform](https://www.ter
 
 ## Katkıda Bulunma
 
-Kod katkısında bulunmak isteyenler için [Katkı Kılavuzumuza](https://github.com/langgenius/dify/blob/main/CONTRIBUTING_TR.md) bakabilirsiniz.
+Kod katkısında bulunmak isteyenler için [Katkı Kılavuzumuza](https://github.com/langgenius/dify/blob/main/CONTRIBUTING/CONTRIBUTING_TR.md) bakabilirsiniz.
 Aynı zamanda, lütfen Dify'ı sosyal medyada, etkinliklerde ve konferanslarda paylaşarak desteklemeyi düşünün.
 
 > Dify'ı Mandarin veya İngilizce dışındaki dillere çevirmemize yardımcı olacak katkıda bulunanlara ihtiyacımız var. Yardımcı olmakla ilgileniyorsanız, lütfen daha fazla bilgi için [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) dosyasına bakın ve [Discord Topluluk Sunucumuzdaki](https://discord.gg/8Tpq4AcN9c) `global-users` kanalında bize bir yorum bırakın.
@@ -189,4 +189,4 @@ Gizliliğinizi korumak için, lütfen güvenlik sorunlarını GitHub'da paylaşm
 
 ## Lisans
 
-Bu depo, temel olarak Apache 2.0 lisansı ve birkaç ek kısıtlama içeren [Dify Açık Kaynak Lisansı](LICENSE) altında kullanıma sunulmuştur.
+Bu depo, temel olarak Apache 2.0 lisansı ve birkaç ek kısıtlama içeren [Dify Açık Kaynak Lisansı](../LICENSE) altında kullanıma sunulmuştur.

README/README_TW.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](./images/GitHub_README_if.png)
+![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>
@@ -39,7 +39,7 @@
 </p>
 
 <p align="center">
-  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
   <a href="./README_TW.md"><img alt="繁體中文文件" src="https://img.shields.io/badge/繁體中文-d9d9d9"></a>
   <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
   <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
@@ -173,7 +173,7 @@ Dify 的所有功能都提供相應的 API，因此您可以輕鬆地將 Dify
 
 ## 貢獻
 
-對於想要貢獻程式碼的開發者，請參閱我們的[貢獻指南](https://github.com/langgenius/dify/blob/main/CONTRIBUTING_TW.md)。
+對於想要貢獻程式碼的開發者，請參閱我們的[貢獻指南](https://github.com/langgenius/dify/blob/main/CONTRIBUTING/CONTRIBUTING_TW.md)。
 同時，也請考慮透過在社群媒體和各種活動與會議上分享 Dify 來支持我們。
 
 > 我們正在尋找貢獻者協助將 Dify 翻譯成中文和英文以外的語言。如果您有興趣幫忙，請查看 [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) 獲取更多資訊，並在我們的 [Discord 社群伺服器](https://discord.gg/8Tpq4AcN9c) 的 `global-users` 頻道留言給我們。
@@ -201,4 +201,4 @@ Dify 的所有功能都提供相應的 API，因此您可以輕鬆地將 Dify
 
 ## 授權條款
 
-本代碼庫採用 [Dify 開源授權](LICENSE)，這基本上是 Apache 2.0 授權加上一些額外限制條款。
+本代碼庫採用 [Dify 開源授權](../LICENSE)，這基本上是 Apache 2.0 授權加上一些額外限制條款。

README/README_VI.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](./images/GitHub_README_if.png)
+![cover-v5-optimized](../images/GitHub_README_if.png)
 
 <p align="center">
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
@@ -35,7 +35,7 @@
 </p>
 
 <p align="center">
-  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
   <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
   <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
   <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
@@ -162,7 +162,7 @@ Triển khai Dify lên AKS chỉ với một cú nhấp chuột bằng [Azure De
 
 ## Đóng góp
 
-Đối với những người muốn đóng góp mã, xem [Hướng dẫn Đóng góp](https://github.com/langgenius/dify/blob/main/CONTRIBUTING_VI.md) của chúng tôi.
+Đối với những người muốn đóng góp mã, xem [Hướng dẫn Đóng góp](https://github.com/langgenius/dify/blob/main/CONTRIBUTING/CONTRIBUTING_VI.md) của chúng tôi.
 Đồng thời, vui lòng xem xét hỗ trợ Dify bằng cách chia sẻ nó trên mạng xã hội và tại các sự kiện và hội nghị.
 
 > Chúng tôi đang tìm kiếm người đóng góp để giúp dịch Dify sang các ngôn ngữ khác ngoài tiếng Trung hoặc tiếng Anh. Nếu bạn quan tâm đến việc giúp đỡ, vui lòng xem [README i18n](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) để biết thêm thông tin và để lại bình luận cho chúng tôi trong kênh `global-users` của [Máy chủ Cộng đồng Discord](https://discord.gg/8Tpq4AcN9c) của chúng tôi.
@@ -190,4 +190,4 @@ Triển khai Dify lên AKS chỉ với một cú nhấp chuột bằng [Azure De
 
 ## Giấy phép
 
-Kho lưu trữ này có sẵn theo [Giấy phép Mã nguồn Mở Dify](LICENSE), về cơ bản là Apache 2.0 với một vài hạn chế bổ sung.
+Kho lưu trữ này có sẵn theo [Giấy phép Mã nguồn Mở Dify](../LICENSE), về cơ bản là Apache 2.0 với một vài hạn chế bổ sung.

api/.env.example

@@ -75,6 +75,8 @@ DB_PASSWORD=difyai123456
 DB_HOST=localhost
 DB_PORT=5432
 DB_DATABASE=dify
+SQLALCHEMY_POOL_PRE_PING=true
+SQLALCHEMY_POOL_TIMEOUT=30
 
 # Storage configuration
 # use for store upload files, private keys...
@@ -302,6 +304,8 @@ BAIDU_VECTOR_DB_API_KEY=dify
 BAIDU_VECTOR_DB_DATABASE=dify
 BAIDU_VECTOR_DB_SHARD=1
 BAIDU_VECTOR_DB_REPLICAS=3
+BAIDU_VECTOR_DB_INVERTED_INDEX_ANALYZER=DEFAULT_ANALYZER
+BAIDU_VECTOR_DB_INVERTED_INDEX_PARSER_MODE=COARSE_MODE
 
 # Upstash configuration
 UPSTASH_VECTOR_URL=your-server-url
@@ -327,7 +331,7 @@ MATRIXONE_DATABASE=dify
 LINDORM_URL=http://ld-*******************-proxy-search-pub.lindorm.aliyuncs.com:30070
 LINDORM_USERNAME=admin
 LINDORM_PASSWORD=admin
-USING_UGC_INDEX=False
+LINDORM_USING_UGC=True
 LINDORM_QUERY_TIMEOUT=1
 
 # OceanBase Vector configuration
@@ -404,6 +408,9 @@ SSRF_DEFAULT_TIME_OUT=5
 SSRF_DEFAULT_CONNECT_TIME_OUT=5
 SSRF_DEFAULT_READ_TIME_OUT=5
 SSRF_DEFAULT_WRITE_TIME_OUT=5
+SSRF_POOL_MAX_CONNECTIONS=100
+SSRF_POOL_MAX_KEEPALIVE_CONNECTIONS=20
+SSRF_POOL_KEEPALIVE_EXPIRY=5.0
 
 BATCH_UPLOAD_LIMIT=10
 KEYWORD_DATA_SOURCE_TYPE=database
@@ -414,6 +421,10 @@ WORKFLOW_FILE_UPLOAD_LIMIT=10
 # CODE EXECUTION CONFIGURATION
 CODE_EXECUTION_ENDPOINT=http://127.0.0.1:8194
 CODE_EXECUTION_API_KEY=dify-sandbox
+CODE_EXECUTION_SSL_VERIFY=True
+CODE_EXECUTION_POOL_MAX_CONNECTIONS=100
+CODE_EXECUTION_POOL_MAX_KEEPALIVE_CONNECTIONS=20
+CODE_EXECUTION_POOL_KEEPALIVE_EXPIRY=5.0
 CODE_MAX_NUMBER=9223372036854775807
 CODE_MIN_NUMBER=-9223372036854775808
 CODE_MAX_STRING_LENGTH=80000
@@ -457,9 +468,18 @@ INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=4000
 WORKFLOW_MAX_EXECUTION_STEPS=500
 WORKFLOW_MAX_EXECUTION_TIME=1200
 WORKFLOW_CALL_MAX_DEPTH=5
-WORKFLOW_PARALLEL_DEPTH_LIMIT=3
 MAX_VARIABLE_SIZE=204800
 
+# GraphEngine Worker Pool Configuration
+# Minimum number of workers per GraphEngine instance (default: 1)
+GRAPH_ENGINE_MIN_WORKERS=1
+# Maximum number of workers per GraphEngine instance (default: 10)
+GRAPH_ENGINE_MAX_WORKERS=10
+# Queue depth threshold that triggers worker scale up (default: 3)
+GRAPH_ENGINE_SCALE_UP_THRESHOLD=3
+# Seconds of idle time before scaling down workers (default: 5.0)
+GRAPH_ENGINE_SCALE_DOWN_IDLE_TIME=5.0
+
 # Workflow storage configuration
 # Options: rdbms, hybrid
 # rdbms: Use only the relational database (default)
@@ -529,6 +549,7 @@ ENDPOINT_URL_TEMPLATE=http://localhost:5002/e/{hook_id}
 
 # Reset password token expiry minutes
 RESET_PASSWORD_TOKEN_EXPIRY_MINUTES=5
+EMAIL_REGISTER_TOKEN_EXPIRY_MINUTES=5
 CHANGE_EMAIL_TOKEN_EXPIRY_MINUTES=5
 OWNER_TRANSFER_TOKEN_EXPIRY_MINUTES=5
 
@@ -568,3 +589,7 @@ QUEUE_MONITOR_INTERVAL=30
 # Swagger UI configuration
 SWAGGER_UI_ENABLED=true
 SWAGGER_UI_PATH=/swagger-ui.html
+
+# Whether to encrypt dataset IDs when exporting DSL files (default: true)
+# Set to false to export dataset IDs as plain text for easier cross-environment import
+DSL_EXPORT_ENCRYPT_DATASET_ID=true

api/.importlinter

@@ -0,0 +1,105 @@
+[importlinter]
+root_packages =
+    core
+    configs
+    controllers
+    models
+    tasks
+    services
+
+[importlinter:contract:workflow]
+name = Workflow
+type=layers
+layers =
+    graph_engine
+    graph_events
+    graph
+    nodes
+    node_events
+    entities
+containers =
+    core.workflow
+ignore_imports =
+    core.workflow.nodes.base.node -> core.workflow.graph_events
+    core.workflow.nodes.iteration.iteration_node -> core.workflow.graph_events
+    core.workflow.nodes.loop.loop_node -> core.workflow.graph_events
+
+    core.workflow.nodes.node_factory -> core.workflow.graph
+    core.workflow.nodes.iteration.iteration_node -> core.workflow.graph_engine
+    core.workflow.nodes.iteration.iteration_node -> core.workflow.graph
+    core.workflow.nodes.iteration.iteration_node -> core.workflow.graph_engine.command_channels
+    core.workflow.nodes.loop.loop_node -> core.workflow.graph_engine
+    core.workflow.nodes.loop.loop_node -> core.workflow.graph
+    core.workflow.nodes.loop.loop_node -> core.workflow.graph_engine.command_channels
+
+[importlinter:contract:rsc]
+name = RSC
+type = layers
+layers =
+    graph_engine
+    response_coordinator
+containers =
+    core.workflow.graph_engine
+
+[importlinter:contract:worker]
+name = Worker
+type = layers
+layers =
+    graph_engine
+    worker
+containers =
+    core.workflow.graph_engine
+
+[importlinter:contract:graph-engine-architecture]
+name = Graph Engine Architecture
+type = layers
+layers =
+    graph_engine
+    orchestration
+    command_processing
+    event_management
+    error_handler
+    graph_traversal
+    graph_state_manager
+    worker_management
+    domain
+containers =
+    core.workflow.graph_engine
+
+[importlinter:contract:domain-isolation]
+name = Domain Model Isolation
+type = forbidden
+source_modules =
+    core.workflow.graph_engine.domain
+forbidden_modules =
+    core.workflow.graph_engine.worker_management
+    core.workflow.graph_engine.command_channels
+    core.workflow.graph_engine.layers
+    core.workflow.graph_engine.protocols
+
+[importlinter:contract:worker-management]
+name = Worker Management
+type = forbidden
+source_modules =
+    core.workflow.graph_engine.worker_management
+forbidden_modules =
+    core.workflow.graph_engine.orchestration
+    core.workflow.graph_engine.command_processing
+    core.workflow.graph_engine.event_management
+
+
+[importlinter:contract:graph-traversal-components]
+name = Graph Traversal Components
+type = layers
+layers =
+    edge_processor
+    skip_propagator
+containers =
+    core.workflow.graph_engine.graph_traversal
+
+[importlinter:contract:command-channels]
+name = Command Channels Independence
+type = independence
+modules =
+    core.workflow.graph_engine.command_channels.in_memory_channel
+    core.workflow.graph_engine.command_channels.redis_channel

api/.ruff.toml

@@ -5,7 +5,7 @@ line-length = 120
 quote-style = "double"
 
 [lint]
-preview = false
+preview = true
 select = [
     "B",       # flake8-bugbear rules
     "C4",      # flake8-comprehensions
@@ -30,6 +30,7 @@ select = [
     "RUF022",  # unsorted-dunder-all
     "S506",    # unsafe-yaml-load
     "SIM",     # flake8-simplify rules
+    "T201",    # print-found
     "TRY400",  # error-instead-of-exception
     "TRY401",  # verbose-log-message
     "UP",      # pyupgrade rules
@@ -45,6 +46,7 @@ select = [
     "G001", # don't use str format to logging messages
     "G003", # don't use + in logging messages
     "G004", # don't use f-strings to format logging messages
+    "UP042", # use StrEnum
 ]
 
 ignore = [
@@ -64,6 +66,7 @@ ignore = [
     "B006",    # mutable-argument-default
     "B007",    # unused-loop-control-variable
     "B026",    # star-arg-unpacking-after-keyword-arg
+    "B901",    # allow return in yield
     "B903",    # class-as-data-structure
     "B904",    # raise-without-from-inside-except
     "B905",    # zip-without-explicit-strict
@@ -89,11 +92,18 @@ ignore = [
 "configs/*" = [
     "N802", # invalid-function-name
 ]
+"core/model_runtime/callbacks/base_callback.py" = [
+    "T201",
+]
+"core/workflow/callbacks/workflow_logging_callback.py" = [
+    "T201",
+]
 "libs/gmpy2_pkcs10aep_cipher.py" = [
     "N803", # invalid-argument-name
 ]
 "tests/*" = [
     "F811", # redefined-while-unused
+    "T201", # allow print in tests
 ]
 
 [lint.pyflakes]

api/README.md

@@ -80,10 +80,10 @@
 1. If you need to handle and debug the async tasks (e.g. dataset importing and documents indexing), please start the worker service.
 
 ```bash
-uv run celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation
+uv run celery -A app.celery worker -P gevent -c 2 --loglevel INFO -Q dataset,generation,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation
 ```
 
-Addition, if you want to debug the celery scheduled tasks, you can use the following command in another terminal:
+Additionally, if you want to debug the celery scheduled tasks, you can run the following command in another terminal to start the beat service:
 
 ```bash
 uv run celery -A app.celery beat
@@ -108,5 +108,5 @@ uv run celery -A app.celery beat
    ../dev/reformat               # Run all formatters and linters
    uv run ruff check --fix ./    # Fix linting issues
    uv run ruff format ./         # Format code
-   uv run mypy .                 # Type checking
+   uv run basedpyright .         # Type checking
    ```

api/app.py

@@ -1,4 +1,3 @@
-import os
 import sys
 
 
@@ -17,20 +16,20 @@ else:
     # It seems that JetBrains Python debugger does not work well with gevent,
     # so we need to disable gevent in debug mode.
     # If you are using debugpy and set GEVENT_SUPPORT=True, you can debug with gevent.
-    if (flask_debug := os.environ.get("FLASK_DEBUG", "0")) and flask_debug.lower() in {"false", "0", "no"}:
-        from gevent import monkey
+    # if (flask_debug := os.environ.get("FLASK_DEBUG", "0")) and flask_debug.lower() in {"false", "0", "no"}:
+    # from gevent import monkey
+    #
+    # # gevent
+    # monkey.patch_all()
+    #
+    # from grpc.experimental import gevent as grpc_gevent  # type: ignore
+    #
+    # # grpc gevent
+    # grpc_gevent.init_gevent()
 
-        # gevent
-        monkey.patch_all()
-
-        from grpc.experimental import gevent as grpc_gevent  # type: ignore
-
-        # grpc gevent
-        grpc_gevent.init_gevent()
-
-        import psycogreen.gevent  # type: ignore
-
-        psycogreen.gevent.patch_psycopg()
+    # import psycogreen.gevent  # type: ignore
+    #
+    # psycogreen.gevent.patch_psycopg()
 
     from app_factory import create_app
 

api/app_factory.py

@@ -25,6 +25,9 @@ def create_flask_app_with_configs() -> DifyApp:
         # add an unique identifier to each request
         RecyclableContextVar.increment_thread_recycles()
 
+    # Capture the decorator's return value to avoid pyright reportUnusedFunction
+    _ = before_request
+
     return dify_app
 
 

api/celery_entrypoint.py

@@ -0,0 +1,13 @@
+import psycogreen.gevent as pscycogreen_gevent  # type: ignore
+from grpc.experimental import gevent as grpc_gevent  # type: ignore
+
+# grpc gevent
+grpc_gevent.init_gevent()
+print("gRPC patched with gevent.", flush=True)  # noqa: T201
+pscycogreen_gevent.patch_psycopg()
+print("psycopg2 patched with gevent.", flush=True)  # noqa: T201
+
+
+from app import app, celery
+
+__all__ = ["app", "celery"]

api/child_class.py

@@ -1,11 +0,0 @@
-from tests.integration_tests.utils.parent_class import ParentClass
-
-
-class ChildClass(ParentClass):
-    """Test child class for module import helper tests"""
-
-    def __init__(self, name):
-        super().__init__(name)
-
-    def get_name(self):
-        return f"Child: {self.name}"

api/commands.py

@@ -2,7 +2,7 @@ import base64
 import json
 import logging
 import secrets
-from typing import Any, Optional
+from typing import Any
 
 import click
 import sqlalchemy as sa
@@ -10,32 +10,41 @@ from flask import current_app
 from pydantic import TypeAdapter
 from sqlalchemy import select
 from sqlalchemy.exc import SQLAlchemyError
+from sqlalchemy.orm import sessionmaker
 
 from configs import dify_config
 from constants.languages import languages
-from core.plugin.entities.plugin import ToolProviderID
+from core.helper import encrypter
+from core.plugin.impl.plugin import PluginInstaller
 from core.rag.datasource.vdb.vector_factory import Vector
 from core.rag.datasource.vdb.vector_type import VectorType
 from core.rag.index_processor.constant.built_in_field import BuiltInField
 from core.rag.models.document import Document
+from core.tools.entities.tool_entities import CredentialType
 from core.tools.utils.system_oauth_encryption import encrypt_system_oauth_params
 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 extensions.storage.opendal_storage import OpenDALStorage
+from extensions.storage.storage_type import StorageType
 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
 from models import Tenant
 from models.dataset import Dataset, DatasetCollectionBinding, DatasetMetadata, DatasetMetadataBinding, DocumentSegment
 from models.dataset import Document as DatasetDocument
-from models.model import Account, App, AppAnnotationSetting, AppMode, Conversation, MessageAnnotation
+from models.model import Account, App, AppAnnotationSetting, AppMode, Conversation, MessageAnnotation, UploadFile
+from models.oauth import DatasourceOauthParamConfig, DatasourceProvider
 from models.provider import Provider, ProviderModel
+from models.provider_ids import DatasourceProviderID, ToolProviderID
+from models.source import DataSourceApiKeyAuthBinding, DataSourceOauthBinding
 from models.tools import ToolOAuthSystemClient
 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
+from services.plugin.plugin_service import PluginService
 from tasks.remove_app_and_related_data_task import delete_draft_variables_batch
 
 logger = logging.getLogger(__name__)
@@ -53,31 +62,30 @@ def reset_password(email, new_password, password_confirm):
     if str(new_password).strip() != str(password_confirm).strip():
         click.echo(click.style("Passwords do not match.", fg="red"))
         return
+    with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
+        account = session.query(Account).where(Account.email == email).one_or_none()
 
-    account = db.session.query(Account).where(Account.email == email).one_or_none()
+        if not account:
+            click.echo(click.style(f"Account not found for email: {email}", fg="red"))
+            return
 
-    if not account:
-        click.echo(click.style(f"Account not found for email: {email}", fg="red"))
-        return
+        try:
+            valid_password(new_password)
+        except:
+            click.echo(click.style(f"Invalid password. Must match {password_pattern}", fg="red"))
+            return
 
-    try:
-        valid_password(new_password)
-    except:
-        click.echo(click.style(f"Invalid password. Must match {password_pattern}", fg="red"))
-        return
+        # generate password salt
+        salt = secrets.token_bytes(16)
+        base64_salt = base64.b64encode(salt).decode()
 
-    # generate password salt
-    salt = secrets.token_bytes(16)
-    base64_salt = base64.b64encode(salt).decode()
-
-    # encrypt password with salt
-    password_hashed = hash_password(new_password, salt)
-    base64_password_hashed = base64.b64encode(password_hashed).decode()
-    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"))
+        # encrypt password with salt
+        password_hashed = hash_password(new_password, salt)
+        base64_password_hashed = base64.b64encode(password_hashed).decode()
+        account.password = base64_password_hashed
+        account.password_salt = base64_salt
+        AccountService.reset_login_error_rate_limit(email)
+        click.echo(click.style("Password reset successfully.", fg="green"))
 
 
 @click.command("reset-email", help="Reset the account email.")
@@ -92,22 +100,21 @@ def reset_email(email, new_email, email_confirm):
     if str(new_email).strip() != str(email_confirm).strip():
         click.echo(click.style("New emails do not match.", fg="red"))
         return
+    with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
+        account = session.query(Account).where(Account.email == email).one_or_none()
 
-    account = db.session.query(Account).where(Account.email == email).one_or_none()
+        if not account:
+            click.echo(click.style(f"Account not found for email: {email}", fg="red"))
+            return
 
-    if not account:
-        click.echo(click.style(f"Account not found for email: {email}", fg="red"))
-        return
+        try:
+            email_validate(new_email)
+        except:
+            click.echo(click.style(f"Invalid email: {new_email}", fg="red"))
+            return
 
-    try:
-        email_validate(new_email)
-    except:
-        click.echo(click.style(f"Invalid email: {new_email}", fg="red"))
-        return
-
-    account.email = new_email
-    db.session.commit()
-    click.echo(click.style("Email updated successfully.", fg="green"))
+        account.email = new_email
+        click.echo(click.style("Email updated successfully.", fg="green"))
 
 
 @click.command(
@@ -131,25 +138,24 @@ def reset_encrypt_key_pair():
     if dify_config.EDITION != "SELF_HOSTED":
         click.echo(click.style("This command is only for SELF_HOSTED installations.", fg="red"))
         return
+    with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
+        tenants = session.query(Tenant).all()
+        for tenant in tenants:
+            if not tenant:
+                click.echo(click.style("No workspaces found. Run /install first.", fg="red"))
+                return
 
-    tenants = db.session.query(Tenant).all()
-    for tenant in tenants:
-        if not tenant:
-            click.echo(click.style("No workspaces found. Run /install first.", fg="red"))
-            return
+            tenant.encrypt_public_key = generate_key_pair(tenant.id)
 
-        tenant.encrypt_public_key = generate_key_pair(tenant.id)
+            session.query(Provider).where(Provider.provider_type == "custom", Provider.tenant_id == tenant.id).delete()
+            session.query(ProviderModel).where(ProviderModel.tenant_id == tenant.id).delete()
 
-        db.session.query(Provider).where(Provider.provider_type == "custom", Provider.tenant_id == tenant.id).delete()
-        db.session.query(ProviderModel).where(ProviderModel.tenant_id == tenant.id).delete()
-        db.session.commit()
-
-        click.echo(
-            click.style(
-                f"Congratulations! The asymmetric key pair of workspace {tenant.id} has been reset.",
-                fg="green",
+            click.echo(
+                click.style(
+                    f"Congratulations! The asymmetric key pair of workspace {tenant.id} has been reset.",
+                    fg="green",
+                )
             )
-        )
 
 
 @click.command("vdb-migrate", help="Migrate vector db.")
@@ -174,14 +180,15 @@ def migrate_annotation_vector_database():
         try:
             # get apps info
             per_page = 50
-            apps = (
-                db.session.query(App)
-                .where(App.status == "normal")
-                .order_by(App.created_at.desc())
-                .limit(per_page)
-                .offset((page - 1) * per_page)
-                .all()
-            )
+            with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
+                apps = (
+                    session.query(App)
+                    .where(App.status == "normal")
+                    .order_by(App.created_at.desc())
+                    .limit(per_page)
+                    .offset((page - 1) * per_page)
+                    .all()
+                )
             if not apps:
                 break
         except SQLAlchemyError:
@@ -195,24 +202,27 @@ def migrate_annotation_vector_database():
             )
             try:
                 click.echo(f"Creating app annotation index: {app.id}")
-                app_annotation_setting = (
-                    db.session.query(AppAnnotationSetting).where(AppAnnotationSetting.app_id == app.id).first()
-                )
+                with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
+                    app_annotation_setting = (
+                        session.query(AppAnnotationSetting).where(AppAnnotationSetting.app_id == app.id).first()
+                    )
 
-                if not app_annotation_setting:
-                    skipped_count = skipped_count + 1
-                    click.echo(f"App annotation setting disabled: {app.id}")
-                    continue
-                # get dataset_collection_binding info
-                dataset_collection_binding = (
-                    db.session.query(DatasetCollectionBinding)
-                    .where(DatasetCollectionBinding.id == app_annotation_setting.collection_binding_id)
-                    .first()
-                )
-                if not dataset_collection_binding:
-                    click.echo(f"App annotation collection binding not found: {app.id}")
-                    continue
-                annotations = db.session.query(MessageAnnotation).where(MessageAnnotation.app_id == app.id).all()
+                    if not app_annotation_setting:
+                        skipped_count = skipped_count + 1
+                        click.echo(f"App annotation setting disabled: {app.id}")
+                        continue
+                    # get dataset_collection_binding info
+                    dataset_collection_binding = (
+                        session.query(DatasetCollectionBinding)
+                        .where(DatasetCollectionBinding.id == app_annotation_setting.collection_binding_id)
+                        .first()
+                    )
+                    if not dataset_collection_binding:
+                        click.echo(f"App annotation collection binding not found: {app.id}")
+                        continue
+                    annotations = session.scalars(
+                        select(MessageAnnotation).where(MessageAnnotation.app_id == app.id)
+                    ).all()
                 dataset = Dataset(
                     id=app.id,
                     tenant_id=app.tenant_id,
@@ -367,29 +377,25 @@ def migrate_knowledge_vector_database():
                     )
                     raise e
 
-                dataset_documents = (
-                    db.session.query(DatasetDocument)
-                    .where(
+                dataset_documents = db.session.scalars(
+                    select(DatasetDocument).where(
                         DatasetDocument.dataset_id == dataset.id,
                         DatasetDocument.indexing_status == "completed",
                         DatasetDocument.enabled == True,
                         DatasetDocument.archived == False,
                     )
-                    .all()
-                )
+                ).all()
 
                 documents = []
                 segments_count = 0
                 for dataset_document in dataset_documents:
-                    segments = (
-                        db.session.query(DocumentSegment)
-                        .where(
+                    segments = db.session.scalars(
+                        select(DocumentSegment).where(
                             DocumentSegment.document_id == dataset_document.id,
                             DocumentSegment.status == "completed",
                             DocumentSegment.enabled == True,
                         )
-                        .all()
-                    )
+                    ).all()
 
                     for segment in segments:
                         document = Document(
@@ -479,12 +485,12 @@ def convert_to_agent_apps():
             click.echo(f"Converting app: {app.id}")
 
             try:
-                app.mode = AppMode.AGENT_CHAT.value
+                app.mode = AppMode.AGENT_CHAT
                 db.session.commit()
 
                 # update conversation mode to agent
                 db.session.query(Conversation).where(Conversation.app_id == app.id).update(
-                    {Conversation.mode: AppMode.AGENT_CHAT.value}
+                    {Conversation.mode: AppMode.AGENT_CHAT}
                 )
 
                 db.session.commit()
@@ -511,7 +517,7 @@ def add_qdrant_index(field: str):
         from qdrant_client.http.exceptions import UnexpectedResponse
         from qdrant_client.http.models import PayloadSchemaType
 
-        from core.rag.datasource.vdb.qdrant.qdrant_vector import QdrantConfig
+        from core.rag.datasource.vdb.qdrant.qdrant_vector import PathQdrantParams, QdrantConfig
 
         for binding in bindings:
             if dify_config.QDRANT_URL is None:
@@ -525,7 +531,21 @@ def add_qdrant_index(field: str):
                 prefer_grpc=dify_config.QDRANT_GRPC_ENABLED,
             )
             try:
-                client = qdrant_client.QdrantClient(**qdrant_config.to_qdrant_params())
+                params = qdrant_config.to_qdrant_params()
+                # Check the type before using
+                if isinstance(params, PathQdrantParams):
+                    # PathQdrantParams case
+                    client = qdrant_client.QdrantClient(path=params.path)
+                else:
+                    # UrlQdrantParams case - params is UrlQdrantParams
+                    client = qdrant_client.QdrantClient(
+                        url=params.url,
+                        api_key=params.api_key,
+                        timeout=int(params.timeout),
+                        verify=params.verify,
+                        grpc_port=params.grpc_port,
+                        prefer_grpc=params.prefer_grpc,
+                    )
                 # create payload index
                 client.create_payload_index(binding.collection_name, field, field_schema=PayloadSchemaType.KEYWORD)
                 create_count += 1
@@ -571,7 +591,7 @@ def old_metadata_migration():
         for document in documents:
             if document.doc_metadata:
                 doc_metadata = document.doc_metadata
-                for key, value in doc_metadata.items():
+                for key in doc_metadata:
                     for field in BuiltInField:
                         if field.value == key:
                             break
@@ -627,7 +647,7 @@ def old_metadata_migration():
 @click.option("--email", prompt=True, help="Tenant account email.")
 @click.option("--name", prompt=True, help="Workspace name.")
 @click.option("--language", prompt=True, help="Account language, default: en-US.")
-def create_tenant(email: str, language: Optional[str] = None, name: Optional[str] = None):
+def create_tenant(email: str, language: str | None = None, name: str | None = None):
     """
     Create tenant account
     """
@@ -719,18 +739,18 @@ where sites.id is null limit 1000"""
                 try:
                     app = db.session.query(App).where(App.id == app_id).first()
                     if not app:
-                        print(f"App {app_id} not found")
+                        logger.info("App %s not found", app_id)
                         continue
 
                     tenant = app.tenant
                     if tenant:
                         accounts = tenant.get_accounts()
                         if not accounts:
-                            print(f"Fix failed for app {app.id}")
+                            logger.info("Fix failed for app %s", app.id)
                             continue
 
                         account = accounts[0]
-                        print(f"Fixing missing site for app {app.id}")
+                        logger.info("Fixing missing site for app %s", app.id)
                         app_was_created.send(app, account=account)
                 except Exception:
                     failed_app_ids.append(app_id)
@@ -941,7 +961,7 @@ def clear_orphaned_file_records(force: bool):
             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(sa.text(query), {"ids": tuple([record["id"] for record in orphaned_message_files])})
+                conn.execute(sa.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")
             )
@@ -1233,15 +1253,17 @@ def _find_orphaned_draft_variables(batch_size: int = 1000) -> list[str]:
 
 def _count_orphaned_draft_variables() -> dict[str, Any]:
     """
-    Count orphaned draft variables by app.
+    Count orphaned draft variables by app, including associated file counts.
 
     Returns:
-        Dictionary with statistics about orphaned variables
+        Dictionary with statistics about orphaned variables and files
     """
-    query = """
+    # Count orphaned variables by app
+    variables_query = """
         SELECT
             wdv.app_id,
-            COUNT(*) as variable_count
+            COUNT(*) as variable_count,
+            COUNT(wdv.file_id) as file_count
         FROM workflow_draft_variables AS wdv
         WHERE NOT EXISTS(
             SELECT 1 FROM apps WHERE apps.id = wdv.app_id
@@ -1251,14 +1273,21 @@ def _count_orphaned_draft_variables() -> dict[str, Any]:
     """
 
     with db.engine.connect() as conn:
-        result = conn.execute(sa.text(query))
-        orphaned_by_app = {row[0]: row[1] for row in result}
+        result = conn.execute(sa.text(variables_query))
+        orphaned_by_app = {}
+        total_files = 0
 
-        total_orphaned = sum(orphaned_by_app.values())
+        for row in result:
+            app_id, variable_count, file_count = row
+            orphaned_by_app[app_id] = {"variables": variable_count, "files": file_count}
+            total_files += file_count
+
+        total_orphaned = sum(app_data["variables"] for app_data in orphaned_by_app.values())
         app_count = len(orphaned_by_app)
 
         return {
             "total_orphaned_variables": total_orphaned,
+            "total_orphaned_files": total_files,
             "orphaned_app_count": app_count,
             "orphaned_by_app": orphaned_by_app,
         }
@@ -1287,6 +1316,7 @@ def cleanup_orphaned_draft_variables(
     stats = _count_orphaned_draft_variables()
 
     logger.info("Found %s orphaned draft variables", stats["total_orphaned_variables"])
+    logger.info("Found %s associated offload files", stats["total_orphaned_files"])
     logger.info("Across %s non-existent apps", stats["orphaned_app_count"])
 
     if stats["total_orphaned_variables"] == 0:
@@ -1295,10 +1325,10 @@ def cleanup_orphaned_draft_variables(
 
     if dry_run:
         logger.info("DRY RUN: Would delete the following:")
-        for app_id, count in sorted(stats["orphaned_by_app"].items(), key=lambda x: x[1], reverse=True)[
+        for app_id, data in sorted(stats["orphaned_by_app"].items(), key=lambda x: x[1]["variables"], reverse=True)[
             :10
         ]:  # Show top 10
-            logger.info("  App %s: %s variables", app_id, count)
+            logger.info("  App %s: %s variables, %s files", app_id, data["variables"], data["files"])
         if len(stats["orphaned_by_app"]) > 10:
             logger.info("  ... and %s more apps", len(stats["orphaned_by_app"]) - 10)
         return
@@ -1307,7 +1337,8 @@ def cleanup_orphaned_draft_variables(
     if not force:
         click.confirm(
             f"Are you sure you want to delete {stats['total_orphaned_variables']} "
-            f"orphaned draft variables from {stats['orphaned_app_count']} apps?",
+            f"orphaned draft variables and {stats['total_orphaned_files']} associated files "
+            f"from {stats['orphaned_app_count']} apps?",
             abort=True,
         )
 
@@ -1340,3 +1371,456 @@ def cleanup_orphaned_draft_variables(
                 continue
 
     logger.info("Cleanup completed. Total deleted: %s variables across %s apps", total_deleted, processed_apps)
+
+
+@click.command("setup-datasource-oauth-client", help="Setup datasource oauth client.")
+@click.option("--provider", prompt=True, help="Provider name")
+@click.option("--client-params", prompt=True, help="Client Params")
+def setup_datasource_oauth_client(provider, client_params):
+    """
+    Setup datasource oauth client
+    """
+    provider_id = DatasourceProviderID(provider)
+    provider_name = provider_id.provider_name
+    plugin_id = provider_id.plugin_id
+
+    try:
+        # json validate
+        click.echo(click.style(f"Validating client params: {client_params}", fg="yellow"))
+        client_params_dict = TypeAdapter(dict[str, Any]).validate_json(client_params)
+        click.echo(click.style("Client params validated successfully.", fg="green"))
+    except Exception as e:
+        click.echo(click.style(f"Error parsing client params: {str(e)}", fg="red"))
+        return
+
+    click.echo(click.style(f"Ready to delete existing oauth client params: {provider_name}", fg="yellow"))
+    deleted_count = (
+        db.session.query(DatasourceOauthParamConfig)
+        .filter_by(
+            provider=provider_name,
+            plugin_id=plugin_id,
+        )
+        .delete()
+    )
+    if deleted_count > 0:
+        click.echo(click.style(f"Deleted {deleted_count} existing oauth client params.", fg="yellow"))
+
+    click.echo(click.style(f"Ready to setup datasource oauth client: {provider_name}", fg="yellow"))
+    oauth_client = DatasourceOauthParamConfig(
+        provider=provider_name,
+        plugin_id=plugin_id,
+        system_credentials=client_params_dict,
+    )
+    db.session.add(oauth_client)
+    db.session.commit()
+    click.echo(click.style(f"provider: {provider_name}", fg="green"))
+    click.echo(click.style(f"plugin_id: {plugin_id}", fg="green"))
+    click.echo(click.style(f"params: {json.dumps(client_params_dict, indent=2, ensure_ascii=False)}", fg="green"))
+    click.echo(click.style(f"Datasource oauth client setup successfully. id: {oauth_client.id}", fg="green"))
+
+
+@click.command("transform-datasource-credentials", help="Transform datasource credentials.")
+def transform_datasource_credentials():
+    """
+    Transform datasource credentials
+    """
+    try:
+        installer_manager = PluginInstaller()
+        plugin_migration = PluginMigration()
+
+        notion_plugin_id = "langgenius/notion_datasource"
+        firecrawl_plugin_id = "langgenius/firecrawl_datasource"
+        jina_plugin_id = "langgenius/jina_datasource"
+        notion_plugin_unique_identifier = plugin_migration._fetch_plugin_unique_identifier(notion_plugin_id)  # pyright: ignore[reportPrivateUsage]
+        firecrawl_plugin_unique_identifier = plugin_migration._fetch_plugin_unique_identifier(firecrawl_plugin_id)  # pyright: ignore[reportPrivateUsage]
+        jina_plugin_unique_identifier = plugin_migration._fetch_plugin_unique_identifier(jina_plugin_id)  # pyright: ignore[reportPrivateUsage]
+        oauth_credential_type = CredentialType.OAUTH2
+        api_key_credential_type = CredentialType.API_KEY
+
+        # deal notion credentials
+        deal_notion_count = 0
+        notion_credentials = db.session.query(DataSourceOauthBinding).filter_by(provider="notion").all()
+        if notion_credentials:
+            notion_credentials_tenant_mapping: dict[str, list[DataSourceOauthBinding]] = {}
+            for notion_credential in notion_credentials:
+                tenant_id = notion_credential.tenant_id
+                if tenant_id not in notion_credentials_tenant_mapping:
+                    notion_credentials_tenant_mapping[tenant_id] = []
+                notion_credentials_tenant_mapping[tenant_id].append(notion_credential)
+            for tenant_id, notion_tenant_credentials in notion_credentials_tenant_mapping.items():
+                tenant = db.session.query(Tenant).filter_by(id=tenant_id).first()
+                if not tenant:
+                    continue
+                try:
+                    # check notion plugin is installed
+                    installed_plugins = installer_manager.list_plugins(tenant_id)
+                    installed_plugins_ids = [plugin.plugin_id for plugin in installed_plugins]
+                    if notion_plugin_id not in installed_plugins_ids:
+                        if notion_plugin_unique_identifier:
+                            # install notion plugin
+                            PluginService.install_from_marketplace_pkg(tenant_id, [notion_plugin_unique_identifier])
+                    auth_count = 0
+                    for notion_tenant_credential in notion_tenant_credentials:
+                        auth_count += 1
+                        # get credential oauth params
+                        access_token = notion_tenant_credential.access_token
+                        # notion info
+                        notion_info = notion_tenant_credential.source_info
+                        workspace_id = notion_info.get("workspace_id")
+                        workspace_name = notion_info.get("workspace_name")
+                        workspace_icon = notion_info.get("workspace_icon")
+                        new_credentials = {
+                            "integration_secret": encrypter.encrypt_token(tenant_id, access_token),
+                            "workspace_id": workspace_id,
+                            "workspace_name": workspace_name,
+                            "workspace_icon": workspace_icon,
+                        }
+                        datasource_provider = DatasourceProvider(
+                            provider="notion_datasource",
+                            tenant_id=tenant_id,
+                            plugin_id=notion_plugin_id,
+                            auth_type=oauth_credential_type.value,
+                            encrypted_credentials=new_credentials,
+                            name=f"Auth {auth_count}",
+                            avatar_url=workspace_icon or "default",
+                            is_default=False,
+                        )
+                        db.session.add(datasource_provider)
+                        deal_notion_count += 1
+                except Exception as e:
+                    click.echo(
+                        click.style(
+                            f"Error transforming notion credentials: {str(e)}, tenant_id: {tenant_id}", fg="red"
+                        )
+                    )
+                    continue
+                db.session.commit()
+        # deal firecrawl credentials
+        deal_firecrawl_count = 0
+        firecrawl_credentials = db.session.query(DataSourceApiKeyAuthBinding).filter_by(provider="firecrawl").all()
+        if firecrawl_credentials:
+            firecrawl_credentials_tenant_mapping: dict[str, list[DataSourceApiKeyAuthBinding]] = {}
+            for firecrawl_credential in firecrawl_credentials:
+                tenant_id = firecrawl_credential.tenant_id
+                if tenant_id not in firecrawl_credentials_tenant_mapping:
+                    firecrawl_credentials_tenant_mapping[tenant_id] = []
+                firecrawl_credentials_tenant_mapping[tenant_id].append(firecrawl_credential)
+            for tenant_id, firecrawl_tenant_credentials in firecrawl_credentials_tenant_mapping.items():
+                tenant = db.session.query(Tenant).filter_by(id=tenant_id).first()
+                if not tenant:
+                    continue
+                try:
+                    # check firecrawl plugin is installed
+                    installed_plugins = installer_manager.list_plugins(tenant_id)
+                    installed_plugins_ids = [plugin.plugin_id for plugin in installed_plugins]
+                    if firecrawl_plugin_id not in installed_plugins_ids:
+                        if firecrawl_plugin_unique_identifier:
+                            # install firecrawl plugin
+                            PluginService.install_from_marketplace_pkg(tenant_id, [firecrawl_plugin_unique_identifier])
+
+                    auth_count = 0
+                    for firecrawl_tenant_credential in firecrawl_tenant_credentials:
+                        auth_count += 1
+                        # get credential api key
+                        credentials_json = json.loads(firecrawl_tenant_credential.credentials)
+                        api_key = credentials_json.get("config", {}).get("api_key")
+                        base_url = credentials_json.get("config", {}).get("base_url")
+                        new_credentials = {
+                            "firecrawl_api_key": api_key,
+                            "base_url": base_url,
+                        }
+                        datasource_provider = DatasourceProvider(
+                            provider="firecrawl",
+                            tenant_id=tenant_id,
+                            plugin_id=firecrawl_plugin_id,
+                            auth_type=api_key_credential_type.value,
+                            encrypted_credentials=new_credentials,
+                            name=f"Auth {auth_count}",
+                            avatar_url="default",
+                            is_default=False,
+                        )
+                        db.session.add(datasource_provider)
+                        deal_firecrawl_count += 1
+                except Exception as e:
+                    click.echo(
+                        click.style(
+                            f"Error transforming firecrawl credentials: {str(e)}, tenant_id: {tenant_id}", fg="red"
+                        )
+                    )
+                    continue
+                db.session.commit()
+        # deal jina credentials
+        deal_jina_count = 0
+        jina_credentials = db.session.query(DataSourceApiKeyAuthBinding).filter_by(provider="jinareader").all()
+        if jina_credentials:
+            jina_credentials_tenant_mapping: dict[str, list[DataSourceApiKeyAuthBinding]] = {}
+            for jina_credential in jina_credentials:
+                tenant_id = jina_credential.tenant_id
+                if tenant_id not in jina_credentials_tenant_mapping:
+                    jina_credentials_tenant_mapping[tenant_id] = []
+                jina_credentials_tenant_mapping[tenant_id].append(jina_credential)
+            for tenant_id, jina_tenant_credentials in jina_credentials_tenant_mapping.items():
+                tenant = db.session.query(Tenant).filter_by(id=tenant_id).first()
+                if not tenant:
+                    continue
+                try:
+                    # check jina plugin is installed
+                    installed_plugins = installer_manager.list_plugins(tenant_id)
+                    installed_plugins_ids = [plugin.plugin_id for plugin in installed_plugins]
+                    if jina_plugin_id not in installed_plugins_ids:
+                        if jina_plugin_unique_identifier:
+                            # install jina plugin
+                            logger.debug("Installing Jina plugin %s", jina_plugin_unique_identifier)
+                            PluginService.install_from_marketplace_pkg(tenant_id, [jina_plugin_unique_identifier])
+
+                    auth_count = 0
+                    for jina_tenant_credential in jina_tenant_credentials:
+                        auth_count += 1
+                        # get credential api key
+                        credentials_json = json.loads(jina_tenant_credential.credentials)
+                        api_key = credentials_json.get("config", {}).get("api_key")
+                        new_credentials = {
+                            "integration_secret": api_key,
+                        }
+                        datasource_provider = DatasourceProvider(
+                            provider="jina",
+                            tenant_id=tenant_id,
+                            plugin_id=jina_plugin_id,
+                            auth_type=api_key_credential_type.value,
+                            encrypted_credentials=new_credentials,
+                            name=f"Auth {auth_count}",
+                            avatar_url="default",
+                            is_default=False,
+                        )
+                        db.session.add(datasource_provider)
+                        deal_jina_count += 1
+                except Exception as e:
+                    click.echo(
+                        click.style(f"Error transforming jina credentials: {str(e)}, tenant_id: {tenant_id}", fg="red")
+                    )
+                    continue
+                db.session.commit()
+    except Exception as e:
+        click.echo(click.style(f"Error parsing client params: {str(e)}", fg="red"))
+        return
+    click.echo(click.style(f"Transforming notion successfully. deal_notion_count: {deal_notion_count}", fg="green"))
+    click.echo(
+        click.style(f"Transforming firecrawl successfully. deal_firecrawl_count: {deal_firecrawl_count}", fg="green")
+    )
+    click.echo(click.style(f"Transforming jina successfully. deal_jina_count: {deal_jina_count}", fg="green"))
+
+
+@click.command("install-rag-pipeline-plugins", help="Install rag pipeline plugins.")
+@click.option(
+    "--input_file", prompt=True, help="The file to store the extracted unique identifiers.", default="plugins.jsonl"
+)
+@click.option(
+    "--output_file", prompt=True, help="The file to store the installed plugins.", default="installed_plugins.jsonl"
+)
+@click.option("--workers", prompt=True, help="The number of workers to install plugins.", default=100)
+def install_rag_pipeline_plugins(input_file, output_file, workers):
+    """
+    Install rag pipeline plugins
+    """
+    click.echo(click.style("Installing rag pipeline plugins", fg="yellow"))
+    plugin_migration = PluginMigration()
+    plugin_migration.install_rag_pipeline_plugins(
+        input_file,
+        output_file,
+        workers,
+    )
+    click.echo(click.style("Installing rag pipeline plugins successfully", fg="green"))
+
+
+@click.command(
+    "migrate-oss",
+    help="Migrate files from Local or OpenDAL source to a cloud OSS storage (destination must NOT be local/opendal).",
+)
+@click.option(
+    "--path",
+    "paths",
+    multiple=True,
+    help="Storage path prefixes to migrate (repeatable). Defaults: privkeys, upload_files, image_files,"
+    " tools, website_files, keyword_files, ops_trace",
+)
+@click.option(
+    "--source",
+    type=click.Choice(["local", "opendal"], case_sensitive=False),
+    default="opendal",
+    show_default=True,
+    help="Source storage type to read from",
+)
+@click.option("--overwrite", is_flag=True, default=False, help="Overwrite destination if file already exists")
+@click.option("--dry-run", is_flag=True, default=False, help="Show what would be migrated without uploading")
+@click.option("-f", "--force", is_flag=True, help="Skip confirmation and run without prompts")
+@click.option(
+    "--update-db/--no-update-db",
+    default=True,
+    help="Update upload_files.storage_type from source type to current storage after migration",
+)
+def migrate_oss(
+    paths: tuple[str, ...],
+    source: str,
+    overwrite: bool,
+    dry_run: bool,
+    force: bool,
+    update_db: bool,
+):
+    """
+    Copy all files under selected prefixes from a source storage
+    (Local filesystem or OpenDAL-backed) into the currently configured
+    destination storage backend, then optionally update DB records.
+
+    Expected usage: set STORAGE_TYPE (and its credentials) to your target backend.
+    """
+    # Ensure target storage is not local/opendal
+    if dify_config.STORAGE_TYPE in (StorageType.LOCAL, StorageType.OPENDAL):
+        click.echo(
+            click.style(
+                "Target STORAGE_TYPE must be a cloud OSS (not 'local' or 'opendal').\n"
+                "Please set STORAGE_TYPE to one of: s3, aliyun-oss, azure-blob, google-storage, tencent-cos, \n"
+                "volcengine-tos, supabase, oci-storage, huawei-obs, baidu-obs, clickzetta-volume.",
+                fg="red",
+            )
+        )
+        return
+
+    # Default paths if none specified
+    default_paths = ("privkeys", "upload_files", "image_files", "tools", "website_files", "keyword_files", "ops_trace")
+    path_list = list(paths) if paths else list(default_paths)
+    is_source_local = source.lower() == "local"
+
+    click.echo(click.style("Preparing migration to target storage.", fg="yellow"))
+    click.echo(click.style(f"Target storage type: {dify_config.STORAGE_TYPE}", fg="white"))
+    if is_source_local:
+        src_root = dify_config.STORAGE_LOCAL_PATH
+        click.echo(click.style(f"Source: local fs, root: {src_root}", fg="white"))
+    else:
+        click.echo(click.style(f"Source: opendal scheme={dify_config.OPENDAL_SCHEME}", fg="white"))
+    click.echo(click.style(f"Paths to migrate: {', '.join(path_list)}", fg="white"))
+    click.echo("")
+
+    if not force:
+        click.confirm("Proceed with migration?", abort=True)
+
+    # Instantiate source storage
+    try:
+        if is_source_local:
+            src_root = dify_config.STORAGE_LOCAL_PATH
+            source_storage = OpenDALStorage(scheme="fs", root=src_root)
+        else:
+            source_storage = OpenDALStorage(scheme=dify_config.OPENDAL_SCHEME)
+    except Exception as e:
+        click.echo(click.style(f"Failed to initialize source storage: {str(e)}", fg="red"))
+        return
+
+    total_files = 0
+    copied_files = 0
+    skipped_files = 0
+    errored_files = 0
+    copied_upload_file_keys: list[str] = []
+
+    for prefix in path_list:
+        click.echo(click.style(f"Scanning source path: {prefix}", fg="white"))
+        try:
+            keys = source_storage.scan(path=prefix, files=True, directories=False)
+        except FileNotFoundError:
+            click.echo(click.style(f"  -> Skipping missing path: {prefix}", fg="yellow"))
+            continue
+        except NotImplementedError:
+            click.echo(click.style("  -> Source storage does not support scanning.", fg="red"))
+            return
+        except Exception as e:
+            click.echo(click.style(f"  -> Error scanning '{prefix}': {str(e)}", fg="red"))
+            continue
+
+        click.echo(click.style(f"Found {len(keys)} files under {prefix}", fg="white"))
+
+        for key in keys:
+            total_files += 1
+
+            # check destination existence
+            if not overwrite:
+                try:
+                    if storage.exists(key):
+                        skipped_files += 1
+                        continue
+                except Exception as e:
+                    # existence check failures should not block migration attempt
+                    # but should be surfaced to user as a warning for visibility
+                    click.echo(
+                        click.style(
+                            f"  -> Warning: failed target existence check for {key}: {str(e)}",
+                            fg="yellow",
+                        )
+                    )
+
+            if dry_run:
+                copied_files += 1
+                continue
+
+            # read from source and write to destination
+            try:
+                data = source_storage.load_once(key)
+            except FileNotFoundError:
+                errored_files += 1
+                click.echo(click.style(f"  -> Missing on source: {key}", fg="yellow"))
+                continue
+            except Exception as e:
+                errored_files += 1
+                click.echo(click.style(f"  -> Error reading {key}: {str(e)}", fg="red"))
+                continue
+
+            try:
+                storage.save(key, data)
+                copied_files += 1
+                if prefix == "upload_files":
+                    copied_upload_file_keys.append(key)
+            except Exception as e:
+                errored_files += 1
+                click.echo(click.style(f"  -> Error writing {key} to target: {str(e)}", fg="red"))
+                continue
+
+    click.echo("")
+    click.echo(click.style("Migration summary:", fg="yellow"))
+    click.echo(click.style(f"  Total:   {total_files}", fg="white"))
+    click.echo(click.style(f"  Copied:  {copied_files}", fg="green"))
+    click.echo(click.style(f"  Skipped: {skipped_files}", fg="white"))
+    if errored_files:
+        click.echo(click.style(f"  Errors:  {errored_files}", fg="red"))
+
+    if dry_run:
+        click.echo(click.style("Dry-run complete. No changes were made.", fg="green"))
+        return
+
+    if errored_files:
+        click.echo(
+            click.style(
+                "Some files failed to migrate. Review errors above before updating DB records.",
+                fg="yellow",
+            )
+        )
+        if update_db and not force:
+            if not click.confirm("Proceed to update DB storage_type despite errors?", default=False):
+                update_db = False
+
+    # Optionally update DB records for upload_files.storage_type (only for successfully copied upload_files)
+    if update_db:
+        if not copied_upload_file_keys:
+            click.echo(click.style("No upload_files copied. Skipping DB storage_type update.", fg="yellow"))
+        else:
+            try:
+                source_storage_type = StorageType.LOCAL if is_source_local else StorageType.OPENDAL
+                updated = (
+                    db.session.query(UploadFile)
+                    .where(
+                        UploadFile.storage_type == source_storage_type,
+                        UploadFile.key.in_(copied_upload_file_keys),
+                    )
+                    .update({UploadFile.storage_type: dify_config.STORAGE_TYPE}, synchronize_session=False)
+                )
+                db.session.commit()
+                click.echo(click.style(f"Updated storage_type for {updated} upload_files records.", fg="green"))
+            except Exception as e:
+                db.session.rollback()
+                click.echo(click.style(f"Failed to update DB storage_type: {str(e)}", fg="red"))

api/configs/__init__.py

@@ -1,3 +1,3 @@
 from .app_config import DifyConfig
 
-dify_config = DifyConfig()
+dify_config = DifyConfig()  # type: ignore

api/configs/extra/notion_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,28 +7,28 @@ class NotionConfig(BaseSettings):
     Configuration settings for Notion integration
     """
 
-    NOTION_CLIENT_ID: Optional[str] = Field(
+    NOTION_CLIENT_ID: str | None = Field(
         description="Client ID for Notion API authentication. Required for OAuth 2.0 flow.",
         default=None,
     )
 
-    NOTION_CLIENT_SECRET: Optional[str] = Field(
+    NOTION_CLIENT_SECRET: str | None = Field(
         description="Client secret for Notion API authentication. Required for OAuth 2.0 flow.",
         default=None,
     )
 
-    NOTION_INTEGRATION_TYPE: Optional[str] = Field(
+    NOTION_INTEGRATION_TYPE: str | None = Field(
         description="Type of Notion integration."
         " Set to 'internal' for internal integrations, or None for public integrations.",
         default=None,
     )
 
-    NOTION_INTERNAL_SECRET: Optional[str] = Field(
+    NOTION_INTERNAL_SECRET: str | None = Field(
         description="Secret key for internal Notion integrations. Required when NOTION_INTEGRATION_TYPE is 'internal'.",
         default=None,
     )
 
-    NOTION_INTEGRATION_TOKEN: Optional[str] = Field(
+    NOTION_INTEGRATION_TOKEN: str | None = Field(
         description="Integration token for Notion API access. Used for direct API calls without OAuth flow.",
         default=None,
     )

api/configs/extra/sentry_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, NonNegativeFloat
 from pydantic_settings import BaseSettings
 
@@ -9,7 +7,7 @@ class SentryConfig(BaseSettings):
     Configuration settings for Sentry error tracking and performance monitoring
     """
 
-    SENTRY_DSN: Optional[str] = Field(
+    SENTRY_DSN: str | None = Field(
         description="Sentry Data Source Name (DSN)."
         " This is the unique identifier of your Sentry project, used to send events to the correct project.",
         default=None,

api/configs/feature/__init__.py

@@ -1,4 +1,5 @@
-from typing import Literal, Optional
+from enum import StrEnum
+from typing import Literal
 
 from pydantic import (
     AliasChoices,
@@ -31,6 +32,12 @@ class SecurityConfig(BaseSettings):
         description="Duration in minutes for which a password reset token remains valid",
         default=5,
     )
+
+    EMAIL_REGISTER_TOKEN_EXPIRY_MINUTES: PositiveInt = Field(
+        description="Duration in minutes for which a email register token remains valid",
+        default=5,
+    )
+
     CHANGE_EMAIL_TOKEN_EXPIRY_MINUTES: PositiveInt = Field(
         description="Duration in minutes for which a change email token remains valid",
         default=5,
@@ -51,7 +58,7 @@ class SecurityConfig(BaseSettings):
         default=False,
     )
 
-    ADMIN_API_KEY: Optional[str] = Field(
+    ADMIN_API_KEY: str | None = Field(
         description="admin api key for authentication",
         default=None,
     )
@@ -91,21 +98,36 @@ class CodeExecutionSandboxConfig(BaseSettings):
         default="dify-sandbox",
     )
 
-    CODE_EXECUTION_CONNECT_TIMEOUT: Optional[float] = Field(
+    CODE_EXECUTION_CONNECT_TIMEOUT: float | None = Field(
         description="Connection timeout in seconds for code execution requests",
         default=10.0,
     )
 
-    CODE_EXECUTION_READ_TIMEOUT: Optional[float] = Field(
+    CODE_EXECUTION_READ_TIMEOUT: float | None = Field(
         description="Read timeout in seconds for code execution requests",
         default=60.0,
     )
 
-    CODE_EXECUTION_WRITE_TIMEOUT: Optional[float] = Field(
+    CODE_EXECUTION_WRITE_TIMEOUT: float | None = Field(
         description="Write timeout in seconds for code execution request",
         default=10.0,
     )
 
+    CODE_EXECUTION_POOL_MAX_CONNECTIONS: PositiveInt = Field(
+        description="Maximum number of concurrent connections for the code execution HTTP client",
+        default=100,
+    )
+
+    CODE_EXECUTION_POOL_MAX_KEEPALIVE_CONNECTIONS: PositiveInt = Field(
+        description="Maximum number of persistent keep-alive connections for the code execution HTTP client",
+        default=20,
+    )
+
+    CODE_EXECUTION_POOL_KEEPALIVE_EXPIRY: PositiveFloat | None = Field(
+        description="Keep-alive expiry in seconds for idle connections (set to None to disable)",
+        default=5.0,
+    )
+
     CODE_MAX_NUMBER: PositiveInt = Field(
         description="Maximum allowed numeric value in code execution",
         default=9223372036854775807,
@@ -146,6 +168,11 @@ class CodeExecutionSandboxConfig(BaseSettings):
         default=1000,
     )
 
+    CODE_EXECUTION_SSL_VERIFY: bool = Field(
+        description="Enable or disable SSL verification for code execution requests",
+        default=True,
+    )
+
 
 class PluginConfig(BaseSettings):
     """
@@ -362,17 +389,17 @@ class HttpConfig(BaseSettings):
         default=3,
     )
 
-    SSRF_PROXY_ALL_URL: Optional[str] = Field(
+    SSRF_PROXY_ALL_URL: str | None = Field(
         description="Proxy URL for HTTP or HTTPS requests to prevent Server-Side Request Forgery (SSRF)",
         default=None,
     )
 
-    SSRF_PROXY_HTTP_URL: Optional[str] = Field(
+    SSRF_PROXY_HTTP_URL: str | None = Field(
         description="Proxy URL for HTTP requests to prevent Server-Side Request Forgery (SSRF)",
         default=None,
     )
 
-    SSRF_PROXY_HTTPS_URL: Optional[str] = Field(
+    SSRF_PROXY_HTTPS_URL: str | None = Field(
         description="Proxy URL for HTTPS requests to prevent Server-Side Request Forgery (SSRF)",
         default=None,
     )
@@ -397,6 +424,21 @@ class HttpConfig(BaseSettings):
         default=5,
     )
 
+    SSRF_POOL_MAX_CONNECTIONS: PositiveInt = Field(
+        description="Maximum number of concurrent connections for the SSRF HTTP client",
+        default=100,
+    )
+
+    SSRF_POOL_MAX_KEEPALIVE_CONNECTIONS: PositiveInt = Field(
+        description="Maximum number of persistent keep-alive connections for the SSRF HTTP client",
+        default=20,
+    )
+
+    SSRF_POOL_KEEPALIVE_EXPIRY: PositiveFloat | None = Field(
+        description="Keep-alive expiry in seconds for idle SSRF connections (set to None to disable)",
+        default=5.0,
+    )
+
     RESPECT_XFORWARD_HEADERS_ENABLED: bool = Field(
         description="Enable handling of X-Forwarded-For, X-Forwarded-Proto, and X-Forwarded-Port headers"
         " when the app is behind a single trusted reverse proxy.",
@@ -414,7 +456,7 @@ class InnerAPIConfig(BaseSettings):
         default=False,
     )
 
-    INNER_API_KEY: Optional[str] = Field(
+    INNER_API_KEY: str | None = Field(
         description="API key for accessing the internal API",
         default=None,
     )
@@ -430,7 +472,7 @@ class LoggingConfig(BaseSettings):
         default="INFO",
     )
 
-    LOG_FILE: Optional[str] = Field(
+    LOG_FILE: str | None = Field(
         description="File path for log output.",
         default=None,
     )
@@ -450,12 +492,12 @@ class LoggingConfig(BaseSettings):
         default="%(asctime)s.%(msecs)03d %(levelname)s [%(threadName)s] [%(filename)s:%(lineno)d] - %(message)s",
     )
 
-    LOG_DATEFORMAT: Optional[str] = Field(
+    LOG_DATEFORMAT: str | None = Field(
         description="Date format string for log timestamps",
         default=None,
     )
 
-    LOG_TZ: Optional[str] = Field(
+    LOG_TZ: str | None = Field(
         description="Timezone for log timestamps (e.g., 'America/New_York')",
         default="UTC",
     )
@@ -499,6 +541,22 @@ class UpdateConfig(BaseSettings):
     )
 
 
+class WorkflowVariableTruncationConfig(BaseSettings):
+    WORKFLOW_VARIABLE_TRUNCATION_MAX_SIZE: PositiveInt = Field(
+        # 100KB
+        1024_000,
+        description="Maximum size for variable to trigger final truncation.",
+    )
+    WORKFLOW_VARIABLE_TRUNCATION_STRING_LENGTH: PositiveInt = Field(
+        100000,
+        description="maximum length for string to trigger tuncation, measure in number of characters",
+    )
+    WORKFLOW_VARIABLE_TRUNCATION_ARRAY_LENGTH: PositiveInt = Field(
+        1000,
+        description="maximum length for array to trigger truncation.",
+    )
+
+
 class WorkflowConfig(BaseSettings):
     """
     Configuration for workflow execution
@@ -519,16 +577,33 @@ class WorkflowConfig(BaseSettings):
         default=5,
     )
 
-    WORKFLOW_PARALLEL_DEPTH_LIMIT: PositiveInt = Field(
-        description="Maximum allowed depth for nested parallel executions",
-        default=3,
-    )
-
     MAX_VARIABLE_SIZE: PositiveInt = Field(
         description="Maximum size in bytes for a single variable in workflows. Default to 200 KB.",
         default=200 * 1024,
     )
 
+    # GraphEngine Worker Pool Configuration
+    GRAPH_ENGINE_MIN_WORKERS: PositiveInt = Field(
+        description="Minimum number of workers per GraphEngine instance",
+        default=1,
+    )
+
+    GRAPH_ENGINE_MAX_WORKERS: PositiveInt = Field(
+        description="Maximum number of workers per GraphEngine instance",
+        default=10,
+    )
+
+    GRAPH_ENGINE_SCALE_UP_THRESHOLD: PositiveInt = Field(
+        description="Queue depth threshold that triggers worker scale up",
+        default=3,
+    )
+
+    GRAPH_ENGINE_SCALE_DOWN_IDLE_TIME: float = Field(
+        description="Seconds of idle time before scaling down workers",
+        default=5.0,
+        ge=0.1,
+    )
+
 
 class WorkflowNodeExecutionConfig(BaseSettings):
     """
@@ -589,22 +664,22 @@ class AuthConfig(BaseSettings):
         default="/console/api/oauth/authorize",
     )
 
-    GITHUB_CLIENT_ID: Optional[str] = Field(
+    GITHUB_CLIENT_ID: str | None = Field(
         description="GitHub OAuth client ID",
         default=None,
     )
 
-    GITHUB_CLIENT_SECRET: Optional[str] = Field(
+    GITHUB_CLIENT_SECRET: str | None = Field(
         description="GitHub OAuth client secret",
         default=None,
     )
 
-    GOOGLE_CLIENT_ID: Optional[str] = Field(
+    GOOGLE_CLIENT_ID: str | None = Field(
         description="Google OAuth client ID",
         default=None,
     )
 
-    GOOGLE_CLIENT_SECRET: Optional[str] = Field(
+    GOOGLE_CLIENT_SECRET: str | None = Field(
         description="Google OAuth client secret",
         default=None,
     )
@@ -639,6 +714,11 @@ class AuthConfig(BaseSettings):
         default=86400,
     )
 
+    EMAIL_REGISTER_LOCKOUT_DURATION: PositiveInt = Field(
+        description="Time (in seconds) a user must wait before retrying email register after exceeding the rate limit.",
+        default=86400,
+    )
+
 
 class ModerationConfig(BaseSettings):
     """
@@ -662,47 +742,71 @@ class ToolConfig(BaseSettings):
     )
 
 
+class TemplateMode(StrEnum):
+    # unsafe mode allows flexible operations in templates, but may cause security vulnerabilities
+    UNSAFE = "unsafe"
+
+    # sandbox mode restricts some unsafe operations like accessing __class__.
+    # however, it is still not 100% safe, for example, cpu exploitation can happen.
+    SANDBOX = "sandbox"
+
+    # templating is disabled
+    DISABLED = "disabled"
+
+
 class MailConfig(BaseSettings):
     """
     Configuration for email services
     """
 
-    MAIL_TYPE: Optional[str] = Field(
+    MAIL_TEMPLATING_MODE: TemplateMode = Field(
+        description="Template mode for email services",
+        default=TemplateMode.SANDBOX,
+    )
+
+    MAIL_TEMPLATING_TIMEOUT: int = Field(
+        description="""
+        Timeout for email templating in seconds. Used to prevent infinite loops in malicious templates. 
+        Only available in sandbox mode.""",
+        default=3,
+    )
+
+    MAIL_TYPE: str | None = Field(
         description="Email service provider type ('smtp' or 'resend' or 'sendGrid), default to None.",
         default=None,
     )
 
-    MAIL_DEFAULT_SEND_FROM: Optional[str] = Field(
+    MAIL_DEFAULT_SEND_FROM: str | None = Field(
         description="Default email address to use as the sender",
         default=None,
     )
 
-    RESEND_API_KEY: Optional[str] = Field(
+    RESEND_API_KEY: str | None = Field(
         description="API key for Resend email service",
         default=None,
     )
 
-    RESEND_API_URL: Optional[str] = Field(
+    RESEND_API_URL: str | None = Field(
         description="API URL for Resend email service",
         default=None,
     )
 
-    SMTP_SERVER: Optional[str] = Field(
+    SMTP_SERVER: str | None = Field(
         description="SMTP server hostname",
         default=None,
     )
 
-    SMTP_PORT: Optional[int] = Field(
+    SMTP_PORT: int | None = Field(
         description="SMTP server port number",
         default=465,
     )
 
-    SMTP_USERNAME: Optional[str] = Field(
+    SMTP_USERNAME: str | None = Field(
         description="Username for SMTP authentication",
         default=None,
     )
 
-    SMTP_PASSWORD: Optional[str] = Field(
+    SMTP_PASSWORD: str | None = Field(
         description="Password for SMTP authentication",
         default=None,
     )
@@ -722,7 +826,7 @@ class MailConfig(BaseSettings):
         default=50,
     )
 
-    SENDGRID_API_KEY: Optional[str] = Field(
+    SENDGRID_API_KEY: str | None = Field(
         description="API key for SendGrid service",
         default=None,
     )
@@ -745,17 +849,17 @@ class RagEtlConfig(BaseSettings):
         default="database",
     )
 
-    UNSTRUCTURED_API_URL: Optional[str] = Field(
+    UNSTRUCTURED_API_URL: str | None = Field(
         description="API URL for Unstructured.io service",
         default=None,
     )
 
-    UNSTRUCTURED_API_KEY: Optional[str] = Field(
+    UNSTRUCTURED_API_KEY: str | None = Field(
         description="API key for Unstructured.io service",
         default="",
     )
 
-    SCARF_NO_ANALYTICS: Optional[str] = Field(
+    SCARF_NO_ANALYTICS: str | None = Field(
         description="This is about whether to disable Scarf analytics in Unstructured library.",
         default="false",
     )
@@ -796,6 +900,11 @@ class DataSetConfig(BaseSettings):
         default=30,
     )
 
+    DSL_EXPORT_ENCRYPT_DATASET_ID: bool = Field(
+        description="Enable or disable dataset ID encryption when exporting DSL files",
+        default=True,
+    )
+
 
 class WorkspaceConfig(BaseSettings):
     """
@@ -1025,5 +1134,6 @@ class FeatureConfig(
     CeleryBeatConfig,
     CeleryScheduleTasksConfig,
     WorkflowLogConfig,
+    WorkflowVariableTruncationConfig,
 ):
     pass

api/configs/feature/hosted_service/__init__.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, NonNegativeInt
 from pydantic_settings import BaseSettings
 
@@ -40,17 +38,17 @@ class HostedOpenAiConfig(BaseSettings):
     Configuration for hosted OpenAI service
     """
 
-    HOSTED_OPENAI_API_KEY: Optional[str] = Field(
+    HOSTED_OPENAI_API_KEY: str | None = Field(
         description="API key for hosted OpenAI service",
         default=None,
     )
 
-    HOSTED_OPENAI_API_BASE: Optional[str] = Field(
+    HOSTED_OPENAI_API_BASE: str | None = Field(
         description="Base URL for hosted OpenAI API",
         default=None,
     )
 
-    HOSTED_OPENAI_API_ORGANIZATION: Optional[str] = Field(
+    HOSTED_OPENAI_API_ORGANIZATION: str | None = Field(
         description="Organization ID for hosted OpenAI service",
         default=None,
     )
@@ -110,12 +108,12 @@ class HostedAzureOpenAiConfig(BaseSettings):
         default=False,
     )
 
-    HOSTED_AZURE_OPENAI_API_KEY: Optional[str] = Field(
+    HOSTED_AZURE_OPENAI_API_KEY: str | None = Field(
         description="API key for hosted Azure OpenAI service",
         default=None,
     )
 
-    HOSTED_AZURE_OPENAI_API_BASE: Optional[str] = Field(
+    HOSTED_AZURE_OPENAI_API_BASE: str | None = Field(
         description="Base URL for hosted Azure OpenAI API",
         default=None,
     )
@@ -131,12 +129,12 @@ class HostedAnthropicConfig(BaseSettings):
     Configuration for hosted Anthropic service
     """
 
-    HOSTED_ANTHROPIC_API_BASE: Optional[str] = Field(
+    HOSTED_ANTHROPIC_API_BASE: str | None = Field(
         description="Base URL for hosted Anthropic API",
         default=None,
     )
 
-    HOSTED_ANTHROPIC_API_KEY: Optional[str] = Field(
+    HOSTED_ANTHROPIC_API_KEY: str | None = Field(
         description="API key for hosted Anthropic service",
         default=None,
     )
@@ -222,11 +220,28 @@ class HostedFetchAppTemplateConfig(BaseSettings):
     )
 
 
+class HostedFetchPipelineTemplateConfig(BaseSettings):
+    """
+    Configuration for fetching pipeline templates
+    """
+
+    HOSTED_FETCH_PIPELINE_TEMPLATES_MODE: str = Field(
+        description="Mode for fetching pipeline templates: remote, db, or builtin default to remote,",
+        default="remote",
+    )
+
+    HOSTED_FETCH_PIPELINE_TEMPLATES_REMOTE_DOMAIN: str = Field(
+        description="Domain for fetching remote pipeline templates",
+        default="https://tmpl.dify.ai",
+    )
+
+
 class HostedServiceConfig(
     # place the configs in alphabet order
     HostedAnthropicConfig,
     HostedAzureOpenAiConfig,
     HostedFetchAppTemplateConfig,
+    HostedFetchPipelineTemplateConfig,
     HostedMinmaxConfig,
     HostedOpenAiConfig,
     HostedSparkConfig,

api/configs/middleware/__init__.py

@@ -1,5 +1,5 @@
 import os
-from typing import Any, Literal, Optional
+from typing import Any, Literal
 from urllib.parse import parse_qsl, quote_plus
 
 from pydantic import Field, NonNegativeFloat, NonNegativeInt, PositiveFloat, PositiveInt, computed_field
@@ -78,18 +78,18 @@ class StorageConfig(BaseSettings):
 
 
 class VectorStoreConfig(BaseSettings):
-    VECTOR_STORE: Optional[str] = Field(
+    VECTOR_STORE: str | None = Field(
         description="Type of vector store to use for efficient similarity search."
         " Set to None if not using a vector store.",
         default=None,
     )
 
-    VECTOR_STORE_WHITELIST_ENABLE: Optional[bool] = Field(
+    VECTOR_STORE_WHITELIST_ENABLE: bool | None = Field(
         description="Enable whitelist for vector store.",
         default=False,
     )
 
-    VECTOR_INDEX_NAME_PREFIX: Optional[str] = Field(
+    VECTOR_INDEX_NAME_PREFIX: str | None = Field(
         description="Prefix used to create collection name in vector database",
         default="Vector_index",
     )
@@ -187,6 +187,11 @@ class DatabaseConfig(BaseSettings):
         default=False,
     )
 
+    SQLALCHEMY_POOL_TIMEOUT: NonNegativeInt = Field(
+        description="Number of seconds to wait for a connection from the pool before raising a timeout error.",
+        default=30,
+    )
+
     RETRIEVAL_SERVICE_EXECUTORS: NonNegativeInt = Field(
         description="Number of processes for the retrieval service, default to CPU cores.",
         default=os.cpu_count() or 1,
@@ -216,6 +221,7 @@ class DatabaseConfig(BaseSettings):
             "connect_args": connect_args,
             "pool_use_lifo": self.SQLALCHEMY_POOL_USE_LIFO,
             "pool_reset_on_return": None,
+            "pool_timeout": self.SQLALCHEMY_POOL_TIMEOUT,
         }
 
 
@@ -225,26 +231,26 @@ class CeleryConfig(DatabaseConfig):
         default="redis",
     )
 
-    CELERY_BROKER_URL: Optional[str] = Field(
+    CELERY_BROKER_URL: str | None = Field(
         description="URL of the message broker for Celery tasks.",
         default=None,
     )
 
-    CELERY_USE_SENTINEL: Optional[bool] = Field(
+    CELERY_USE_SENTINEL: bool | None = Field(
         description="Whether to use Redis Sentinel for high availability.",
         default=False,
     )
 
-    CELERY_SENTINEL_MASTER_NAME: Optional[str] = Field(
+    CELERY_SENTINEL_MASTER_NAME: str | None = Field(
         description="Name of the Redis Sentinel master.",
         default=None,
     )
 
-    CELERY_SENTINEL_PASSWORD: Optional[str] = Field(
+    CELERY_SENTINEL_PASSWORD: str | None = Field(
         description="Password of the Redis Sentinel master.",
         default=None,
     )
-    CELERY_SENTINEL_SOCKET_TIMEOUT: Optional[PositiveFloat] = Field(
+    CELERY_SENTINEL_SOCKET_TIMEOUT: PositiveFloat | None = Field(
         description="Timeout for Redis Sentinel socket operations in seconds.",
         default=0.1,
     )
@@ -268,12 +274,12 @@ class InternalTestConfig(BaseSettings):
     Configuration settings for Internal Test
     """
 
-    AWS_SECRET_ACCESS_KEY: Optional[str] = Field(
+    AWS_SECRET_ACCESS_KEY: str | None = Field(
         description="Internal test AWS secret access key",
         default=None,
     )
 
-    AWS_ACCESS_KEY_ID: Optional[str] = Field(
+    AWS_ACCESS_KEY_ID: str | None = Field(
         description="Internal test AWS access key ID",
         default=None,
     )
@@ -284,15 +290,15 @@ class DatasetQueueMonitorConfig(BaseSettings):
     Configuration settings for Dataset Queue Monitor
     """
 
-    QUEUE_MONITOR_THRESHOLD: Optional[NonNegativeInt] = Field(
+    QUEUE_MONITOR_THRESHOLD: NonNegativeInt | None = Field(
         description="Threshold for dataset queue monitor",
         default=200,
     )
-    QUEUE_MONITOR_ALERT_EMAILS: Optional[str] = Field(
+    QUEUE_MONITOR_ALERT_EMAILS: str | None = Field(
         description="Emails for dataset queue monitor alert, separated by commas",
         default=None,
     )
-    QUEUE_MONITOR_INTERVAL: Optional[NonNegativeFloat] = Field(
+    QUEUE_MONITOR_INTERVAL: NonNegativeFloat | None = Field(
         description="Interval for dataset queue monitor in minutes",
         default=30,
     )
@@ -300,8 +306,7 @@ class DatasetQueueMonitorConfig(BaseSettings):
 
 class MiddlewareConfig(
     # place the configs in alphabet order
-    CeleryConfig,
-    DatabaseConfig,
+    CeleryConfig,  # Note: CeleryConfig already inherits from DatabaseConfig
     KeywordStoreConfig,
     RedisConfig,
     # configs of storage and storage providers

api/configs/middleware/cache/redis_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, NonNegativeInt, PositiveFloat, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -19,12 +17,12 @@ class RedisConfig(BaseSettings):
         default=6379,
     )
 
-    REDIS_USERNAME: Optional[str] = Field(
+    REDIS_USERNAME: str | None = Field(
         description="Username for Redis authentication (if required)",
         default=None,
     )
 
-    REDIS_PASSWORD: Optional[str] = Field(
+    REDIS_PASSWORD: str | None = Field(
         description="Password for Redis authentication (if required)",
         default=None,
     )
@@ -44,47 +42,47 @@ class RedisConfig(BaseSettings):
         default="CERT_NONE",
     )
 
-    REDIS_SSL_CA_CERTS: Optional[str] = Field(
+    REDIS_SSL_CA_CERTS: str | None = Field(
         description="Path to the CA certificate file for SSL verification",
         default=None,
     )
 
-    REDIS_SSL_CERTFILE: Optional[str] = Field(
+    REDIS_SSL_CERTFILE: str | None = Field(
         description="Path to the client certificate file for SSL authentication",
         default=None,
     )
 
-    REDIS_SSL_KEYFILE: Optional[str] = Field(
+    REDIS_SSL_KEYFILE: str | None = Field(
         description="Path to the client private key file for SSL authentication",
         default=None,
     )
 
-    REDIS_USE_SENTINEL: Optional[bool] = Field(
+    REDIS_USE_SENTINEL: bool | None = Field(
         description="Enable Redis Sentinel mode for high availability",
         default=False,
     )
 
-    REDIS_SENTINELS: Optional[str] = Field(
+    REDIS_SENTINELS: str | None = Field(
         description="Comma-separated list of Redis Sentinel nodes (host:port)",
         default=None,
     )
 
-    REDIS_SENTINEL_SERVICE_NAME: Optional[str] = Field(
+    REDIS_SENTINEL_SERVICE_NAME: str | None = Field(
         description="Name of the Redis Sentinel service to monitor",
         default=None,
     )
 
-    REDIS_SENTINEL_USERNAME: Optional[str] = Field(
+    REDIS_SENTINEL_USERNAME: str | None = Field(
         description="Username for Redis Sentinel authentication (if required)",
         default=None,
     )
 
-    REDIS_SENTINEL_PASSWORD: Optional[str] = Field(
+    REDIS_SENTINEL_PASSWORD: str | None = Field(
         description="Password for Redis Sentinel authentication (if required)",
         default=None,
     )
 
-    REDIS_SENTINEL_SOCKET_TIMEOUT: Optional[PositiveFloat] = Field(
+    REDIS_SENTINEL_SOCKET_TIMEOUT: PositiveFloat | None = Field(
         description="Socket timeout in seconds for Redis Sentinel connections",
         default=0.1,
     )
@@ -94,12 +92,12 @@ class RedisConfig(BaseSettings):
         default=False,
     )
 
-    REDIS_CLUSTERS: Optional[str] = Field(
+    REDIS_CLUSTERS: str | None = Field(
         description="Comma-separated list of Redis Clusters nodes (host:port)",
         default=None,
     )
 
-    REDIS_CLUSTERS_PASSWORD: Optional[str] = Field(
+    REDIS_CLUSTERS_PASSWORD: str | None = Field(
         description="Password for Redis Clusters authentication (if required)",
         default=None,
     )

api/configs/middleware/storage/aliyun_oss_storage_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,37 +7,37 @@ class AliyunOSSStorageConfig(BaseSettings):
     Configuration settings for Aliyun Object Storage Service (OSS)
     """
 
-    ALIYUN_OSS_BUCKET_NAME: Optional[str] = Field(
+    ALIYUN_OSS_BUCKET_NAME: str | None = Field(
         description="Name of the Aliyun OSS bucket to store and retrieve objects",
         default=None,
     )
 
-    ALIYUN_OSS_ACCESS_KEY: Optional[str] = Field(
+    ALIYUN_OSS_ACCESS_KEY: str | None = Field(
         description="Access key ID for authenticating with Aliyun OSS",
         default=None,
     )
 
-    ALIYUN_OSS_SECRET_KEY: Optional[str] = Field(
+    ALIYUN_OSS_SECRET_KEY: str | None = Field(
         description="Secret access key for authenticating with Aliyun OSS",
         default=None,
     )
 
-    ALIYUN_OSS_ENDPOINT: Optional[str] = Field(
+    ALIYUN_OSS_ENDPOINT: str | None = Field(
         description="URL of the Aliyun OSS endpoint for your chosen region",
         default=None,
     )
 
-    ALIYUN_OSS_REGION: Optional[str] = Field(
+    ALIYUN_OSS_REGION: str | None = Field(
         description="Aliyun OSS region where your bucket is located (e.g., 'oss-cn-hangzhou')",
         default=None,
     )
 
-    ALIYUN_OSS_AUTH_VERSION: Optional[str] = Field(
+    ALIYUN_OSS_AUTH_VERSION: str | None = Field(
         description="Version of the authentication protocol to use with Aliyun OSS (e.g., 'v4')",
         default=None,
     )
 
-    ALIYUN_OSS_PATH: Optional[str] = Field(
+    ALIYUN_OSS_PATH: str | None = Field(
         description="Base path within the bucket to store objects (e.g., 'my-app-data/')",
         default=None,
     )

api/configs/middleware/storage/amazon_s3_storage_config.py

@@ -1,4 +1,4 @@
-from typing import Literal, Optional
+from typing import Literal
 
 from pydantic import Field
 from pydantic_settings import BaseSettings
@@ -9,27 +9,27 @@ class S3StorageConfig(BaseSettings):
     Configuration settings for S3-compatible object storage
     """
 
-    S3_ENDPOINT: Optional[str] = Field(
+    S3_ENDPOINT: str | None = Field(
         description="URL of the S3-compatible storage endpoint (e.g., 'https://s3.amazonaws.com')",
         default=None,
     )
 
-    S3_REGION: Optional[str] = Field(
+    S3_REGION: str | None = Field(
         description="Region where the S3 bucket is located (e.g., 'us-east-1')",
         default=None,
     )
 
-    S3_BUCKET_NAME: Optional[str] = Field(
+    S3_BUCKET_NAME: str | None = Field(
         description="Name of the S3 bucket to store and retrieve objects",
         default=None,
     )
 
-    S3_ACCESS_KEY: Optional[str] = Field(
+    S3_ACCESS_KEY: str | None = Field(
         description="Access key ID for authenticating with the S3 service",
         default=None,
     )
 
-    S3_SECRET_KEY: Optional[str] = Field(
+    S3_SECRET_KEY: str | None = Field(
         description="Secret access key for authenticating with the S3 service",
         default=None,
     )

api/configs/middleware/storage/azure_blob_storage_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,22 +7,22 @@ class AzureBlobStorageConfig(BaseSettings):
     Configuration settings for Azure Blob Storage
     """
 
-    AZURE_BLOB_ACCOUNT_NAME: Optional[str] = Field(
+    AZURE_BLOB_ACCOUNT_NAME: str | None = Field(
         description="Name of the Azure Storage account (e.g., 'mystorageaccount')",
         default=None,
     )
 
-    AZURE_BLOB_ACCOUNT_KEY: Optional[str] = Field(
+    AZURE_BLOB_ACCOUNT_KEY: str | None = Field(
         description="Access key for authenticating with the Azure Storage account",
         default=None,
     )
 
-    AZURE_BLOB_CONTAINER_NAME: Optional[str] = Field(
+    AZURE_BLOB_CONTAINER_NAME: str | None = Field(
         description="Name of the Azure Blob container to store and retrieve objects",
         default=None,
     )
 
-    AZURE_BLOB_ACCOUNT_URL: Optional[str] = Field(
+    AZURE_BLOB_ACCOUNT_URL: str | None = Field(
         description="URL of the Azure Blob storage endpoint (e.g., 'https://mystorageaccount.blob.core.windows.net')",
         default=None,
     )

api/configs/middleware/storage/baidu_obs_storage_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,22 +7,22 @@ class BaiduOBSStorageConfig(BaseSettings):
     Configuration settings for Baidu Object Storage Service (OBS)
     """
 
-    BAIDU_OBS_BUCKET_NAME: Optional[str] = Field(
+    BAIDU_OBS_BUCKET_NAME: str | None = Field(
         description="Name of the Baidu OBS bucket to store and retrieve objects (e.g., 'my-obs-bucket')",
         default=None,
     )
 
-    BAIDU_OBS_ACCESS_KEY: Optional[str] = Field(
+    BAIDU_OBS_ACCESS_KEY: str | None = Field(
         description="Access Key ID for authenticating with Baidu OBS",
         default=None,
     )
 
-    BAIDU_OBS_SECRET_KEY: Optional[str] = Field(
+    BAIDU_OBS_SECRET_KEY: str | None = Field(
         description="Secret Access Key for authenticating with Baidu OBS",
         default=None,
     )
 
-    BAIDU_OBS_ENDPOINT: Optional[str] = Field(
+    BAIDU_OBS_ENDPOINT: str | None = Field(
         description="URL of the Baidu OSS endpoint for your chosen region (e.g., 'https://.bj.bcebos.com')",
         default=None,
     )

api/configs/middleware/storage/clickzetta_volume_storage_config.py

@@ -1,7 +1,5 @@
 """ClickZetta Volume Storage Configuration"""
 
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,17 +7,17 @@ from pydantic_settings import BaseSettings
 class ClickZettaVolumeStorageConfig(BaseSettings):
     """Configuration for ClickZetta Volume storage."""
 
-    CLICKZETTA_VOLUME_USERNAME: Optional[str] = Field(
+    CLICKZETTA_VOLUME_USERNAME: str | None = Field(
         description="Username for ClickZetta Volume authentication",
         default=None,
     )
 
-    CLICKZETTA_VOLUME_PASSWORD: Optional[str] = Field(
+    CLICKZETTA_VOLUME_PASSWORD: str | None = Field(
         description="Password for ClickZetta Volume authentication",
         default=None,
     )
 
-    CLICKZETTA_VOLUME_INSTANCE: Optional[str] = Field(
+    CLICKZETTA_VOLUME_INSTANCE: str | None = Field(
         description="ClickZetta instance identifier",
         default=None,
     )
@@ -49,7 +47,7 @@ class ClickZettaVolumeStorageConfig(BaseSettings):
         default="user",
     )
 
-    CLICKZETTA_VOLUME_NAME: Optional[str] = Field(
+    CLICKZETTA_VOLUME_NAME: str | None = Field(
         description="ClickZetta volume name for external volumes",
         default=None,
     )

api/configs/middleware/storage/google_cloud_storage_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,12 +7,12 @@ class GoogleCloudStorageConfig(BaseSettings):
     Configuration settings for Google Cloud Storage
     """
 
-    GOOGLE_STORAGE_BUCKET_NAME: Optional[str] = Field(
+    GOOGLE_STORAGE_BUCKET_NAME: str | None = Field(
         description="Name of the Google Cloud Storage bucket to store and retrieve objects (e.g., 'my-gcs-bucket')",
         default=None,
     )
 
-    GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64: Optional[str] = Field(
+    GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64: str | None = Field(
         description="Base64-encoded JSON key file for Google Cloud service account authentication",
         default=None,
     )

api/configs/middleware/storage/huawei_obs_storage_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,22 +7,22 @@ class HuaweiCloudOBSStorageConfig(BaseSettings):
     Configuration settings for Huawei Cloud Object Storage Service (OBS)
     """
 
-    HUAWEI_OBS_BUCKET_NAME: Optional[str] = Field(
+    HUAWEI_OBS_BUCKET_NAME: str | None = Field(
         description="Name of the Huawei Cloud OBS bucket to store and retrieve objects (e.g., 'my-obs-bucket')",
         default=None,
     )
 
-    HUAWEI_OBS_ACCESS_KEY: Optional[str] = Field(
+    HUAWEI_OBS_ACCESS_KEY: str | None = Field(
         description="Access Key ID for authenticating with Huawei Cloud OBS",
         default=None,
     )
 
-    HUAWEI_OBS_SECRET_KEY: Optional[str] = Field(
+    HUAWEI_OBS_SECRET_KEY: str | None = Field(
         description="Secret Access Key for authenticating with Huawei Cloud OBS",
         default=None,
     )
 
-    HUAWEI_OBS_SERVER: Optional[str] = Field(
+    HUAWEI_OBS_SERVER: str | None = Field(
         description="Endpoint URL for Huawei Cloud OBS (e.g., 'https://obs.cn-north-4.myhuaweicloud.com')",
         default=None,
     )

api/configs/middleware/storage/oci_storage_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,27 +7,27 @@ class OCIStorageConfig(BaseSettings):
     Configuration settings for Oracle Cloud Infrastructure (OCI) Object Storage
     """
 
-    OCI_ENDPOINT: Optional[str] = Field(
+    OCI_ENDPOINT: str | None = Field(
         description="URL of the OCI Object Storage endpoint (e.g., 'https://objectstorage.us-phoenix-1.oraclecloud.com')",
         default=None,
     )
 
-    OCI_REGION: Optional[str] = Field(
+    OCI_REGION: str | None = Field(
         description="OCI region where the bucket is located (e.g., 'us-phoenix-1')",
         default=None,
     )
 
-    OCI_BUCKET_NAME: Optional[str] = Field(
+    OCI_BUCKET_NAME: str | None = Field(
         description="Name of the OCI Object Storage bucket to store and retrieve objects (e.g., 'my-oci-bucket')",
         default=None,
     )
 
-    OCI_ACCESS_KEY: Optional[str] = Field(
+    OCI_ACCESS_KEY: str | None = Field(
         description="Access key (also known as API key) for authenticating with OCI Object Storage",
         default=None,
     )
 
-    OCI_SECRET_KEY: Optional[str] = Field(
+    OCI_SECRET_KEY: str | None = Field(
         description="Secret key associated with the access key for authenticating with OCI Object Storage",
         default=None,
     )

api/configs/middleware/storage/supabase_storage_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,17 +7,17 @@ class SupabaseStorageConfig(BaseSettings):
     Configuration settings for Supabase Object Storage Service
     """
 
-    SUPABASE_BUCKET_NAME: Optional[str] = Field(
+    SUPABASE_BUCKET_NAME: str | None = Field(
         description="Name of the Supabase bucket to store and retrieve objects (e.g., 'dify-bucket')",
         default=None,
     )
 
-    SUPABASE_API_KEY: Optional[str] = Field(
+    SUPABASE_API_KEY: str | None = Field(
         description="API KEY for authenticating with Supabase",
         default=None,
     )
 
-    SUPABASE_URL: Optional[str] = Field(
+    SUPABASE_URL: str | None = Field(
         description="URL of the Supabase",
         default=None,
     )

api/configs/middleware/storage/tencent_cos_storage_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,27 +7,27 @@ class TencentCloudCOSStorageConfig(BaseSettings):
     Configuration settings for Tencent Cloud Object Storage (COS)
     """
 
-    TENCENT_COS_BUCKET_NAME: Optional[str] = Field(
+    TENCENT_COS_BUCKET_NAME: str | None = Field(
         description="Name of the Tencent Cloud COS bucket to store and retrieve objects",
         default=None,
     )
 
-    TENCENT_COS_REGION: Optional[str] = Field(
+    TENCENT_COS_REGION: str | None = Field(
         description="Tencent Cloud region where the COS bucket is located (e.g., 'ap-guangzhou')",
         default=None,
     )
 
-    TENCENT_COS_SECRET_ID: Optional[str] = Field(
+    TENCENT_COS_SECRET_ID: str | None = Field(
         description="SecretId for authenticating with Tencent Cloud COS (part of API credentials)",
         default=None,
     )
 
-    TENCENT_COS_SECRET_KEY: Optional[str] = Field(
+    TENCENT_COS_SECRET_KEY: str | None = Field(
         description="SecretKey for authenticating with Tencent Cloud COS (part of API credentials)",
         default=None,
     )
 
-    TENCENT_COS_SCHEME: Optional[str] = Field(
+    TENCENT_COS_SCHEME: str | None = Field(
         description="Protocol scheme for COS requests: 'https' (recommended) or 'http'",
         default=None,
     )

api/configs/middleware/storage/volcengine_tos_storage_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,27 +7,27 @@ class VolcengineTOSStorageConfig(BaseSettings):
     Configuration settings for Volcengine Tinder Object Storage (TOS)
     """
 
-    VOLCENGINE_TOS_BUCKET_NAME: Optional[str] = Field(
+    VOLCENGINE_TOS_BUCKET_NAME: str | None = Field(
         description="Name of the Volcengine TOS bucket to store and retrieve objects (e.g., 'my-tos-bucket')",
         default=None,
     )
 
-    VOLCENGINE_TOS_ACCESS_KEY: Optional[str] = Field(
+    VOLCENGINE_TOS_ACCESS_KEY: str | None = Field(
         description="Access Key ID for authenticating with Volcengine TOS",
         default=None,
     )
 
-    VOLCENGINE_TOS_SECRET_KEY: Optional[str] = Field(
+    VOLCENGINE_TOS_SECRET_KEY: str | None = Field(
         description="Secret Access Key for authenticating with Volcengine TOS",
         default=None,
     )
 
-    VOLCENGINE_TOS_ENDPOINT: Optional[str] = Field(
+    VOLCENGINE_TOS_ENDPOINT: str | None = Field(
         description="URL of the Volcengine TOS endpoint (e.g., 'https://tos-cn-beijing.volces.com')",
         default=None,
     )
 
-    VOLCENGINE_TOS_REGION: Optional[str] = Field(
+    VOLCENGINE_TOS_REGION: str | None = Field(
         description="Volcengine region where the TOS bucket is located (e.g., 'cn-beijing')",
         default=None,
     )

api/configs/middleware/vdb/analyticdb_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -11,37 +9,37 @@ class AnalyticdbConfig(BaseSettings):
     https://www.alibabacloud.com/help/en/analyticdb-for-postgresql/getting-started/create-an-instance-instances-with-vector-engine-optimization-enabled
     """
 
-    ANALYTICDB_KEY_ID: Optional[str] = Field(
+    ANALYTICDB_KEY_ID: str | None = Field(
         default=None, description="The Access Key ID provided by Alibaba Cloud for API authentication."
     )
-    ANALYTICDB_KEY_SECRET: Optional[str] = Field(
+    ANALYTICDB_KEY_SECRET: str | None = Field(
         default=None, description="The Secret Access Key corresponding to the Access Key ID for secure API access."
     )
-    ANALYTICDB_REGION_ID: Optional[str] = Field(
+    ANALYTICDB_REGION_ID: str | None = Field(
         default=None,
         description="The region where the AnalyticDB instance is deployed (e.g., 'cn-hangzhou', 'ap-southeast-1').",
     )
-    ANALYTICDB_INSTANCE_ID: Optional[str] = Field(
+    ANALYTICDB_INSTANCE_ID: str | None = Field(
         default=None,
         description="The unique identifier of the AnalyticDB instance you want to connect to.",
     )
-    ANALYTICDB_ACCOUNT: Optional[str] = Field(
+    ANALYTICDB_ACCOUNT: str | None = Field(
         default=None,
         description="The account name used to log in to the AnalyticDB instance"
         " (usually the initial account created with the instance).",
     )
-    ANALYTICDB_PASSWORD: Optional[str] = Field(
+    ANALYTICDB_PASSWORD: str | None = Field(
         default=None, description="The password associated with the AnalyticDB account for database authentication."
     )
-    ANALYTICDB_NAMESPACE: Optional[str] = Field(
+    ANALYTICDB_NAMESPACE: str | None = Field(
         default=None, description="The namespace within AnalyticDB for schema isolation (if using namespace feature)."
     )
-    ANALYTICDB_NAMESPACE_PASSWORD: Optional[str] = Field(
+    ANALYTICDB_NAMESPACE_PASSWORD: str | None = Field(
         default=None,
         description="The password for accessing the specified namespace within the AnalyticDB instance"
         " (if namespace feature is enabled).",
     )
-    ANALYTICDB_HOST: Optional[str] = Field(
+    ANALYTICDB_HOST: str | None = Field(
         default=None, description="The host of the AnalyticDB instance you want to connect to."
     )
     ANALYTICDB_PORT: PositiveInt = Field(

api/configs/middleware/vdb/baidu_vector_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, NonNegativeInt, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,7 +7,7 @@ class BaiduVectorDBConfig(BaseSettings):
     Configuration settings for Baidu Vector Database
     """
 
-    BAIDU_VECTOR_DB_ENDPOINT: Optional[str] = Field(
+    BAIDU_VECTOR_DB_ENDPOINT: str | None = Field(
         description="URL of the Baidu Vector Database service (e.g., 'http://vdb.bj.baidubce.com')",
         default=None,
     )
@@ -19,17 +17,17 @@ class BaiduVectorDBConfig(BaseSettings):
         default=30000,
     )
 
-    BAIDU_VECTOR_DB_ACCOUNT: Optional[str] = Field(
+    BAIDU_VECTOR_DB_ACCOUNT: str | None = Field(
         description="Account for authenticating with the Baidu Vector Database",
         default=None,
     )
 
-    BAIDU_VECTOR_DB_API_KEY: Optional[str] = Field(
+    BAIDU_VECTOR_DB_API_KEY: str | None = Field(
         description="API key for authenticating with the Baidu Vector Database service",
         default=None,
     )
 
-    BAIDU_VECTOR_DB_DATABASE: Optional[str] = Field(
+    BAIDU_VECTOR_DB_DATABASE: str | None = Field(
         description="Name of the specific Baidu Vector Database to connect to",
         default=None,
     )
@@ -43,3 +41,13 @@ class BaiduVectorDBConfig(BaseSettings):
         description="Number of replicas for the Baidu Vector Database (default is 3)",
         default=3,
     )
+
+    BAIDU_VECTOR_DB_INVERTED_INDEX_ANALYZER: str = Field(
+        description="Analyzer type for inverted index in Baidu Vector Database (default is DEFAULT_ANALYZER)",
+        default="DEFAULT_ANALYZER",
+    )
+
+    BAIDU_VECTOR_DB_INVERTED_INDEX_PARSER_MODE: str = Field(
+        description="Parser mode for inverted index in Baidu Vector Database (default is COARSE_MODE)",
+        default="COARSE_MODE",
+    )

api/configs/middleware/vdb/chroma_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,7 +7,7 @@ class ChromaConfig(BaseSettings):
     Configuration settings for Chroma vector database
     """
 
-    CHROMA_HOST: Optional[str] = Field(
+    CHROMA_HOST: str | None = Field(
         description="Hostname or IP address of the Chroma server (e.g., 'localhost' or '192.168.1.100')",
         default=None,
     )
@@ -19,22 +17,22 @@ class ChromaConfig(BaseSettings):
         default=8000,
     )
 
-    CHROMA_TENANT: Optional[str] = Field(
+    CHROMA_TENANT: str | None = Field(
         description="Tenant identifier for multi-tenancy support in Chroma",
         default=None,
     )
 
-    CHROMA_DATABASE: Optional[str] = Field(
+    CHROMA_DATABASE: str | None = Field(
         description="Name of the Chroma database to connect to",
         default=None,
     )
 
-    CHROMA_AUTH_PROVIDER: Optional[str] = Field(
+    CHROMA_AUTH_PROVIDER: str | None = Field(
         description="Authentication provider for Chroma (e.g., 'basic', 'token', or a custom provider)",
         default=None,
     )
 
-    CHROMA_AUTH_CREDENTIALS: Optional[str] = Field(
+    CHROMA_AUTH_CREDENTIALS: str | None = Field(
         description="Authentication credentials for Chroma (format depends on the auth provider)",
         default=None,
     )

api/configs/middleware/vdb/clickzetta_config.py

@@ -1,69 +1,68 @@
-from typing import Optional
-
-from pydantic import BaseModel, Field
+from pydantic import Field
+from pydantic_settings import BaseSettings
 
 
-class ClickzettaConfig(BaseModel):
+class ClickzettaConfig(BaseSettings):
     """
     Clickzetta Lakehouse vector database configuration
     """
 
-    CLICKZETTA_USERNAME: Optional[str] = Field(
+    CLICKZETTA_USERNAME: str | None = Field(
         description="Username for authenticating with Clickzetta Lakehouse",
         default=None,
     )
 
-    CLICKZETTA_PASSWORD: Optional[str] = Field(
+    CLICKZETTA_PASSWORD: str | None = Field(
         description="Password for authenticating with Clickzetta Lakehouse",
         default=None,
     )
 
-    CLICKZETTA_INSTANCE: Optional[str] = Field(
+    CLICKZETTA_INSTANCE: str | None = Field(
         description="Clickzetta Lakehouse instance ID",
         default=None,
     )
 
-    CLICKZETTA_SERVICE: Optional[str] = Field(
+    CLICKZETTA_SERVICE: str | None = Field(
         description="Clickzetta API service endpoint (e.g., 'api.clickzetta.com')",
         default="api.clickzetta.com",
     )
 
-    CLICKZETTA_WORKSPACE: Optional[str] = Field(
+    CLICKZETTA_WORKSPACE: str | None = Field(
         description="Clickzetta workspace name",
         default="default",
     )
 
-    CLICKZETTA_VCLUSTER: Optional[str] = Field(
+    CLICKZETTA_VCLUSTER: str | None = Field(
         description="Clickzetta virtual cluster name",
         default="default_ap",
     )
 
-    CLICKZETTA_SCHEMA: Optional[str] = Field(
+    CLICKZETTA_SCHEMA: str | None = Field(
         description="Database schema name in Clickzetta",
         default="public",
     )
 
-    CLICKZETTA_BATCH_SIZE: Optional[int] = Field(
+    CLICKZETTA_BATCH_SIZE: int | None = Field(
         description="Batch size for bulk insert operations",
         default=100,
     )
 
-    CLICKZETTA_ENABLE_INVERTED_INDEX: Optional[bool] = Field(
+    CLICKZETTA_ENABLE_INVERTED_INDEX: bool | None = Field(
         description="Enable inverted index for full-text search capabilities",
         default=True,
     )
 
-    CLICKZETTA_ANALYZER_TYPE: Optional[str] = Field(
+    CLICKZETTA_ANALYZER_TYPE: str | None = Field(
         description="Analyzer type for full-text search: keyword, english, chinese, unicode",
         default="chinese",
     )
 
-    CLICKZETTA_ANALYZER_MODE: Optional[str] = Field(
+    CLICKZETTA_ANALYZER_MODE: str | None = Field(
         description="Analyzer mode for tokenization: max_word (fine-grained) or smart (intelligent)",
         default="smart",
     )
 
-    CLICKZETTA_VECTOR_DISTANCE_FUNCTION: Optional[str] = Field(
+    CLICKZETTA_VECTOR_DISTANCE_FUNCTION: str | None = Field(
         description="Distance function for vector similarity: l2_distance or cosine_distance",
         default="cosine_distance",
     )

api/configs/middleware/vdb/couchbase_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,27 +7,27 @@ class CouchbaseConfig(BaseSettings):
     Couchbase configs
     """
 
-    COUCHBASE_CONNECTION_STRING: Optional[str] = Field(
+    COUCHBASE_CONNECTION_STRING: str | None = Field(
         description="COUCHBASE connection string",
         default=None,
     )
 
-    COUCHBASE_USER: Optional[str] = Field(
+    COUCHBASE_USER: str | None = Field(
         description="COUCHBASE user",
         default=None,
     )
 
-    COUCHBASE_PASSWORD: Optional[str] = Field(
+    COUCHBASE_PASSWORD: str | None = Field(
         description="COUCHBASE password",
         default=None,
     )
 
-    COUCHBASE_BUCKET_NAME: Optional[str] = Field(
+    COUCHBASE_BUCKET_NAME: str | None = Field(
         description="COUCHBASE bucket name",
         default=None,
     )
 
-    COUCHBASE_SCOPE_NAME: Optional[str] = Field(
+    COUCHBASE_SCOPE_NAME: str | None = Field(
         description="COUCHBASE scope name",
         default=None,
     )

api/configs/middleware/vdb/elasticsearch_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt, model_validator
 from pydantic_settings import BaseSettings
 
@@ -10,7 +8,7 @@ class ElasticsearchConfig(BaseSettings):
     Can load from environment variables or .env files.
     """
 
-    ELASTICSEARCH_HOST: Optional[str] = Field(
+    ELASTICSEARCH_HOST: str | None = Field(
         description="Hostname or IP address of the Elasticsearch server (e.g., 'localhost' or '192.168.1.100')",
         default="127.0.0.1",
     )
@@ -20,30 +18,28 @@ class ElasticsearchConfig(BaseSettings):
         default=9200,
     )
 
-    ELASTICSEARCH_USERNAME: Optional[str] = Field(
+    ELASTICSEARCH_USERNAME: str | None = Field(
         description="Username for authenticating with Elasticsearch (default is 'elastic')",
         default="elastic",
     )
 
-    ELASTICSEARCH_PASSWORD: Optional[str] = Field(
+    ELASTICSEARCH_PASSWORD: str | None = Field(
         description="Password for authenticating with Elasticsearch (default is 'elastic')",
         default="elastic",
     )
 
     # Elastic Cloud (optional)
-    ELASTICSEARCH_USE_CLOUD: Optional[bool] = Field(
+    ELASTICSEARCH_USE_CLOUD: bool | None = Field(
         description="Set to True to use Elastic Cloud instead of self-hosted Elasticsearch", default=False
     )
-    ELASTICSEARCH_CLOUD_URL: Optional[str] = Field(
+    ELASTICSEARCH_CLOUD_URL: str | None = Field(
         description="Full URL for Elastic Cloud deployment (e.g., 'https://example.es.region.aws.found.io:443')",
         default=None,
     )
-    ELASTICSEARCH_API_KEY: Optional[str] = Field(
-        description="API key for authenticating with Elastic Cloud", default=None
-    )
+    ELASTICSEARCH_API_KEY: str | None = Field(description="API key for authenticating with Elastic Cloud", default=None)
 
     # Common options
-    ELASTICSEARCH_CA_CERTS: Optional[str] = Field(
+    ELASTICSEARCH_CA_CERTS: str | None = Field(
         description="Path to CA certificate file for SSL verification", default=None
     )
     ELASTICSEARCH_VERIFY_CERTS: bool = Field(

api/configs/middleware/vdb/huawei_cloud_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,17 +7,17 @@ class HuaweiCloudConfig(BaseSettings):
     Configuration settings for Huawei cloud search service
     """
 
-    HUAWEI_CLOUD_HOSTS: Optional[str] = Field(
+    HUAWEI_CLOUD_HOSTS: str | None = Field(
         description="Hostname or IP address of the Huawei cloud search service instance",
         default=None,
     )
 
-    HUAWEI_CLOUD_USER: Optional[str] = Field(
+    HUAWEI_CLOUD_USER: str | None = Field(
         description="Username for authenticating with Huawei cloud search service",
         default=None,
     )
 
-    HUAWEI_CLOUD_PASSWORD: Optional[str] = Field(
+    HUAWEI_CLOUD_PASSWORD: str | None = Field(
         description="Password for authenticating with Huawei cloud search service",
         default=None,
     )

api/configs/middleware/vdb/lindorm_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,27 +7,27 @@ class LindormConfig(BaseSettings):
     Lindorm configs
     """
 
-    LINDORM_URL: Optional[str] = Field(
+    LINDORM_URL: str | None = Field(
         description="Lindorm url",
         default=None,
     )
-    LINDORM_USERNAME: Optional[str] = Field(
+    LINDORM_USERNAME: str | None = Field(
         description="Lindorm user",
         default=None,
     )
-    LINDORM_PASSWORD: Optional[str] = Field(
+    LINDORM_PASSWORD: str | None = Field(
         description="Lindorm password",
         default=None,
     )
-    DEFAULT_INDEX_TYPE: Optional[str] = Field(
+    LINDORM_INDEX_TYPE: str | None = Field(
         description="Lindorm Vector Index Type, hnsw or flat is available in dify",
         default="hnsw",
     )
-    DEFAULT_DISTANCE_TYPE: Optional[str] = Field(
+    LINDORM_DISTANCE_TYPE: str | None = Field(
         description="Vector Distance Type, support l2, cosinesimil, innerproduct", default="l2"
     )
-    USING_UGC_INDEX: Optional[bool] = Field(
-        description="Using UGC index will store the same type of Index in a single index but can retrieve separately.",
-        default=False,
+    LINDORM_USING_UGC: bool | None = Field(
+        description="Using UGC index will store indexes with the same IndexType/Dimension in a single big index.",
+        default=True,
     )
-    LINDORM_QUERY_TIMEOUT: Optional[float] = Field(description="The lindorm search request timeout (s)", default=2.0)
+    LINDORM_QUERY_TIMEOUT: float | None = Field(description="The lindorm search request timeout (s)", default=2.0)

api/configs/middleware/vdb/matrixone_config.py

@@ -1,7 +1,8 @@
-from pydantic import BaseModel, Field
+from pydantic import Field
+from pydantic_settings import BaseSettings
 
 
-class MatrixoneConfig(BaseModel):
+class MatrixoneConfig(BaseSettings):
     """Matrixone vector database configuration."""
 
     MATRIXONE_HOST: str = Field(default="localhost", description="Host address of the Matrixone server")

api/configs/middleware/vdb/milvus_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,22 +7,22 @@ class MilvusConfig(BaseSettings):
     Configuration settings for Milvus vector database
     """
 
-    MILVUS_URI: Optional[str] = Field(
+    MILVUS_URI: str | None = Field(
         description="URI for connecting to the Milvus server (e.g., 'http://localhost:19530' or 'https://milvus-instance.example.com:19530')",
         default="http://127.0.0.1:19530",
     )
 
-    MILVUS_TOKEN: Optional[str] = Field(
+    MILVUS_TOKEN: str | None = Field(
         description="Authentication token for Milvus, if token-based authentication is enabled",
         default=None,
     )
 
-    MILVUS_USER: Optional[str] = Field(
+    MILVUS_USER: str | None = Field(
         description="Username for authenticating with Milvus, if username/password authentication is enabled",
         default=None,
     )
 
-    MILVUS_PASSWORD: Optional[str] = Field(
+    MILVUS_PASSWORD: str | None = Field(
         description="Password for authenticating with Milvus, if username/password authentication is enabled",
         default=None,
     )
@@ -40,7 +38,7 @@ class MilvusConfig(BaseSettings):
         default=True,
     )
 
-    MILVUS_ANALYZER_PARAMS: Optional[str] = Field(
+    MILVUS_ANALYZER_PARAMS: str | None = Field(
         description='Milvus text analyzer parameters, e.g., {"type": "chinese"} for Chinese segmentation support.',
         default=None,
     )

api/configs/middleware/vdb/oceanbase_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,27 +7,27 @@ class OceanBaseVectorConfig(BaseSettings):
     Configuration settings for OceanBase Vector database
     """
 
-    OCEANBASE_VECTOR_HOST: Optional[str] = Field(
+    OCEANBASE_VECTOR_HOST: str | None = Field(
         description="Hostname or IP address of the OceanBase Vector server (e.g. 'localhost')",
         default=None,
     )
 
-    OCEANBASE_VECTOR_PORT: Optional[PositiveInt] = Field(
+    OCEANBASE_VECTOR_PORT: PositiveInt | None = Field(
         description="Port number on which the OceanBase Vector server is listening (default is 2881)",
         default=2881,
     )
 
-    OCEANBASE_VECTOR_USER: Optional[str] = Field(
+    OCEANBASE_VECTOR_USER: str | None = Field(
         description="Username for authenticating with the OceanBase Vector database",
         default=None,
     )
 
-    OCEANBASE_VECTOR_PASSWORD: Optional[str] = Field(
+    OCEANBASE_VECTOR_PASSWORD: str | None = Field(
         description="Password for authenticating with the OceanBase Vector database",
         default=None,
     )
 
-    OCEANBASE_VECTOR_DATABASE: Optional[str] = Field(
+    OCEANBASE_VECTOR_DATABASE: str | None = Field(
         description="Name of the OceanBase Vector database to connect to",
         default=None,
     )
@@ -39,3 +37,15 @@ class OceanBaseVectorConfig(BaseSettings):
         "with older versions",
         default=False,
     )
+
+    OCEANBASE_FULLTEXT_PARSER: str | None = Field(
+        description=(
+            "Fulltext parser to use for text indexing. "
+            "Built-in options: 'ngram' (N-gram tokenizer for English/numbers), "
+            "'beng' (Basic English tokenizer), 'space' (Space-based tokenizer), "
+            "'ngram2' (Improved N-gram tokenizer), 'ik' (Chinese tokenizer). "
+            "External plugins (require installation): 'japanese_ftparser' (Japanese tokenizer), "
+            "'thai_ftparser' (Thai tokenizer). Default is 'ik'"
+        ),
+        default="ik",
+    )

api/configs/middleware/vdb/opengauss_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,7 +7,7 @@ class OpenGaussConfig(BaseSettings):
     Configuration settings for OpenGauss
     """
 
-    OPENGAUSS_HOST: Optional[str] = Field(
+    OPENGAUSS_HOST: str | None = Field(
         description="Hostname or IP address of the OpenGauss server(e.g., 'localhost')",
         default=None,
     )
@@ -19,17 +17,17 @@ class OpenGaussConfig(BaseSettings):
         default=6600,
     )
 
-    OPENGAUSS_USER: Optional[str] = Field(
+    OPENGAUSS_USER: str | None = Field(
         description="Username for authenticating with the OpenGauss database",
         default=None,
     )
 
-    OPENGAUSS_PASSWORD: Optional[str] = Field(
+    OPENGAUSS_PASSWORD: str | None = Field(
         description="Password for authenticating with the OpenGauss database",
         default=None,
     )
 
-    OPENGAUSS_DATABASE: Optional[str] = Field(
+    OPENGAUSS_DATABASE: str | None = Field(
         description="Name of the OpenGauss database to connect to",
         default=None,
     )

api/configs/middleware/vdb/opensearch_config.py

@@ -1,5 +1,5 @@
-import enum
-from typing import Literal, Optional
+from enum import Enum
+from typing import Literal
 
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
@@ -10,7 +10,7 @@ class OpenSearchConfig(BaseSettings):
     Configuration settings for OpenSearch
     """
 
-    class AuthMethod(enum.StrEnum):
+    class AuthMethod(Enum):
         """
         Authentication method for OpenSearch
         """
@@ -18,7 +18,7 @@ class OpenSearchConfig(BaseSettings):
         BASIC = "basic"
         AWS_MANAGED_IAM = "aws_managed_iam"
 
-    OPENSEARCH_HOST: Optional[str] = Field(
+    OPENSEARCH_HOST: str | None = Field(
         description="Hostname or IP address of the OpenSearch server (e.g., 'localhost' or 'opensearch.example.com')",
         default=None,
     )
@@ -43,21 +43,21 @@ class OpenSearchConfig(BaseSettings):
         default=AuthMethod.BASIC,
     )
 
-    OPENSEARCH_USER: Optional[str] = Field(
+    OPENSEARCH_USER: str | None = Field(
         description="Username for authenticating with OpenSearch",
         default=None,
     )
 
-    OPENSEARCH_PASSWORD: Optional[str] = Field(
+    OPENSEARCH_PASSWORD: str | None = Field(
         description="Password for authenticating with OpenSearch",
         default=None,
     )
 
-    OPENSEARCH_AWS_REGION: Optional[str] = Field(
+    OPENSEARCH_AWS_REGION: str | None = Field(
         description="AWS region for OpenSearch (e.g. 'us-west-2')",
         default=None,
     )
 
-    OPENSEARCH_AWS_SERVICE: Optional[Literal["es", "aoss"]] = Field(
+    OPENSEARCH_AWS_SERVICE: Literal["es", "aoss"] | None = Field(
         description="AWS service for OpenSearch (e.g. 'aoss' for OpenSearch Serverless)", default=None
     )

api/configs/middleware/vdb/oracle_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,33 +7,33 @@ class OracleConfig(BaseSettings):
     Configuration settings for Oracle database
     """
 
-    ORACLE_USER: Optional[str] = Field(
+    ORACLE_USER: str | None = Field(
         description="Username for authenticating with the Oracle database",
         default=None,
     )
 
-    ORACLE_PASSWORD: Optional[str] = Field(
+    ORACLE_PASSWORD: str | None = Field(
         description="Password for authenticating with the Oracle database",
         default=None,
     )
 
-    ORACLE_DSN: Optional[str] = Field(
+    ORACLE_DSN: str | None = Field(
         description="Oracle database connection string. For traditional database, use format 'host:port/service_name'. "
         "For autonomous database, use the service name from tnsnames.ora in the wallet",
         default=None,
     )
 
-    ORACLE_CONFIG_DIR: Optional[str] = Field(
+    ORACLE_CONFIG_DIR: str | None = Field(
         description="Directory containing the tnsnames.ora configuration file. Only used in thin mode connection",
         default=None,
     )
 
-    ORACLE_WALLET_LOCATION: Optional[str] = Field(
+    ORACLE_WALLET_LOCATION: str | None = Field(
         description="Oracle wallet directory path containing the wallet files for secure connection",
         default=None,
     )
 
-    ORACLE_WALLET_PASSWORD: Optional[str] = Field(
+    ORACLE_WALLET_PASSWORD: str | None = Field(
         description="Password to decrypt the Oracle wallet, if it is encrypted",
         default=None,
     )

api/configs/middleware/vdb/pgvector_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,7 +7,7 @@ class PGVectorConfig(BaseSettings):
     Configuration settings for PGVector (PostgreSQL with vector extension)
     """
 
-    PGVECTOR_HOST: Optional[str] = Field(
+    PGVECTOR_HOST: str | None = Field(
         description="Hostname or IP address of the PostgreSQL server with PGVector extension (e.g., 'localhost')",
         default=None,
     )
@@ -19,17 +17,17 @@ class PGVectorConfig(BaseSettings):
         default=5433,
     )
 
-    PGVECTOR_USER: Optional[str] = Field(
+    PGVECTOR_USER: str | None = Field(
         description="Username for authenticating with the PostgreSQL database",
         default=None,
     )
 
-    PGVECTOR_PASSWORD: Optional[str] = Field(
+    PGVECTOR_PASSWORD: str | None = Field(
         description="Password for authenticating with the PostgreSQL database",
         default=None,
     )
 
-    PGVECTOR_DATABASE: Optional[str] = Field(
+    PGVECTOR_DATABASE: str | None = Field(
         description="Name of the PostgreSQL database to connect to",
         default=None,
     )

api/configs/middleware/vdb/pgvectors_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,7 +7,7 @@ class PGVectoRSConfig(BaseSettings):
     Configuration settings for PGVecto.RS (Rust-based vector extension for PostgreSQL)
     """
 
-    PGVECTO_RS_HOST: Optional[str] = Field(
+    PGVECTO_RS_HOST: str | None = Field(
         description="Hostname or IP address of the PostgreSQL server with PGVecto.RS extension (e.g., 'localhost')",
         default=None,
     )
@@ -19,17 +17,17 @@ class PGVectoRSConfig(BaseSettings):
         default=5431,
     )
 
-    PGVECTO_RS_USER: Optional[str] = Field(
+    PGVECTO_RS_USER: str | None = Field(
         description="Username for authenticating with the PostgreSQL database using PGVecto.RS",
         default=None,
     )
 
-    PGVECTO_RS_PASSWORD: Optional[str] = Field(
+    PGVECTO_RS_PASSWORD: str | None = Field(
         description="Password for authenticating with the PostgreSQL database using PGVecto.RS",
         default=None,
     )
 
-    PGVECTO_RS_DATABASE: Optional[str] = Field(
+    PGVECTO_RS_DATABASE: str | None = Field(
         description="Name of the PostgreSQL database with PGVecto.RS extension to connect to",
         default=None,
     )

api/configs/middleware/vdb/qdrant_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, NonNegativeInt, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,12 +7,12 @@ class QdrantConfig(BaseSettings):
     Configuration settings for Qdrant vector database
     """
 
-    QDRANT_URL: Optional[str] = Field(
+    QDRANT_URL: str | None = Field(
         description="URL of the Qdrant server (e.g., 'http://localhost:6333' or 'https://qdrant.example.com')",
         default=None,
     )
 
-    QDRANT_API_KEY: Optional[str] = Field(
+    QDRANT_API_KEY: str | None = Field(
         description="API key for authenticating with the Qdrant server",
         default=None,
     )

api/configs/middleware/vdb/relyt_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,7 +7,7 @@ class RelytConfig(BaseSettings):
     Configuration settings for Relyt database
     """
 
-    RELYT_HOST: Optional[str] = Field(
+    RELYT_HOST: str | None = Field(
         description="Hostname or IP address of the Relyt server (e.g., 'localhost' or 'relyt.example.com')",
         default=None,
     )
@@ -19,17 +17,17 @@ class RelytConfig(BaseSettings):
         default=9200,
     )
 
-    RELYT_USER: Optional[str] = Field(
+    RELYT_USER: str | None = Field(
         description="Username for authenticating with the Relyt database",
         default=None,
     )
 
-    RELYT_PASSWORD: Optional[str] = Field(
+    RELYT_PASSWORD: str | None = Field(
         description="Password for authenticating with the Relyt database",
         default=None,
     )
 
-    RELYT_DATABASE: Optional[str] = Field(
+    RELYT_DATABASE: str | None = Field(
         description="Name of the Relyt database to connect to (default is 'default')",
         default="default",
     )

api/configs/middleware/vdb/tablestore_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,22 +7,22 @@ class TableStoreConfig(BaseSettings):
     Configuration settings for TableStore.
     """
 
-    TABLESTORE_ENDPOINT: Optional[str] = Field(
+    TABLESTORE_ENDPOINT: str | None = Field(
         description="Endpoint address of the TableStore server (e.g. 'https://instance-name.cn-hangzhou.ots.aliyuncs.com')",
         default=None,
     )
 
-    TABLESTORE_INSTANCE_NAME: Optional[str] = Field(
+    TABLESTORE_INSTANCE_NAME: str | None = Field(
         description="Instance name to access TableStore server (eg. 'instance-name')",
         default=None,
     )
 
-    TABLESTORE_ACCESS_KEY_ID: Optional[str] = Field(
+    TABLESTORE_ACCESS_KEY_ID: str | None = Field(
         description="AccessKey id for the instance name",
         default=None,
     )
 
-    TABLESTORE_ACCESS_KEY_SECRET: Optional[str] = Field(
+    TABLESTORE_ACCESS_KEY_SECRET: str | None = Field(
         description="AccessKey secret for the instance name",
         default=None,
     )

api/configs/middleware/vdb/tencent_vector_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, NonNegativeInt, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,12 +7,12 @@ class TencentVectorDBConfig(BaseSettings):
     Configuration settings for Tencent Vector Database
     """
 
-    TENCENT_VECTOR_DB_URL: Optional[str] = Field(
+    TENCENT_VECTOR_DB_URL: str | None = Field(
         description="URL of the Tencent Vector Database service (e.g., 'https://vectordb.tencentcloudapi.com')",
         default=None,
     )
 
-    TENCENT_VECTOR_DB_API_KEY: Optional[str] = Field(
+    TENCENT_VECTOR_DB_API_KEY: str | None = Field(
         description="API key for authenticating with the Tencent Vector Database service",
         default=None,
     )
@@ -24,12 +22,12 @@ class TencentVectorDBConfig(BaseSettings):
         default=30,
     )
 
-    TENCENT_VECTOR_DB_USERNAME: Optional[str] = Field(
+    TENCENT_VECTOR_DB_USERNAME: str | None = Field(
         description="Username for authenticating with the Tencent Vector Database (if required)",
         default=None,
     )
 
-    TENCENT_VECTOR_DB_PASSWORD: Optional[str] = Field(
+    TENCENT_VECTOR_DB_PASSWORD: str | None = Field(
         description="Password for authenticating with the Tencent Vector Database (if required)",
         default=None,
     )
@@ -44,7 +42,7 @@ class TencentVectorDBConfig(BaseSettings):
         default=2,
     )
 
-    TENCENT_VECTOR_DB_DATABASE: Optional[str] = Field(
+    TENCENT_VECTOR_DB_DATABASE: str | None = Field(
         description="Name of the specific Tencent Vector Database to connect to",
         default=None,
     )

api/configs/middleware/vdb/tidb_on_qdrant_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, NonNegativeInt, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,12 +7,12 @@ class TidbOnQdrantConfig(BaseSettings):
     Tidb on Qdrant configs
     """
 
-    TIDB_ON_QDRANT_URL: Optional[str] = Field(
+    TIDB_ON_QDRANT_URL: str | None = Field(
         description="Tidb on Qdrant url",
         default=None,
     )
 
-    TIDB_ON_QDRANT_API_KEY: Optional[str] = Field(
+    TIDB_ON_QDRANT_API_KEY: str | None = Field(
         description="Tidb on Qdrant api key",
         default=None,
     )
@@ -34,37 +32,37 @@ class TidbOnQdrantConfig(BaseSettings):
         default=6334,
     )
 
-    TIDB_PUBLIC_KEY: Optional[str] = Field(
+    TIDB_PUBLIC_KEY: str | None = Field(
         description="Tidb account public key",
         default=None,
     )
 
-    TIDB_PRIVATE_KEY: Optional[str] = Field(
+    TIDB_PRIVATE_KEY: str | None = Field(
         description="Tidb account private key",
         default=None,
     )
 
-    TIDB_API_URL: Optional[str] = Field(
+    TIDB_API_URL: str | None = Field(
         description="Tidb API url",
         default=None,
     )
 
-    TIDB_IAM_API_URL: Optional[str] = Field(
+    TIDB_IAM_API_URL: str | None = Field(
         description="Tidb IAM API url",
         default=None,
     )
 
-    TIDB_REGION: Optional[str] = Field(
+    TIDB_REGION: str | None = Field(
         description="Tidb serverless region",
         default="regions/aws-us-east-1",
     )
 
-    TIDB_PROJECT_ID: Optional[str] = Field(
+    TIDB_PROJECT_ID: str | None = Field(
         description="Tidb project id",
         default=None,
     )
 
-    TIDB_SPEND_LIMIT: Optional[int] = Field(
+    TIDB_SPEND_LIMIT: int | None = Field(
         description="Tidb spend limit",
         default=100,
     )

api/configs/middleware/vdb/tidb_vector_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,27 +7,27 @@ class TiDBVectorConfig(BaseSettings):
     Configuration settings for TiDB Vector database
     """
 
-    TIDB_VECTOR_HOST: Optional[str] = Field(
+    TIDB_VECTOR_HOST: str | None = Field(
         description="Hostname or IP address of the TiDB Vector server (e.g., 'localhost' or 'tidb.example.com')",
         default=None,
     )
 
-    TIDB_VECTOR_PORT: Optional[PositiveInt] = Field(
+    TIDB_VECTOR_PORT: PositiveInt | None = Field(
         description="Port number on which the TiDB Vector server is listening (default is 4000)",
         default=4000,
     )
 
-    TIDB_VECTOR_USER: Optional[str] = Field(
+    TIDB_VECTOR_USER: str | None = Field(
         description="Username for authenticating with the TiDB Vector database",
         default=None,
     )
 
-    TIDB_VECTOR_PASSWORD: Optional[str] = Field(
+    TIDB_VECTOR_PASSWORD: str | None = Field(
         description="Password for authenticating with the TiDB Vector database",
         default=None,
     )
 
-    TIDB_VECTOR_DATABASE: Optional[str] = Field(
+    TIDB_VECTOR_DATABASE: str | None = Field(
         description="Name of the TiDB Vector database to connect to",
         default=None,
     )

api/configs/middleware/vdb/upstash_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,12 +7,12 @@ class UpstashConfig(BaseSettings):
     Configuration settings for Upstash vector database
     """
 
-    UPSTASH_VECTOR_URL: Optional[str] = Field(
+    UPSTASH_VECTOR_URL: str | None = Field(
         description="URL of the upstash server (e.g., 'https://vector.upstash.io')",
         default=None,
     )
 
-    UPSTASH_VECTOR_TOKEN: Optional[str] = Field(
+    UPSTASH_VECTOR_TOKEN: str | None = Field(
         description="Token for authenticating with the upstash server",
         default=None,
     )

api/configs/middleware/vdb/vastbase_vector_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,7 +7,7 @@ class VastbaseVectorConfig(BaseSettings):
     Configuration settings for Vector (Vastbase with vector extension)
     """
 
-    VASTBASE_HOST: Optional[str] = Field(
+    VASTBASE_HOST: str | None = Field(
         description="Hostname or IP address of the Vastbase server with Vector extension (e.g., 'localhost')",
         default=None,
     )
@@ -19,17 +17,17 @@ class VastbaseVectorConfig(BaseSettings):
         default=5432,
     )
 
-    VASTBASE_USER: Optional[str] = Field(
+    VASTBASE_USER: str | None = Field(
         description="Username for authenticating with the Vastbase database",
         default=None,
     )
 
-    VASTBASE_PASSWORD: Optional[str] = Field(
+    VASTBASE_PASSWORD: str | None = Field(
         description="Password for authenticating with the Vastbase database",
         default=None,
     )
 
-    VASTBASE_DATABASE: Optional[str] = Field(
+    VASTBASE_DATABASE: str | None = Field(
         description="Name of the Vastbase database to connect to",
         default=None,
     )

api/configs/middleware/vdb/vikingdb_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -11,14 +9,14 @@ class VikingDBConfig(BaseSettings):
     https://www.volcengine.com/docs/6291/65568
     """
 
-    VIKINGDB_ACCESS_KEY: Optional[str] = Field(
+    VIKINGDB_ACCESS_KEY: str | None = Field(
         description="The Access Key provided by Volcengine VikingDB for API authentication."
         "Refer to the following documentation for details on obtaining credentials:"
         "https://www.volcengine.com/docs/6291/65568",
         default=None,
     )
 
-    VIKINGDB_SECRET_KEY: Optional[str] = Field(
+    VIKINGDB_SECRET_KEY: str | None = Field(
         description="The Secret Key provided by Volcengine VikingDB for API authentication.",
         default=None,
     )

api/configs/middleware/vdb/weaviate_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,12 +7,12 @@ class WeaviateConfig(BaseSettings):
     Configuration settings for Weaviate vector database
     """
 
-    WEAVIATE_ENDPOINT: Optional[str] = Field(
+    WEAVIATE_ENDPOINT: str | None = Field(
         description="URL of the Weaviate server (e.g., 'http://localhost:8080' or 'https://weaviate.example.com')",
         default=None,
     )
 
-    WEAVIATE_API_KEY: Optional[str] = Field(
+    WEAVIATE_API_KEY: str | None = Field(
         description="API key for authenticating with the Weaviate server",
         default=None,
     )

api/configs/packaging/__init__.py

@@ -1,6 +1,6 @@
 from pydantic import Field
 
-from configs.packaging.pyproject import PyProjectConfig, PyProjectTomlConfig
+from configs.packaging.pyproject import PyProjectTomlConfig
 
 
 class PackagingInfo(PyProjectTomlConfig):

api/configs/remote_settings_sources/apollo/__init__.py

@@ -1,5 +1,5 @@
 from collections.abc import Mapping
-from typing import Any, Optional
+from typing import Any
 
 from pydantic import Field
 from pydantic.fields import FieldInfo
@@ -15,22 +15,22 @@ class ApolloSettingsSourceInfo(BaseSettings):
     Packaging build information
     """
 
-    APOLLO_APP_ID: Optional[str] = Field(
+    APOLLO_APP_ID: str | None = Field(
         description="apollo app_id",
         default=None,
     )
 
-    APOLLO_CLUSTER: Optional[str] = Field(
+    APOLLO_CLUSTER: str | None = Field(
         description="apollo cluster",
         default=None,
     )
 
-    APOLLO_CONFIG_URL: Optional[str] = Field(
+    APOLLO_CONFIG_URL: str | None = Field(
         description="apollo config url",
         default=None,
     )
 
-    APOLLO_NAMESPACE: Optional[str] = Field(
+    APOLLO_NAMESPACE: str | None = Field(
         description="apollo namespace",
         default=None,
     )

api/configs/remote_settings_sources/apollo/client.py

@@ -4,8 +4,9 @@ import logging
 import os
 import threading
 import time
-from collections.abc import Mapping
+from collections.abc import Callable, Mapping
 from pathlib import Path
+from typing import Any
 
 from .python_3x import http_request, makedirs_wrapper
 from .utils import (
@@ -25,13 +26,13 @@ logger = logging.getLogger(__name__)
 class ApolloClient:
     def __init__(
         self,
-        config_url,
-        app_id,
-        cluster="default",
-        secret="",
-        start_hot_update=True,
-        change_listener=None,
-        _notification_map=None,
+        config_url: str,
+        app_id: str,
+        cluster: str = "default",
+        secret: str = "",
+        start_hot_update: bool = True,
+        change_listener: Callable[[str, str, str, Any], None] | None = None,
+        _notification_map: dict[str, int] | None = None,
     ):
         # Core routing parameters
         self.config_url = config_url
@@ -47,17 +48,17 @@ class ApolloClient:
         # Private control variables
         self._cycle_time = 5
         self._stopping = False
-        self._cache = {}
-        self._no_key = {}
-        self._hash = {}
+        self._cache: dict[str, dict[str, Any]] = {}
+        self._no_key: dict[str, str] = {}
+        self._hash: dict[str, str] = {}
         self._pull_timeout = 75
         self._cache_file_path = os.path.expanduser("~") + "/.dify/config/remote-settings/apollo/cache/"
-        self._long_poll_thread = None
+        self._long_poll_thread: threading.Thread | None = None
         self._change_listener = change_listener  # "add" "delete" "update"
         if _notification_map is None:
             _notification_map = {"application": -1}
         self._notification_map = _notification_map
-        self.last_release_key = None
+        self.last_release_key: str | None = None
         # Private startup method
         self._path_checker()
         if start_hot_update:
@@ -68,7 +69,7 @@ class ApolloClient:
         heartbeat.daemon = True
         heartbeat.start()
 
-    def get_json_from_net(self, namespace="application"):
+    def get_json_from_net(self, namespace: str = "application") -> dict[str, Any] | None:
         url = "{}/configs/{}/{}/{}?releaseKey={}&ip={}".format(
             self.config_url, self.app_id, self.cluster, namespace, "", self.ip
         )
@@ -88,7 +89,7 @@ class ApolloClient:
             logger.exception("an error occurred in get_json_from_net")
             return None
 
-    def get_value(self, key, default_val=None, namespace="application"):
+    def get_value(self, key: str, default_val: Any = None, namespace: str = "application") -> Any:
         try:
             # read memory configuration
             namespace_cache = self._cache.get(namespace)
@@ -104,7 +105,8 @@ class ApolloClient:
             namespace_data = self.get_json_from_net(namespace)
             val = get_value_from_dict(namespace_data, key)
             if val is not None:
-                self._update_cache_and_file(namespace_data, namespace)
+                if namespace_data is not None:
+                    self._update_cache_and_file(namespace_data, namespace)
                 return val
 
             # read the file configuration
@@ -126,23 +128,23 @@ class ApolloClient:
     # to ensure the real-time correctness of the function call.
     # If the user does not have the same default val twice
     # and the default val is used here, there may be a problem.
-    def _set_local_cache_none(self, namespace, key):
+    def _set_local_cache_none(self, namespace: str, key: str) -> None:
         no_key = no_key_cache_key(namespace, key)
         self._no_key[no_key] = key
 
-    def _start_hot_update(self):
+    def _start_hot_update(self) -> None:
         self._long_poll_thread = threading.Thread(target=self._listener)
         # When the asynchronous thread is started, the daemon thread will automatically exit
         # when the main thread is launched.
         self._long_poll_thread.daemon = True
         self._long_poll_thread.start()
 
-    def stop(self):
+    def stop(self) -> None:
         self._stopping = True
         logger.info("Stopping listener...")
 
     # Call the set callback function, and if it is abnormal, try it out
-    def _call_listener(self, namespace, old_kv, new_kv):
+    def _call_listener(self, namespace: str, old_kv: dict[str, Any] | None, new_kv: dict[str, Any] | None) -> None:
         if self._change_listener is None:
             return
         if old_kv is None:
@@ -168,12 +170,12 @@ class ApolloClient:
         except BaseException as e:
             logger.warning(str(e))
 
-    def _path_checker(self):
+    def _path_checker(self) -> None:
         if not os.path.isdir(self._cache_file_path):
             makedirs_wrapper(self._cache_file_path)
 
     # update the local cache and file cache
-    def _update_cache_and_file(self, namespace_data, namespace="application"):
+    def _update_cache_and_file(self, namespace_data: dict[str, Any], namespace: str = "application") -> None:
         # update the local cache
         self._cache[namespace] = namespace_data
         # update the file cache
@@ -187,7 +189,7 @@ class ApolloClient:
             self._hash[namespace] = new_hash
 
     # get the configuration from the local file
-    def _get_local_cache(self, namespace="application"):
+    def _get_local_cache(self, namespace: str = "application") -> dict[str, Any]:
         cache_file_path = os.path.join(self._cache_file_path, f"{self.app_id}_configuration_{namespace}.txt")
         if os.path.isfile(cache_file_path):
             with open(cache_file_path) as f:
@@ -195,8 +197,8 @@ class ApolloClient:
             return result
         return {}
 
-    def _long_poll(self):
-        notifications = []
+    def _long_poll(self) -> None:
+        notifications: list[dict[str, Any]] = []
         for key in self._cache:
             namespace_data = self._cache[key]
             notification_id = -1
@@ -236,7 +238,7 @@ class ApolloClient:
         except Exception as e:
             logger.warning(str(e))
 
-    def _get_net_and_set_local(self, namespace, n_id, call_change=False):
+    def _get_net_and_set_local(self, namespace: str, n_id: int, call_change: bool = False) -> None:
         namespace_data = self.get_json_from_net(namespace)
         if not namespace_data:
             return
@@ -248,7 +250,7 @@ class ApolloClient:
             new_kv = namespace_data.get(CONFIGURATIONS)
             self._call_listener(namespace, old_kv, new_kv)
 
-    def _listener(self):
+    def _listener(self) -> None:
         logger.info("start long_poll")
         while not self._stopping:
             self._long_poll()
@@ -266,13 +268,13 @@ class ApolloClient:
         headers["Timestamp"] = time_unix_now
         return headers
 
-    def _heart_beat(self):
+    def _heart_beat(self) -> None:
         while not self._stopping:
             for namespace in self._notification_map:
                 self._do_heart_beat(namespace)
             time.sleep(60 * 10)  # 10 minutes
 
-    def _do_heart_beat(self, namespace):
+    def _do_heart_beat(self, namespace: str) -> None:
         url = f"{self.config_url}/configs/{self.app_id}/{self.cluster}/{namespace}?ip={self.ip}"
         try:
             code, body = http_request(url, timeout=3, headers=self._sign_headers(url))
@@ -292,7 +294,7 @@ class ApolloClient:
             logger.exception("an error occurred in _do_heart_beat")
             return None
 
-    def get_all_dicts(self, namespace):
+    def get_all_dicts(self, namespace: str) -> dict[str, Any] | None:
         namespace_data = self._cache.get(namespace)
         if namespace_data is None:
             net_namespace_data = self.get_json_from_net(namespace)

api/configs/remote_settings_sources/apollo/python_3x.py

@@ -2,6 +2,8 @@ import logging
 import os
 import ssl
 import urllib.request
+from collections.abc import Mapping
+from typing import Any
 from urllib import parse
 from urllib.error import HTTPError
 
@@ -19,9 +21,9 @@ urllib.request.install_opener(opener)
 logger = logging.getLogger(__name__)
 
 
-def http_request(url, timeout, headers={}):
+def http_request(url: str, timeout: int | float, headers: Mapping[str, str] = {}) -> tuple[int, str | None]:
     try:
-        request = urllib.request.Request(url, headers=headers)
+        request = urllib.request.Request(url, headers=dict(headers))
         res = urllib.request.urlopen(request, timeout=timeout)
         body = res.read().decode("utf-8")
         return res.code, body
@@ -33,9 +35,9 @@ def http_request(url, timeout, headers={}):
         raise e
 
 
-def url_encode(params):
+def url_encode(params: dict[str, Any]) -> str:
     return parse.urlencode(params)
 
 
-def makedirs_wrapper(path):
+def makedirs_wrapper(path: str) -> None:
     os.makedirs(path, exist_ok=True)