init

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-bookworm
 
 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/autofix.yml

@@ -15,20 +15,42 @@ 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 .
           # 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: |

.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/style.yml

@@ -12,7 +12,6 @@ permissions:
   statuses: write
   contents: read
 
-
 jobs:
   python-style:
     name: Python Style
@@ -44,6 +43,10 @@ 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
@@ -99,7 +102,6 @@ jobs:
         working-directory: ./web
         run: |
           pnpm run lint
-          pnpm run eslint
 
   docker-compose-template:
     name: Docker Compose Template

.gitignore

@@ -230,4 +230,8 @@ api/.env.backup
 
 # Benchmark
 scripts/stress-test/setup/config/
-scripts/stress-test/reports/
+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 --directory api basedpyright         # 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

Makefile

@@ -26,7 +26,6 @@ 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
@@ -61,8 +60,9 @@ check:
 	@echo "✅ Code check complete"
 
 lint:
-	@echo "🔧 Running ruff format and check with fixes..."
-	@uv run --directory api --dev sh -c 'ruff format ./api && ruff check --fix ./api'
+	@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:

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="./docs/zh-TW/README.md"><img alt="繁體中文文件" src="https://img.shields.io/badge/繁體中文-d9d9d9"></a>
+  <a href="./docs/zh-CN/README.md"><img alt="简体中文文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="./docs/ja-JP/README.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="./docs/es-ES/README.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
+  <a href="./docs/fr-FR/README.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
+  <a href="./docs/tlh/README.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
+  <a href="./docs/ko-KR/README.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
+  <a href="./docs/ar-SA/README.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
+  <a href="./docs/tr-TR/README.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
+  <a href="./docs/vi-VN/README.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
+  <a href="./docs/de-DE/README.md"><img alt="README in Deutsch" src="https://img.shields.io/badge/German-d9d9d9"></a>
+  <a href="./docs/bn-BD/README.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.

api/.env.example

@@ -76,6 +76,7 @@ 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...
@@ -303,6 +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
@@ -328,7 +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
@@ -405,6 +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
@@ -415,10 +421,14 @@ 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
-TEMPLATE_TRANSFORM_MAX_LENGTH=80000
+CODE_MAX_STRING_LENGTH=400000
+TEMPLATE_TRANSFORM_MAX_LENGTH=400000
 CODE_MAX_STRING_ARRAY_LENGTH=30
 CODE_MAX_OBJECT_ARRAY_LENGTH=30
 CODE_MAX_NUMBER_ARRAY_LENGTH=1000
@@ -458,9 +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)

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
@@ -65,6 +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
@@ -90,11 +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

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

@@ -50,6 +50,7 @@ def initialize_extensions(app: DifyApp):
         ext_commands,
         ext_compress,
         ext_database,
+        ext_elasticsearch,
         ext_hosting_provider,
         ext_import_modules,
         ext_logging,
@@ -82,6 +83,7 @@ def initialize_extensions(app: DifyApp):
         ext_migrate,
         ext_redis,
         ext_storage,
+        ext_elasticsearch,
         ext_celery,
         ext_login,
         ext_mail,

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/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,
@@ -57,7 +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,
     )
@@ -97,21 +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,
@@ -134,7 +150,7 @@ class CodeExecutionSandboxConfig(BaseSettings):
 
     CODE_MAX_STRING_LENGTH: PositiveInt = Field(
         description="Maximum allowed length for strings in code execution",
-        default=80000,
+        default=400_000,
     )
 
     CODE_MAX_STRING_ARRAY_LENGTH: PositiveInt = Field(
@@ -152,6 +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):
     """
@@ -368,17 +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,
     )
@@ -403,6 +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.",
@@ -420,7 +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,
     )
@@ -436,7 +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,
     )
@@ -456,12 +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",
     )
@@ -505,6 +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
@@ -525,16 +577,38 @@ 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,
     )
 
+    TEMPLATE_TRANSFORM_MAX_LENGTH: PositiveInt = Field(
+        description="Maximum number of characters allowed in Template Transform node output",
+        default=400_000,
+    )
+
+    # 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):
     """
@@ -585,6 +659,67 @@ class RepositoryConfig(BaseSettings):
     )
 
 
+class ElasticsearchConfig(BaseSettings):
+    """
+    Configuration for Elasticsearch integration
+    """
+
+    ELASTICSEARCH_ENABLED: bool = Field(
+        description="Enable Elasticsearch for workflow logs storage",
+        default=False,
+    )
+
+    ELASTICSEARCH_HOSTS: list[str] = Field(
+        description="List of Elasticsearch hosts",
+        default=["http://localhost:9200"],
+    )
+
+    ELASTICSEARCH_USERNAME: str | None = Field(
+        description="Elasticsearch username for authentication",
+        default=None,
+    )
+
+    ELASTICSEARCH_PASSWORD: str | None = Field(
+        description="Elasticsearch password for authentication",
+        default=None,
+    )
+
+    ELASTICSEARCH_USE_SSL: bool = Field(
+        description="Use SSL/TLS for Elasticsearch connections",
+        default=False,
+    )
+
+    ELASTICSEARCH_VERIFY_CERTS: bool = Field(
+        description="Verify SSL certificates for Elasticsearch connections",
+        default=True,
+    )
+
+    ELASTICSEARCH_CA_CERTS: str | None = Field(
+        description="Path to CA certificates file for Elasticsearch SSL verification",
+        default=None,
+    )
+
+    ELASTICSEARCH_TIMEOUT: int = Field(
+        description="Elasticsearch request timeout in seconds",
+        default=30,
+    )
+
+    ELASTICSEARCH_MAX_RETRIES: int = Field(
+        description="Maximum number of retries for Elasticsearch requests",
+        default=3,
+    )
+
+    ELASTICSEARCH_INDEX_PREFIX: str = Field(
+        description="Prefix for Elasticsearch indices",
+        default="dify",
+    )
+
+    ELASTICSEARCH_RETENTION_DAYS: int = Field(
+        description="Number of days to retain data in Elasticsearch",
+        default=30,
+    )
+
+
 class AuthConfig(BaseSettings):
     """
     Configuration for authentication and OAuth
@@ -595,22 +730,22 @@ 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,
     )
@@ -673,47 +808,71 @@ 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,
     )
@@ -733,7 +892,7 @@ 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,
     )
@@ -756,17 +915,17 @@ 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",
     )
@@ -1010,6 +1169,7 @@ class FeatureConfig(
     AuthConfig,  # Changed from OAuthConfig to AuthConfig
     BillingConfig,
     CodeExecutionSandboxConfig,
+    ElasticsearchConfig,
     PluginConfig,
     MarketplaceConfig,
     DataSetConfig,
@@ -1041,5 +1201,6 @@ 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,
     )

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

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,62 +7,62 @@ 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/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 @@
 from enum import Enum
-from typing import Literal, Optional
+from typing import Literal
 
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
@@ -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/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/utils.py

@@ -29,7 +29,7 @@ def no_key_cache_key(namespace: str, key: str) -> str:
 
 
 # Returns whether the obtained value is obtained, and None if it does not
-def get_value_from_dict(namespace_cache: dict[str, Any] | None, key: str) -> Any | None:
+def get_value_from_dict(namespace_cache: dict[str, Any] | None, key: str) -> Any:
     if namespace_cache:
         kv_data = namespace_cache.get(CONFIGURATIONS)
         if kv_data is None:

api/configs/remote_settings_sources/nacos/http_request.py

@@ -5,7 +5,7 @@ import logging
 import os
 import time
 
-import requests
+import httpx
 
 logger = logging.getLogger(__name__)
 
@@ -30,10 +30,10 @@ class NacosHttpClient:
             params = {}
         try:
             self._inject_auth_info(headers, params)
-            response = requests.request(method, url="http://" + self.server + url, headers=headers, params=params)
+            response = httpx.request(method, url="http://" + self.server + url, headers=headers, params=params)
             response.raise_for_status()
             return response.text
-        except requests.RequestException as e:
+        except httpx.RequestError as e:
             return f"Request to Nacos failed: {e}"
 
     def _inject_auth_info(self, headers: dict[str, str], params: dict[str, str], module: str = "config") -> None:
@@ -78,7 +78,7 @@ class NacosHttpClient:
         params = {"username": self.username, "password": self.password}
         url = "http://" + self.server + "/nacos/v1/auth/login"
         try:
-            resp = requests.request("POST", url, headers=None, params=params)
+            resp = httpx.request("POST", url, headers=None, params=params)
             resp.raise_for_status()
             response_data = resp.json()
             self.token = response_data.get("accessToken")

api/constants/__init__.py

@@ -1,4 +1,5 @@
 from configs import dify_config
+from libs.collection_utils import convert_to_lower_and_upper_set
 
 HIDDEN_VALUE = "[__HIDDEN__]"
 UNKNOWN_VALUE = "[__UNKNOWN__]"
@@ -6,24 +7,39 @@ UUID_NIL = "00000000-0000-0000-0000-000000000000"
 
 DEFAULT_FILE_NUMBER_LIMITS = 3
 
-IMAGE_EXTENSIONS = ["jpg", "jpeg", "png", "webp", "gif", "svg"]
-IMAGE_EXTENSIONS.extend([ext.upper() for ext in IMAGE_EXTENSIONS])
+IMAGE_EXTENSIONS = convert_to_lower_and_upper_set({"jpg", "jpeg", "png", "webp", "gif", "svg"})
 
-VIDEO_EXTENSIONS = ["mp4", "mov", "mpeg", "webm"]
-VIDEO_EXTENSIONS.extend([ext.upper() for ext in VIDEO_EXTENSIONS])
+VIDEO_EXTENSIONS = convert_to_lower_and_upper_set({"mp4", "mov", "mpeg", "webm"})
 
-AUDIO_EXTENSIONS = ["mp3", "m4a", "wav", "amr", "mpga"]
-AUDIO_EXTENSIONS.extend([ext.upper() for ext in AUDIO_EXTENSIONS])
+AUDIO_EXTENSIONS = convert_to_lower_and_upper_set({"mp3", "m4a", "wav", "amr", "mpga"})
 
-
-_doc_extensions: list[str]
+_doc_extensions: set[str]
 if dify_config.ETL_TYPE == "Unstructured":
-    _doc_extensions = ["txt", "markdown", "md", "mdx", "pdf", "html", "htm", "xlsx", "xls", "vtt", "properties"]
-    _doc_extensions.extend(("doc", "docx", "csv", "eml", "msg", "pptx", "xml", "epub"))
+    _doc_extensions = {
+        "txt",
+        "markdown",
+        "md",
+        "mdx",
+        "pdf",
+        "html",
+        "htm",
+        "xlsx",
+        "xls",
+        "vtt",
+        "properties",
+        "doc",
+        "docx",
+        "csv",
+        "eml",
+        "msg",
+        "pptx",
+        "xml",
+        "epub",
+    }
     if dify_config.UNSTRUCTURED_API_URL:
-        _doc_extensions.append("ppt")
+        _doc_extensions.add("ppt")
 else:
-    _doc_extensions = [
+    _doc_extensions = {
         "txt",
         "markdown",
         "md",
@@ -37,5 +53,5 @@ else:
         "csv",
         "vtt",
         "properties",
-    ]
-DOCUMENT_EXTENSIONS = _doc_extensions + [ext.upper() for ext in _doc_extensions]
+    }
+DOCUMENT_EXTENSIONS: set[str] = convert_to_lower_and_upper_set(_doc_extensions)

api/contexts/__init__.py

@@ -5,6 +5,7 @@ from typing import TYPE_CHECKING
 from contexts.wrapper import RecyclableContextVar
 
 if TYPE_CHECKING:
+    from core.datasource.__base.datasource_provider import DatasourcePluginProviderController
     from core.model_runtime.entities.model_entities import AIModelEntity
     from core.plugin.entities.plugin_daemon import PluginModelProviderEntity
     from core.tools.plugin_tool.provider import PluginToolProviderController
@@ -32,3 +33,11 @@ plugin_model_schema_lock: RecyclableContextVar[Lock] = RecyclableContextVar(Cont
 plugin_model_schemas: RecyclableContextVar[dict[str, "AIModelEntity"]] = RecyclableContextVar(
     ContextVar("plugin_model_schemas")
 )
+
+datasource_plugin_providers: RecyclableContextVar[dict[str, "DatasourcePluginProviderController"]] = (
+    RecyclableContextVar(ContextVar("datasource_plugin_providers"))
+)
+
+datasource_plugin_providers_lock: RecyclableContextVar[Lock] = RecyclableContextVar(
+    ContextVar("datasource_plugin_providers_lock")
+)

api/controllers/console/__init__.py

@@ -1,31 +1,10 @@
+from importlib import import_module
+
 from flask import Blueprint
 from flask_restx import Namespace
 
 from libs.external_api import ExternalApi
 
-from .app.app_import import AppImportApi, AppImportCheckDependenciesApi, AppImportConfirmApi
-from .explore.audio import ChatAudioApi, ChatTextApi
-from .explore.completion import ChatApi, ChatStopApi, CompletionApi, CompletionStopApi
-from .explore.conversation import (
-    ConversationApi,
-    ConversationListApi,
-    ConversationPinApi,
-    ConversationRenameApi,
-    ConversationUnPinApi,
-)
-from .explore.message import (
-    MessageFeedbackApi,
-    MessageListApi,
-    MessageMoreLikeThisApi,
-    MessageSuggestedQuestionApi,
-)
-from .explore.workflow import (
-    InstalledAppWorkflowRunApi,
-    InstalledAppWorkflowTaskStopApi,
-)
-from .files import FileApi, FilePreviewApi, FileSupportTypeApi
-from .remote_files import RemoteFileInfoApi, RemoteFileUploadApi
-
 bp = Blueprint("console", __name__, url_prefix="/console/api")
 
 api = ExternalApi(
@@ -35,23 +14,23 @@ api = ExternalApi(
     description="Console management APIs for app configuration, monitoring, and administration",
 )
 
-# Create namespace
 console_ns = Namespace("console", description="Console management API operations", path="/")
 
-# File
-api.add_resource(FileApi, "/files/upload")
-api.add_resource(FilePreviewApi, "/files/<uuid:file_id>/preview")
-api.add_resource(FileSupportTypeApi, "/files/support-type")
+RESOURCE_MODULES = (
+    "controllers.console.app.app_import",
+    "controllers.console.explore.audio",
+    "controllers.console.explore.completion",
+    "controllers.console.explore.conversation",
+    "controllers.console.explore.message",
+    "controllers.console.explore.workflow",
+    "controllers.console.files",
+    "controllers.console.remote_files",
+)
 
-# Remote files
-api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")
-api.add_resource(RemoteFileUploadApi, "/remote-files/upload")
-
-# Import App
-api.add_resource(AppImportApi, "/apps/imports")
-api.add_resource(AppImportConfirmApi, "/apps/imports/<string:import_id>/confirm")
-api.add_resource(AppImportCheckDependenciesApi, "/apps/imports/<string:app_id>/check-dependencies")
+for module_name in RESOURCE_MODULES:
+    import_module(module_name)
 
+# Ensure resource modules are imported so route decorators are evaluated.
 # Import other controllers
 from . import (
     admin,
@@ -61,6 +40,7 @@ from . import (
     init_validate,
     ping,
     setup,
+    spec,
     version,
 )
 
@@ -114,6 +94,15 @@ from .datasets import (
     metadata,
     website,
 )
+from .datasets.rag_pipeline import (
+    datasource_auth,
+    datasource_content_preview,
+    rag_pipeline,
+    rag_pipeline_datasets,
+    rag_pipeline_draft_variable,
+    rag_pipeline_import,
+    rag_pipeline_workflow,
+)
 
 # Import explore controllers
 from .explore import (
@@ -140,77 +129,6 @@ from .workspace import (
     workspace,
 )
 
-# Explore Audio
-api.add_resource(ChatAudioApi, "/installed-apps/<uuid:installed_app_id>/audio-to-text", endpoint="installed_app_audio")
-api.add_resource(ChatTextApi, "/installed-apps/<uuid:installed_app_id>/text-to-audio", endpoint="installed_app_text")
-
-# Explore Completion
-api.add_resource(
-    CompletionApi, "/installed-apps/<uuid:installed_app_id>/completion-messages", endpoint="installed_app_completion"
-)
-api.add_resource(
-    CompletionStopApi,
-    "/installed-apps/<uuid:installed_app_id>/completion-messages/<string:task_id>/stop",
-    endpoint="installed_app_stop_completion",
-)
-api.add_resource(
-    ChatApi, "/installed-apps/<uuid:installed_app_id>/chat-messages", endpoint="installed_app_chat_completion"
-)
-api.add_resource(
-    ChatStopApi,
-    "/installed-apps/<uuid:installed_app_id>/chat-messages/<string:task_id>/stop",
-    endpoint="installed_app_stop_chat_completion",
-)
-
-# Explore Conversation
-api.add_resource(
-    ConversationRenameApi,
-    "/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>/name",
-    endpoint="installed_app_conversation_rename",
-)
-api.add_resource(
-    ConversationListApi, "/installed-apps/<uuid:installed_app_id>/conversations", endpoint="installed_app_conversations"
-)
-api.add_resource(
-    ConversationApi,
-    "/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>",
-    endpoint="installed_app_conversation",
-)
-api.add_resource(
-    ConversationPinApi,
-    "/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>/pin",
-    endpoint="installed_app_conversation_pin",
-)
-api.add_resource(
-    ConversationUnPinApi,
-    "/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>/unpin",
-    endpoint="installed_app_conversation_unpin",
-)
-
-
-# Explore Message
-api.add_resource(MessageListApi, "/installed-apps/<uuid:installed_app_id>/messages", endpoint="installed_app_messages")
-api.add_resource(
-    MessageFeedbackApi,
-    "/installed-apps/<uuid:installed_app_id>/messages/<uuid:message_id>/feedbacks",
-    endpoint="installed_app_message_feedback",
-)
-api.add_resource(
-    MessageMoreLikeThisApi,
-    "/installed-apps/<uuid:installed_app_id>/messages/<uuid:message_id>/more-like-this",
-    endpoint="installed_app_more_like_this",
-)
-api.add_resource(
-    MessageSuggestedQuestionApi,
-    "/installed-apps/<uuid:installed_app_id>/messages/<uuid:message_id>/suggested-questions",
-    endpoint="installed_app_suggested_question",
-)
-# Explore Workflow
-api.add_resource(InstalledAppWorkflowRunApi, "/installed-apps/<uuid:installed_app_id>/workflows/run")
-api.add_resource(
-    InstalledAppWorkflowTaskStopApi, "/installed-apps/<uuid:installed_app_id>/workflows/tasks/<string:task_id>/stop"
-)
-
 api.add_namespace(console_ns)
 
 __all__ = [
@@ -238,6 +156,8 @@ __all__ = [
     "datasets",
     "datasets_document",
     "datasets_segments",
+    "datasource_auth",
+    "datasource_content_preview",
     "email_register",
     "endpoint",
     "extension",
@@ -263,10 +183,16 @@ __all__ = [
     "parameter",
     "ping",
     "plugin",
+    "rag_pipeline",
+    "rag_pipeline_datasets",
+    "rag_pipeline_draft_variable",
+    "rag_pipeline_import",
+    "rag_pipeline_workflow",
     "recommended_app",
     "saved_message",
     "setup",
     "site",
+    "spec",
     "statistic",
     "tags",
     "tool_providers",

api/controllers/console/apikey.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 import flask_restx
 from flask_login import current_user
 from flask_restx import Resource, fields, marshal_with
@@ -50,7 +48,7 @@ class BaseApiKeyListResource(Resource):
     method_decorators = [account_initialization_required, login_required, setup_required]
 
     resource_type: str | None = None
-    resource_model: Optional[type] = None
+    resource_model: type | None = None
     resource_id_field: str | None = None
     token_prefix: str | None = None
     max_keys = 10
@@ -103,7 +101,7 @@ class BaseApiKeyResource(Resource):
     method_decorators = [account_initialization_required, login_required, setup_required]
 
     resource_type: str | None = None
-    resource_model: Optional[type] = None
+    resource_model: type | None = None
     resource_id_field: str | None = None
 
     def delete(self, resource_id, api_key_id):

api/controllers/console/app/app.py

@@ -19,6 +19,7 @@ from core.ops.ops_trace_manager import OpsTraceManager
 from extensions.ext_database import db
 from fields.app_fields import app_detail_fields, app_detail_fields_with_site, app_pagination_fields
 from libs.login import login_required
+from libs.validators import validate_description_length
 from models import Account, App
 from services.app_dsl_service import AppDslService, ImportMode
 from services.app_service import AppService
@@ -28,12 +29,6 @@ from services.feature_service import FeatureService
 ALLOW_CREATE_APP_MODES = ["chat", "agent-chat", "advanced-chat", "workflow", "completion"]
 
 
-def _validate_description_length(description):
-    if description and len(description) > 400:
-        raise ValueError("Description cannot exceed 400 characters.")
-    return description
-
-
 @console_ns.route("/apps")
 class AppListApi(Resource):
     @api.doc("list_apps")
@@ -138,7 +133,7 @@ class AppListApi(Resource):
         """Create app"""
         parser = reqparse.RequestParser()
         parser.add_argument("name", type=str, required=True, location="json")
-        parser.add_argument("description", type=_validate_description_length, location="json")
+        parser.add_argument("description", type=validate_description_length, location="json")
         parser.add_argument("mode", type=str, choices=ALLOW_CREATE_APP_MODES, location="json")
         parser.add_argument("icon_type", type=str, location="json")
         parser.add_argument("icon", type=str, location="json")
@@ -219,7 +214,7 @@ class AppApi(Resource):
 
         parser = reqparse.RequestParser()
         parser.add_argument("name", type=str, required=True, nullable=False, location="json")
-        parser.add_argument("description", type=_validate_description_length, location="json")
+        parser.add_argument("description", type=validate_description_length, location="json")
         parser.add_argument("icon_type", type=str, location="json")
         parser.add_argument("icon", type=str, location="json")
         parser.add_argument("icon_background", type=str, location="json")
@@ -297,7 +292,7 @@ class AppCopyApi(Resource):
 
         parser = reqparse.RequestParser()
         parser.add_argument("name", type=str, location="json")
-        parser.add_argument("description", type=_validate_description_length, location="json")
+        parser.add_argument("description", type=validate_description_length, location="json")
         parser.add_argument("icon_type", type=str, location="json")
         parser.add_argument("icon", type=str, location="json")
         parser.add_argument("icon_background", type=str, location="json")

api/controllers/console/app/app_import.py

@@ -20,7 +20,10 @@ from services.app_dsl_service import AppDslService, ImportStatus
 from services.enterprise.enterprise_service import EnterpriseService
 from services.feature_service import FeatureService
 
+from .. import console_ns
 
+
+@console_ns.route("/apps/imports")
 class AppImportApi(Resource):
     @setup_required
     @login_required
@@ -74,6 +77,7 @@ class AppImportApi(Resource):
         return result.model_dump(mode="json"), 200
 
 
+@console_ns.route("/apps/imports/<string:import_id>/confirm")
 class AppImportConfirmApi(Resource):
     @setup_required
     @login_required
@@ -98,6 +102,7 @@ class AppImportConfirmApi(Resource):
         return result.model_dump(mode="json"), 200
 
 
+@console_ns.route("/apps/imports/<string:app_id>/check-dependencies")
 class AppImportCheckDependenciesApi(Resource):
     @setup_required
     @login_required

api/controllers/console/app/conversation.py

@@ -1,6 +1,7 @@
 from datetime import datetime
 
 import pytz  # pip install pytz
+import sqlalchemy as sa
 from flask_login import current_user
 from flask_restx import Resource, marshal_with, reqparse
 from flask_restx.inputs import int_range
@@ -70,7 +71,7 @@ class CompletionConversationApi(Resource):
         parser.add_argument("limit", type=int_range(1, 100), default=20, location="args")
         args = parser.parse_args()
 
-        query = db.select(Conversation).where(
+        query = sa.select(Conversation).where(
             Conversation.app_id == app_model.id, Conversation.mode == "completion", Conversation.is_deleted.is_(False)
         )
 
@@ -236,7 +237,7 @@ class ChatConversationApi(Resource):
             .subquery()
         )
 
-        query = db.select(Conversation).where(Conversation.app_id == app_model.id, Conversation.is_deleted.is_(False))
+        query = sa.select(Conversation).where(Conversation.app_id == app_model.id, Conversation.is_deleted.is_(False))
 
         if args["keyword"]:
             keyword_filter = f"%{args['keyword']}%"

api/controllers/console/app/generator.py

@@ -16,7 +16,10 @@ from core.helper.code_executor.javascript.javascript_code_provider import Javasc
 from core.helper.code_executor.python3.python3_code_provider import Python3CodeProvider
 from core.llm_generator.llm_generator import LLMGenerator
 from core.model_runtime.errors.invoke import InvokeError
+from extensions.ext_database import db
 from libs.login import login_required
+from models import App
+from services.workflow_service import WorkflowService
 
 
 @console_ns.route("/rule-generate")
@@ -205,9 +208,6 @@ class InstructionGenerateApi(Resource):
         try:
             # Generate from nothing for a workflow node
             if (args["current"] == code_template or args["current"] == "") and args["node_id"] != "":
-                from models import App, db
-                from services.workflow_service import WorkflowService
-
                 app = db.session.query(App).where(App.id == args["flow_id"]).first()
                 if not app:
                     return {"error": f"app {args['flow_id']} not found"}, 400
@@ -261,6 +261,7 @@ class InstructionGenerateApi(Resource):
                     instruction=args["instruction"],
                     model_config=args["model_config"],
                     ideal_output=args["ideal_output"],
+                    workflow_service=WorkflowService(),
                 )
             return {"error": "incompatible parameters"}, 400
         except ProviderTokenNotInitError as ex:

api/controllers/console/app/message.py

@@ -62,6 +62,9 @@ class ChatMessageListApi(Resource):
     @account_initialization_required
     @marshal_with(message_infinite_scroll_pagination_fields)
     def get(self, app_model):
+        if not isinstance(current_user, Account) or not current_user.has_edit_permission:
+            raise Forbidden()
+
         parser = reqparse.RequestParser()
         parser.add_argument("conversation_id", required=True, type=uuid_value, location="args")
         parser.add_argument("first_id", type=uuid_value, location="args")

api/controllers/console/app/statistic.py

@@ -50,8 +50,9 @@ class DailyMessageStatistic(Resource):
 FROM
     messages
 WHERE
-    app_id = :app_id"""
-        arg_dict = {"tz": account.timezone, "app_id": app_model.id}
+    app_id = :app_id
+    AND invoke_from != :invoke_from"""
+        arg_dict = {"tz": account.timezone, "app_id": app_model.id, "invoke_from": InvokeFrom.DEBUGGER.value}
 
         timezone = pytz.timezone(account.timezone)
         utc_timezone = pytz.utc
@@ -187,8 +188,9 @@ class DailyTerminalsStatistic(Resource):
 FROM
     messages
 WHERE
-    app_id = :app_id"""
-        arg_dict = {"tz": account.timezone, "app_id": app_model.id}
+    app_id = :app_id
+    AND invoke_from != :invoke_from"""
+        arg_dict = {"tz": account.timezone, "app_id": app_model.id, "invoke_from": InvokeFrom.DEBUGGER.value}
 
         timezone = pytz.timezone(account.timezone)
         utc_timezone = pytz.utc
@@ -259,8 +261,9 @@ class DailyTokenCostStatistic(Resource):
 FROM
     messages
 WHERE
-    app_id = :app_id"""
-        arg_dict = {"tz": account.timezone, "app_id": app_model.id}
+    app_id = :app_id
+    AND invoke_from != :invoke_from"""
+        arg_dict = {"tz": account.timezone, "app_id": app_model.id, "invoke_from": InvokeFrom.DEBUGGER.value}
 
         timezone = pytz.timezone(account.timezone)
         utc_timezone = pytz.utc
@@ -340,8 +343,9 @@ FROM
             messages m
             ON c.id = m.conversation_id
         WHERE
-            c.app_id = :app_id"""
-        arg_dict = {"tz": account.timezone, "app_id": app_model.id}
+            c.app_id = :app_id
+            AND m.invoke_from != :invoke_from"""
+        arg_dict = {"tz": account.timezone, "app_id": app_model.id, "invoke_from": InvokeFrom.DEBUGGER.value}
 
         timezone = pytz.timezone(account.timezone)
         utc_timezone = pytz.utc
@@ -426,8 +430,9 @@ LEFT JOIN
     message_feedbacks mf
     ON mf.message_id=m.id AND mf.rating='like'
 WHERE
-    m.app_id = :app_id"""
-        arg_dict = {"tz": account.timezone, "app_id": app_model.id}
+    m.app_id = :app_id
+    AND m.invoke_from != :invoke_from"""
+        arg_dict = {"tz": account.timezone, "app_id": app_model.id, "invoke_from": InvokeFrom.DEBUGGER.value}
 
         timezone = pytz.timezone(account.timezone)
         utc_timezone = pytz.utc
@@ -502,8 +507,9 @@ class AverageResponseTimeStatistic(Resource):
 FROM
     messages
 WHERE
-    app_id = :app_id"""
-        arg_dict = {"tz": account.timezone, "app_id": app_model.id}
+    app_id = :app_id
+    AND invoke_from != :invoke_from"""
+        arg_dict = {"tz": account.timezone, "app_id": app_model.id, "invoke_from": InvokeFrom.DEBUGGER.value}
 
         timezone = pytz.timezone(account.timezone)
         utc_timezone = pytz.utc
@@ -576,8 +582,9 @@ class TokensPerSecondStatistic(Resource):
 FROM
     messages
 WHERE
-    app_id = :app_id"""
-        arg_dict = {"tz": account.timezone, "app_id": app_model.id}
+    app_id = :app_id
+    AND invoke_from != :invoke_from"""
+        arg_dict = {"tz": account.timezone, "app_id": app_model.id, "invoke_from": InvokeFrom.DEBUGGER.value}
 
         timezone = pytz.timezone(account.timezone)
         utc_timezone = pytz.utc

api/controllers/console/app/workflow.py

@@ -4,13 +4,12 @@ from collections.abc import Sequence
 from typing import cast
 
 from flask import abort, request
-from flask_restx import Resource, inputs, marshal_with, reqparse
+from flask_restx import Resource, fields, inputs, marshal_with, reqparse
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 
 import services
-from configs import dify_config
-from controllers.console import api
+from controllers.console import api, console_ns
 from controllers.console.app.error import ConversationCompletedError, DraftWorkflowNotExist, DraftWorkflowNotSync
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
@@ -20,6 +19,7 @@ from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.file.models import File
 from core.helper.trace_id_helper import get_external_trace_id
+from core.workflow.graph_engine.manager import GraphEngineManager
 from extensions.ext_database import db
 from factories import file_factory, variable_factory
 from fields.workflow_fields import workflow_fields, workflow_pagination_fields
@@ -57,7 +57,13 @@ def _parse_file(workflow: Workflow, files: list[dict] | None = None) -> Sequence
     return file_objs
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflows/draft")
 class DraftWorkflowApi(Resource):
+    @api.doc("get_draft_workflow")
+    @api.doc(description="Get draft workflow for an application")
+    @api.doc(params={"app_id": "Application ID"})
+    @api.response(200, "Draft workflow retrieved successfully", workflow_fields)
+    @api.response(404, "Draft workflow not found")
     @setup_required
     @login_required
     @account_initialization_required
@@ -86,6 +92,23 @@ class DraftWorkflowApi(Resource):
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
+    @api.doc("sync_draft_workflow")
+    @api.doc(description="Sync draft workflow configuration")
+    @api.expect(
+        api.model(
+            "SyncDraftWorkflowRequest",
+            {
+                "graph": fields.Raw(required=True, description="Workflow graph configuration"),
+                "features": fields.Raw(required=True, description="Workflow features configuration"),
+                "hash": fields.String(description="Workflow hash for validation"),
+                "environment_variables": fields.List(fields.Raw, required=True, description="Environment variables"),
+                "conversation_variables": fields.List(fields.Raw, description="Conversation variables"),
+            },
+        )
+    )
+    @api.response(200, "Draft workflow synced successfully", workflow_fields)
+    @api.response(400, "Invalid workflow configuration")
+    @api.response(403, "Permission denied")
     def post(self, app_model: App):
         """
         Sync draft workflow
@@ -159,7 +182,25 @@ class DraftWorkflowApi(Resource):
         }
 
 
+@console_ns.route("/apps/<uuid:app_id>/advanced-chat/workflows/draft/run")
 class AdvancedChatDraftWorkflowRunApi(Resource):
+    @api.doc("run_advanced_chat_draft_workflow")
+    @api.doc(description="Run draft workflow for advanced chat application")
+    @api.doc(params={"app_id": "Application ID"})
+    @api.expect(
+        api.model(
+            "AdvancedChatWorkflowRunRequest",
+            {
+                "query": fields.String(required=True, description="User query"),
+                "inputs": fields.Raw(description="Input variables"),
+                "files": fields.List(fields.Raw, description="File uploads"),
+                "conversation_id": fields.String(description="Conversation ID"),
+            },
+        )
+    )
+    @api.response(200, "Workflow run started successfully")
+    @api.response(400, "Invalid request parameters")
+    @api.response(403, "Permission denied")
     @setup_required
     @login_required
     @account_initialization_required
@@ -208,7 +249,23 @@ class AdvancedChatDraftWorkflowRunApi(Resource):
             raise InternalServerError()
 
 
+@console_ns.route("/apps/<uuid:app_id>/advanced-chat/workflows/draft/iteration/nodes/<string:node_id>/run")
 class AdvancedChatDraftRunIterationNodeApi(Resource):
+    @api.doc("run_advanced_chat_draft_iteration_node")
+    @api.doc(description="Run draft workflow iteration node for advanced chat")
+    @api.doc(params={"app_id": "Application ID", "node_id": "Node ID"})
+    @api.expect(
+        api.model(
+            "IterationNodeRunRequest",
+            {
+                "task_id": fields.String(required=True, description="Task ID"),
+                "inputs": fields.Raw(description="Input variables"),
+            },
+        )
+    )
+    @api.response(200, "Iteration node run started successfully")
+    @api.response(403, "Permission denied")
+    @api.response(404, "Node not found")
     @setup_required
     @login_required
     @account_initialization_required
@@ -244,7 +301,23 @@ class AdvancedChatDraftRunIterationNodeApi(Resource):
             raise InternalServerError()
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflows/draft/iteration/nodes/<string:node_id>/run")
 class WorkflowDraftRunIterationNodeApi(Resource):
+    @api.doc("run_workflow_draft_iteration_node")
+    @api.doc(description="Run draft workflow iteration node")
+    @api.doc(params={"app_id": "Application ID", "node_id": "Node ID"})
+    @api.expect(
+        api.model(
+            "WorkflowIterationNodeRunRequest",
+            {
+                "task_id": fields.String(required=True, description="Task ID"),
+                "inputs": fields.Raw(description="Input variables"),
+            },
+        )
+    )
+    @api.response(200, "Workflow iteration node run started successfully")
+    @api.response(403, "Permission denied")
+    @api.response(404, "Node not found")
     @setup_required
     @login_required
     @account_initialization_required
@@ -280,7 +353,23 @@ class WorkflowDraftRunIterationNodeApi(Resource):
             raise InternalServerError()
 
 
+@console_ns.route("/apps/<uuid:app_id>/advanced-chat/workflows/draft/loop/nodes/<string:node_id>/run")
 class AdvancedChatDraftRunLoopNodeApi(Resource):
+    @api.doc("run_advanced_chat_draft_loop_node")
+    @api.doc(description="Run draft workflow loop node for advanced chat")
+    @api.doc(params={"app_id": "Application ID", "node_id": "Node ID"})
+    @api.expect(
+        api.model(
+            "LoopNodeRunRequest",
+            {
+                "task_id": fields.String(required=True, description="Task ID"),
+                "inputs": fields.Raw(description="Input variables"),
+            },
+        )
+    )
+    @api.response(200, "Loop node run started successfully")
+    @api.response(403, "Permission denied")
+    @api.response(404, "Node not found")
     @setup_required
     @login_required
     @account_initialization_required
@@ -317,7 +406,23 @@ class AdvancedChatDraftRunLoopNodeApi(Resource):
             raise InternalServerError()
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflows/draft/loop/nodes/<string:node_id>/run")
 class WorkflowDraftRunLoopNodeApi(Resource):
+    @api.doc("run_workflow_draft_loop_node")
+    @api.doc(description="Run draft workflow loop node")
+    @api.doc(params={"app_id": "Application ID", "node_id": "Node ID"})
+    @api.expect(
+        api.model(
+            "WorkflowLoopNodeRunRequest",
+            {
+                "task_id": fields.String(required=True, description="Task ID"),
+                "inputs": fields.Raw(description="Input variables"),
+            },
+        )
+    )
+    @api.response(200, "Workflow loop node run started successfully")
+    @api.response(403, "Permission denied")
+    @api.response(404, "Node not found")
     @setup_required
     @login_required
     @account_initialization_required
@@ -354,7 +459,22 @@ class WorkflowDraftRunLoopNodeApi(Resource):
             raise InternalServerError()
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflows/draft/run")
 class DraftWorkflowRunApi(Resource):
+    @api.doc("run_draft_workflow")
+    @api.doc(description="Run draft workflow")
+    @api.doc(params={"app_id": "Application ID"})
+    @api.expect(
+        api.model(
+            "DraftWorkflowRunRequest",
+            {
+                "inputs": fields.Raw(required=True, description="Input variables"),
+                "files": fields.List(fields.Raw, description="File uploads"),
+            },
+        )
+    )
+    @api.response(200, "Draft workflow run started successfully")
+    @api.response(403, "Permission denied")
     @setup_required
     @login_required
     @account_initialization_required
@@ -393,7 +513,14 @@ class DraftWorkflowRunApi(Resource):
             raise InvokeRateLimitHttpError(ex.description)
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflow-runs/tasks/<string:task_id>/stop")
 class WorkflowTaskStopApi(Resource):
+    @api.doc("stop_workflow_task")
+    @api.doc(description="Stop running workflow task")
+    @api.doc(params={"app_id": "Application ID", "task_id": "Task ID"})
+    @api.response(200, "Task stopped successfully")
+    @api.response(404, "Task not found")
+    @api.response(403, "Permission denied")
     @setup_required
     @login_required
     @account_initialization_required
@@ -409,12 +536,32 @@ class WorkflowTaskStopApi(Resource):
         if not current_user.has_edit_permission:
             raise Forbidden()
 
-        AppQueueManager.set_stop_flag(task_id, InvokeFrom.DEBUGGER, current_user.id)
+        # Stop using both mechanisms for backward compatibility
+        # Legacy stop flag mechanism (without user check)
+        AppQueueManager.set_stop_flag_no_user_check(task_id)
+
+        # New graph engine command channel mechanism
+        GraphEngineManager.send_stop_command(task_id)
 
         return {"result": "success"}
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflows/draft/nodes/<string:node_id>/run")
 class DraftWorkflowNodeRunApi(Resource):
+    @api.doc("run_draft_workflow_node")
+    @api.doc(description="Run draft workflow node")
+    @api.doc(params={"app_id": "Application ID", "node_id": "Node ID"})
+    @api.expect(
+        api.model(
+            "DraftWorkflowNodeRunRequest",
+            {
+                "inputs": fields.Raw(description="Input variables"),
+            },
+        )
+    )
+    @api.response(200, "Node run started successfully", workflow_run_node_execution_fields)
+    @api.response(403, "Permission denied")
+    @api.response(404, "Node not found")
     @setup_required
     @login_required
     @account_initialization_required
@@ -462,7 +609,13 @@ class DraftWorkflowNodeRunApi(Resource):
         return workflow_node_execution
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflows/publish")
 class PublishedWorkflowApi(Resource):
+    @api.doc("get_published_workflow")
+    @api.doc(description="Get published workflow for an application")
+    @api.doc(params={"app_id": "Application ID"})
+    @api.response(200, "Published workflow retrieved successfully", workflow_fields)
+    @api.response(404, "Published workflow not found")
     @setup_required
     @login_required
     @account_initialization_required
@@ -534,7 +687,12 @@ class PublishedWorkflowApi(Resource):
         }
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflows/default-workflow-block-configs")
 class DefaultBlockConfigsApi(Resource):
+    @api.doc("get_default_block_configs")
+    @api.doc(description="Get default block configurations for workflow")
+    @api.doc(params={"app_id": "Application ID"})
+    @api.response(200, "Default block configurations retrieved successfully")
     @setup_required
     @login_required
     @account_initialization_required
@@ -555,7 +713,13 @@ class DefaultBlockConfigsApi(Resource):
         return workflow_service.get_default_block_configs()
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflows/default-workflow-block-configs/<string:block_type>")
 class DefaultBlockConfigApi(Resource):
+    @api.doc("get_default_block_config")
+    @api.doc(description="Get default block configuration by type")
+    @api.doc(params={"app_id": "Application ID", "block_type": "Block type"})
+    @api.response(200, "Default block configuration retrieved successfully")
+    @api.response(404, "Block type not found")
     @setup_required
     @login_required
     @account_initialization_required
@@ -588,7 +752,14 @@ class DefaultBlockConfigApi(Resource):
         return workflow_service.get_default_block_config(node_type=block_type, filters=filters)
 
 
+@console_ns.route("/apps/<uuid:app_id>/convert-to-workflow")
 class ConvertToWorkflowApi(Resource):
+    @api.doc("convert_to_workflow")
+    @api.doc(description="Convert application to workflow mode")
+    @api.doc(params={"app_id": "Application ID"})
+    @api.response(200, "Application converted to workflow successfully")
+    @api.response(400, "Application cannot be converted")
+    @api.response(403, "Permission denied")
     @setup_required
     @login_required
     @account_initialization_required
@@ -625,20 +796,12 @@ class ConvertToWorkflowApi(Resource):
         }
 
 
-class WorkflowConfigApi(Resource):
-    """Resource for workflow configuration."""
-
-    @setup_required
-    @login_required
-    @account_initialization_required
-    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
-    def get(self, app_model: App):
-        return {
-            "parallel_depth_limit": dify_config.WORKFLOW_PARALLEL_DEPTH_LIMIT,
-        }
-
-
+@console_ns.route("/apps/<uuid:app_id>/workflows")
 class PublishedAllWorkflowApi(Resource):
+    @api.doc("get_all_published_workflows")
+    @api.doc(description="Get all published workflows for an application")
+    @api.doc(params={"app_id": "Application ID"})
+    @api.response(200, "Published workflows retrieved successfully", workflow_pagination_fields)
     @setup_required
     @login_required
     @account_initialization_required
@@ -689,7 +852,23 @@ class PublishedAllWorkflowApi(Resource):
             }
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflows/<string:workflow_id>")
 class WorkflowByIdApi(Resource):
+    @api.doc("update_workflow_by_id")
+    @api.doc(description="Update workflow by ID")
+    @api.doc(params={"app_id": "Application ID", "workflow_id": "Workflow ID"})
+    @api.expect(
+        api.model(
+            "UpdateWorkflowRequest",
+            {
+                "environment_variables": fields.List(fields.Raw, description="Environment variables"),
+                "conversation_variables": fields.List(fields.Raw, description="Conversation variables"),
+            },
+        )
+    )
+    @api.response(200, "Workflow updated successfully", workflow_fields)
+    @api.response(404, "Workflow not found")
+    @api.response(403, "Permission denied")
     @setup_required
     @login_required
     @account_initialization_required
@@ -780,7 +959,14 @@ class WorkflowByIdApi(Resource):
         return None, 204
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflows/draft/nodes/<string:node_id>/last-run")
 class DraftWorkflowNodeLastRunApi(Resource):
+    @api.doc("get_draft_workflow_node_last_run")
+    @api.doc(description="Get last run result for draft workflow node")
+    @api.doc(params={"app_id": "Application ID", "node_id": "Node ID"})
+    @api.response(200, "Node last run retrieved successfully", workflow_run_node_execution_fields)
+    @api.response(404, "Node last run not found")
+    @api.response(403, "Permission denied")
     @setup_required
     @login_required
     @account_initialization_required
@@ -799,73 +985,3 @@ class DraftWorkflowNodeLastRunApi(Resource):
         if node_exec is None:
             raise NotFound("last run not found")
         return node_exec
-
-
-api.add_resource(
-    DraftWorkflowApi,
-    "/apps/<uuid:app_id>/workflows/draft",
-)
-api.add_resource(
-    WorkflowConfigApi,
-    "/apps/<uuid:app_id>/workflows/draft/config",
-)
-api.add_resource(
-    AdvancedChatDraftWorkflowRunApi,
-    "/apps/<uuid:app_id>/advanced-chat/workflows/draft/run",
-)
-api.add_resource(
-    DraftWorkflowRunApi,
-    "/apps/<uuid:app_id>/workflows/draft/run",
-)
-api.add_resource(
-    WorkflowTaskStopApi,
-    "/apps/<uuid:app_id>/workflow-runs/tasks/<string:task_id>/stop",
-)
-api.add_resource(
-    DraftWorkflowNodeRunApi,
-    "/apps/<uuid:app_id>/workflows/draft/nodes/<string:node_id>/run",
-)
-api.add_resource(
-    AdvancedChatDraftRunIterationNodeApi,
-    "/apps/<uuid:app_id>/advanced-chat/workflows/draft/iteration/nodes/<string:node_id>/run",
-)
-api.add_resource(
-    WorkflowDraftRunIterationNodeApi,
-    "/apps/<uuid:app_id>/workflows/draft/iteration/nodes/<string:node_id>/run",
-)
-api.add_resource(
-    AdvancedChatDraftRunLoopNodeApi,
-    "/apps/<uuid:app_id>/advanced-chat/workflows/draft/loop/nodes/<string:node_id>/run",
-)
-api.add_resource(
-    WorkflowDraftRunLoopNodeApi,
-    "/apps/<uuid:app_id>/workflows/draft/loop/nodes/<string:node_id>/run",
-)
-api.add_resource(
-    PublishedWorkflowApi,
-    "/apps/<uuid:app_id>/workflows/publish",
-)
-api.add_resource(
-    PublishedAllWorkflowApi,
-    "/apps/<uuid:app_id>/workflows",
-)
-api.add_resource(
-    DefaultBlockConfigsApi,
-    "/apps/<uuid:app_id>/workflows/default-workflow-block-configs",
-)
-api.add_resource(
-    DefaultBlockConfigApi,
-    "/apps/<uuid:app_id>/workflows/default-workflow-block-configs/<string:block_type>",
-)
-api.add_resource(
-    ConvertToWorkflowApi,
-    "/apps/<uuid:app_id>/convert-to-workflow",
-)
-api.add_resource(
-    WorkflowByIdApi,
-    "/apps/<uuid:app_id>/workflows/<string:workflow_id>",
-)
-api.add_resource(
-    DraftWorkflowNodeLastRunApi,
-    "/apps/<uuid:app_id>/workflows/draft/nodes/<string:node_id>/last-run",
-)

api/controllers/console/app/workflow_app_log.py

@@ -3,10 +3,10 @@ from flask_restx import Resource, marshal_with, reqparse
 from flask_restx.inputs import int_range
 from sqlalchemy.orm import Session
 
-from controllers.console import api
+from controllers.console import api, console_ns
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
-from core.workflow.entities.workflow_execution import WorkflowExecutionStatus
+from core.workflow.enums import WorkflowExecutionStatus
 from extensions.ext_database import db
 from fields.workflow_app_log_fields import workflow_app_log_pagination_fields
 from libs.login import login_required
@@ -15,7 +15,24 @@ from models.model import AppMode
 from services.workflow_app_service import WorkflowAppService
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflow-app-logs")
 class WorkflowAppLogApi(Resource):
+    @api.doc("get_workflow_app_logs")
+    @api.doc(description="Get workflow application execution logs")
+    @api.doc(params={"app_id": "Application ID"})
+    @api.doc(
+        params={
+            "keyword": "Search keyword for filtering logs",
+            "status": "Filter by execution status (succeeded, failed, stopped, partial-succeeded)",
+            "created_at__before": "Filter logs created before this timestamp",
+            "created_at__after": "Filter logs created after this timestamp",
+            "created_by_end_user_session_id": "Filter by end user session ID",
+            "created_by_account": "Filter by account",
+            "page": "Page number (1-99999)",
+            "limit": "Number of items per page (1-100)",
+        }
+    )
+    @api.response(200, "Workflow app logs retrieved successfully", workflow_app_log_pagination_fields)
     @setup_required
     @login_required
     @account_initialization_required
@@ -78,6 +95,3 @@ class WorkflowAppLogApi(Resource):
             )
 
             return workflow_app_log_pagination
-
-
-api.add_resource(WorkflowAppLogApi, "/apps/<uuid:app_id>/workflow-app-logs")

api/controllers/console/app/workflow_draft_variable.py

@@ -6,21 +6,23 @@ from flask_restx import Resource, fields, inputs, marshal, marshal_with, reqpars
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import Forbidden
 
-from controllers.console import api
+from controllers.console import api, console_ns
 from controllers.console.app.error import (
     DraftWorkflowNotExist,
 )
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
 from controllers.web.error import InvalidArgumentError, NotFoundError
+from core.file import helpers as file_helpers
 from core.variables.segment_group import SegmentGroup
 from core.variables.segments import ArrayFileSegment, FileSegment, Segment
 from core.variables.types import SegmentType
 from core.workflow.constants import CONVERSATION_VARIABLE_NODE_ID, SYSTEM_VARIABLE_NODE_ID
+from extensions.ext_database import db
 from factories.file_factory import build_from_mapping, build_from_mappings
 from factories.variable_factory import build_segment_with_type
 from libs.login import current_user, login_required
-from models import App, AppMode, db
+from models import App, AppMode
 from models.account import Account
 from models.workflow import WorkflowDraftVariable
 from services.workflow_draft_variable_service import WorkflowDraftVariableList, WorkflowDraftVariableService
@@ -74,6 +76,22 @@ def _serialize_variable_type(workflow_draft_var: WorkflowDraftVariable) -> str:
     return value_type.exposed_type().value
 
 
+def _serialize_full_content(variable: WorkflowDraftVariable) -> dict | None:
+    """Serialize full_content information for large variables."""
+    if not variable.is_truncated():
+        return None
+
+    variable_file = variable.variable_file
+    assert variable_file is not None
+
+    return {
+        "size_bytes": variable_file.size,
+        "value_type": variable_file.value_type.exposed_type().value,
+        "length": variable_file.length,
+        "download_url": file_helpers.get_signed_file_url(variable_file.upload_file_id, as_attachment=True),
+    }
+
+
 _WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS = {
     "id": fields.String,
     "type": fields.String(attribute=lambda model: model.get_variable_type()),
@@ -83,11 +101,13 @@ _WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS = {
     "value_type": fields.String(attribute=_serialize_variable_type),
     "edited": fields.Boolean(attribute=lambda model: model.edited),
     "visible": fields.Boolean,
+    "is_truncated": fields.Boolean(attribute=lambda model: model.file_id is not None),
 }
 
 _WORKFLOW_DRAFT_VARIABLE_FIELDS = dict(
     _WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS,
     value=fields.Raw(attribute=_serialize_var_value),
+    full_content=fields.Raw(attribute=_serialize_full_content),
 )
 
 _WORKFLOW_DRAFT_ENV_VARIABLE_FIELDS = {
@@ -144,7 +164,13 @@ def _api_prerequisite(f):
     return wrapper
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflows/draft/variables")
 class WorkflowVariableCollectionApi(Resource):
+    @api.doc("get_workflow_variables")
+    @api.doc(description="Get draft workflow variables")
+    @api.doc(params={"app_id": "Application ID"})
+    @api.doc(params={"page": "Page number (1-100000)", "limit": "Number of items per page (1-100)"})
+    @api.response(200, "Workflow variables retrieved successfully", _WORKFLOW_DRAFT_VARIABLE_LIST_WITHOUT_VALUE_FIELDS)
     @_api_prerequisite
     @marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_WITHOUT_VALUE_FIELDS)
     def get(self, app_model: App):
@@ -173,6 +199,9 @@ class WorkflowVariableCollectionApi(Resource):
 
         return workflow_vars
 
+    @api.doc("delete_workflow_variables")
+    @api.doc(description="Delete all draft workflow variables")
+    @api.response(204, "Workflow variables deleted successfully")
     @_api_prerequisite
     def delete(self, app_model: App):
         draft_var_srv = WorkflowDraftVariableService(
@@ -201,7 +230,12 @@ def validate_node_id(node_id: str) -> NoReturn | None:
     return None
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflows/draft/nodes/<string:node_id>/variables")
 class NodeVariableCollectionApi(Resource):
+    @api.doc("get_node_variables")
+    @api.doc(description="Get variables for a specific node")
+    @api.doc(params={"app_id": "Application ID", "node_id": "Node ID"})
+    @api.response(200, "Node variables retrieved successfully", _WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
     @_api_prerequisite
     @marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
     def get(self, app_model: App, node_id: str):
@@ -214,6 +248,9 @@ class NodeVariableCollectionApi(Resource):
 
         return node_vars
 
+    @api.doc("delete_node_variables")
+    @api.doc(description="Delete all variables for a specific node")
+    @api.response(204, "Node variables deleted successfully")
     @_api_prerequisite
     def delete(self, app_model: App, node_id: str):
         validate_node_id(node_id)
@@ -223,10 +260,16 @@ class NodeVariableCollectionApi(Resource):
         return Response("", 204)
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflows/draft/variables/<uuid:variable_id>")
 class VariableApi(Resource):
     _PATCH_NAME_FIELD = "name"
     _PATCH_VALUE_FIELD = "value"
 
+    @api.doc("get_variable")
+    @api.doc(description="Get a specific workflow variable")
+    @api.doc(params={"app_id": "Application ID", "variable_id": "Variable ID"})
+    @api.response(200, "Variable retrieved successfully", _WORKFLOW_DRAFT_VARIABLE_FIELDS)
+    @api.response(404, "Variable not found")
     @_api_prerequisite
     @marshal_with(_WORKFLOW_DRAFT_VARIABLE_FIELDS)
     def get(self, app_model: App, variable_id: str):
@@ -240,6 +283,19 @@ class VariableApi(Resource):
             raise NotFoundError(description=f"variable not found, id={variable_id}")
         return variable
 
+    @api.doc("update_variable")
+    @api.doc(description="Update a workflow variable")
+    @api.expect(
+        api.model(
+            "UpdateVariableRequest",
+            {
+                "name": fields.String(description="Variable name"),
+                "value": fields.Raw(description="Variable value"),
+            },
+        )
+    )
+    @api.response(200, "Variable updated successfully", _WORKFLOW_DRAFT_VARIABLE_FIELDS)
+    @api.response(404, "Variable not found")
     @_api_prerequisite
     @marshal_with(_WORKFLOW_DRAFT_VARIABLE_FIELDS)
     def patch(self, app_model: App, variable_id: str):
@@ -302,6 +358,10 @@ class VariableApi(Resource):
         db.session.commit()
         return variable
 
+    @api.doc("delete_variable")
+    @api.doc(description="Delete a workflow variable")
+    @api.response(204, "Variable deleted successfully")
+    @api.response(404, "Variable not found")
     @_api_prerequisite
     def delete(self, app_model: App, variable_id: str):
         draft_var_srv = WorkflowDraftVariableService(
@@ -317,7 +377,14 @@ class VariableApi(Resource):
         return Response("", 204)
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflows/draft/variables/<uuid:variable_id>/reset")
 class VariableResetApi(Resource):
+    @api.doc("reset_variable")
+    @api.doc(description="Reset a workflow variable to its default value")
+    @api.doc(params={"app_id": "Application ID", "variable_id": "Variable ID"})
+    @api.response(200, "Variable reset successfully", _WORKFLOW_DRAFT_VARIABLE_FIELDS)
+    @api.response(204, "Variable reset (no content)")
+    @api.response(404, "Variable not found")
     @_api_prerequisite
     def put(self, app_model: App, variable_id: str):
         draft_var_srv = WorkflowDraftVariableService(
@@ -358,7 +425,13 @@ def _get_variable_list(app_model: App, node_id) -> WorkflowDraftVariableList:
     return draft_vars
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflows/draft/conversation-variables")
 class ConversationVariableCollectionApi(Resource):
+    @api.doc("get_conversation_variables")
+    @api.doc(description="Get conversation variables for workflow")
+    @api.doc(params={"app_id": "Application ID"})
+    @api.response(200, "Conversation variables retrieved successfully", _WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
+    @api.response(404, "Draft workflow not found")
     @_api_prerequisite
     @marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
     def get(self, app_model: App):
@@ -374,14 +447,25 @@ class ConversationVariableCollectionApi(Resource):
         return _get_variable_list(app_model, CONVERSATION_VARIABLE_NODE_ID)
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflows/draft/system-variables")
 class SystemVariableCollectionApi(Resource):
+    @api.doc("get_system_variables")
+    @api.doc(description="Get system variables for workflow")
+    @api.doc(params={"app_id": "Application ID"})
+    @api.response(200, "System variables retrieved successfully", _WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
     @_api_prerequisite
     @marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
     def get(self, app_model: App):
         return _get_variable_list(app_model, SYSTEM_VARIABLE_NODE_ID)
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflows/draft/environment-variables")
 class EnvironmentVariableCollectionApi(Resource):
+    @api.doc("get_environment_variables")
+    @api.doc(description="Get environment variables for workflow")
+    @api.doc(params={"app_id": "Application ID"})
+    @api.response(200, "Environment variables retrieved successfully")
+    @api.response(404, "Draft workflow not found")
     @_api_prerequisite
     def get(self, app_model: App):
         """
@@ -413,16 +497,3 @@ class EnvironmentVariableCollectionApi(Resource):
             )
 
         return {"items": env_vars_list}
-
-
-api.add_resource(
-    WorkflowVariableCollectionApi,
-    "/apps/<uuid:app_id>/workflows/draft/variables",
-)
-api.add_resource(NodeVariableCollectionApi, "/apps/<uuid:app_id>/workflows/draft/nodes/<string:node_id>/variables")
-api.add_resource(VariableApi, "/apps/<uuid:app_id>/workflows/draft/variables/<uuid:variable_id>")
-api.add_resource(VariableResetApi, "/apps/<uuid:app_id>/workflows/draft/variables/<uuid:variable_id>/reset")
-
-api.add_resource(ConversationVariableCollectionApi, "/apps/<uuid:app_id>/workflows/draft/conversation-variables")
-api.add_resource(SystemVariableCollectionApi, "/apps/<uuid:app_id>/workflows/draft/system-variables")
-api.add_resource(EnvironmentVariableCollectionApi, "/apps/<uuid:app_id>/workflows/draft/environment-variables")

api/controllers/console/app/workflow_run.py

@@ -4,7 +4,7 @@ from flask_login import current_user
 from flask_restx import Resource, marshal_with, reqparse
 from flask_restx.inputs import int_range
 
-from controllers.console import api
+from controllers.console import api, console_ns
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
 from fields.workflow_run_fields import (
@@ -19,7 +19,13 @@ from models import Account, App, AppMode, EndUser
 from services.workflow_run_service import WorkflowRunService
 
 
+@console_ns.route("/apps/<uuid:app_id>/advanced-chat/workflow-runs")
 class AdvancedChatAppWorkflowRunListApi(Resource):
+    @api.doc("get_advanced_chat_workflow_runs")
+    @api.doc(description="Get advanced chat workflow run list")
+    @api.doc(params={"app_id": "Application ID"})
+    @api.doc(params={"last_id": "Last run ID for pagination", "limit": "Number of items per page (1-100)"})
+    @api.response(200, "Workflow runs retrieved successfully", advanced_chat_workflow_run_pagination_fields)
     @setup_required
     @login_required
     @account_initialization_required
@@ -40,7 +46,13 @@ class AdvancedChatAppWorkflowRunListApi(Resource):
         return result
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflow-runs")
 class WorkflowRunListApi(Resource):
+    @api.doc("get_workflow_runs")
+    @api.doc(description="Get workflow run list")
+    @api.doc(params={"app_id": "Application ID"})
+    @api.doc(params={"last_id": "Last run ID for pagination", "limit": "Number of items per page (1-100)"})
+    @api.response(200, "Workflow runs retrieved successfully", workflow_run_pagination_fields)
     @setup_required
     @login_required
     @account_initialization_required
@@ -61,7 +73,13 @@ class WorkflowRunListApi(Resource):
         return result
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflow-runs/<uuid:run_id>")
 class WorkflowRunDetailApi(Resource):
+    @api.doc("get_workflow_run_detail")
+    @api.doc(description="Get workflow run detail")
+    @api.doc(params={"app_id": "Application ID", "run_id": "Workflow run ID"})
+    @api.response(200, "Workflow run detail retrieved successfully", workflow_run_detail_fields)
+    @api.response(404, "Workflow run not found")
     @setup_required
     @login_required
     @account_initialization_required
@@ -79,7 +97,13 @@ class WorkflowRunDetailApi(Resource):
         return workflow_run
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflow-runs/<uuid:run_id>/node-executions")
 class WorkflowRunNodeExecutionListApi(Resource):
+    @api.doc("get_workflow_run_node_executions")
+    @api.doc(description="Get workflow run node execution list")
+    @api.doc(params={"app_id": "Application ID", "run_id": "Workflow run ID"})
+    @api.response(200, "Node executions retrieved successfully", workflow_run_node_execution_list_fields)
+    @api.response(404, "Workflow run not found")
     @setup_required
     @login_required
     @account_initialization_required
@@ -100,9 +124,3 @@ class WorkflowRunNodeExecutionListApi(Resource):
         )
 
         return {"data": node_executions}
-
-
-api.add_resource(AdvancedChatAppWorkflowRunListApi, "/apps/<uuid:app_id>/advanced-chat/workflow-runs")
-api.add_resource(WorkflowRunListApi, "/apps/<uuid:app_id>/workflow-runs")
-api.add_resource(WorkflowRunDetailApi, "/apps/<uuid:app_id>/workflow-runs/<uuid:run_id>")
-api.add_resource(WorkflowRunNodeExecutionListApi, "/apps/<uuid:app_id>/workflow-runs/<uuid:run_id>/node-executions")

api/controllers/console/app/workflow_statistic.py

@@ -7,7 +7,7 @@ from flask import jsonify
 from flask_login import current_user
 from flask_restx import Resource, reqparse
 
-from controllers.console import api
+from controllers.console import api, console_ns
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
 from extensions.ext_database import db
@@ -17,7 +17,13 @@ from models.enums import WorkflowRunTriggeredFrom
 from models.model import AppMode
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflow/statistics/daily-conversations")
 class WorkflowDailyRunsStatistic(Resource):
+    @api.doc("get_workflow_daily_runs_statistic")
+    @api.doc(description="Get workflow daily runs statistics")
+    @api.doc(params={"app_id": "Application ID"})
+    @api.doc(params={"start": "Start date and time (YYYY-MM-DD HH:MM)", "end": "End date and time (YYYY-MM-DD HH:MM)"})
+    @api.response(200, "Daily runs statistics retrieved successfully")
     @get_app_model
     @setup_required
     @login_required
@@ -79,7 +85,13 @@ WHERE
         return jsonify({"data": response_data})
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflow/statistics/daily-terminals")
 class WorkflowDailyTerminalsStatistic(Resource):
+    @api.doc("get_workflow_daily_terminals_statistic")
+    @api.doc(description="Get workflow daily terminals statistics")
+    @api.doc(params={"app_id": "Application ID"})
+    @api.doc(params={"start": "Start date and time (YYYY-MM-DD HH:MM)", "end": "End date and time (YYYY-MM-DD HH:MM)"})
+    @api.response(200, "Daily terminals statistics retrieved successfully")
     @get_app_model
     @setup_required
     @login_required
@@ -141,7 +153,13 @@ WHERE
         return jsonify({"data": response_data})
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflow/statistics/token-costs")
 class WorkflowDailyTokenCostStatistic(Resource):
+    @api.doc("get_workflow_daily_token_cost_statistic")
+    @api.doc(description="Get workflow daily token cost statistics")
+    @api.doc(params={"app_id": "Application ID"})
+    @api.doc(params={"start": "Start date and time (YYYY-MM-DD HH:MM)", "end": "End date and time (YYYY-MM-DD HH:MM)"})
+    @api.response(200, "Daily token cost statistics retrieved successfully")
     @get_app_model
     @setup_required
     @login_required
@@ -208,7 +226,13 @@ WHERE
         return jsonify({"data": response_data})
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflow/statistics/average-app-interactions")
 class WorkflowAverageAppInteractionStatistic(Resource):
+    @api.doc("get_workflow_average_app_interaction_statistic")
+    @api.doc(description="Get workflow average app interaction statistics")
+    @api.doc(params={"app_id": "Application ID"})
+    @api.doc(params={"start": "Start date and time (YYYY-MM-DD HH:MM)", "end": "End date and time (YYYY-MM-DD HH:MM)"})
+    @api.response(200, "Average app interaction statistics retrieved successfully")
     @setup_required
     @login_required
     @account_initialization_required
@@ -285,11 +309,3 @@ GROUP BY
                 )
 
         return jsonify({"data": response_data})
-
-
-api.add_resource(WorkflowDailyRunsStatistic, "/apps/<uuid:app_id>/workflow/statistics/daily-conversations")
-api.add_resource(WorkflowDailyTerminalsStatistic, "/apps/<uuid:app_id>/workflow/statistics/daily-terminals")
-api.add_resource(WorkflowDailyTokenCostStatistic, "/apps/<uuid:app_id>/workflow/statistics/token-costs")
-api.add_resource(
-    WorkflowAverageAppInteractionStatistic, "/apps/<uuid:app_id>/workflow/statistics/average-app-interactions"
-)

api/controllers/console/app/wraps.py

@@ -1,6 +1,6 @@
 from collections.abc import Callable
 from functools import wraps
-from typing import Optional, ParamSpec, TypeVar, Union
+from typing import ParamSpec, TypeVar, Union
 
 from controllers.console.app.error import AppNotFoundError
 from extensions.ext_database import db
@@ -12,7 +12,7 @@ P = ParamSpec("P")
 R = TypeVar("R")
 
 
-def _load_app_model(app_id: str) -> Optional[App]:
+def _load_app_model(app_id: str) -> App | None:
     assert isinstance(current_user, Account)
     app_model = (
         db.session.query(App)
@@ -22,7 +22,7 @@ def _load_app_model(app_id: str) -> Optional[App]:
     return app_model
 
 
-def get_app_model(view: Optional[Callable[P, R]] = None, *, mode: Union[AppMode, list[AppMode], None] = None):
+def get_app_model(view: Callable[P, R] | None = None, *, mode: Union[AppMode, list[AppMode], None] = None):
     def decorator(view_func: Callable[P, R]):
         @wraps(view_func)
         def decorated_view(*args: P.args, **kwargs: P.kwargs):

api/controllers/console/auth/data_source_bearer_auth.py

@@ -2,7 +2,7 @@ from flask_login import current_user
 from flask_restx import Resource, reqparse
 from werkzeug.exceptions import Forbidden
 
-from controllers.console import api
+from controllers.console import console_ns
 from controllers.console.auth.error import ApiKeyAuthFailedError
 from libs.login import login_required
 from services.auth.api_key_auth_service import ApiKeyAuthService
@@ -10,6 +10,7 @@ from services.auth.api_key_auth_service import ApiKeyAuthService
 from ..wraps import account_initialization_required, setup_required
 
 
+@console_ns.route("/api-key-auth/data-source")
 class ApiKeyAuthDataSource(Resource):
     @setup_required
     @login_required
@@ -33,6 +34,7 @@ class ApiKeyAuthDataSource(Resource):
         return {"sources": []}
 
 
+@console_ns.route("/api-key-auth/data-source/binding")
 class ApiKeyAuthDataSourceBinding(Resource):
     @setup_required
     @login_required
@@ -54,6 +56,7 @@ class ApiKeyAuthDataSourceBinding(Resource):
         return {"result": "success"}, 200
 
 
+@console_ns.route("/api-key-auth/data-source/<uuid:binding_id>")
 class ApiKeyAuthDataSourceBindingDelete(Resource):
     @setup_required
     @login_required
@@ -66,8 +69,3 @@ class ApiKeyAuthDataSourceBindingDelete(Resource):
         ApiKeyAuthService.delete_provider_auth(current_user.current_tenant_id, binding_id)
 
         return {"result": "success"}, 204
-
-
-api.add_resource(ApiKeyAuthDataSource, "/api-key-auth/data-source")
-api.add_resource(ApiKeyAuthDataSourceBinding, "/api-key-auth/data-source/binding")
-api.add_resource(ApiKeyAuthDataSourceBindingDelete, "/api-key-auth/data-source/<uuid:binding_id>")

api/controllers/console/auth/data_source_oauth.py

@@ -1,6 +1,6 @@
 import logging
 
-import requests
+import httpx
 from flask import current_app, redirect, request
 from flask_login import current_user
 from flask_restx import Resource, fields
@@ -119,7 +119,7 @@ class OAuthDataSourceBinding(Resource):
                 return {"error": "Invalid code"}, 400
             try:
                 oauth_provider.get_access_token(code)
-            except requests.HTTPError as e:
+            except httpx.HTTPStatusError as e:
                 logger.exception(
                     "An error occurred during the OAuthCallback process with %s: %s", provider, e.response.text
                 )
@@ -152,7 +152,7 @@ class OAuthDataSourceSync(Resource):
             return {"error": "Invalid provider"}, 400
         try:
             oauth_provider.sync_data_source(binding_id)
-        except requests.HTTPError as e:
+        except httpx.HTTPStatusError as e:
             logger.exception(
                 "An error occurred during the OAuthCallback process with %s: %s", provider, e.response.text
             )

api/controllers/console/auth/email_register.py

@@ -5,7 +5,7 @@ from sqlalchemy.orm import Session
 
 from configs import dify_config
 from constants.languages import languages
-from controllers.console import api
+from controllers.console import console_ns
 from controllers.console.auth.error import (
     EmailAlreadyInUseError,
     EmailCodeError,
@@ -25,6 +25,7 @@ from services.billing_service import BillingService
 from services.errors.account import AccountNotFoundError, AccountRegisterError
 
 
+@console_ns.route("/email-register/send-email")
 class EmailRegisterSendEmailApi(Resource):
     @setup_required
     @email_password_login_enabled
@@ -52,6 +53,7 @@ class EmailRegisterSendEmailApi(Resource):
         return {"result": "success", "data": token}
 
 
+@console_ns.route("/email-register/validity")
 class EmailRegisterCheckApi(Resource):
     @setup_required
     @email_password_login_enabled
@@ -92,6 +94,7 @@ class EmailRegisterCheckApi(Resource):
         return {"is_valid": True, "email": token_data.get("email"), "token": new_token}
 
 
+@console_ns.route("/email-register")
 class EmailRegisterResetApi(Resource):
     @setup_required
     @email_password_login_enabled
@@ -148,8 +151,3 @@ class EmailRegisterResetApi(Resource):
             raise AccountInFreezeError()
 
         return account
-
-
-api.add_resource(EmailRegisterSendEmailApi, "/email-register/send-email")
-api.add_resource(EmailRegisterCheckApi, "/email-register/validity")
-api.add_resource(EmailRegisterResetApi, "/email-register")

api/controllers/console/auth/forgot_password.py

@@ -221,8 +221,3 @@ class ForgotPasswordResetApi(Resource):
             TenantService.create_tenant_member(tenant, account, role="owner")
             account.current_tenant = tenant
             tenant_was_created.send(tenant)
-
-
-api.add_resource(ForgotPasswordSendEmailApi, "/forgot-password")
-api.add_resource(ForgotPasswordCheckApi, "/forgot-password/validity")
-api.add_resource(ForgotPasswordResetApi, "/forgot-password/resets")

api/controllers/console/auth/login.py

@@ -7,7 +7,7 @@ from flask_restx import Resource, reqparse
 import services
 from configs import dify_config
 from constants.languages import languages
-from controllers.console import api
+from controllers.console import console_ns
 from controllers.console.auth.error import (
     AuthenticationFailedError,
     EmailCodeError,
@@ -34,6 +34,7 @@ from services.errors.workspace import WorkSpaceNotAllowedCreateError, Workspaces
 from services.feature_service import FeatureService
 
 
+@console_ns.route("/login")
 class LoginApi(Resource):
     """Resource for user login."""
 
@@ -91,6 +92,7 @@ class LoginApi(Resource):
         return {"result": "success", "data": token_pair.model_dump()}
 
 
+@console_ns.route("/logout")
 class LogoutApi(Resource):
     @setup_required
     def get(self):
@@ -102,6 +104,7 @@ class LogoutApi(Resource):
         return {"result": "success"}
 
 
+@console_ns.route("/reset-password")
 class ResetPasswordSendEmailApi(Resource):
     @setup_required
     @email_password_login_enabled
@@ -130,6 +133,7 @@ class ResetPasswordSendEmailApi(Resource):
         return {"result": "success", "data": token}
 
 
+@console_ns.route("/email-code-login")
 class EmailCodeLoginSendEmailApi(Resource):
     @setup_required
     def post(self):
@@ -162,6 +166,7 @@ class EmailCodeLoginSendEmailApi(Resource):
         return {"result": "success", "data": token}
 
 
+@console_ns.route("/email-code-login/validity")
 class EmailCodeLoginApi(Resource):
     @setup_required
     def post(self):
@@ -218,6 +223,7 @@ class EmailCodeLoginApi(Resource):
         return {"result": "success", "data": token_pair.model_dump()}
 
 
+@console_ns.route("/refresh-token")
 class RefreshTokenApi(Resource):
     def post(self):
         parser = reqparse.RequestParser()
@@ -229,11 +235,3 @@ class RefreshTokenApi(Resource):
             return {"result": "success", "data": new_token_pair.model_dump()}
         except Exception as e:
             return {"result": "fail", "data": str(e)}, 401
-
-
-api.add_resource(LoginApi, "/login")
-api.add_resource(LogoutApi, "/logout")
-api.add_resource(EmailCodeLoginSendEmailApi, "/email-code-login")
-api.add_resource(EmailCodeLoginApi, "/email-code-login/validity")
-api.add_resource(ResetPasswordSendEmailApi, "/reset-password")
-api.add_resource(RefreshTokenApi, "/refresh-token")

api/controllers/console/auth/oauth.py

@@ -1,7 +1,6 @@
 import logging
-from typing import Optional
 
-import requests
+import httpx
 from flask import current_app, redirect, request
 from flask_restx import Resource
 from sqlalchemy import select
@@ -102,8 +101,10 @@ class OAuthCallback(Resource):
         try:
             token = oauth_provider.get_access_token(code)
             user_info = oauth_provider.get_user_info(token)
-        except requests.RequestException as e:
-            error_text = e.response.text if e.response else str(e)
+        except httpx.RequestError as e:
+            error_text = str(e)
+            if isinstance(e, httpx.HTTPStatusError):
+                error_text = e.response.text
             logger.exception("An error occurred during the OAuth process with %s: %s", provider, error_text)
             return {"error": "OAuth process failed"}, 400
 
@@ -157,8 +158,8 @@ class OAuthCallback(Resource):
         )
 
 
-def _get_account_by_openid_or_email(provider: str, user_info: OAuthUserInfo) -> Optional[Account]:
-    account: Optional[Account] = Account.get_by_openid(provider, user_info.id)
+def _get_account_by_openid_or_email(provider: str, user_info: OAuthUserInfo) -> Account | None:
+    account: Account | None = Account.get_by_openid(provider, user_info.id)
 
     if not account:
         with Session(db.engine) as session:

api/controllers/console/auth/oauth_server.py

@@ -14,7 +14,7 @@ from models.account import Account
 from models.model import OAuthProviderApp
 from services.oauth_server import OAUTH_ACCESS_TOKEN_EXPIRES_IN, OAuthGrantType, OAuthServerService
 
-from .. import api
+from .. import console_ns
 
 P = ParamSpec("P")
 R = TypeVar("R")
@@ -86,6 +86,7 @@ def oauth_server_access_token_required(view: Callable[Concatenate[T, OAuthProvid
     return decorated
 
 
+@console_ns.route("/oauth/provider")
 class OAuthServerAppApi(Resource):
     @setup_required
     @oauth_server_client_id_required
@@ -108,6 +109,7 @@ class OAuthServerAppApi(Resource):
         )
 
 
+@console_ns.route("/oauth/provider/authorize")
 class OAuthServerUserAuthorizeApi(Resource):
     @setup_required
     @login_required
@@ -125,6 +127,7 @@ class OAuthServerUserAuthorizeApi(Resource):
         )
 
 
+@console_ns.route("/oauth/provider/token")
 class OAuthServerUserTokenApi(Resource):
     @setup_required
     @oauth_server_client_id_required
@@ -180,6 +183,7 @@ class OAuthServerUserTokenApi(Resource):
             )
 
 
+@console_ns.route("/oauth/provider/account")
 class OAuthServerUserAccountApi(Resource):
     @setup_required
     @oauth_server_client_id_required
@@ -194,9 +198,3 @@ class OAuthServerUserAccountApi(Resource):
                 "timezone": account.timezone,
             }
         )
-
-
-api.add_resource(OAuthServerAppApi, "/oauth/provider")
-api.add_resource(OAuthServerUserAuthorizeApi, "/oauth/provider/authorize")
-api.add_resource(OAuthServerUserTokenApi, "/oauth/provider/token")
-api.add_resource(OAuthServerUserAccountApi, "/oauth/provider/account")

api/controllers/console/billing/billing.py

@@ -1,12 +1,13 @@
 from flask_restx import Resource, reqparse
 
-from controllers.console import api
+from controllers.console import console_ns
 from controllers.console.wraps import account_initialization_required, only_edition_cloud, setup_required
 from libs.login import current_user, login_required
 from models.model import Account
 from services.billing_service import BillingService
 
 
+@console_ns.route("/billing/subscription")
 class Subscription(Resource):
     @setup_required
     @login_required
@@ -26,6 +27,7 @@ class Subscription(Resource):
         )
 
 
+@console_ns.route("/billing/invoices")
 class Invoices(Resource):
     @setup_required
     @login_required
@@ -36,7 +38,3 @@ class Invoices(Resource):
         BillingService.is_tenant_owner_or_admin(current_user)
         assert current_user.current_tenant_id is not None
         return BillingService.get_invoices(current_user.email, current_user.current_tenant_id)
-
-
-api.add_resource(Subscription, "/billing/subscription")
-api.add_resource(Invoices, "/billing/invoices")

api/controllers/console/billing/compliance.py

@@ -6,10 +6,11 @@ from libs.helper import extract_remote_ip
 from libs.login import login_required
 from services.billing_service import BillingService
 
-from .. import api
+from .. import console_ns
 from ..wraps import account_initialization_required, only_edition_cloud, setup_required
 
 
+@console_ns.route("/compliance/download")
 class ComplianceApi(Resource):
     @setup_required
     @login_required
@@ -30,6 +31,3 @@ class ComplianceApi(Resource):
             ip=ip_address,
             device_info=device_info,
         )
-
-
-api.add_resource(ComplianceApi, "/compliance/download")

api/controllers/console/datasets/data_source.py

@@ -1,4 +1,6 @@
 import json
+from collections.abc import Generator
+from typing import cast
 
 from flask import request
 from flask_login import current_user
@@ -7,8 +9,10 @@ from sqlalchemy import select
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import NotFound
 
-from controllers.console import api
+from controllers.console import console_ns
 from controllers.console.wraps import account_initialization_required, setup_required
+from core.datasource.entities.datasource_entities import DatasourceProviderType, OnlineDocumentPagesMessage
+from core.datasource.online_document.online_document_plugin import OnlineDocumentDatasourcePlugin
 from core.indexing_runner import IndexingRunner
 from core.rag.extractor.entity.datasource_type import DatasourceType
 from core.rag.extractor.entity.extract_setting import ExtractSetting
@@ -19,9 +23,14 @@ from libs.datetime_utils import naive_utc_now
 from libs.login import login_required
 from models import DataSourceOauthBinding, Document
 from services.dataset_service import DatasetService, DocumentService
+from services.datasource_provider_service import DatasourceProviderService
 from tasks.document_indexing_sync_task import document_indexing_sync_task
 
 
+@console_ns.route(
+    "/data-source/integrates",
+    "/data-source/integrates/<uuid:binding_id>/<string:action>",
+)
 class DataSourceApi(Resource):
     @setup_required
     @login_required
@@ -104,6 +113,7 @@ class DataSourceApi(Resource):
         return {"result": "success"}, 200
 
 
+@console_ns.route("/notion/pre-import/pages")
 class DataSourceNotionListApi(Resource):
     @setup_required
     @login_required
@@ -111,6 +121,18 @@ class DataSourceNotionListApi(Resource):
     @marshal_with(integrate_notion_info_list_fields)
     def get(self):
         dataset_id = request.args.get("dataset_id", default=None, type=str)
+        credential_id = request.args.get("credential_id", default=None, type=str)
+        if not credential_id:
+            raise ValueError("Credential id is required.")
+        datasource_provider_service = DatasourceProviderService()
+        credential = datasource_provider_service.get_datasource_credentials(
+            tenant_id=current_user.current_tenant_id,
+            credential_id=credential_id,
+            provider="notion_datasource",
+            plugin_id="langgenius/notion_datasource",
+        )
+        if not credential:
+            raise NotFound("Credential not found.")
         exist_page_ids = []
         with Session(db.engine) as session:
             # import notion in the exist dataset
@@ -134,59 +156,79 @@ class DataSourceNotionListApi(Resource):
                         data_source_info = json.loads(document.data_source_info)
                         exist_page_ids.append(data_source_info["notion_page_id"])
             # get all authorized pages
-            data_source_bindings = session.scalars(
-                select(DataSourceOauthBinding).filter_by(
-                    tenant_id=current_user.current_tenant_id, provider="notion", disabled=False
+            from core.datasource.datasource_manager import DatasourceManager
+
+            datasource_runtime = DatasourceManager.get_datasource_runtime(
+                provider_id="langgenius/notion_datasource/notion_datasource",
+                datasource_name="notion_datasource",
+                tenant_id=current_user.current_tenant_id,
+                datasource_type=DatasourceProviderType.ONLINE_DOCUMENT,
+            )
+            datasource_provider_service = DatasourceProviderService()
+            if credential:
+                datasource_runtime.runtime.credentials = credential
+            datasource_runtime = cast(OnlineDocumentDatasourcePlugin, datasource_runtime)
+            online_document_result: Generator[OnlineDocumentPagesMessage, None, None] = (
+                datasource_runtime.get_online_document_pages(
+                    user_id=current_user.id,
+                    datasource_parameters={},
+                    provider_type=datasource_runtime.datasource_provider_type(),
                 )
-            ).all()
-            if not data_source_bindings:
-                return {"notion_info": []}, 200
-            pre_import_info_list = []
-            for data_source_binding in data_source_bindings:
-                source_info = data_source_binding.source_info
-                pages = source_info["pages"]
-                # Filter out already bound pages
-                for page in pages:
-                    if page["page_id"] in exist_page_ids:
-                        page["is_bound"] = True
-                    else:
-                        page["is_bound"] = False
-                pre_import_info = {
-                    "workspace_name": source_info["workspace_name"],
-                    "workspace_icon": source_info["workspace_icon"],
-                    "workspace_id": source_info["workspace_id"],
-                    "pages": pages,
-                }
-                pre_import_info_list.append(pre_import_info)
-            return {"notion_info": pre_import_info_list}, 200
+            )
+            try:
+                pages = []
+                workspace_info = {}
+                for message in online_document_result:
+                    result = message.result
+                    for info in result:
+                        workspace_info = {
+                            "workspace_id": info.workspace_id,
+                            "workspace_name": info.workspace_name,
+                            "workspace_icon": info.workspace_icon,
+                        }
+                        for page in info.pages:
+                            page_info = {
+                                "page_id": page.page_id,
+                                "page_name": page.page_name,
+                                "type": page.type,
+                                "parent_id": page.parent_id,
+                                "is_bound": page.page_id in exist_page_ids,
+                                "page_icon": page.page_icon,
+                            }
+                            pages.append(page_info)
+            except Exception as e:
+                raise e
+            return {"notion_info": {**workspace_info, "pages": pages}}, 200
 
 
+@console_ns.route(
+    "/notion/workspaces/<uuid:workspace_id>/pages/<uuid:page_id>/<string:page_type>/preview",
+    "/datasets/notion-indexing-estimate",
+)
 class DataSourceNotionApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
     def get(self, workspace_id, page_id, page_type):
+        credential_id = request.args.get("credential_id", default=None, type=str)
+        if not credential_id:
+            raise ValueError("Credential id is required.")
+        datasource_provider_service = DatasourceProviderService()
+        credential = datasource_provider_service.get_datasource_credentials(
+            tenant_id=current_user.current_tenant_id,
+            credential_id=credential_id,
+            provider="notion_datasource",
+            plugin_id="langgenius/notion_datasource",
+        )
+
         workspace_id = str(workspace_id)
         page_id = str(page_id)
-        with Session(db.engine) as session:
-            data_source_binding = session.execute(
-                select(DataSourceOauthBinding).where(
-                    db.and_(
-                        DataSourceOauthBinding.tenant_id == current_user.current_tenant_id,
-                        DataSourceOauthBinding.provider == "notion",
-                        DataSourceOauthBinding.disabled == False,
-                        DataSourceOauthBinding.source_info["workspace_id"] == f'"{workspace_id}"',
-                    )
-                )
-            ).scalar_one_or_none()
-        if not data_source_binding:
-            raise NotFound("Data source binding not found.")
 
         extractor = NotionExtractor(
             notion_workspace_id=workspace_id,
             notion_obj_id=page_id,
             notion_page_type=page_type,
-            notion_access_token=data_source_binding.access_token,
+            notion_access_token=credential.get("integration_secret"),
             tenant_id=current_user.current_tenant_id,
         )
 
@@ -211,10 +253,12 @@ class DataSourceNotionApi(Resource):
         extract_settings = []
         for notion_info in notion_info_list:
             workspace_id = notion_info["workspace_id"]
+            credential_id = notion_info.get("credential_id")
             for page in notion_info["pages"]:
                 extract_setting = ExtractSetting(
                     datasource_type=DatasourceType.NOTION.value,
                     notion_info={
+                        "credential_id": credential_id,
                         "notion_workspace_id": workspace_id,
                         "notion_obj_id": page["page_id"],
                         "notion_page_type": page["type"],
@@ -234,6 +278,7 @@ class DataSourceNotionApi(Resource):
         return response.model_dump(), 200
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/notion/sync")
 class DataSourceNotionDatasetSyncApi(Resource):
     @setup_required
     @login_required
@@ -250,6 +295,7 @@ class DataSourceNotionDatasetSyncApi(Resource):
         return {"result": "success"}, 200
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/notion/sync")
 class DataSourceNotionDocumentSyncApi(Resource):
     @setup_required
     @login_required
@@ -266,16 +312,3 @@ class DataSourceNotionDocumentSyncApi(Resource):
             raise NotFound("Document not found.")
         document_indexing_sync_task.delay(dataset_id_str, document_id_str)
         return {"result": "success"}, 200
-
-
-api.add_resource(DataSourceApi, "/data-source/integrates", "/data-source/integrates/<uuid:binding_id>/<string:action>")
-api.add_resource(DataSourceNotionListApi, "/notion/pre-import/pages")
-api.add_resource(
-    DataSourceNotionApi,
-    "/notion/workspaces/<uuid:workspace_id>/pages/<uuid:page_id>/<string:page_type>/preview",
-    "/datasets/notion-indexing-estimate",
-)
-api.add_resource(DataSourceNotionDatasetSyncApi, "/datasets/<uuid:dataset_id>/notion/sync")
-api.add_resource(
-    DataSourceNotionDocumentSyncApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/notion/sync"
-)

api/controllers/console/datasets/datasets.py

@@ -1,13 +1,14 @@
-import flask_restx
+from typing import Any, cast
+
 from flask import request
 from flask_login import current_user
-from flask_restx import Resource, marshal, marshal_with, reqparse
+from flask_restx import Resource, fields, marshal, marshal_with, reqparse
 from sqlalchemy import select
 from werkzeug.exceptions import Forbidden, NotFound
 
 import services
 from configs import dify_config
-from controllers.console import api
+from controllers.console import api, console_ns
 from controllers.console.apikey import api_key_fields, api_key_list
 from controllers.console.app.error import ProviderNotInitializeError
 from controllers.console.datasets.error import DatasetInUseError, DatasetNameDuplicateError, IndexingEstimateError
@@ -20,7 +21,6 @@ from controllers.console.wraps import (
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.indexing_runner import IndexingRunner
 from core.model_runtime.entities.model_entities import ModelType
-from core.plugin.entities.plugin import ModelProviderID
 from core.provider_manager import ProviderManager
 from core.rag.datasource.vdb.vector_type import VectorType
 from core.rag.extractor.entity.datasource_type import DatasourceType
@@ -31,24 +31,35 @@ from fields.app_fields import related_app_list
 from fields.dataset_fields import dataset_detail_fields, dataset_query_detail_fields
 from fields.document_fields import document_status_fields
 from libs.login import login_required
+from libs.validators import validate_description_length
 from models import ApiToken, Dataset, Document, DocumentSegment, UploadFile
+from models.account import Account
 from models.dataset import DatasetPermissionEnum
+from models.provider_ids import ModelProviderID
 from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService
 
 
-def _validate_name(name):
+def _validate_name(name: str) -> str:
     if not name or len(name) < 1 or len(name) > 40:
         raise ValueError("Name must be between 1 to 40 characters.")
     return name
 
 
-def _validate_description_length(description):
-    if description and len(description) > 400:
-        raise ValueError("Description cannot exceed 400 characters.")
-    return description
-
-
+@console_ns.route("/datasets")
 class DatasetListApi(Resource):
+    @api.doc("get_datasets")
+    @api.doc(description="Get list of datasets")
+    @api.doc(
+        params={
+            "page": "Page number (default: 1)",
+            "limit": "Number of items per page (default: 20)",
+            "ids": "Filter by dataset IDs (list)",
+            "keyword": "Search keyword",
+            "tag_ids": "Filter by tag IDs (list)",
+            "include_all": "Include all datasets (default: false)",
+        }
+    )
+    @api.response(200, "Datasets retrieved successfully")
     @setup_required
     @login_required
     @account_initialization_required
@@ -78,7 +89,7 @@ class DatasetListApi(Resource):
         for embedding_model in embedding_models:
             model_names.append(f"{embedding_model.model}:{embedding_model.provider.provider}")
 
-        data = marshal(datasets, dataset_detail_fields)
+        data = cast(list[dict[str, Any]], marshal(datasets, dataset_detail_fields))
         for item in data:
             # convert embedding_model_provider to plugin standard format
             if item["indexing_technique"] == "high_quality" and item["embedding_model_provider"]:
@@ -100,6 +111,24 @@ class DatasetListApi(Resource):
         response = {"data": data, "has_more": len(datasets) == limit, "limit": limit, "total": total, "page": page}
         return response, 200
 
+    @api.doc("create_dataset")
+    @api.doc(description="Create a new dataset")
+    @api.expect(
+        api.model(
+            "CreateDatasetRequest",
+            {
+                "name": fields.String(required=True, description="Dataset name (1-40 characters)"),
+                "description": fields.String(description="Dataset description (max 400 characters)"),
+                "indexing_technique": fields.String(description="Indexing technique"),
+                "permission": fields.String(description="Dataset permission"),
+                "provider": fields.String(description="Provider"),
+                "external_knowledge_api_id": fields.String(description="External knowledge API ID"),
+                "external_knowledge_id": fields.String(description="External knowledge ID"),
+            },
+        )
+    )
+    @api.response(201, "Dataset created successfully")
+    @api.response(400, "Invalid request parameters")
     @setup_required
     @login_required
     @account_initialization_required
@@ -115,7 +144,7 @@ class DatasetListApi(Resource):
         )
         parser.add_argument(
             "description",
-            type=_validate_description_length,
+            type=validate_description_length,
             nullable=True,
             required=False,
             default="",
@@ -160,7 +189,7 @@ class DatasetListApi(Resource):
                 name=args["name"],
                 description=args["description"],
                 indexing_technique=args["indexing_technique"],
-                account=current_user,
+                account=cast(Account, current_user),
                 permission=DatasetPermissionEnum.ONLY_ME,
                 provider=args["provider"],
                 external_knowledge_api_id=args["external_knowledge_api_id"],
@@ -172,7 +201,14 @@ class DatasetListApi(Resource):
         return marshal(dataset, dataset_detail_fields), 201
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>")
 class DatasetApi(Resource):
+    @api.doc("get_dataset")
+    @api.doc(description="Get dataset details")
+    @api.doc(params={"dataset_id": "Dataset ID"})
+    @api.response(200, "Dataset retrieved successfully", dataset_detail_fields)
+    @api.response(404, "Dataset not found")
+    @api.response(403, "Permission denied")
     @setup_required
     @login_required
     @account_initialization_required
@@ -185,7 +221,7 @@ class DatasetApi(Resource):
             DatasetService.check_dataset_permission(dataset, current_user)
         except services.errors.account.NoPermissionError as e:
             raise Forbidden(str(e))
-        data = marshal(dataset, dataset_detail_fields)
+        data = cast(dict[str, Any], marshal(dataset, dataset_detail_fields))
         if dataset.indexing_technique == "high_quality":
             if dataset.embedding_model_provider:
                 provider_id = ModelProviderID(dataset.embedding_model_provider)
@@ -215,6 +251,23 @@ class DatasetApi(Resource):
 
         return data, 200
 
+    @api.doc("update_dataset")
+    @api.doc(description="Update dataset details")
+    @api.expect(
+        api.model(
+            "UpdateDatasetRequest",
+            {
+                "name": fields.String(description="Dataset name"),
+                "description": fields.String(description="Dataset description"),
+                "permission": fields.String(description="Dataset permission"),
+                "indexing_technique": fields.String(description="Indexing technique"),
+                "external_retrieval_model": fields.Raw(description="External retrieval model settings"),
+            },
+        )
+    )
+    @api.response(200, "Dataset updated successfully", dataset_detail_fields)
+    @api.response(404, "Dataset not found")
+    @api.response(403, "Permission denied")
     @setup_required
     @login_required
     @account_initialization_required
@@ -232,7 +285,7 @@ class DatasetApi(Resource):
             help="type is required. Name must be between 1 to 40 characters.",
             type=_validate_name,
         )
-        parser.add_argument("description", location="json", store_missing=False, type=_validate_description_length)
+        parser.add_argument("description", location="json", store_missing=False, type=validate_description_length)
         parser.add_argument(
             "indexing_technique",
             type=str,
@@ -281,6 +334,15 @@ class DatasetApi(Resource):
             location="json",
             help="Invalid external knowledge api id.",
         )
+
+        parser.add_argument(
+            "icon_info",
+            type=dict,
+            required=False,
+            nullable=True,
+            location="json",
+            help="Invalid icon info.",
+        )
         args = parser.parse_args()
         data = request.get_json()
 
@@ -304,7 +366,7 @@ class DatasetApi(Resource):
         if dataset is None:
             raise NotFound("Dataset not found.")
 
-        result_data = marshal(dataset, dataset_detail_fields)
+        result_data = cast(dict[str, Any], marshal(dataset, dataset_detail_fields))
         tenant_id = current_user.current_tenant_id
 
         if data.get("partial_member_list") and data.get("permission") == "partial_members":
@@ -331,7 +393,7 @@ class DatasetApi(Resource):
         dataset_id_str = str(dataset_id)
 
         # The role of the current user in the ta table must be admin, owner, or editor
-        if not current_user.is_editor or current_user.is_dataset_operator:
+        if not (current_user.is_editor or current_user.is_dataset_operator):
             raise Forbidden()
 
         try:
@@ -344,7 +406,12 @@ class DatasetApi(Resource):
             raise DatasetInUseError()
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/use-check")
 class DatasetUseCheckApi(Resource):
+    @api.doc("check_dataset_use")
+    @api.doc(description="Check if dataset is in use")
+    @api.doc(params={"dataset_id": "Dataset ID"})
+    @api.response(200, "Dataset use status retrieved successfully")
     @setup_required
     @login_required
     @account_initialization_required
@@ -355,7 +422,12 @@ class DatasetUseCheckApi(Resource):
         return {"is_using": dataset_is_using}, 200
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/queries")
 class DatasetQueryApi(Resource):
+    @api.doc("get_dataset_queries")
+    @api.doc(description="Get dataset query history")
+    @api.doc(params={"dataset_id": "Dataset ID"})
+    @api.response(200, "Query history retrieved successfully", dataset_query_detail_fields)
     @setup_required
     @login_required
     @account_initialization_required
@@ -385,7 +457,11 @@ class DatasetQueryApi(Resource):
         return response, 200
 
 
+@console_ns.route("/datasets/indexing-estimate")
 class DatasetIndexingEstimateApi(Resource):
+    @api.doc("estimate_dataset_indexing")
+    @api.doc(description="Estimate dataset indexing cost")
+    @api.response(200, "Indexing estimate calculated successfully")
     @setup_required
     @login_required
     @account_initialization_required
@@ -433,10 +509,12 @@ class DatasetIndexingEstimateApi(Resource):
             notion_info_list = args["info_list"]["notion_info_list"]
             for notion_info in notion_info_list:
                 workspace_id = notion_info["workspace_id"]
+                credential_id = notion_info.get("credential_id")
                 for page in notion_info["pages"]:
                     extract_setting = ExtractSetting(
                         datasource_type=DatasourceType.NOTION.value,
                         notion_info={
+                            "credential_id": credential_id,
                             "notion_workspace_id": workspace_id,
                             "notion_obj_id": page["page_id"],
                             "notion_page_type": page["type"],
@@ -486,7 +564,12 @@ class DatasetIndexingEstimateApi(Resource):
         return response.model_dump(), 200
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/related-apps")
 class DatasetRelatedAppListApi(Resource):
+    @api.doc("get_dataset_related_apps")
+    @api.doc(description="Get applications related to dataset")
+    @api.doc(params={"dataset_id": "Dataset ID"})
+    @api.response(200, "Related apps retrieved successfully", related_app_list)
     @setup_required
     @login_required
     @account_initialization_required
@@ -513,7 +596,12 @@ class DatasetRelatedAppListApi(Resource):
         return {"data": related_apps, "total": len(related_apps)}, 200
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/indexing-status")
 class DatasetIndexingStatusApi(Resource):
+    @api.doc("get_dataset_indexing_status")
+    @api.doc(description="Get dataset indexing status")
+    @api.doc(params={"dataset_id": "Dataset ID"})
+    @api.response(200, "Indexing status retrieved successfully")
     @setup_required
     @login_required
     @account_initialization_required
@@ -560,11 +648,15 @@ class DatasetIndexingStatusApi(Resource):
         return data, 200
 
 
+@console_ns.route("/datasets/api-keys")
 class DatasetApiKeyApi(Resource):
     max_keys = 10
     token_prefix = "dataset-"
     resource_type = "dataset"
 
+    @api.doc("get_dataset_api_keys")
+    @api.doc(description="Get dataset API keys")
+    @api.response(200, "API keys retrieved successfully", api_key_list)
     @setup_required
     @login_required
     @account_initialization_required
@@ -593,7 +685,7 @@ class DatasetApiKeyApi(Resource):
         )
 
         if current_key_count >= self.max_keys:
-            flask_restx.abort(
+            api.abort(
                 400,
                 message=f"Cannot create more than {self.max_keys} API keys for this resource type.",
                 code="max_keys_exceeded",
@@ -609,9 +701,14 @@ class DatasetApiKeyApi(Resource):
         return api_token, 200
 
 
+@console_ns.route("/datasets/api-keys/<uuid:api_key_id>")
 class DatasetApiDeleteApi(Resource):
     resource_type = "dataset"
 
+    @api.doc("delete_dataset_api_key")
+    @api.doc(description="Delete dataset API key")
+    @api.doc(params={"api_key_id": "API key ID"})
+    @api.response(204, "API key deleted successfully")
     @setup_required
     @login_required
     @account_initialization_required
@@ -633,7 +730,7 @@ class DatasetApiDeleteApi(Resource):
         )
 
         if key is None:
-            flask_restx.abort(404, message="API key not found")
+            api.abort(404, message="API key not found")
 
         db.session.query(ApiToken).where(ApiToken.id == api_key_id).delete()
         db.session.commit()
@@ -641,7 +738,24 @@ class DatasetApiDeleteApi(Resource):
         return {"result": "success"}, 204
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/api-keys/<string:status>")
+class DatasetEnableApiApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self, dataset_id, status):
+        dataset_id_str = str(dataset_id)
+
+        DatasetService.update_dataset_api_status(dataset_id_str, status == "enable")
+
+        return {"result": "success"}, 200
+
+
+@console_ns.route("/datasets/api-base-info")
 class DatasetApiBaseUrlApi(Resource):
+    @api.doc("get_dataset_api_base_info")
+    @api.doc(description="Get dataset API base information")
+    @api.response(200, "API base info retrieved successfully")
     @setup_required
     @login_required
     @account_initialization_required
@@ -649,7 +763,11 @@ class DatasetApiBaseUrlApi(Resource):
         return {"api_base_url": (dify_config.SERVICE_API_URL or request.host_url.rstrip("/")) + "/v1"}
 
 
+@console_ns.route("/datasets/retrieval-setting")
 class DatasetRetrievalSettingApi(Resource):
+    @api.doc("get_dataset_retrieval_setting")
+    @api.doc(description="Get dataset retrieval settings")
+    @api.response(200, "Retrieval settings retrieved successfully")
     @setup_required
     @login_required
     @account_initialization_required
@@ -661,7 +779,6 @@ class DatasetRetrievalSettingApi(Resource):
                 | VectorType.TIDB_VECTOR
                 | VectorType.CHROMA
                 | VectorType.PGVECTO_RS
-                | VectorType.BAIDU
                 | VectorType.VIKINGDB
                 | VectorType.UPSTASH
             ):
@@ -688,6 +805,7 @@ class DatasetRetrievalSettingApi(Resource):
                 | VectorType.TENCENT
                 | VectorType.MATRIXONE
                 | VectorType.CLICKZETTA
+                | VectorType.BAIDU
             ):
                 return {
                     "retrieval_method": [
@@ -700,7 +818,12 @@ class DatasetRetrievalSettingApi(Resource):
                 raise ValueError(f"Unsupported vector db type {vector_type}.")
 
 
+@console_ns.route("/datasets/retrieval-setting/<string:vector_type>")
 class DatasetRetrievalSettingMockApi(Resource):
+    @api.doc("get_dataset_retrieval_setting_mock")
+    @api.doc(description="Get mock dataset retrieval settings by vector type")
+    @api.doc(params={"vector_type": "Vector store type"})
+    @api.response(200, "Mock retrieval settings retrieved successfully")
     @setup_required
     @login_required
     @account_initialization_required
@@ -712,7 +835,6 @@ class DatasetRetrievalSettingMockApi(Resource):
                 | VectorType.TIDB_VECTOR
                 | VectorType.CHROMA
                 | VectorType.PGVECTO_RS
-                | VectorType.BAIDU
                 | VectorType.VIKINGDB
                 | VectorType.UPSTASH
             ):
@@ -737,6 +859,7 @@ class DatasetRetrievalSettingMockApi(Resource):
                 | VectorType.HUAWEI_CLOUD
                 | VectorType.MATRIXONE
                 | VectorType.CLICKZETTA
+                | VectorType.BAIDU
             ):
                 return {
                     "retrieval_method": [
@@ -749,7 +872,13 @@ class DatasetRetrievalSettingMockApi(Resource):
                 raise ValueError(f"Unsupported vector db type {vector_type}.")
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/error-docs")
 class DatasetErrorDocs(Resource):
+    @api.doc("get_dataset_error_docs")
+    @api.doc(description="Get dataset error documents")
+    @api.doc(params={"dataset_id": "Dataset ID"})
+    @api.response(200, "Error documents retrieved successfully")
+    @api.response(404, "Dataset not found")
     @setup_required
     @login_required
     @account_initialization_required
@@ -763,7 +892,14 @@ class DatasetErrorDocs(Resource):
         return {"data": [marshal(item, document_status_fields) for item in results], "total": len(results)}, 200
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/permission-part-users")
 class DatasetPermissionUserListApi(Resource):
+    @api.doc("get_dataset_permission_users")
+    @api.doc(description="Get dataset permission user list")
+    @api.doc(params={"dataset_id": "Dataset ID"})
+    @api.response(200, "Permission users retrieved successfully")
+    @api.response(404, "Dataset not found")
+    @api.response(403, "Permission denied")
     @setup_required
     @login_required
     @account_initialization_required
@@ -784,7 +920,13 @@ class DatasetPermissionUserListApi(Resource):
         }, 200
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/auto-disable-logs")
 class DatasetAutoDisableLogApi(Resource):
+    @api.doc("get_dataset_auto_disable_logs")
+    @api.doc(description="Get dataset auto disable logs")
+    @api.doc(params={"dataset_id": "Dataset ID"})
+    @api.response(200, "Auto disable logs retrieved successfully")
+    @api.response(404, "Dataset not found")
     @setup_required
     @login_required
     @account_initialization_required
@@ -794,20 +936,3 @@ class DatasetAutoDisableLogApi(Resource):
         if dataset is None:
             raise NotFound("Dataset not found.")
         return DatasetService.get_dataset_auto_disable_logs(dataset_id_str), 200
-
-
-api.add_resource(DatasetListApi, "/datasets")
-api.add_resource(DatasetApi, "/datasets/<uuid:dataset_id>")
-api.add_resource(DatasetUseCheckApi, "/datasets/<uuid:dataset_id>/use-check")
-api.add_resource(DatasetQueryApi, "/datasets/<uuid:dataset_id>/queries")
-api.add_resource(DatasetErrorDocs, "/datasets/<uuid:dataset_id>/error-docs")
-api.add_resource(DatasetIndexingEstimateApi, "/datasets/indexing-estimate")
-api.add_resource(DatasetRelatedAppListApi, "/datasets/<uuid:dataset_id>/related-apps")
-api.add_resource(DatasetIndexingStatusApi, "/datasets/<uuid:dataset_id>/indexing-status")
-api.add_resource(DatasetApiKeyApi, "/datasets/api-keys")
-api.add_resource(DatasetApiDeleteApi, "/datasets/api-keys/<uuid:api_key_id>")
-api.add_resource(DatasetApiBaseUrlApi, "/datasets/api-base-info")
-api.add_resource(DatasetRetrievalSettingApi, "/datasets/retrieval-setting")
-api.add_resource(DatasetRetrievalSettingMockApi, "/datasets/retrieval-setting/<string:vector_type>")
-api.add_resource(DatasetPermissionUserListApi, "/datasets/<uuid:dataset_id>/permission-part-users")
-api.add_resource(DatasetAutoDisableLogApi, "/datasets/<uuid:dataset_id>/auto-disable-logs")

api/controllers/console/datasets/datasets_document.py

@@ -1,16 +1,18 @@
+import json
 import logging
 from argparse import ArgumentTypeError
 from collections.abc import Sequence
 from typing import Literal, cast
 
+import sqlalchemy as sa
 from flask import request
 from flask_login import current_user
-from flask_restx import Resource, marshal, marshal_with, reqparse
+from flask_restx import Resource, fields, marshal, marshal_with, reqparse
 from sqlalchemy import asc, desc, select
 from werkzeug.exceptions import Forbidden, NotFound
 
 import services
-from controllers.console import api
+from controllers.console import api, console_ns
 from controllers.console.app.error import (
     ProviderModelCurrentlyNotSupportError,
     ProviderNotInitializeError,
@@ -53,6 +55,8 @@ from fields.document_fields import (
 from libs.datetime_utils import naive_utc_now
 from libs.login import login_required
 from models import Dataset, DatasetProcessRule, Document, DocumentSegment, UploadFile
+from models.account import Account
+from models.dataset import DocumentPipelineExecutionLog
 from services.dataset_service import DatasetService, DocumentService
 from services.entities.knowledge_entities.knowledge_entities import KnowledgeConfig
 
@@ -98,7 +102,12 @@ class DocumentResource(Resource):
         return documents
 
 
+@console_ns.route("/datasets/process-rule")
 class GetProcessRuleApi(Resource):
+    @api.doc("get_process_rule")
+    @api.doc(description="Get dataset document processing rules")
+    @api.doc(params={"document_id": "Document ID (optional)"})
+    @api.response(200, "Process rules retrieved successfully")
     @setup_required
     @login_required
     @account_initialization_required
@@ -140,7 +149,21 @@ class GetProcessRuleApi(Resource):
         return {"mode": mode, "rules": rules, "limits": limits}
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/documents")
 class DatasetDocumentListApi(Resource):
+    @api.doc("get_dataset_documents")
+    @api.doc(description="Get documents in a dataset")
+    @api.doc(
+        params={
+            "dataset_id": "Dataset ID",
+            "page": "Page number (default: 1)",
+            "limit": "Number of items per page (default: 20)",
+            "keyword": "Search keyword",
+            "sort": "Sort order (default: -created_at)",
+            "fetch": "Fetch full details (default: false)",
+        }
+    )
+    @api.response(200, "Documents retrieved successfully")
     @setup_required
     @login_required
     @account_initialization_required
@@ -190,13 +213,13 @@ class DatasetDocumentListApi(Resource):
 
         if sort == "hit_count":
             sub_query = (
-                db.select(DocumentSegment.document_id, db.func.sum(DocumentSegment.hit_count).label("total_hit_count"))
+                sa.select(DocumentSegment.document_id, sa.func.sum(DocumentSegment.hit_count).label("total_hit_count"))
                 .group_by(DocumentSegment.document_id)
                 .subquery()
             )
 
             query = query.outerjoin(sub_query, sub_query.c.document_id == Document.id).order_by(
-                sort_logic(db.func.coalesce(sub_query.c.total_hit_count, 0)),
+                sort_logic(sa.func.coalesce(sub_query.c.total_hit_count, 0)),
                 sort_logic(Document.position),
             )
         elif sort == "created_at":
@@ -324,7 +347,23 @@ class DatasetDocumentListApi(Resource):
         return {"result": "success"}, 204
 
 
+@console_ns.route("/datasets/init")
 class DatasetInitApi(Resource):
+    @api.doc("init_dataset")
+    @api.doc(description="Initialize dataset with documents")
+    @api.expect(
+        api.model(
+            "DatasetInitRequest",
+            {
+                "upload_file_id": fields.String(required=True, description="Upload file ID"),
+                "indexing_technique": fields.String(description="Indexing technique"),
+                "process_rule": fields.Raw(description="Processing rules"),
+                "data_source": fields.Raw(description="Data source configuration"),
+            },
+        )
+    )
+    @api.response(201, "Dataset initialized successfully", dataset_and_document_fields)
+    @api.response(400, "Invalid request parameters")
     @setup_required
     @login_required
     @account_initialization_required
@@ -380,7 +419,9 @@ class DatasetInitApi(Resource):
 
         try:
             dataset, documents, batch = DocumentService.save_document_without_dataset_id(
-                tenant_id=current_user.current_tenant_id, knowledge_config=knowledge_config, account=current_user
+                tenant_id=current_user.current_tenant_id,
+                knowledge_config=knowledge_config,
+                account=cast(Account, current_user),
             )
         except ProviderTokenNotInitError as ex:
             raise ProviderNotInitializeError(ex.description)
@@ -394,7 +435,14 @@ class DatasetInitApi(Resource):
         return response
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/indexing-estimate")
 class DocumentIndexingEstimateApi(DocumentResource):
+    @api.doc("estimate_document_indexing")
+    @api.doc(description="Estimate document indexing cost")
+    @api.doc(params={"dataset_id": "Dataset ID", "document_id": "Document ID"})
+    @api.response(200, "Indexing estimate calculated successfully")
+    @api.response(404, "Document not found")
+    @api.response(400, "Document already finished")
     @setup_required
     @login_required
     @account_initialization_required
@@ -407,7 +455,7 @@ class DocumentIndexingEstimateApi(DocumentResource):
             raise DocumentAlreadyFinishedError()
 
         data_process_rule = document.dataset_process_rule
-        data_process_rule_dict = data_process_rule.to_dict()
+        data_process_rule_dict = data_process_rule.to_dict() if data_process_rule else {}
 
         response = {"tokens": 0, "total_price": 0, "currency": "USD", "total_segments": 0, "preview": []}
 
@@ -457,6 +505,7 @@ class DocumentIndexingEstimateApi(DocumentResource):
         return response, 200
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/batch/<string:batch>/indexing-estimate")
 class DocumentBatchIndexingEstimateApi(DocumentResource):
     @setup_required
     @login_required
@@ -468,7 +517,7 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
         if not documents:
             return {"tokens": 0, "total_price": 0, "currency": "USD", "total_segments": 0, "preview": []}, 200
         data_process_rule = documents[0].dataset_process_rule
-        data_process_rule_dict = data_process_rule.to_dict()
+        data_process_rule_dict = data_process_rule.to_dict() if data_process_rule else {}
         extract_settings = []
         for document in documents:
             if document.indexing_status in {"completed", "error"}:
@@ -499,6 +548,7 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
                 extract_setting = ExtractSetting(
                     datasource_type=DatasourceType.NOTION.value,
                     notion_info={
+                        "credential_id": data_source_info["credential_id"],
                         "notion_workspace_id": data_source_info["notion_workspace_id"],
                         "notion_obj_id": data_source_info["notion_page_id"],
                         "notion_page_type": data_source_info["type"],
@@ -549,6 +599,7 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
                 raise IndexingEstimateError(str(e))
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/batch/<string:batch>/indexing-status")
 class DocumentBatchIndexingStatusApi(DocumentResource):
     @setup_required
     @login_required
@@ -593,7 +644,13 @@ class DocumentBatchIndexingStatusApi(DocumentResource):
         return data
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/indexing-status")
 class DocumentIndexingStatusApi(DocumentResource):
+    @api.doc("get_document_indexing_status")
+    @api.doc(description="Get document indexing status")
+    @api.doc(params={"dataset_id": "Dataset ID", "document_id": "Document ID"})
+    @api.response(200, "Indexing status retrieved successfully")
+    @api.response(404, "Document not found")
     @setup_required
     @login_required
     @account_initialization_required
@@ -635,9 +692,21 @@ class DocumentIndexingStatusApi(DocumentResource):
         return marshal(document_dict, document_status_fields)
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>")
 class DocumentApi(DocumentResource):
     METADATA_CHOICES = {"all", "only", "without"}
 
+    @api.doc("get_document")
+    @api.doc(description="Get document details")
+    @api.doc(
+        params={
+            "dataset_id": "Dataset ID",
+            "document_id": "Document ID",
+            "metadata": "Metadata inclusion (all/only/without)",
+        }
+    )
+    @api.response(200, "Document retrieved successfully")
+    @api.response(404, "Document not found")
     @setup_required
     @login_required
     @account_initialization_required
@@ -654,7 +723,7 @@ class DocumentApi(DocumentResource):
             response = {"id": document.id, "doc_type": document.doc_type, "doc_metadata": document.doc_metadata_details}
         elif metadata == "without":
             dataset_process_rules = DatasetService.get_process_rules(dataset_id)
-            document_process_rules = document.dataset_process_rule.to_dict()
+            document_process_rules = document.dataset_process_rule.to_dict() if document.dataset_process_rule else {}
             data_source_info = document.data_source_detail_dict
             response = {
                 "id": document.id,
@@ -687,7 +756,7 @@ class DocumentApi(DocumentResource):
             }
         else:
             dataset_process_rules = DatasetService.get_process_rules(dataset_id)
-            document_process_rules = document.dataset_process_rule.to_dict()
+            document_process_rules = document.dataset_process_rule.to_dict() if document.dataset_process_rule else {}
             data_source_info = document.data_source_detail_dict
             response = {
                 "id": document.id,
@@ -746,7 +815,16 @@ class DocumentApi(DocumentResource):
         return {"result": "success"}, 204
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/processing/<string:action>")
 class DocumentProcessingApi(DocumentResource):
+    @api.doc("update_document_processing")
+    @api.doc(description="Update document processing status (pause/resume)")
+    @api.doc(
+        params={"dataset_id": "Dataset ID", "document_id": "Document ID", "action": "Action to perform (pause/resume)"}
+    )
+    @api.response(200, "Processing status updated successfully")
+    @api.response(404, "Document not found")
+    @api.response(400, "Invalid action")
     @setup_required
     @login_required
     @account_initialization_required
@@ -781,7 +859,23 @@ class DocumentProcessingApi(DocumentResource):
         return {"result": "success"}, 200
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/metadata")
 class DocumentMetadataApi(DocumentResource):
+    @api.doc("update_document_metadata")
+    @api.doc(description="Update document metadata")
+    @api.doc(params={"dataset_id": "Dataset ID", "document_id": "Document ID"})
+    @api.expect(
+        api.model(
+            "UpdateDocumentMetadataRequest",
+            {
+                "doc_type": fields.String(description="Document type"),
+                "doc_metadata": fields.Raw(description="Document metadata"),
+            },
+        )
+    )
+    @api.response(200, "Document metadata updated successfully")
+    @api.response(404, "Document not found")
+    @api.response(403, "Permission denied")
     @setup_required
     @login_required
     @account_initialization_required
@@ -825,6 +919,7 @@ class DocumentMetadataApi(DocumentResource):
         return {"result": "success", "message": "Document metadata updated."}, 200
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/documents/status/<string:action>/batch")
 class DocumentStatusApi(DocumentResource):
     @setup_required
     @login_required
@@ -861,6 +956,7 @@ class DocumentStatusApi(DocumentResource):
         return {"result": "success"}, 200
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/processing/pause")
 class DocumentPauseApi(DocumentResource):
     @setup_required
     @login_required
@@ -894,6 +990,7 @@ class DocumentPauseApi(DocumentResource):
         return {"result": "success"}, 204
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/processing/resume")
 class DocumentRecoverApi(DocumentResource):
     @setup_required
     @login_required
@@ -924,6 +1021,7 @@ class DocumentRecoverApi(DocumentResource):
         return {"result": "success"}, 204
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/retry")
 class DocumentRetryApi(DocumentResource):
     @setup_required
     @login_required
@@ -967,6 +1065,7 @@ class DocumentRetryApi(DocumentResource):
         return {"result": "success"}, 204
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/rename")
 class DocumentRenameApi(DocumentResource):
     @setup_required
     @login_required
@@ -977,7 +1076,9 @@ class DocumentRenameApi(DocumentResource):
         if not current_user.is_dataset_editor:
             raise Forbidden()
         dataset = DatasetService.get_dataset(dataset_id)
-        DatasetService.check_dataset_operator_permission(current_user, dataset)
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        DatasetService.check_dataset_operator_permission(cast(Account, current_user), dataset)
         parser = reqparse.RequestParser()
         parser.add_argument("name", type=str, required=True, nullable=False, location="json")
         args = parser.parse_args()
@@ -990,6 +1091,7 @@ class DocumentRenameApi(DocumentResource):
         return document
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/website-sync")
 class WebsiteDocumentSyncApi(DocumentResource):
     @setup_required
     @login_required
@@ -1017,24 +1119,37 @@ class WebsiteDocumentSyncApi(DocumentResource):
         return {"result": "success"}, 200
 
 
-api.add_resource(GetProcessRuleApi, "/datasets/process-rule")
-api.add_resource(DatasetDocumentListApi, "/datasets/<uuid:dataset_id>/documents")
-api.add_resource(DatasetInitApi, "/datasets/init")
-api.add_resource(
-    DocumentIndexingEstimateApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/indexing-estimate"
-)
-api.add_resource(DocumentBatchIndexingEstimateApi, "/datasets/<uuid:dataset_id>/batch/<string:batch>/indexing-estimate")
-api.add_resource(DocumentBatchIndexingStatusApi, "/datasets/<uuid:dataset_id>/batch/<string:batch>/indexing-status")
-api.add_resource(DocumentIndexingStatusApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/indexing-status")
-api.add_resource(DocumentApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>")
-api.add_resource(
-    DocumentProcessingApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/processing/<string:action>"
-)
-api.add_resource(DocumentMetadataApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/metadata")
-api.add_resource(DocumentStatusApi, "/datasets/<uuid:dataset_id>/documents/status/<string:action>/batch")
-api.add_resource(DocumentPauseApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/processing/pause")
-api.add_resource(DocumentRecoverApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/processing/resume")
-api.add_resource(DocumentRetryApi, "/datasets/<uuid:dataset_id>/retry")
-api.add_resource(DocumentRenameApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/rename")
+@console_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/pipeline-execution-log")
+class DocumentPipelineExecutionLogApi(DocumentResource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id, document_id):
+        dataset_id = str(dataset_id)
+        document_id = str(document_id)
 
-api.add_resource(WebsiteDocumentSyncApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/website-sync")
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        document = DocumentService.get_document(dataset.id, document_id)
+        if not document:
+            raise NotFound("Document not found.")
+        log = (
+            db.session.query(DocumentPipelineExecutionLog)
+            .filter_by(document_id=document_id)
+            .order_by(DocumentPipelineExecutionLog.created_at.desc())
+            .first()
+        )
+        if not log:
+            return {
+                "datasource_info": None,
+                "datasource_type": None,
+                "input_data": None,
+                "datasource_node_id": None,
+            }, 200
+        return {
+            "datasource_info": json.loads(log.datasource_info),
+            "datasource_type": log.datasource_type,
+            "input_data": log.input_data,
+            "datasource_node_id": log.datasource_node_id,
+        }, 200

api/controllers/console/datasets/datasets_segments.py

@@ -7,7 +7,7 @@ from sqlalchemy import select
 from werkzeug.exceptions import Forbidden, NotFound
 
 import services
-from controllers.console import api
+from controllers.console import console_ns
 from controllers.console.app.error import ProviderNotInitializeError
 from controllers.console.datasets.error import (
     ChildChunkDeleteIndexError,
@@ -37,6 +37,7 @@ from services.errors.chunk import ChildChunkIndexingError as ChildChunkIndexingS
 from tasks.batch_create_segment_to_index_task import batch_create_segment_to_index_task
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments")
 class DatasetDocumentSegmentListApi(Resource):
     @setup_required
     @login_required
@@ -139,6 +140,7 @@ class DatasetDocumentSegmentListApi(Resource):
         return {"result": "success"}, 204
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segment/<string:action>")
 class DatasetDocumentSegmentApi(Resource):
     @setup_required
     @login_required
@@ -193,6 +195,7 @@ class DatasetDocumentSegmentApi(Resource):
         return {"result": "success"}, 200
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segment")
 class DatasetDocumentSegmentAddApi(Resource):
     @setup_required
     @login_required
@@ -244,6 +247,7 @@ class DatasetDocumentSegmentAddApi(Resource):
         return {"data": marshal(segment, segment_fields), "doc_form": document.doc_form}, 200
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/<uuid:segment_id>")
 class DatasetDocumentSegmentUpdateApi(Resource):
     @setup_required
     @login_required
@@ -345,6 +349,10 @@ class DatasetDocumentSegmentUpdateApi(Resource):
         return {"result": "success"}, 204
 
 
+@console_ns.route(
+    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/batch_import",
+    "/datasets/batch_import_status/<uuid:job_id>",
+)
 class DatasetDocumentSegmentBatchImportApi(Resource):
     @setup_required
     @login_required
@@ -384,7 +392,12 @@ class DatasetDocumentSegmentBatchImportApi(Resource):
             # send batch add segments task
             redis_client.setnx(indexing_cache_key, "waiting")
             batch_create_segment_to_index_task.delay(
-                str(job_id), upload_file_id, dataset_id, document_id, current_user.current_tenant_id, current_user.id
+                str(job_id),
+                upload_file_id,
+                dataset_id,
+                document_id,
+                current_user.current_tenant_id,
+                current_user.id,
             )
         except Exception as e:
             return {"error": str(e)}, 500
@@ -393,7 +406,9 @@ class DatasetDocumentSegmentBatchImportApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def get(self, job_id):
+    def get(self, job_id=None, dataset_id=None, document_id=None):
+        if job_id is None:
+            raise NotFound("The job does not exist.")
         job_id = str(job_id)
         indexing_cache_key = f"segment_batch_import_{job_id}"
         cache_result = redis_client.get(indexing_cache_key)
@@ -403,6 +418,7 @@ class DatasetDocumentSegmentBatchImportApi(Resource):
         return {"job_id": job_id, "job_status": cache_result.decode()}, 200
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/<uuid:segment_id>/child_chunks")
 class ChildChunkAddApi(Resource):
     @setup_required
     @login_required
@@ -457,7 +473,8 @@ class ChildChunkAddApi(Resource):
         parser.add_argument("content", type=str, required=True, nullable=False, location="json")
         args = parser.parse_args()
         try:
-            child_chunk = SegmentService.create_child_chunk(args.get("content"), segment, document, dataset)
+            content = args["content"]
+            child_chunk = SegmentService.create_child_chunk(content, segment, document, dataset)
         except ChildChunkIndexingServiceError as e:
             raise ChildChunkIndexingError(str(e))
         return {"data": marshal(child_chunk, child_chunk_fields)}, 200
@@ -546,13 +563,17 @@ class ChildChunkAddApi(Resource):
         parser.add_argument("chunks", type=list, required=True, nullable=False, location="json")
         args = parser.parse_args()
         try:
-            chunks = [ChildChunkUpdateArgs(**chunk) for chunk in args.get("chunks")]
+            chunks_data = args["chunks"]
+            chunks = [ChildChunkUpdateArgs(**chunk) for chunk in chunks_data]
             child_chunks = SegmentService.update_child_chunks(chunks, segment, document, dataset)
         except ChildChunkIndexingServiceError as e:
             raise ChildChunkIndexingError(str(e))
         return {"data": marshal(child_chunks, child_chunk_fields)}, 200
 
 
+@console_ns.route(
+    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/<uuid:segment_id>/child_chunks/<uuid:child_chunk_id>"
+)
 class ChildChunkUpdateApi(Resource):
     @setup_required
     @login_required
@@ -660,33 +681,8 @@ class ChildChunkUpdateApi(Resource):
         parser.add_argument("content", type=str, required=True, nullable=False, location="json")
         args = parser.parse_args()
         try:
-            child_chunk = SegmentService.update_child_chunk(
-                args.get("content"), child_chunk, segment, document, dataset
-            )
+            content = args["content"]
+            child_chunk = SegmentService.update_child_chunk(content, child_chunk, segment, document, dataset)
         except ChildChunkIndexingServiceError as e:
             raise ChildChunkIndexingError(str(e))
         return {"data": marshal(child_chunk, child_chunk_fields)}, 200
-
-
-api.add_resource(DatasetDocumentSegmentListApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments")
-api.add_resource(
-    DatasetDocumentSegmentApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segment/<string:action>"
-)
-api.add_resource(DatasetDocumentSegmentAddApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segment")
-api.add_resource(
-    DatasetDocumentSegmentUpdateApi,
-    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/<uuid:segment_id>",
-)
-api.add_resource(
-    DatasetDocumentSegmentBatchImportApi,
-    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/batch_import",
-    "/datasets/batch_import_status/<uuid:job_id>",
-)
-api.add_resource(
-    ChildChunkAddApi,
-    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/<uuid:segment_id>/child_chunks",
-)
-api.add_resource(
-    ChildChunkUpdateApi,
-    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/<uuid:segment_id>/child_chunks/<uuid:child_chunk_id>",
-)

api/controllers/console/datasets/error.py

@@ -71,3 +71,9 @@ class ChildChunkDeleteIndexError(BaseHTTPException):
     error_code = "child_chunk_delete_index_error"
     description = "Delete child chunk index failed: {message}"
     code = 500
+
+
+class PipelineNotFoundError(BaseHTTPException):
+    error_code = "pipeline_not_found"
+    description = "Pipeline not found."
+    code = 404

api/controllers/console/datasets/external.py

@@ -1,27 +1,41 @@
+from typing import cast
+
 from flask import request
 from flask_login import current_user
-from flask_restx import Resource, marshal, reqparse
+from flask_restx import Resource, fields, marshal, reqparse
 from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 
 import services
-from controllers.console import api
+from controllers.console import api, console_ns
 from controllers.console.datasets.error import DatasetNameDuplicateError
 from controllers.console.wraps import account_initialization_required, setup_required
 from fields.dataset_fields import dataset_detail_fields
 from libs.login import login_required
+from models.account import Account
 from services.dataset_service import DatasetService
 from services.external_knowledge_service import ExternalDatasetService
 from services.hit_testing_service import HitTestingService
 from services.knowledge_service import ExternalDatasetTestService
 
 
-def _validate_name(name):
+def _validate_name(name: str) -> str:
     if not name or len(name) < 1 or len(name) > 100:
         raise ValueError("Name must be between 1 to 100 characters.")
     return name
 
 
+@console_ns.route("/datasets/external-knowledge-api")
 class ExternalApiTemplateListApi(Resource):
+    @api.doc("get_external_api_templates")
+    @api.doc(description="Get external knowledge API templates")
+    @api.doc(
+        params={
+            "page": "Page number (default: 1)",
+            "limit": "Number of items per page (default: 20)",
+            "keyword": "Search keyword",
+        }
+    )
+    @api.response(200, "External API templates retrieved successfully")
     @setup_required
     @login_required
     @account_initialization_required
@@ -79,7 +93,13 @@ class ExternalApiTemplateListApi(Resource):
         return external_knowledge_api.to_dict(), 201
 
 
+@console_ns.route("/datasets/external-knowledge-api/<uuid:external_knowledge_api_id>")
 class ExternalApiTemplateApi(Resource):
+    @api.doc("get_external_api_template")
+    @api.doc(description="Get external knowledge API template details")
+    @api.doc(params={"external_knowledge_api_id": "External knowledge API ID"})
+    @api.response(200, "External API template retrieved successfully")
+    @api.response(404, "Template not found")
     @setup_required
     @login_required
     @account_initialization_required
@@ -131,14 +151,19 @@ class ExternalApiTemplateApi(Resource):
         external_knowledge_api_id = str(external_knowledge_api_id)
 
         # The role of the current user in the ta table must be admin, owner, or editor
-        if not current_user.is_editor or current_user.is_dataset_operator:
+        if not (current_user.is_editor or current_user.is_dataset_operator):
             raise Forbidden()
 
         ExternalDatasetService.delete_external_knowledge_api(current_user.current_tenant_id, external_knowledge_api_id)
         return {"result": "success"}, 204
 
 
+@console_ns.route("/datasets/external-knowledge-api/<uuid:external_knowledge_api_id>/use-check")
 class ExternalApiUseCheckApi(Resource):
+    @api.doc("check_external_api_usage")
+    @api.doc(description="Check if external knowledge API is being used")
+    @api.doc(params={"external_knowledge_api_id": "External knowledge API ID"})
+    @api.response(200, "Usage check completed successfully")
     @setup_required
     @login_required
     @account_initialization_required
@@ -151,7 +176,24 @@ class ExternalApiUseCheckApi(Resource):
         return {"is_using": external_knowledge_api_is_using, "count": count}, 200
 
 
+@console_ns.route("/datasets/external")
 class ExternalDatasetCreateApi(Resource):
+    @api.doc("create_external_dataset")
+    @api.doc(description="Create external knowledge dataset")
+    @api.expect(
+        api.model(
+            "CreateExternalDatasetRequest",
+            {
+                "external_knowledge_api_id": fields.String(required=True, description="External knowledge API ID"),
+                "external_knowledge_id": fields.String(required=True, description="External knowledge ID"),
+                "name": fields.String(required=True, description="Dataset name"),
+                "description": fields.String(description="Dataset description"),
+            },
+        )
+    )
+    @api.response(201, "External dataset created successfully", dataset_detail_fields)
+    @api.response(400, "Invalid parameters")
+    @api.response(403, "Permission denied")
     @setup_required
     @login_required
     @account_initialization_required
@@ -191,7 +233,24 @@ class ExternalDatasetCreateApi(Resource):
         return marshal(dataset, dataset_detail_fields), 201
 
 
+@console_ns.route("/datasets/<uuid:dataset_id>/external-hit-testing")
 class ExternalKnowledgeHitTestingApi(Resource):
+    @api.doc("test_external_knowledge_retrieval")
+    @api.doc(description="Test external knowledge retrieval for dataset")
+    @api.doc(params={"dataset_id": "Dataset ID"})
+    @api.expect(
+        api.model(
+            "ExternalHitTestingRequest",
+            {
+                "query": fields.String(required=True, description="Query text for testing"),
+                "retrieval_model": fields.Raw(description="Retrieval model configuration"),
+                "external_retrieval_model": fields.Raw(description="External retrieval model configuration"),
+            },
+        )
+    )
+    @api.response(200, "External hit testing completed successfully")
+    @api.response(404, "Dataset not found")
+    @api.response(400, "Invalid parameters")
     @setup_required
     @login_required
     @account_initialization_required
@@ -218,7 +277,7 @@ class ExternalKnowledgeHitTestingApi(Resource):
             response = HitTestingService.external_retrieve(
                 dataset=dataset,
                 query=args["query"],
-                account=current_user,
+                account=cast(Account, current_user),
                 external_retrieval_model=args["external_retrieval_model"],
                 metadata_filtering_conditions=args["metadata_filtering_conditions"],
             )
@@ -228,8 +287,22 @@ class ExternalKnowledgeHitTestingApi(Resource):
             raise InternalServerError(str(e))
 
 
+@console_ns.route("/test/retrieval")
 class BedrockRetrievalApi(Resource):
     # this api is only for internal testing
+    @api.doc("bedrock_retrieval_test")
+    @api.doc(description="Bedrock retrieval test (internal use only)")
+    @api.expect(
+        api.model(
+            "BedrockRetrievalTestRequest",
+            {
+                "retrieval_setting": fields.Raw(required=True, description="Retrieval settings"),
+                "query": fields.String(required=True, description="Query text"),
+                "knowledge_id": fields.String(required=True, description="Knowledge ID"),
+            },
+        )
+    )
+    @api.response(200, "Bedrock retrieval test completed")
     def post(self):
         parser = reqparse.RequestParser()
         parser.add_argument("retrieval_setting", nullable=False, required=True, type=dict, location="json")
@@ -247,12 +320,3 @@ class BedrockRetrievalApi(Resource):
             args["retrieval_setting"], args["query"], args["knowledge_id"]
         )
         return result, 200
-
-
-api.add_resource(ExternalKnowledgeHitTestingApi, "/datasets/<uuid:dataset_id>/external-hit-testing")
-api.add_resource(ExternalDatasetCreateApi, "/datasets/external")
-api.add_resource(ExternalApiTemplateListApi, "/datasets/external-knowledge-api")
-api.add_resource(ExternalApiTemplateApi, "/datasets/external-knowledge-api/<uuid:external_knowledge_api_id>")
-api.add_resource(ExternalApiUseCheckApi, "/datasets/external-knowledge-api/<uuid:external_knowledge_api_id>/use-check")
-# this api is only for internal test
-api.add_resource(BedrockRetrievalApi, "/test/retrieval")