| English | 简体中文 | 日本語 |

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval, especially for handling complex, heterogeneous documents.

It adopts a modular architecture that combines multimodal preprocessing, semantic vector indexing, intelligent retrieval, and large language model inference. At its core, WeKnora follows the RAG (Retrieval-Augmented Generation) paradigm, enabling high-quality, context-aware answers by combining relevant document chunks with model reasoning.

Website: https://weknora.weixin.qq.com

v0.2.0 Highlights:

• 🤖 Agent Mode: New ReACT Agent mode that can call built-in tools, MCP tools, and web search, providing comprehensive summary reports through multiple iterations and reflection
• 📚 Multi-Type Knowledge Bases: Support for FAQ and document knowledge base types, with new features including folder import, URL import, tag management, and online entry
• ⚙️ Conversation Strategy: Support for configuring Agent models, normal mode models, retrieval thresholds, and Prompts, with precise control over multi-turn conversation behavior
• 🌐 Web Search: Support for extensible web search engines with built-in DuckDuckGo search engine
• 🔌 MCP Tool Integration: Support for extending Agent capabilities through MCP, with built-in uvx and npx launchers, supporting multiple transport methods
• 🎨 New UI: Optimized conversation interface with Agent mode/normal mode switching, tool call process display, and comprehensive knowledge base management interface upgrade
• ⚡ Infrastructure Upgrade: Introduced MQ async task management, support for automatic database migration, and fast development mode

Important: Starting from v0.1.3, WeKnora includes login authentication functionality to enhance system security. For production deployments, we strongly recommend:

• Deploy WeKnora services in internal/private network environments rather than public internet
• Avoid exposing the service directly to public networks to prevent potential information leakage
• Configure proper firewall rules and access controls for your deployment environment
• Regularly update to the latest version for security patches and improvements

WeKnora employs a modern modular design to build a complete document understanding and retrieval pipeline. The system primarily includes document parsing, vector processing, retrieval engine, and large model inference as core modules, with each component being flexibly configurable and extendable.

• 🤖 Agent Mode: Support for ReACT Agent mode that can use built-in tools to retrieve knowledge bases, MCP tools, and web search tools to access external services, providing comprehensive summary reports through multiple iterations and reflection
• 🔍 Precise Understanding: Structured content extraction from PDFs, Word documents, images and more into unified semantic views
• 🧠 Intelligent Reasoning: Leverages LLMs to understand document context and user intent for accurate Q&A and multi-turn conversations
• 📚 Multi-Type Knowledge Bases: Support for FAQ and document knowledge base types, with folder import, URL import, tag management, and online entry capabilities
• 🔧 Flexible Extension: All components from parsing and embedding to retrieval and generation are decoupled for easy customization
• ⚡ Efficient Retrieval: Hybrid retrieval strategies combining keywords, vectors, and knowledge graphs, with cross-knowledge base retrieval support
• 🌐 Web Search: Support for extensible web search engines with built-in DuckDuckGo search engine
• 🔌 MCP Tool Integration: Support for extending Agent capabilities through MCP, with built-in uvx and npx launchers, supporting multiple transport methods
• ⚙️ Conversation Strategy: Support for configuring Agent models, normal mode models, retrieval thresholds, and Prompts, with precise control over multi-turn conversation behavior
• 🎯 User-Friendly: Intuitive web interface and standardized APIs for zero technical barriers
• 🔒 Secure & Controlled: Support for local deployment and private cloud, ensuring complete data sovereignty

Make sure the following tools are installed on your system:

• Docker
• Docker Compose
• Git

# Clone the main repository
git clone https://github.com/Tencent/WeKnora.git
cd WeKnora

# Copy example env file
cp .env.example .env

# Edit .env and set required values
# All variables are documented in the .env.example comments

Check the images that need to be started in the .env file.

./scripts/start_all.sh

or

make start-all

ollama serve > /dev/null 2>&1 &

• Minimum core services

docker compose up -d

• All features enabled

docker-compose --profile full up -d

• Tracing logs required

docker-compose --profile jaeger up -d

• Neo4j knowledge graph required

docker-compose --profile neo4j up -d

• Minio file storage service required

docker-compose --profile minio up -d

• Multiple options combination

docker-compose --profile neo4j --profile minio up -d

./scripts/start_all.sh --stop
# Or
make stop-all

Once started, services will be available at:

• Web UI: http://localhost
• Backend API: http://localhost:8080
• Jaeger Tracing: http://localhost:16686

WeKnora serves as the core technology framework for the WeChat Dialog Open Platform, providing a more convenient usage approach:

• Zero-code Deployment: Simply upload knowledge to quickly deploy intelligent Q&A services within the WeChat ecosystem, achieving an "ask and answer" experience
• Efficient Question Management: Support for categorized management of high-frequency questions, with rich data tools to ensure accurate, reliable, and easily maintainable answers
• WeChat Ecosystem Integration: Through the WeChat Dialog Open Platform, WeKnora's intelligent Q&A capabilities can be seamlessly integrated into WeChat Official Accounts, Mini Programs, and other WeChat scenarios, enhancing user interaction experiences

git clone https://github.com/Tencent/WeKnora

It is recommended to directly refer to the MCP Configuration Guide for configuration.

Configure the MCP client to connect to the server:

{
  "mcpServers": {
    "weknora": {
      "args": [
        "path/to/WeKnora/mcp-server/run_server.py"
      ],
      "command": "python",
      "env":{
        "WEKNORA_API_KEY":"Enter your WeKnora instance, open developer tools, check the request header x-api-key starting with sk",
        "WEKNORA_BASE_URL":"http(s)://your-weknora-address/api/v1"
      }
    }
  }
}

Run directly using stdio command:

pip install weknora-mcp-server
python -m weknora-mcp-server

To help users quickly configure various models and reduce trial-and-error costs, we've improved the original configuration file initialization method by adding a Web UI interface for model configuration. Before using, please ensure the code is updated to the latest version. The specific steps are as follows: If this is your first time using this project, you can skip steps ①② and go directly to steps ③④.

./scripts/start_all.sh --stop

make clean-db

./scripts/start_all.sh

http://localhost

On your first visit, you will be automatically redirected to the registration/login page. After completing registration, please create a new knowledge base and finish the relevant settings on its configuration page.

Knowledge Base Management	Conversation Settings
Agent Mode Tool Call Process

Knowledge Base Management: Support for creating FAQ and document knowledge base types, with multiple import methods including drag-and-drop, folder import, and URL import. Automatically identifies document structures and extracts core knowledge to establish indexes. Supports tag management and online entry. The system clearly displays processing progress and document status, achieving efficient knowledge base management.

Agent Mode: Support for ReACT Agent mode that can use built-in tools to retrieve knowledge bases, call user-configured MCP tools and web search tools to access external services, providing comprehensive summary reports through multiple iterations and reflection. Supports cross-knowledge base retrieval, allowing selection of multiple knowledge bases for simultaneous retrieval.

Conversation Strategy: Support for configuring Agent models, normal mode models, retrieval thresholds, and online Prompt configuration, with precise control over multi-turn conversation behavior and retrieval execution methods. The conversation input box supports Agent mode/normal mode switching, enabling/disabling web search, and selecting conversation models.

WeKnora supports transforming documents into knowledge graphs, displaying the relationships between different sections of the documents. Once the knowledge graph feature is enabled, the system analyzes and constructs an internal semantic association network that not only helps users understand document content but also provides structured support for indexing and retrieval, enhancing the relevance and breadth of search results.

For detailed configuration, please refer to the Knowledge Graph Configuration Guide.

Please refer to the MCP Configuration Guide for the necessary setup.

Troubleshooting FAQ: Troubleshooting FAQ

Detailed API documentation is available at: API Docs

If you need to frequently modify code, you don't need to rebuild Docker images every time! Use fast development mode:

# Method 1: Using Make commands (Recommended)
make dev-start      # Start infrastructure
make dev-app        # Start backend (new terminal)
make dev-frontend   # Start frontend (new terminal)

# Method 2: One-click start
./scripts/quick-dev.sh

# Method 3: Using scripts
./scripts/dev.sh start     # Start infrastructure
./scripts/dev.sh app       # Start backend (new terminal)
./scripts/dev.sh frontend  # Start frontend (new terminal)

Development Advantages:

• ✅ Frontend modifications auto hot-reload (no restart needed)
• ✅ Backend modifications quick restart (5-10 seconds, supports Air hot-reload)
• ✅ No need to rebuild Docker images
• ✅ Support IDE breakpoint debugging

Detailed Documentation: Development Environment Quick Start

WeKnora/
├── client/      # go client
├── cmd/         # Main entry point
├── config/      # Configuration files
├── docker/      # docker images files
├── docreader/   # Document parsing app
├── docs/        # Project documentation
├── frontend/    # Frontend app
├── internal/    # Core business logic
├── mcp-server/  # MCP server
├── migrations/  # DB migration scripts
└── scripts/     # Shell scripts

We welcome community contributions! For suggestions, bugs, or feature requests, please submit an Issue or directly create a Pull Request.

• 🐛 Bug Fixes: Discover and fix system defects
• ✨ New Features: Propose and implement new capabilities
• 📚 Documentation: Improve project documentation
• 🧪 Test Cases: Write unit and integration tests
• 🎨 UI/UX Enhancements: Improve user interface and experience

1. Fork the project to your GitHub account
2. Create a feature branch git checkout -b feature/amazing-feature
3. Commit changes git commit -m 'Add amazing feature'
4. Push branch git push origin feature/amazing-feature
5. Create a Pull Request with detailed description of changes

• Follow Go Code Review Comments
• Format code using gofmt
• Add necessary unit tests
• Update relevant documentation

Use Conventional Commits standard:

feat: Add document batch upload functionality
fix: Resolve vector retrieval precision issue
docs: Update API documentation
test: Add retrieval engine test cases
refactor: Restructure document parsing module

Thanks to these excellent contributors:

This project is licensed under the MIT License. You are free to use, modify, and distribute the code with proper attribution.