An open-source Retrieval-Augmented Generation engine that combines deep document understanding with advanced AI agent capabilities.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install open-ragflow
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install open-ragflow using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Open RAGFlow?
Open RAGFlow is a robust, full-stack engine designed to bridge the gap between static data and AI intelligence. It features a Python backend and a React-based frontend, optimized for microservice deployment via Docker. By leveraging this Openclaw Skills resource, developers can implement high-performance RAG workflows that integrate DeepDoc parsing with complex agentic reasoning.
The system is built for scalability and flexibility, supporting multiple LLM providers and specialized document engines like Elasticsearch or Infinity. Whether you are self-hosting on-premises or deploying to the cloud, this skill provides the tools to manage the entire lifecycle of your knowledge base and AI interactions.
Open RAGFlow Use Cases
- Self-hosting a private RAG engine using Docker Compose or source code.
- Configuring multi-provider LLM setups and embedding models for custom domains.
- Automating knowledge base management and document parsing via a dedicated CLI.
- Building complex AI agent workflows using the canvas-based visual editor.
- Troubleshooting deployment issues and optimizing performance for large-scale data sets.
How Open RAGFlow Works
- Infrastructure setup involving Docker containers for the backend, frontend, and database services.
- Configuration of environment variables and LLM API keys within the service templates to enable AI capabilities.
- Data ingestion where documents are processed through the DeepDoc engine for optimal chunking and understanding.
- Knowledge base creation and indexing in a specialized document engine like Elasticsearch or Infinity.
- Agent deployment where users interact with the RAG pipeline via the web UI, CLI, or REST API.
Open RAGFlow Setup
To get started with Open RAGFlow using Openclaw Skills, follow these steps:
git clone https://github.com/infiniflow/ragflow.git
cd ragflow/docker
docker compose -f docker-compose.yml up -d
# Monitor initialization logs
docker logs -f docker-ragflow-cpu-1
Configure your LLM API keys in docker/service_conf.yaml.template under the user_default_llm section, then restart the services:
docker compose -f docker-compose.yml up -d
Open RAGFlow Data Schema & Taxonomy
The skill organizes its data across several integrated infrastructure components to ensure high availability and performance:
| Component | Purpose |
|---|---|
| MySQL | Stores metadata for users, datasets, agents, and chat history. |
| MinIO | Handles object storage for raw documents and processed file chunks. |
| Elasticsearch/Infinity | Provides vector search and document indexing for retrieval-augmented generation. |
| Redis | Manages caching, task queuing, and session states for the application. |
Open RAGFlow Advanced Features
- GraphRAG support for complex relationship mapping and retrieval within deeply nested knowledge bases.
- Canvas-based workflow builder for designing sophisticated AI agents with conditional logic and multi-step reasoning.
- Support for custom sandboxed code execution using gVisor for secure computational tasks.
- Comprehensive CLI for headless management of models, datasets, and agents, perfect for automation within Openclaw Skills pipelines.
- Multi-engine flexibility allowing users to switch between Elasticsearch and the lightweight Infinity document engine.
SKILL.md
Loading
Related Openclaw Skills
RAGFlow
RAGFlow is a professional-grade open-source RAG engine that integrates DeepDoc parsing with a canvas-based agent workflow system.
Voice Note Transcriber
A bridge between your voice recordings and Obsidian that uses OpenAI Whisper to transcribe audio and append it directly to your daily notes.
Baozi Prediction Markets
A powerful Solana-based prediction market skill for real-time odds analysis and automated betting execution.
PR Auto-Review
Automate code reviews, service health checks, and Discord notifications for every pull request in your development pipeline.
bee-products-read
A specialized skill for reading and extracting comprehensive product lists and metadata from Bee-powered websites via open API access.
Node.js Best Practices & Code Auditor
A comprehensive quality enforcement skill that audits Node.js applications for security, performance, and architectural integrity.
Featured*
