Open-source RAG engine with deep document parsing (tables, charts, images) and an official MCP server. Deploy via Docker, call via REST API. 80k GitHub stars.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your assistant, with RAGFlow connected:
- Deep Document Parse
Use RAGFlow to parse complex documents: ‹what you need›
- Knowledge Retrieval
Use RAGFlow to query ingested knowledge bases: ‹what you're looking for›
- Agent Workflows
Use RAGFlow to build multi-step agentic workflows in a canvas UI: ‹what you need›
Connect it over MCP
Connect RAGFlow as an MCP server, following its setup instructions at https://ragflow.io/docs/dev
Its page: ragflow.io/docs/dev
Call the API
Auth An API key from InfiniFlow
Its page: ragflow.io/docs/dev
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- APIMCP
- Auth
- API Key
- Skills
- 3
Skills
Deep Document Parse
Parse complex documents — tables, charts, multi-column layouts — with layout-aware chunking for accurate retrieval.
Knowledge Retrieval
Query ingested knowledge bases via hybrid search (semantic + keyword) with source-cited answers.
Agent Workflows
Build multi-step agentic workflows in a canvas UI that call RAG, APIs, and external tools in sequence.