Skip to content
  1. Home
  2. AI tools
  3. RAGFlow

RAGFlow

Self-hosted RAG engine with document parsing and agent templates

What it is

A retrieval-augmented generation engine that ingests complex documents and serves them as context to LLMs, with built-in agent templates. It is deployed locally with Docker Compose and also offered as a cloud service. For teams that need a full RAG system with a UI, not a library.

Good for

  • Stand up a document question-answering system
  • Index complex PDFs for retrieval
  • Build an agent on top of a knowledge base

Install or run

docker compose -f docker-compose.yml up -d

Command as given in the project README. Read the repository before you run anything on your machine.

What you need

Docker with Compose, run from the cloned repo; an LLM provider key

Worth knowingA multi-container stack with notable CPU, RAM and disk needs; not a lightweight install.

Sources

The summary is ours, written from the README. Spotted an error? See how we work.

More for data & research

See the topic →
  • MarkItDown

    microsoft/markitdown

    Lightweight Python utility that converts files to Markdown for LLMs

    ToolGitHub stars: 195k
  • Docling

    docling-project/docling

    Parse PDFs, Office files and more into structured data for LLMs

    ToolGitHub stars: 71k
  • serviette

    pathwaycom/serviette

    No-code RAG server that keeps answers in sync with a document folder

    ToolGitHub stars: 59k
  • LightRAG

    HKUDS/LightRAG

    Graph-based RAG library and server with pluggable storage backends

    ToolGitHub stars: 41k