RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that integrates RAG with Agent capabilities. It provides a superior context layer for LLMs and offers a streamlined RAG workflow adaptable to enterprises of any scale.

Is ragflow open source?

Yes, licensed under Apache-2.0.

ragflow

Active·★ 91.9k·Apache-2.0·Updated 2026-10-08

★ Most Popular★ Trending★ Essential

RAGFlow is an open-source retrieval-augmented generation (RAG) engine that turns messy documents into a reliable context layer for LLMs. Its strength is deep document understanding: it parses complex PDFs, slides, spreadsheets, scanned images and web pages with layout analysis, OCR and table recognition before chunking, so answers can cite exactly where they came from.

It suits teams building internal knowledge bases, document Q&A and support assistants on top of their own data, especially when the source material is long, scanned or table-heavy. Template-based chunking can be inspected and adjusted by hand, answers come with traceable citations, and recent versions add agentic retrieval with selectable thinking depth plus knowledge compilation into wikis, graphs, mind maps and timelines. Data can be ingested from many sources, including websites via sitemaps and Google BigQuery.

Getting started: the recommended path is Docker Compose (Docker 24+, Compose 2.26.1+) on a machine with at least 4 CPU cores, 16 GB RAM and 50 GB of disk. After the services start you sign in through the web UI and configure an LLM, an embedding model and a reranker. A hosted cloud version is also available.

#RAG#AI Agent#LLM#Open-source#NLP

Features

01Deep document understanding for knowledge extraction from unstructured data.

02Intelligent and template-based chunking with explainable options.

03Grounded citations with reduced hallucinations and traceable references.

04Compatibility with heterogeneous data sources including documents, images, and web pages.

05Automated and effortless RAG workflow orchestration with configurable models and fused re-ranking.

Why choose it

+Strong parsing of complex formats (layout analysis, OCR, table recognition), which is where many RAG pipelines lose quality.

+Explainable, template-based chunking that you can visualise and correct by hand.

+Grounded answers with traceable citations, which helps reviewers trust and verify output.

+Complete product out of the box: web UI, APIs, data-source sync, agentic retrieval and optional MCP support.

Trade-offs

!Heavier to run than a RAG library: the recommended baseline is 4 cores, 16 GB RAM and 50 GB disk, plus several backing services.

!You still need to supply and tune an LLM, an embedding model and a reranker; answer quality depends on those choices.

!Version 1.0 moved the services to Go; check the upgrade notes if you run an older Python-based deployment.

!As a full platform it is less suited to embedding a few lines of retrieval inside an existing app than a code-first library.

Compatibility

Elasticsearch

Native

Verified via docs

Infinity

Supported

Verified via docs

Gemini 3 Pro

Supported

Verified via docs

OpenAI GPT-5 series

Supported

Verified via docs

Confluence

Supported

Verified via docs

Supported

Verified via docs

Quick start

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

Use cases

↳Building high-fidelity, production-ready AI systems with complex data.

↳Developing enterprise-scale knowledge base and intelligent Q&A chatbots.

↳Facilitating intelligent document processing and advanced information retrieval.

How it compares

≈vs LlamaIndex and LangChain: those are code libraries for assembling your own RAG pipeline; RAGFlow is a deployable application with its own UI, parsing engine and APIs.

≈vs Dify: Dify is a broader LLM app builder in which RAG is one feature; RAGFlow goes deeper on document parsing and citation quality.

≈vs GPT Researcher: GPT Researcher researches the web and local files to write reports; RAGFlow is built to serve an ongoing knowledge base for question answering.

Alternatives

MaxKB★ 22.9k

An open-source platform for building enterprise-grade agents. Powerful and easy to use.

vs →

GPT Researcher★ 30.0k

An autonomous agent that conducts deep research on any data using any LLM provider, producing detailed reports with citations from web and local sources.

vs →

Context7★ 62.8k

MCP Server that provides up-to-date code documentation for LLMs and AI code editors.

Brave Search MCP★ 1.5k

Allow your AI Agent to search the real-time internet using Brave Search API. Essential for getting up-to-date information.

Gemini CLI★ 107.3k

An open-source AI agent that brings the power of Gemini directly into your terminal. Supports native MCP.

Open Interpreter★ 68.5k

A coding agent for the terminal, optimized for low-cost and open models. Forked from OpenAI's Codex, it can emulate other agent harnesses and runs commands in a native sandbox.

Flowise★ 55.5k

Visual builder for AI agents and LLM workflows. Discontinued: the repository was archived in August 2026 and the project reached end of life on August 31, 2026.

agents-towards-production★ 21.5k

This repository delivers end-to-end, code-first tutorials covering every layer of production-grade GenAI agents, guiding you from spark to scale with proven patterns and reusable blueprints for real-world launches.

See all alternatives →

Comments

No comments yet. Be the first!

ragflow

Active·★ 91.9k·Apache-2.0·Updated 2026-10-08

★ Most Popular★ Trending★ Essential

#RAG#AI Agent#LLM#Open-source#NLP

Features

01Deep document understanding for knowledge extraction from unstructured data.

02Intelligent and template-based chunking with explainable options.

03Grounded citations with reduced hallucinations and traceable references.

04Compatibility with heterogeneous data sources including documents, images, and web pages.

05Automated and effortless RAG workflow orchestration with configurable models and fused re-ranking.

Why choose it

+Strong parsing of complex formats (layout analysis, OCR, table recognition), which is where many RAG pipelines lose quality.

+Explainable, template-based chunking that you can visualise and correct by hand.

+Grounded answers with traceable citations, which helps reviewers trust and verify output.

+Complete product out of the box: web UI, APIs, data-source sync, agentic retrieval and optional MCP support.

Trade-offs

!Heavier to run than a RAG library: the recommended baseline is 4 cores, 16 GB RAM and 50 GB disk, plus several backing services.

!You still need to supply and tune an LLM, an embedding model and a reranker; answer quality depends on those choices.

!Version 1.0 moved the services to Go; check the upgrade notes if you run an older Python-based deployment.

!As a full platform it is less suited to embedding a few lines of retrieval inside an existing app than a code-first library.

Compatibility

Elasticsearch

Native

Verified via docs

Infinity

Supported

Verified via docs

Gemini 3 Pro

Supported

Verified via docs

OpenAI GPT-5 series

Supported

Verified via docs

Confluence

Supported

Verified via docs

Supported

Verified via docs

Quick start

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

Use cases

↳Building high-fidelity, production-ready AI systems with complex data.

↳Developing enterprise-scale knowledge base and intelligent Q&A chatbots.

↳Facilitating intelligent document processing and advanced information retrieval.

How it compares

≈vs LlamaIndex and LangChain: those are code libraries for assembling your own RAG pipeline; RAGFlow is a deployable application with its own UI, parsing engine and APIs.

≈vs Dify: Dify is a broader LLM app builder in which RAG is one feature; RAGFlow goes deeper on document parsing and citation quality.

≈vs GPT Researcher: GPT Researcher researches the web and local files to write reports; RAGFlow is built to serve an ongoing knowledge base for question answering.