OpenSource-Hub
R

ragflow

SHA-256
87.6k stars·AI Productivity·SHA-256 checksum verified

RAGFlow is a leading open-source RAG engine that fuses deep document understanding with agentic workflows, offering precise, citation-grounded answers. Unlike LangChain's DIY approach, RAGFlow provides a turnkey, enterprise-ready platform with a visual interface and template-based chunking, reducing hallucinations and setup complexity.

Smart Download

Download Download Version

v0.26.4 · 25.2 MB

Open-source RAG engine with deep document understanding and agentic workflows, offering citation-grounded answers out of the box.

Core Features

  • Deep document understanding: automatically extracts knowledge from complex PDFs, Word, PPT, scanned files, and images
  • Template-based chunking: intelligent, explainable chunking templates with visual overview for human intervention
  • Grounded citations with reduced hallucinations: quick view of key references and traceable citations for every answer
  • Compatible with heterogeneous data sources: Word, Slides, Excel, TXT, images, scanned copies, structured data, web pages
  • Automated and effortless RAG workflow: visual orchestration, multiple recall paired with fused re-ranking, intuitive APIs

What It Can't Do

  • The official Docker images are built for x86 platforms only; ARM64 users (e.g., Apple Silicon) must build a Docker image themselves. 2. Before first startup, ensure vm.max_map_count >= 262144, otherwise Elasticsearch will fail to start. 3. The code executor (sandbox) requires gVisor; if not installed, that feature is unavailable. 4. The default startup uses CPU, which can be slow for large PDFs; GPU acceleration requires editing the .env file.

Use Cases

  • Enterprise knowledge base QA: build an internal document Q&A system so employees can query policies, manuals, and technical docs in natural language
  • Intelligent customer support and content generation: create a support assistant from product docs or generate industry reports with citations

Detailed Introduction

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs. It offers a streamlined RAG workflow adaptable to enterprises of any scale, powered by a converged context engine and pre-built agent templates. Key strengths include deep document understanding (extracting knowledge from unstructured data with complex formats), template-based chunking that is intelligent and explainable, and grounded citations that reduce hallucinations. Compared to frameworks like LangChain or LlamaIndex, RAGFlow is a turnkey platform with a visual interface, built-in document parsing, and automated ingestion pipelines, making it significantly easier to deploy and maintain for production use.

Tags

RAGLLMAgent知识库检索增强生成

Getting Started

1

Download installer

Click the button above to download the installer for your system

2

Install the software

Double-click the downloaded installer and follow the prompts

3

For quickest start, use the official cloud service at cloud.ragflow.io — no setup required

4

For self-hosting: ensure CPU ≥ 4 cores, RAM ≥ 16GB, Disk ≥ 50GB, and install Docker 24+ and Docker Compose v2.26.1+

5

Clone the repo, cd into ragflow/docker, and run docker compose -f docker-compose.yml up -d

Install Guide
  1. For quickest start, use the official cloud service at cloud.ragflow.io — no setup required
  2. For self-hosting: ensure CPU ≥ 4 cores, RAM ≥ 16GB, Disk ≥ 50GB, and install Docker 24+ and Docker Compose v2.26.1+
  3. Clone the repo, cd into ragflow/docker, and run docker compose -f docker-compose.yml up -d
File Integrity

SHA-256 checksum verified

Checksum extracted from GitHub official Release page

SHA256 Checksum

639d67416f53effd2ace524d1eb751b58d822c45c67d6c9172db7d855e24c94c

This checksum is extracted from the GitHub Release page. Verify file integrity after download.

All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.

Open Source Transparency

View GitHub Source
Environment Guide

Uninstall Info

To uninstall a local deployment: in the ragflow/docker directory, run docker compose -f docker-compose.yml down to stop and remove containers. To fully clean data, run docker volume prune and then delete the ragflow source directory.

No Extra Dependencies

Ready to use after download. No additional runtime required.

Project Info
LicenseApache-2.0
Last Updated2026-08-13T04:42:56Z
GitHub RepositoryOfficial Website

Similar Projects