← Discover
Discover · GitHub · Ragflow↑ +139 today

Data-driven artificial intelligence engine

RAGFlow is an open source fetch-based generation (RAG) engine that creates a context layer for large language models (LLM). It aims to improve data processing and accuracy of responses by combining advanced RAG techniques with agent capabilities.

Updates

  • August 31, 2026: Stars 88,819 → 89,753, latest release v0.27.1 (August 28, 2026).
  • August 19, 2026: Stars 88,549 → 88,819, latest release v0.27.0 (August 19, 2026).
  • August 15, 2026: Stars 87,648 → 88,549, latest release v0.26.4 (July 7, 2026).

What you get

  • Extracts information from complex documents with high accuracy.
  • It intelligently segments data using template-based methods.
  • It reduces hallucination thanks to answers supported by quotes.

Installation

Download the repository to your computer
git clone https://github.com/infiniflow/ragflow.git
Start the service with Docker
docker compose -f docker/docker-compose.yml up -d

If you don't write code

🤖 Paste this into your AI agent (Claude Code · Codex · Antigravity)

I want to transform the complex documents and unstructured data I have into a high-quality information source that artificial intelligence models can understand. How can I process my data using RAGFlow, configure document fragmentation templates, and create an error-free, source-referencing AI agent using this data?

Related dictionary terms

RAGLLMArtificial Intelligence
Who it is forIt is suitable for developers and businesses that want to process their corporate data securely and with high accuracy with artificial intelligence models.
LicenseApache-2.0

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-08-13: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.