💡 What is RAGFlow?
RAGFlow RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine built on deep document understanding.RAGFlow provides a streamlined set of RAG workflows for businesses and individuals of all sizes, combined with large language modeling (LLM) to provide reliable Q&A and evidence-based querying of different types of complex formats of user data. RAGFlow provides a streamlined RAG workflow for organizations and individuals of all sizes.
pure open source
Available out of the box.

OCR function
This helps us unlock a lot of OCR features, whether you want to deal with documents or Excel data, there are corresponding parsing methods.

🔥 Recent Updates
- 2024-08-02 Support GraphRAG Inspired by graphrag and mind maps.
- 2024-12-18 Upgraded Deepdoc's document layout analysis model.
- 2024-12-04 Support for Pagerank scores for knowledge bases.
- 2024-11-22 Refined the definition and use of variables in Agent.
- 2024-11-01 Adding keyword extraction and related question generation to parsed chunks to improve recall accuracy.
- 2024-08-22 Support for conversion from natural language to SQL statements using RAG technology.
🌟 Main Functions
🍭 "Quality in, quality out"
- on the basis ofDeep Documentation UnderstandingThe ability to extract insights from unstructured data in a variety of complex formats.
- Really fast needle-in-a-haystack testing in infinite context (token) scenarios.
🍱 Template-based text slicing
- Not just smart, but also controllable and interpretable.
- Multiple text templates to choose from
🌱 Justified, minimized hallucinations (hallucination)
- Visualization of the text slicing process with support for manual adjustment.
- Justified: answers provide snapshots of key references and support traceability.
🍔 Compatible with various heterogeneous data sources
- Support rich file types, including Word documents, PPT, excel tables, txt files, images, PDF, photocopies, copies, structured data, web pages and more.
🛀 Hassle free, automated RAG workflows
- Fully optimized RAG workflows support ecosystems ranging from personal applications to mega-enterprises.
- Configurations are supported for the Large Language Model LLM as well as the Vector Model.
- Based on multiplexed recall, fusion reordering.
- Provides easy-to-use APIs for easy integration into various enterprise systems.
Access Address:https://github.com/infiniflow/ragflow