Skip to content

RAGFlow

Repository: infiniflow/ragflowDescription: An open-source RAG engine based on deep document understanding that integrates RAG with Agent capabilities. Key Features:

  • Deep Document Understanding: Advanced parsing of complex document layouts and structures.
  • Template-based Chunking: Intelligent chunking strategies to preserve semantic meaning.
  • Grounded Citations: Minimizes hallucinations by providing direct links to source material.
  • Agent Integration: Combines retrieval with reasoning-based agent workflows. Primary Use Cases: Enterprise knowledge bases, document-heavy RAG applications, and specialized AI assistants. Tags: #rag #llm #document-processing #python Added: 2026-05-24 Source: GitHub

Notes / Why Notable

RAGFlow stands out for its focus on "Deep Document Understanding," which is often a bottleneck in enterprise RAG systems. By treating document parsing as a core feature rather than a preprocessing step, it achieves higher retrieval accuracy.

Maintained with Yeda — Karpathy LLM Wiki paradigm.