RAGFlow

Description

RAGFlow is an open-source Retrieval-Augmented Generation (RAG) engine that combines advanced RAG with agentic capabilities to create a context layer for LLMs, using AI-powered deep document understanding, configurable LLMs and embedding models, template-based chunking, multi-recall with fused re-ranking, grounded citations, and optional sandboxed code execution to extract accurate, traceable knowledge from heterogeneous sources (PDFs, Word, slides, images, Notion, Confluence, S3, etc.); developers and enterprises use it to build production-grade chatbots, knowledge bases, and agentic workflows faster and with fewer hallucinations thanks to pre-built agent templates, APIs, multimodal and cross-language support, and scalable ingestion and deployment tools.