ragflow

View on GitHub

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

★ 91K10,806 forksGoApache-2.0infiniflow

RAGFlow is an open-source RAG engine combining deep document understanding with agentic retrieval and workflow orchestration. It chunks heterogeneous files (PDF, Office, scans), supports configurable LLMs/embeddings, MCP, and produces grounded answers with traceable citations. Self-hostable via Docker.

Use Cases

Build enterprise document QA with traceable citationsIngest PDFs/DOCX/Excel/scanned files into a searchable knowledge baseAgentic retrieval over heterogeneous data sourcesTemplate-based chunking and retrieval tuningGrounded RAG chatbots with reduced hallucinationData sync from Confluence, Notion, S3, Google DriveConfigurable LLM and embedding model orchestrationMulti-modal understanding of images in documentsCode executor sandbox inside agent workflowsExpose RAG datasets as an agent skill/MCP tool

Built With

Language: Go
Frameworks: Flask · Elasticsearch · Infinity · Redis · MySQL · MinIO · Docker · Docling · MinerU · browser-use · OpenAI SDK · Anthropic SDK · gVisor · DeepDoc

ragflow

Use Cases

Built With

Tags