Logo
Deploy Now

Categories

Developer Tools Knowledge Management Machine Learning Chatbot Search Engine Document Management Artificial Intelligence

Stars

89,017

Forks

10,458

Watchers

362

Developer links

Last Updated: 08-22-2026 01:43 PM (UTC)

RAGFlow

RAGFlow has established itself as one of the most widely adopted open-source RAG engines available, powering production AI systems that demand traceable, hallucination-free answers from complex enterprise data. The platform processes PDF, DOCX, Excel, and PPT files through vision-based deep document understanding with layout analysis and OCR, extracting structured knowledge from tables, charts, and images that simpler parsers miss entirely. RAGFlow's hybrid retrieval pipeline combines vector search with BM25 keyword matching and multi-stage reranking across configurable document stores including Elasticsearch, InfiniFlow's Infinity engine, OpenSearch, and OceanBase. Developers connect any combination of LLM providers — OpenAI, DeepSeek, Anthropic Claude, Google Gemini, and locally-hosted models via Ollama — through a unified configuration layer. The visual agent workflow system enables multi-step reasoning chains with persistent memory, tool calling, and pre-built templates for common enterprise scenarios. RAGFlow synchronizes data from Confluence, S3, Notion, and Google Drive, and delivers answers through chat integrations with Feishu, Discord, Telegram, and Line. The Python SDK and RESTful API on port 9380 provide programmatic access to knowledge base management, document parsing, and conversational retrieval. The full stack deploys via Docker Compose with MySQL for metadata, Redis for task orchestration, and MinIO for object storage. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

RAGFlow
RAGFlow
RAGFlow
RAGFlow
RAGFlow

Benefits

  • Deep Document Understanding Pipeline
  • Vision-based layout analysis and OCR extract structured knowledge from PDFs, tables, charts, and images that conventional text-only parsers cannot process accurately.
  • Hybrid Search with Reranking
  • Combines vector similarity search with BM25 keyword matching and multi-stage fused reranking across Elasticsearch, Infinity, or OpenSearch for higher recall precision.
  • Visual Agent Workflow Builder
  • Drag-and-drop canvas for constructing multi-step reasoning chains with persistent memory, tool calling, and pre-built agent templates for common enterprise automation scenarios.
  • Traceable Citation-Backed Answers
  • Every generated response includes verifiable citations linking back to source documents and specific passages, reducing hallucination and enabling auditable AI outputs.

Features

  • Multi-Format Document Parsing
  • Processes PDF, DOCX, Excel, and PPT through DeepDoc vision models with template-driven chunking strategies and configurable user intervention points.
  • Configurable LLM Integration
  • Connects to OpenAI, DeepSeek, Anthropic Claude, Google Gemini, and local models via Ollama through a unified provider abstraction layer.
  • Enterprise Data Synchronization
  • Ingests documents from Confluence, Amazon S3, Notion, and Google Drive with automated synchronization to keep knowledge bases current.
  • Multi-Channel Chat Delivery
  • Deploys conversational interfaces through Feishu, Discord, Telegram, and Line integrations alongside the built-in web chat UI.
  • Python SDK and REST API
  • Programmatic access to knowledge base management, document parsing, and conversational retrieval via Python client library and HTTP endpoints on port 9380.