OpenRAG

Active
GitHub Python Apache-2.0

Description

A comprehensive single-package Retrieval-Augmented Generation platform built on Langflow, Docling, and OpenSearch, providing a complete pipeline from document parsing to vector retrieval and generation with multi-model and multi-vector-database support.

Key Features

  • All-in-one RAG platform: document ingestion, vector search, and LLM-powered generation in a single package
  • Powered by OpenSearch for enterprise-grade scalable vector retrieval
  • Drag-and-drop visual workflow builder powered by Langflow for rapid RAG pipeline iteration
  • Intelligent document parsing via Docling handling messy, real-world data formats
  • Built-in MCP server over Streamable HTTP for connecting AI assistants like Cursor and Claude
  • Python and TypeScript SDKs for programmatic integration

Use Cases

πŸ’‘ Enterprise document search and knowledge base with conversational AI interface
πŸ’‘ Building custom RAG workflows with visual drag-and-drop configuration
πŸ’‘ Connecting AI coding assistants to organizational knowledge via MCP protocol
πŸ’‘ Processing and querying heterogeneous document collections with multi-model support

Tags

rag llm framework python api

Categories

πŸ“š RAG Tools

Quick Start

1. Install: pip install openrag-sdk (or uv run openrag). 2. Launch OpenRAG and open the web UI. 3. Add documents as knowledge, then start chatting with your data. SDK: from openrag_sdk import OpenRAGClient; response = await client.chat.create(message='What is RAG?').
Visit GitHub Visit Website

Related Projects