Neura Market
R2R logo

R2R

Free

A framework for rapid development and deployment of production-ready RAG systems ![GitHub Repo stars](https://img.shields.io/github/stars/SciPhi-AI/R2R?style=social)

FreeFree tier
Inputs: text, image, audioOutputs: text
Type
Open Source
Company
SciPhi AI
Visit Website GitHub (40 stars)

About R2R

R2R is an advanced AI retrieval system that supports Retrieval-Augmented Generation (RAG) with production-ready features. Built around a RESTful API, it offers multimodal content ingestion (parsing .txt, .pdf, .json, .png, .mp3, and more), hybrid search combining semantic and keyword search with reciprocal rank fusion, automatic knowledge graph extraction, and a reasoning agent integrated with retrieval. It also includes a Deep Research API for multi-step reasoning from knowledge bases and the internet. The system is open source and can be installed via pip or deployed with Docker.

Key Features

Multimodal ingestion: parse .txt, .pdf, .json, .png, .mp3 and more
Hybrid search: semantic + keyword search with reciprocal rank fusion
Knowledge graphs: automatic entity relationship extraction
Agentic RAG: reasoning agent integrated with retrieval
User access management: complete authentication and collection system
Deep Research API: multi-step reasoning from knowledge base and internet
RESTful API for integration
Document management: ingest, list, and search documents

Pros & Cons

Pros
  • Open source and free to use
  • Production-ready with comprehensive features
  • Supports multimodal content (text, images, audio)
  • Hybrid search and knowledge graphs for better retrieval
  • Agentic reasoning for complex queries
  • Active community on Discord and GitHub
  • Easy installation via pip or Docker
Cons
  • Requires self-hosting and setup for full deployment
  • Performance depends on external LLM API keys (e.g., OpenAI, Anthropic)
  • Docker setup for full mode may be complex for beginners
  • Documentation may require improvement for advanced configuration

Best For

Building production-ready RAG applicationsCreating deep research agents that combine internal and web dataEnterprise knowledge base Q&A with citationsMultimodal document analysis and retrievalSelf-hosted AI retrieval systems with user management

FAQ

What is R2R?
R2R is an advanced AI retrieval system for production-ready Retrieval-Augmented Generation (RAG) with a RESTful API.
How do I install R2R?
Install via pip: 'pip install r2r', then set your OpenAI API key and run 'python -m r2r.serve'. For full deployment with Docker, clone the repo and use docker compose.
Does R2R support multimodal content?
Yes, it supports parsing .txt, .pdf, .json, .png, .mp3, and more file types.
Is there a REST API?
Yes, R2R is built around a RESTful API for document operations and retrieval.
Is R2R free?
Yes, R2R is open source and free to use.