Introduction

The most advanced AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

r2r

R2R is an all-in-one solution for AI Retrieval-Augmented Generation (RAG) with production-ready features, including multimodal content ingestion, hybrid search functionality, configurable GraphRAG, and user/document management.

R2R also includes a Deep Research API, a multi-step reasoning system that fetches relevant data from your knowledgebase and/or the internet to deliver richer, context-aware answers for complex queries.


Cloud Documentation

Getting Started

  • 🚀 Quickstart A quick introduction to R2R’s core features.
  • ❇️ API & SDKs API reference and Python/JS SDKs for interacting with R2R.

Key Features

Ingestion & Retrieval

  • 📁 Multimodal Ingestion Parse .txt, .pdf, .json, .png, .mp3, and more.
  • 🔍 Hybrid Search Combine semantic and keyword search with reciprocal rank fusion for enhanced relevancy.
  • 🔗 Knowledge Graphs Automatically extract entities and relationships to build knowledge graphs.
  • 🤖 Agentic RAG R2R’s powerful Deep Research agent integrated with RAG over your knowledgebase.

Application Layer

Self-Hosting

  • 🐋 Docker Use Docker to easily deploy the full R2R system into your local environment
  • 🧩 Configuration Set up your application using intuitive configuration files.

Community

Join our Discord server to get support and connect with both the R2R team and other developers. Whether you’re encountering issues, seeking best practices, or sharing your experiences, we’re here to help.


About

  • 🌐 SciPhi Website Explore a managed AI solution powered by R2R.
  • ✉️ Contact Us Get in touch with our team to discuss your specific needs.