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 reasoning_agent (Reasoning Agents with RAG), a multi-step reasoning system that fetches relevant data and delivers 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 reasoning agent integrated with RAG.

Application Layer

• 💻 Web Development
  Building web apps using R2R.
• 🔐 User Auth
  Authenticating users.
• 📂 Collections
  Document collections management.
• 🌐 Web Application
  Connecting with the R2R Application.

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.