Introduction
The most advanced AI retrieval system. Containerized, Retrieval-Augmented Generation (RAG) with a RESTful API.
R2R is the most advanced AI retrieval system. It is an all-in-one solution for Retrieval-Augmented Generation (RAG) with production-ready features, including multimodal content ingestion, hybrid search functionality, configurable GraphRAG, and user and document management.
Key Features
- π Multimodal Ingestion: Parse
.txt
,.pdf
,.json
,.png
,.mp3
, and more. - π Hybrid Search: Combine semantic and keyword search with reciprocal rank fusion for enhanced relevancy.
- π Knowledge Graphs: Automatically extract entities and relationships and build knowledge graphs.
- π GraphRAG: Cluster and summarize communities with over your created graphs for even richer insights.
- ποΈ User Management: Efficiently manage documents and user roles within R2R.
- π Observability: Observe and analyze your RAG engine performance.
- 𧩠Configuration: Setup your application using intuitive configuration files.
- π₯οΈ Dashboard: An open-source React+Next.js admin dashboard to interact with R2R via GUI.
Getting Started
- Installation: Quick installation of R2R using Docker or pip
- Quickstart: A quick introduction to R2Rβs core features
- Setup: Learn how to setup and configure R2R
- API & SDKs: API reference and Python/JS SDKs for interacting with R2R
Cookbooks
-
Advanced RAG Pipelines
- RAG Agent: R2Rβs powerful RAG agent
- Hybrid Search: Introduction to hybrid search
- Advanced RAG: Advanced RAG features
-
Orchestration
- Orchestration: R2R event orchestration
-
Auth & Admin Features
- Web Development: Building webapps using R2R
- User Auth: Authenticating users
- Collections: Document collections
- Analytics & Observability: End-to-end logging and analytics
- Web Application: Connecting with the R2R Application
Community
Join our Discord server to get support and connect with both the R2R team and other developers in the community. Whether youβre encountering issues, looking for advice on best practices, or just want to share your experiences, weβre 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.