R2R
Production retrieval system with ingestion and an API
R2R is profiled here as a RAG Framework tool for engineering teams. Read about features, pricing, and how it compares to related options in the tools directory.
Description
R2R, short for RAG to Riches, is an open-source retrieval framework from SciPhi that packages a RAG pipeline as a deployable service. It handles document ingestion, chunking, embedding, and retrieval behind a REST API, and adds hybrid search and a knowledge-graph layer for queries that span many documents. Teams run it through Docker to stand up a retrieval backend without assembling the pieces by hand. It targets teams moving past notebook prototypes who want a retrieval backend with users, permissions, and ingestion handled in one service. The knowledge-graph layer helps answer questions that span many related documents.
Key Capabilities:
Document ingestion for PDFs, Office files, images, and more
Hybrid search combining semantic and full-text retrieval
GraphRAG with entity and relationship extraction
Agentic retrieval that reasons over multiple search steps
User and document management behind a REST API
Self-hostable via Docker under an MIT license
Alternative tools
- LanceDB
Embedded multimodal vector database on the Lance format
- Milvus
Open-source vector database built for billion-scale search
- Sentence Transformers
Python framework for dense text and image embeddings
- Mem0
Long-term memory layer for AI agents and assistants
- Docling
Open-source document conversion built for RAG pipelines
- Unstructured
Turn raw documents into LLM-ready structured data