← back to the directory
Library / SDK Retrieval & Memory

RAGatouille

1Easy 2state-of-the-art 3ColBERT 4retrieval 5for 6RAG

the six Ws · specification

W1 Who

Maintained by Answer.AI.

W2 What

Makes ColBERT late-interaction retrieval easy to use.

W3 Where

A Python library on your infrastructure.

W4 When

When you need stronger retrieval than plain embeddings.

W5 Why

Brings state-of-the-art ColBERT models to practical RAG.

W6 With

Python, a ColBERT model, and your documents.

W7 Watch

Community-maintained; open-source (Apache-2.0), library only. Runs locally; indexes and models stay on your machine.

ColBERTRetrievalRAG

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.