istGalaxy.
All terms

glossary

What is RAG (retrieval-augmented generation)?

RAG is a method where a language model retrieves relevant documents and grounds its answer in them.

RAG lets the model answer from your up-to-date knowledge base rather than only its training, improving accuracy and enabling source citations.

Examples

Retrieving the relevant policy doc to answer a policy question.

Frequently asked questions

Why does RAG matter?

It reduces hallucination and grounds answers in verifiable sources.

Try istGalaxy with your own data.