Skip to content
Glossary

Retrieval-Augmented Generation (RAG)

Retrieval-augmented generation is a technique that grounds a language model's output in retrieved source documents instead of relying solely on its parametric memory. The system fetches relevant passages from a knowledge base, supplies them as context, and asks the model to answer using only that evidence.

Synonyms: RAG, retrieval augmented generation, grounded generation, context augmentation

Retrieval-augmented generation separates what a model knows from what it was trained on. At query time the retriever pulls the most relevant chunks from a maintained knowledge base, and the model composes an answer constrained to that evidence. This reduces hallucination, makes answers auditable through citations, and lets teams update knowledge without retraining. In a governed setting, RAG is the mechanism that turns a question into a grounded, cited response that a person or policy can verify before it is trusted.

Frequently asked questions

Why use RAG instead of fine-tuning?
RAG keeps knowledge in an external store you can update instantly, so answers stay current and every claim can be traced to a source. Fine-tuning bakes knowledge into weights, which is slower to refresh and harder to attribute.
What does a RAG pipeline include?
Typically ingestion and chunking, embedding, an index for vector or hybrid search, a retriever, and a generation step that conditions the model on the retrieved passages and returns cited evidence.