# Retrieval-Augmented Generation (RAG)

> Retrieval-Augmented Generation (RAG) is a technique where an AI model retrieves relevant information from your own data and uses it to ground its answer — so responses are accurate and current instead of guessed.

_Source: https://plenaura.com/glossary/rag · Last updated: 2026-06-03 · Plenaura_

## Key points

- Connects a language model to your documents, databases, or knowledge base.
- Reduces hallucination by answering from retrieved facts, with citations to the source.
- Lets you update the AI's knowledge by updating the data — no retraining required.

## FAQ

### Why use RAG instead of fine-tuning?

RAG is the right choice when knowledge changes often or must be sourced and citable — you update data, not the model. Fine-tuning changes how the model behaves or its style; the two are often combined.