---
title: "Retrieval-Augmented Generation (RAG)"
description: "RAG is a technique where an AI retrieves relevant information from your own documents and feeds it to the language model, so answers are grounded in your data instead of the model’s general training."
canonical: "https://www.whatsnext-ai.com/glossary/rag"
---

# Retrieval-Augmented Generation (RAG)

RAG is a technique where an AI retrieves relevant information from your own documents and feeds it to the language model, so answers are grounded in your data instead of the model’s general training.

## Definition

It’s how you get an AI that answers from your policies, products and proposals: accurate, cited, and current as your content changes. RAG is usually the fastest, most reliable way to make an LLM useful for a specific business, and a core part of most agents we ship.

## Related

- [Custom AI Development](https://www.whatsnext-ai.com/custom-ai-development)
- [AI-Ready Data](https://www.whatsnext-ai.com/ai-ready-data)

## Source

Lewis et al. (2020) — Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (NeurIPS) (https://arxiv.org/abs/2005.11401)