# Why RAG Exists — Retrieval-Augmented Generation (RAG)

Source: https://www.geekswithgeeks.com/en/rag/b-why

> Understand the knowledge problems of plain language models.

## Models do not know your data

A language model only knows what was in its training data, frozen at a **knowledge cutoff**. It has never seen your company handbook, yesterday's tickets or a private database, and when it lacks the facts it may produce a fluent but invented answer (**hallucination**). **Retrieval-Augmented Generation (RAG)** fixes this at question time: first **retrieve** the passages that are relevant to the question from your own documents, then **augment** the prompt with them, then let the model **generate** an answer based on that text. The facts live in your documents, where they can be updated and cited, not inside the model's weights.

## Look up, then answer

RAG fetches relevant text from your documents and gives it to the model with the question.

![Four steps: question, retrieve, augment, generate.](assets/figures/rag/section-1-map.svg) — Figure 1.1 — Question, retrieve, augment and generate.

## An open-book exam

A closed-book student relies on memory and may guess. An open-book student looks up the right page, then writes the answer and says which page it came from.

## Start with the question, not the tool

Collect 20 real questions your users ask before choosing any vector database. They tell you what to retrieve.

**Quiz:** Where do the facts live in a RAG system?

- [ ] In the tokenizer
- [ ] Only in the model weights
- [x] In your documents, retrieved at question time
- [ ] In the GPU

*Answer:* In your documents, retrieved at question time. RAG keeps knowledge outside the model so it can be updated and cited.