RAG — Retrieval-Augmented Generation

Fact

A method where AI searches outside sources first, then writes an answer.

In Plain Words

RAG is an open-book quiz for AI. It peeks at the notes before it answers.

You meet it when bots search company docs for answers. It cuts made-up answers, but it can still face-plant.

Related Concepts

• Large Language Model
• Vector Embedding
• Vector Database
• AI Hallucination

LLM
RAG gives the LLM outside sources before it writes the answer.

Embedding
Embedding helps RAG find text with a similar meaning.

Vector-db
Vector-db stores and finds the chunks RAG needs.

Hallucination
RAG lowers hallucination risk by giving the AI facts to use.