Technique Updated 2026-04

RAG (Retrieval-Augmented Generation)

Retrieval-Augmented Generation
Definition

RAG is a technique that connects an LLM to external data sources to generate more accurate and up-to-date answers.

See also in the glossary

L
LLM (Large Language Model)
An LLM is an AI model trained on billions of texts, capable of understanding and generating human language.
P
Prompt
A prompt is the instruction or question you give an AI to get a response. It's the interface between you and the model.
A
AI Agent
An AI agent is an autonomous system that uses an LLM to plan, decide and execute real tasks without human intervention at each step.
G
Generative AI
Generative AI refers to artificial intelligence systems capable of creating original content: text, images, video, audio, code.

Tools that use rag

P
Perplexity
The AI answer engine that cites its sources
4.5/5
P
Pinecone
The leading vector database for AI applications
4.6/5
C
Consensus
The AI search engine for scientific literature
4.7/5
N
NotebookLM
Google's AI that turns your docs into an expert assistant
4.5/5

Frequently Asked Questions

What's the difference between RAG and fine-tuning?
Fine-tuning modifies the model itself by retraining it on your data. RAG leaves the model intact and feeds it relevant information at query time. RAG is simpler, cheaper and keeps data up-to-date.
Which tools use RAG?
Perplexity (web search + AI), NotebookLM (document analysis), and most enterprise chatbots connected to an internal knowledge base.