AI Glossary
What is RAG?
RAG (retrieval-augmented generation): RAG — retrieval-augmented generation — lets an AI look up relevant documents first and answer from them, instead of relying only on what it memorized during training.
In plain English
It is the difference between a closed-book and an open-book exam. Plain LLMs answer from memory, which is frozen at training time and fuzzy on detail. A RAG system first fetches the most relevant passages from a knowledge base, puts them in front of the model, and says: answer using these.
Why it matters
- How "chat with your PDF" and most company AI assistants actually work
- Reduces hallucination by grounding answers in real text
- Lets a model answer about things it was never trained on — yesterday’s news, your private files
A concrete example
A support bot using RAG retrieves your product manual’s warranty section and quotes it — instead of inventing a warranty policy that sounds plausible.
Related terms
Learning AI from scratch? Start with the free Learn AI course picks, then put it to work with 50 tested prompts — or get the daily 2-minute briefing, free →