Skip to main content

Lesson 1 · 9 min

What RAG actually is — and when not to use it

RAG is a retrieval system that feeds an LLM. That's it. The hard parts are everything except the LLM.

RAG, plainly

Retrieval-Augmented Generation is a pattern: instead of relying on the LLM's training knowledge, you fetch relevant snippets from your own corpus at query time and stuff them into the prompt.

The LLM still does the writing. It just writes from your context, not from its memory.