← Path
Retrieval-Augmented Generation · Why RAG? Retrieval-Augmented Generation vs Fine-Tuning Explained
0 XP- 1 current stop: learning
- 2 upcoming
- 3 upcoming
- 4 upcoming
- 5 upcoming
Finish after stop 5
Stop 1 of 5 · Library stacks at the start of the route
Trick to keep in mind+3 XP
Open-book exam: look it up each time, don't memorise it.
With retrieval, knowledge stays in a separate store and the model reads the relevant passages for each question. When documents change, you update the store, not the model, and you can say exactly which text was sent. Facts baked into weights, by contrast, are hard to update, and impossible to trace to a source.
Read it once, then a question tests whether the trick stuck.