Nexus Learn

Log in · Create free account

Module 4: Using models with your own data · 9 min

Prompting, RAG or fine-tuning?

A general model does not know your private documents. There are three main ways to fix that.

MethodHow it worksBest forCost and effort
PromptingPut the needed text in the promptSmall, one-off tasksLowest
RAG (retrieval-augmented generation)Search your documents and add the best pieces to the promptQuestions about large or changing documentsMedium
Fine-tuningTrain the model more on your examplesTeaching a style, format or specialised skillHighest

A good rule: start with prompting, move to RAG when you have many documents or they change often, and use fine-tuning only when the first two cannot give the style or skill you need.

Fine-tuning is not a good way to add facts. RAG is better for facts because you can update the documents any time and show the source.

(free account needed to save progress)

← What image and video AI cannot do well  |  How RAG works, step by step →