Skip to content
Module
Module 2 of 6Lesson 1 of 2~20 min

Choose between RAG, long context, injected data and fine-tuning

Building RAG by reflex can cost months of work when a simpler approach would have done the job. This lesson helps a PM choose, need by need, between long context, data supplied by the application, RAG and fine-tuning, and defend that choice to the team with clear product criteria.

Take this lesson: your first course is freeSee the full syllabus

Lesson objective

By the end of this lesson, you will be able to choose, for each information need of your product, between long context, data injected by the application, RAG and fine-tuning, and to justify the choice by volume, update frequency, access rights and cost.

Questions this lesson answers

  • Should you use RAG or long context for a knowledge base?
  • When does fine-tuning make more sense than RAG for an AI assistant?
  • How do you decide if your product actually needs RAG?

Topics covered

  • RAG vs fine-tuning
  • long context
  • LLM fine-tuning
  • choosing an AI approach

In the glossary

Full glossary

Where it fits

Do you need RAG, and on which sources?

Does my need justify RAG, and which sources should go into it?

Lessons in this module

  1. Choose between RAG, long context, injected data and fine-tuning (this lesson)
  2. Inventory sources and metadata

What you will learn in this module

This lesson is part of the course Design a RAG architecture that fits your product

  • Choose, for an information need, between long context, data injected by the application, RAG and fine-tuning, and justify the choice by volume, update frequency, access rights and cost.
  • Specify the source inventory, exclusions, the metadata to capture and the document chunking strategy.

Related courses