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.
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.
Topics covered
- RAG vs fine-tuning
- long context
- LLM fine-tuning
- choosing an AI approach
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
- Choose between RAG, long context, injected data and fine-tuning (this lesson)
- Inventory sources and metadata
What you will learn in the course
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.
- Design retrieval: semantic, keyword or hybrid search, reranking, contextual retrieval, number of passages and relevance threshold.
- Specify the answer grounded in sources, how citations are displayed, how conflicting sources are handled and what happens when nothing is found.
- Specify access filtering before the model reads any passage, and index freshness (resync, deletions, versions).
- Build a set of 30 test questions that covers RAG failure modes and diagnose which stage caused a wrong answer.
- Estimate the cost items of a RAG system and choose between a hosted tool, a managed knowledge base, a vector database and a custom build.
Related courses
- Build an AI assistant for your productAdvanced · ~3 hr
- Evaluate an AI feature: test sets, metrics and LLM judgesAdvanced · ~3 hr
- Ship and monitor an AI feature in productionExpert · ~3 hr