Week 2 (Friday): RAG and Embeddings - grounding in your own data
8 lessons · Back to full syllabus
What you keep
How to make a model answer from your data instead of its training, and why naive RAG fails.
You ship
Your endpoint answering from your own document set.
Lessons
Embeddings intuition
Similar meanings sit close together in vector space - retrieval quality depends on this mental picture.
Build naive RAG, and watch it fail
Embed, store, retrieve, stuff into prompt - then break it instructively.
Chunking
How you split documents decides what retrieval can find - most bad RAG is bad chunking.
Reranking and hybrid search
Reranking reorders candidates by relevance; hybrid search catches exact terms embeddings miss.
RAG evals
Measure retrieval and generation separately - wrong chunks vs right chunks ignored.
Graph RAG
When knowledge has structure and relationships, plain vector RAG leaves value on the table.
Multimodal RAG
Retrieve over images, tables, and diagrams - not just prose.
Ground your capstone in your data
RAG with deliberate chunking and reranking, plus a basic retrieval eval.
Lessons in this module