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

Live

Embeddings intuition

Similar meanings sit close together in vector space - retrieval quality depends on this mental picture.

Read lesson
Live

Build naive RAG, and watch it fail

Embed, store, retrieve, stuff into prompt - then break it instructively.

Read lesson
Live

Chunking

How you split documents decides what retrieval can find - most bad RAG is bad chunking.

Read lesson
Live

Reranking and hybrid search

Reranking reorders candidates by relevance; hybrid search catches exact terms embeddings miss.

Read lesson
Live

RAG evals

Measure retrieval and generation separately - wrong chunks vs right chunks ignored.

Read lesson
Deep dive

Graph RAG

When knowledge has structure and relationships, plain vector RAG leaves value on the table.

Read lesson
Deep dive

Multimodal RAG

Retrieve over images, tables, and diagrams - not just prose.

Read lesson
Assignment

Ground your capstone in your data

RAG with deliberate chunking and reranking, plus a basic retrieval eval.

Read lesson