RAG System Design

The chapters in this module, in reading order.

#	Chapter
00	RAG Fundamentals — The Five-Year-Old Version
01	The confident wrong answer — why a vanilla LLM fails on private knowledge
02	Open-book answering — what changes when the model sees the page
03	Chunking trade-offs — the hidden costs of splitting a document
04	Chunking strategies — the toolkit
05	Embeddings — index cards for meaning
06	Similarity and models — how the librarian measures closeness
07	Vector stores and ANN — the bookshelf at a hundred million chunks
08	The RAG pipeline — from question to grounded answer
09	Query understanding and retrieval — repairing the question before it hits the shelf
10	Reranking — the second pass that saves the answer
11	Prompt augmentation — building the answer brief
12	Retrieval metrics — grading the librarian before grading the writer
13	Faithfulness and RAGAS — measuring whether the answer obeys the evidence
14	Honest admission — what RAG does not solve