Part II · Retrieval
Chapter 07
Retrieval Quality
The highest-leverage chapter in the book — most teams reach for a better model when the failure is three stages upstream, in a component nobody measures.
Deliverable: A hybrid BM25 + dense retriever with reciprocal rank fusion and cross-encoder reranking, measured on a labelled case set.
What's inside
11 topics
- 7.1Why Naive RAG Fails: A Failure Taxonomy
- 7.2Diagnosing Failures by Stage
- 7.3Chunking Strategies Compared
- 7.4Small-to-Big and Contextual Prefixing
- 7.5Hybrid Search: BM25 with Dense Vectors
- 7.6Reciprocal Rank Fusion
- 7.7Cross-Encoder Reranking
- 7.8Metadata Filtering and Query Routing
- 7.9Query Rewriting and Multi-Query Expansion
- 7.10Measuring Retrieval: Recall, MRR, Faithfulness
- 7.11Caching Embeddings and Responses
Preparing PDF viewer…
A note on this content
The book and its chapters are my personal learning notes — compiled from online research and hands-on practice, with most of the content AI-generated from that research and learning. It is not a peer-reviewed publication, and I make no claim that it is 100% error-free. If you spot a mistake, I'd genuinely appreciate hearing about it — contact me.