All books

Retrieval Systems

Retrieval Engineering

Lexical, dense, approximate, hybrid, and reranked search with measurable evidence quality.

10 chapters · 4-6 hours reading · 3-4 hours labs · 5-8 hours project

Chapters

  1. 1Retrieval begins with a relevance contractMental model
  2. 2Model the corpus before choosing an indexData architecture
  3. 3Lexical retrieval and BM25 from first principlesFormal model
  4. 4Dense embeddings as learned retrieval geometryRepresentation
  5. 5Approximate nearest-neighbor indexesSystems architecture
  6. 6Hybrid candidate generation and rank fusionImplementation
  7. 7Reranking, late interaction, and result diversityRanking
  8. 8Implement a retrieval pipeline with explicit stagesFrom first principles
  9. 9Evaluate retrieval as a chain of evidenceEvaluation
  10. 10Secure and operate retrieval in productionOperations