AnyLearn
All cursus
Computer Scienceintermediate

Search Relevance: From BM25 to Hybrid

Vector search did not replace keyword search; production search runs both, because they fail in opposite places. This path builds relevance engineering from the ground up: the inverted index and the analysis decisions baked into it, BM25 and its saturation arithmetic, hybrid retrieval with reciprocal rank fusion, and the evaluation machinery, judgment sets, NDCG, position bias, that tells you whether any of it actually got better.

0 of 4 lessons complete
Sign in to track progress and earn a certificate.

Lessons, in order

  1. 1
    Computer Science
    The Inverted Index, and Why Analysis Decides Everything
    Start
  2. 2
    Computer Science
    BM25: How Lexical Relevance Is Actually Computed
    Start
  3. 3
    Computer Science
    Lexical Meets Vector: Hybrid Search and Rank Fusion
    Start
  4. 4
    Computer Science
    Measuring Relevance: Judgments, NDCG, and the Click Trap
    Start