How deeply does Generative AI in Action cover BM25?

Defines ranking inputs and contrasts alternatives but stops short of mathematical derivation or implementation details.

BM25

BM25 is a probabilistic ranking function that estimates document relevance to a query using term frequency, inverse document frequency, document length, and term-frequency saturation.

BM25 ranks documents by estimating query relevance from term frequency, inverse document frequency, document length, and term-frequency saturation. It is a sparse retrieval option for retrieval-augmented generation when queries closely match document wording and speed matters. section 7.4

Choose BM25 by balancing retrieval behavior and operational constraints:

Prefer sparse retrieval when computational efficiency is important or query terms are expected to match document text closely. section 7.4
Contrast BM25 with TF-IDF, which lacks BM25’s additional treatment of document length and term-frequency saturation. section 7.4
Consider dense retrieval such as DPR when semantic matching and nuanced language understanding outweigh computational cost. section 7.4

How Generative AI in Action covers it

liveBook manning.com

Read Generative AI in Action on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Elasticsearch in Action, Second EditionOkapi BM25 is a probabilistic information-retrieval ranking algorithm that scores documents using term frequency, document frequency, and document-length normalization.
liveBook manning.com

Domain-Specific Small Language ModelsA lexical information-retrieval ranking algorithm that scores documents using term frequency, inverse document frequency, and document length.
liveBook manning.com

The Art of AI Product DevelopmentBM25 is a lexical ranking function that scores documents using term frequency, document frequency, and document-length normalization.
liveBook manning.com

Building Reliable AI SystemsBM25 is a keyword-based ranking algorithm that scores documents according to query-term frequency while accounting for document length and term saturation.

Compare how 5 books explain BM25 →

Related concepts

lexical searchkind of · Lexical search retrieves or ranks items by matching query terms or other surface-text features against indexed content, often using sparse representations and statistical weighting.
hybrid searchused by · Hybrid search is an information-retrieval technique that combines multiple retrieval methods or relevance signals to find or rank relevant results.
similarity searchcontrasts with · Similarity search is a retrieval technique that finds or ranks items by comparing their representations with a query according to a similarity or distance measure.
term frequency-inverse document frequencycontrasts with · Term frequency-inverse document frequency is a text-weighting scheme that combines a term’s frequency in a document with its inverse frequency across a document collection.
Elasticsearchused by · Elasticsearch is a distributed search and analytics engine that indexes data for searching, retrieval, and analysis.
relevanceproduces · Relevance is the degree to which information, a result, or a response pertains to a query, task, purpose, or information need.

This explainer was generated by Manning's knowledge graph from the text of Generative AI in Action. The section links point to the parts of the book it draws on.