liveBook · Manning

Field boosting

As explained in AI-Powered Search

Field boosting assigns different ranking weights to matches depending on the document field in which they occur.

Field boosting assigns different ranking weights to matching terms according to their document fields. A query can give matches in a title more influence than matches in a description, extending the default BM25 keyword score with configurable scoring functions. section 3.2.2

Title matches outweigh description matches

For the query “the cat in the hat,” setting title^10 and description^2.5 makes a title match contribute more strongly to relevance than an equivalent description match. The same request can be expressed through a generic search API or translated into engine-specific syntax. section 3.2.2

How AI-Powered Search covers it

How deep it goes
Defines configurable field weights and demonstrates request syntax without detailing score internals.
Examples
Uses a query for “the cat in the hat” with title^10 and description^2.5.
What it assumes
Assumes keyword querying and familiarity with relevance scores, while exposing field weights through a concrete request.
What you can do after
Apply it via a generic search API by assigning larger boosts to more important document fields.
How it connects
Connects BM25 similarity, relevance scoring, query fields, and search-engine-specific query syntax.

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