Full-text ranking function that weighs how often a term occurs, how rare it is across the corpus and how long each document is.
Also called Okapi BM25.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains BM25 in context, with comparison tables and the common traps.
Related terms
- Full-text search
Keyword retrieval in Azure AI Search that uses an inverted index with BM25 ranking. It excels at exact matches on names, identifiers and product codes but does not catch paraphrased wording.
- Semantic ranker
Feature of Azure AI Search that uses Bing-derived language models to re-order the leading BM25 or hybrid results, optionally adding answers and captions. Relevance improves with no change to embeddings.