The keyword-ranking algorithm behind classic search engines.
1 min readupdated 2026-07-04
/ quick answer
BM25 scores documents by term frequency, inverse document frequency, and length normalization. It's fast, deterministic, and complements dense vector retrieval in hybrid search. The keyword-ranking algorithm behind classic search engines.
The keyword-ranking algorithm behind classic search engines. BM25 scores documents by term frequency, inverse document frequency, and length normalization. It's fast, deterministic, and complements dense vector retrieval in hybrid search. In practice: Elasticsearch and Postgres full-text search both use BM25 under the hood. This dictionary node is part of the Onexial knowledge graph and links to related concepts, workflows and tools below.
Definition
BM25 scores documents by term frequency, inverse document frequency, and length normalization. It's fast, deterministic, and complements dense vector retrieval in hybrid search.
Example
Elasticsearch and Postgres full-text search both use BM25 under the hood.
/ frequently asked
What is BM25?
BM25 scores documents by term frequency, inverse document frequency, and length normalization. It's fast, deterministic, and complements dense vector retrieval in hybrid search.
What is an example of BM25?
Elasticsearch and Postgres full-text search both use BM25 under the hood.
Why does BM25 matter for AI and automation?
The keyword-ranking algorithm behind classic search engines. It connects to the workflows, prompts and tool stacks linked on this page, so you can move from definition to execution without leaving Onexial.