Topic

BM25

All digests tagged BM25

Suggested route

Topic journey

Move from earlier context through the available material to the newest signals. This route is a reading aid, not a difficulty ranking.

Start here

The unreasonable effectiveness of BM25 for agentic search — Jo Kristian Bergum, Hornet.dev Sep 16, 2026 · 18:29 BM25, a 30-year-old lexical scoring function, is making a comeback for Agentic Search. The change is not in the function, but in the user: the LLM agent, which can formulate highly specific queries and execute complex search trajectories.

Recent signals

Vector Isn't Enough: Hybrid Search & Retrieval — Jeff Vestal & James Williams, Elastic Oct 11, 2026 · 1:16:20 Learn how to build robust AI agents by mastering hybrid search. This workshop covers combining semantic (vector) and lexical (BM25) search, using ESQL, and implementing advanced reranking techniques in Elasticsearch.

AI Engineer

Vector Isn't Enough: Hybrid Search & Retrieval — Jeff Vestal & James Williams, Elastic

Learn how to build robust AI agents by mastering hybrid search. This workshop covers combining semantic (vector) and lexical (BM25) search, using ESQL, and implementing advanced reranking techniques in Elasticsearch.

Read article

AI Engineer

The unreasonable effectiveness of BM25 for agentic search — Jo Kristian Bergum, Hornet.dev

BM25, a 30-year-old lexical scoring function, is making a comeback for Agentic Search. The change is not in the function, but in the user: the LLM agent, which can formulate highly specific queries and execute complex search trajectories.

Read article