BM25
Classic lexical ranking function based on term frequency and document length. Strong on exact names and rare terms.
Reference ↗Related
3 articles
65,651 lines on 29 dependencies
Twelve modules we wrote by hand instead of installing a framework: rank fusion in 84 lines, a tool-call salvager in 197. What each replaced, and when a library is still the right call.
Why your retrieval scores cannot be averaged
Our unified search compared three different quantities in one column. The exact answer ranked below a weaker one, purely because of scale. What we measured, and what we changed.
Store a rule as the situation that triggers it
Retrieved by its own wording, a behavioural rule came back 1 time in 5. Stored as the situations it should fire in, 10 of 10. And where the trick stops working.