What does alpha mean here?

The blended score is alpha × dense + (1 − alpha) × BM25, after per-query min-max normalisation. Alpha = 1 is pure dense (semantic), alpha = 0 is pure BM25 (keyword); the tuner finds the mix that ranks relevant docs highest.

Why normalise the scores first?

BM25 and cosine/dot-product scores live on completely different scales, so adding them raw lets one dominate. Min-max normalising each query's scores to 0–1 puts them on equal footing before blending.

How much eval data do I need?

Enough labelled queries that the result is stable — typically 30+ queries with several candidates each. With only a handful of queries the optimal alpha can be noisy, so treat it as a starting point.

No. The sweep runs entirely in your browser. Nothing you paste is sent to a server, stored or logged.

Hybrid Search Weight Tuner

Tune the BM25 ↔ dense blend for hybrid RAG

Hybrid retrieval combines keyword search (BM25) and dense vector search, blended by a weight alpha. Picking alpha by gut feel leaves quality on the table. This tool takes your labelled eval scores and sweeps every alpha from 0 to 1, reporting the value that maximises your chosen retrieval metric — so you ship the blend your own data prefers. It runs in your browser.

How it works

For each query, the candidates’ BM25 and dense scores are min-max normalised to 0–1 (so neither scale dominates), then combined:

score = alpha × dense_norm + (1 − alpha) × bm25_norm

Candidates are re-ranked by the blended score and the chosen metric is computed:

MRR — mean of 1 / rank of the first relevant result per query.
Hit@K — fraction of queries with a relevant result in the top K.

The tuner evaluates alpha at fine steps across [0, 1] and returns the alpha with the best average metric, plus a small table showing how the metric varies so you can see how sensitive your system is to the choice.

Tips and notes

A flat curve means alpha barely matters — pick a value for stability and move on. A sharp peak means the blend really matters; lock it in.
Make sure each query’s candidate list includes the relevant doc(s); otherwise no alpha can rank them and the metric is artificially low.
This optimises the linear blend; if you use reciprocal rank fusion instead, the intuition (balance keyword vs semantic) still holds, but tune RRF’s k separately.