Use RRF sparingly in hybrid search

Published 3 days ago • 1 min read

Reciprocal Rank Fusion merges one system’s search ranking with another’s (ie lexical + embedding search). RRF scores a document with ∑1/rank of each underlying system.

I’ve found RRF is not enough. Here’s the typical pattern I see on teams:

A mature lexical solution exists. It’s pretty good,
The team wants to add untuned, embedding based retrieval,
They deploy a vector DB, and RRF embedding results with the mature system,
Disaster ensues! The poor embedding results drag down the lexical system

RRF’ing good search with bad search just leads to bad outcomes.

Where does RRF work?

It works before a reranker. It’s a great way to merge sources into a single listing for multiple candidates
It works when systems are different, but good. IE the vector / lexical compliment each other with their own unique / good results

-Doug

Events · Consulting · Training (use code search-tips)

You're subscribed to Doug Turnbull's daily search tips where I share tips, blog articles, events, and more. You can always manage your profile:

Vector search means query understanding!? (daily search tip)

Good vector search means more than embeddings. Embeddings don’t know when a result matches / doesn’t match. Similarity floors don’t work consistently - a cutoff that works for one query might be disastrous for another. Even worse: your embedding usually can’t capture every little bit of meaning from your corpus. You need to efficiently pick the best top N candidates from your vector database. What do you need? Query Understanding - translating the query to domain language (categories, colors,...

about 20 hours ago • 1 min read

Blog post on Bayesian BM25

Just sharing my post on Bayesian BM25 and other ways of normalizing BM25 scores. Enjoy! https://softwaredoug.com/blog/2026/03/06/probabilistic-bm25-utopia Do you have any thoughts on normalizing BM25 scores? -Doug Events · Consulting · Training (use code search-tips) You're subscribed to Doug Turnbull's daily search tips where I share tips, blog articles, events, and more. You can always manage your profile:

4 days ago • 1 min read

Ugly hack to force BM25 to 0-1 (daily search tip)

Its convenient to have a lexical score normalized from 0-1. Sadly BM25 scores tend to be all over the place (0.5? 5.1? 12.51?). Fine for ranking. Annoying for other goals. That's why I wrote a post about one way to compute probabilities from BM25. In that post, I allude to one hack that forces BM25 to 0-1. Let's walk through it. A query term’s BM25 score is IDF * TF. Lucene’s TF is already normalized Lucene drops the (k1 + 1) in the numerator of BM25, giving you: Now we’ve got a TF term...

5 days ago • 1 min read