Combining Prefetch Results

The outer query fuses ranked candidate lists from all parallel prefetches into one ranked list of results. Fusion methods differ in whether they use rank, score or directly vector representations of candidates (their similarity to the outer query) and whether final score incorporates payload metadata. All methods support flat (one fusion step) and nested (multi-stage) prefetch structures.

Scores Are Not Comparable Across Prefetches & You Want Some Easy Baseline

Use when: searches produce scores on different scales, like BM25 and cosine on dense embeddings.

RRF

• RRF (Reciprocal Rank Fusion) — rank-based, ignores scores magnitude, a decent default to start with.
• Tune k to control rank sensitivity in RRF fusion.
• Add per-prefetch weights when one search should dominate, using Weighted RRF. Weights should be customized per collection and retrievers' score distributions!

DBSF

• DBSF (Distribution-Based Score Fusion) — normalizes score distributions per prefetch before fusing them, for that, instead of min-max, uses mean +- 3 deviations on prefetched list of scores. Avoid relying on resulting absolute scores, as scores in DBSF are normalized per prefetch (aka per a retrieved list of search results), and might be uncomparable across queries.

Need Custom Fusion

Use when: recency, popularity or other payload values should affect the merged ranking alongside candidate scores or you need a custom fusion.