/combining-searches

name: qdrant-hybrid-search-combining
description: "Fusing scores from multiple searches into a single ranked result (RRF, DBSF, custom fusion). Use when someone asks 'RRF or DBSF?', 'how to combine sparse and dense', 'how to combine scores from multiple searches?', 'custom fusion', 'fusion is not producing good results', 'how do I tune RRF', 'what k should I use', or 'how do I set fusion weights'"

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.

Tune in this order, cheapest first: confirm fusion beats each prefetch alone on your labels, compare Qdrant's default RRF vs DBSF, if tuning RRF: settle `k`, then sweep weights at that `k`, and validate on held-out queries. A weight pair is only valid for the `k` it was tuned with [Tune in this order](https://skills.qdrant.tech/md/documentation/search-tuning/how-to-tune-hybrid-search/?s=tune-in-this-order)

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](https://skills.qdrant.tech/md/documentation/search/hybrid-queries/?s=reciprocal-rank-fusion-rrf)** (Reciprocal Rank Fusion): rank-based, ignores scores magnitude.
• Start with RRF at Qdrant's defaults, `k=2` and equal weights.
• Tune `k` to [control rank sensitivity in RRF fusion](https://skills.qdrant.tech/md/documentation/search/hybrid-queries/?s=setting-rrf-constant-k), choosing the value from your labels [Use labels to choose a `k` range](https://skills.qdrant.tech/md/documentation/search-tuning/how-to-tune-hybrid-search/?s=use-labels-to-choose-a-k-range).
• Add per-prefetch **weights** when one search should dominate, using [Weighted RRF](https://skills.qdrant.tech/md/documentation/search/hybrid-queries/?s=weighted-rrf). Weights should be customized per collection and retrievers' score distributions. [Tune weights last](https://skills.qdrant.tech/md/documentation/search-tuning/how-to-tune-hybrid-search/?s=tune-weights-last).

DBSF

• **[DBSF](https://skills.qdrant.tech/md/documentation/search/hybrid-queries/?s=distribution-based-score-fusion-dbsf)** (Distribution-Based Score Fusion): normalizes each prefetch's scores (mean ± 3 standard deviations) before fusing, so pick it when you trust the retrievers' raw scores to carry magnitude. Normalization is per query, so don't compare absolute DBSF scores across queries, and raise the prefetch `limit` if one outlier makes rankings unstable.
• DBSF has no parameters to tune, so compare it before hand-tuning RRF `k` and weights. Confirm on your own labels [Compare RRF and DBSF on your labels](https://skills.qdrant.tech/md/documentation/search-tuning/how-to-tune-hybrid-search/?s=compare-rrf-and-dbsf-on-your-labels)

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.

**[With formula query](https://skills.qdrant.tech/md/documentation/search/search-relevance/?s=score-boosting)**, access `score` of each prefetch and, if desired, payload field values.

If you want to implement custom fusion on `score` of each prefetch:

• Use decay or any other available expressions for normalizing score distributions before fusing them.
• Parameters of these expressions should be based on the collection & retriever score distributions (for example, adjusting these parameters on a subsample of real queries).
• Formula query is unable to provide ranks for custom fusions

When using `FormulaQuery` over multiple prefetches (e.g. per-representation weighting):

• `$score[i]` indexes prefetches in declaration order. Reordering the `prefetch=` list silently shifts which weight applies to which retriever.
• Provide `defaults` for every `$score[i]` so the formula still evaluates for candidates that surfaced from only a subset of prefetches.
• On Qdrant 1.19.1 or newer, `max` and `min` expressions take the best or worst of several `$score[i]` (for example, keep each point's best score across per-field BM25 prefetches), cap a boost (`min(cap, boost)`), or clamp a value with `max(lo, min(hi, x))`. A point absent from a prefetch has `$score[i]` of `0.0`, which wins `max` over negative scores and `min` over positive ones, so set `defaults` (keys include the `$`, placed beside `formula`, never inside it) to a value outside the expected score range such as `-1e30` for `max` or `1e30` for `min` [Max and min](https://skills.qdrant.tech/md/documentation/search/search-relevance/?s=max-and-min).
• On 1.19.1 or newer, `acosh` supports exact geodesic-distance rescoring for hyperbolic embeddings (Lorentz model with `Dot` distance, `acosh(-$score)`, negated so closest ranks first). The input must be at least 1 [Hyperbolic distance](https://skills.qdrant.tech/md/documentation/search/search-relevance/?s=hyperbolic-distance).
• Start with RRF when scores are on incomparable scales (e.g. BM25 + cosine). Reach for `FormulaQuery` only when explicit per-representation weighting or payload-driven boosts are required, and normalize each `$score[i]` (decay or min-max on a sampled distribution) before combining linearly.

Need Good Ranking of Fused Candidates and Ready To Spend More Resources

Use when: you want to use similarity between query and candidates' vector representations as the prefetches combiner and simultaneously ranker. More resource heavy than score/rank based fusions, but might be necessary due to use case requirements or need in a high top-K precision of results (when parallel prefetches have overall a good recall of retrieved candidates).

More can