Crate rank_fusion 

Rank fusion for hybrid search.

Combine results from multiple retrievers (BM25, dense, sparse) into a single ranking.

use rank_fusion::rrf;

let bm25 = vec![("d1", 12.5), ("d2", 11.0)];
let dense = vec![("d2", 0.9), ("d3", 0.8)];
let fused = rrf(&bm25, &dense);
// d2 ranks highest (appears in both lists)

Algorithms

Function	Uses Scores	Best For
rrf	No	Incompatible score scales
isr	No	When lower ranks matter more
combsum	Yes	Similar scales, trust scores
combmnz	Yes	Reward overlap between lists
borda	No	Simple voting
weighted	Yes	Custom retriever weights
dbsf	Yes	Different score distributions

All have *_multi variants for 3+ lists.

Performance Notes

OpenSearch benchmarks (BEIR) show RRF is ~3-4% lower NDCG than score-based fusion (CombSUM), but ~1-2% faster. RRF excels when score scales are incompatible or unknown. See OpenSearch RRF blog.

Modules

prelude

Prelude for common imports.

Structs

FusionConfig

Configuration for rank-based fusion (Borda, CombSUM, CombMNZ).

RrfConfig

RRF configuration.

WeightedConfig

Weighted fusion configuration.

Enums

FusionError

Errors that can occur during fusion.

FusionMethod

Unified fusion method for dispatching to different algorithms.

Functions

borda

Borda count voting — position-based scoring.

borda_multi

Borda count for 3+ result lists.

borda_with_config

Borda count with configuration.

combmnz

Normalized sum × overlap count (rewards agreement).

combmnz_multi

CombMNZ for 3+ result lists.

combmnz_with_config

CombMNZ with configuration.

combsum

Sum of min-max normalized scores.

combsum_multi

CombSUM for 3+ result lists.

combsum_with_config

CombSUM with configuration.

dbsf

Distribution-Based Score Fusion (DBSF).

dbsf_multi

DBSF for 3+ result lists.

dbsf_with_config

DBSF with configuration.

isr

Inverse Square Root rank fusion with default config (k=1).

isr_multi

ISR for 3+ result lists.

isr_with_config

ISR with custom configuration.

rrf

Reciprocal Rank Fusion of two result lists with default config (k=60).

rrf_into

RRF with preallocated output buffer.

rrf_multi

RRF for 3+ result lists.

rrf_weighted

Weighted RRF: per-retriever weights applied to rank-based scores.

rrf_with_config

RRF with custom configuration.

weighted

Weighted score fusion with configurable retriever trust.

weighted_multi

Weighted fusion for 3+ result lists.

Type Aliases

Result

Result type for fusion operations.