Enum FusionStrategy 

pub enum FusionStrategy {
    Average,
    Maximum,
    RRF {
        k: u32,
    },
    Weighted {
        avg_weight: f32,
        max_weight: f32,
        hit_weight: f32,
    },
}

Strategy for fusing results from multiple vector searches.

Each strategy combines results differently, optimizing for various use cases:

• Average: Good for general-purpose fusion
• Maximum: Emphasizes documents that score very high in any query
• RRF: Position-based fusion, robust to score scale differences
• Weighted: Custom combination with explicit control over factors

Variants

Average

Average score across all queries where the document appears.

Score = mean(scores for this document across queries)

Maximum

Maximum score across all queries.

Score = max(scores for this document across queries)

RRF

Reciprocal Rank Fusion.

Score = Σ 1/(k + rank_i) for each query where document appears. Standard k=60 provides good balance between emphasizing top ranks while still considering lower-ranked results.

Fields

k: u32

Ranking constant (default: 60).

Weighted

Weighted combination of average, maximum, and hit ratio.

Score = avg_weight × avg_score + max_weight × max_score + hit_weight × hit_ratio where hit_ratio = (number of queries containing doc) / (total queries)

Fields

avg_weight: f32

Weight for average score component.

max_weight: f32

Weight for maximum score component.

hit_weight: f32

Weight for hit ratio component.

Implementations

impl FusionStrategy

pub fn rrf_default() -> Self

Creates an RRF strategy with the standard k=60 parameter.

pub fn weighted( avg_weight: f32, max_weight: f32, hit_weight: f32, ) -> Result<Self, FusionError>

Creates a Weighted strategy with validation.

Errors

Returns an error if:

• Weights do not sum to 1.0 (within 0.001 tolerance)
• Any weight is negative

pub fn fuse( &self, results: Vec<Vec<(u64, f32)>>, ) -> Result<Vec<(u64, f32)>, FusionError>

Fuses results from multiple queries into a single ranked list.

Arguments

• results - Vec of search results, one per query. Each inner Vec contains (document_id, score) tuples, assumed sorted by score descending.

Returns

A single Vec of (document_id, fused_score) sorted by score descending.

Errors

Currently infallible, but returns Result for future extensibility.

Trait Implementations

impl Clone for FusionStrategy

fn clone(&self) -> FusionStrategy

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for FusionStrategy

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for FusionStrategy

fn default() -> Self

Returns the “default value” for a type.

impl PartialEq for FusionStrategy

fn eq(&self, other: &FusionStrategy) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for FusionStrategy