Enum FusionMethod 

pub enum FusionMethod {
    Rrf {
        k: f32,
    },
    NormalizedWeightedSum,
}

Method for fusing multiple ranked result lists.

Variants

Rrf

Reciprocal Rank Fusion: score(d) = Σ_i w_i / (k + rank_i(d)).

Rank-based, so it is insensitive to incompatible score scales (BM25 vs cosine similarity). k dampens the impact of top ranks; 60 is the standard value.

Fields

k: f32

NormalizedWeightedSum

Weighted sum of min-max normalized scores: score(d) = Σ_i w_i * (s_i(d) - min_i) / (max_i - min_i).

Score-based, preserves score gaps within each list. Sensitive to outliers; prefer RRF unless the score distributions are known.

Degenerate lists where every score is identical (including single-result lists) have no min-max range; every document in such a list contributes the full weight, as if tied at the top. Avoid feeding filter-like subqueries (many docs, constant score) through this method — use Rrf, which only depends on ranks.

Trait Implementations

impl Clone for FusionMethod

fn clone(&self) -> FusionMethod

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for FusionMethod

impl Debug for FusionMethod

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

Formats the value using the given formatter.

impl Default for FusionMethod

fn default() -> Self

Returns the “default value” for a type.

impl PartialEq for FusionMethod

fn eq(&self, other: &FusionMethod) -> 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 FusionMethod