Enum FusionStrategy 

pub enum FusionStrategy {
    Rrf {
        k: u32,
    },
    WeightedSum,
}

How federated result lists are merged.

Defaults to FusionStrategy::Rrf (rank-based, scale-invariant). See the module docs for why this matters across heterogeneous backends.

Variants

Rrf

Reciprocal Rank Fusion with constant k (typically 60). Rank-based, so no score normalization is required across backends.

Fields

k: u32

RRF smoothing constant (larger = flatter).

WeightedSum

Weighted sum of min-max-normalized per-list scores. Each list is normalized in isolation before summing, so this is only correct when every backend scores on a comparable scale — otherwise prefer FusionStrategy::Rrf.

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.