Enum RankingExpression 

pub enum RankingExpression {
    Fusion {
        sources: Vec<QueryExpression>,
        method: FusionMethod,
        rank_constant: f32,
        rank_window_size: Option<usize>,
        weights: Option<Vec<f32>>,
    },
}

Result-set composition expressions.

See [[feature-rrf-retrievers#RankingExpression]].

Variants

Fusion

Fuse N query sources using a configurable method.

Each source is executed independently, then results are combined using the specified fusion method. Sources can be scoring queries or nested fusion expressions.

Fields

sources: Vec<QueryExpression>

method: FusionMethod

rank_constant: f32

Rank constant k for RRF: score(d) = Σ 1/(k + rank). Default: 60.

rank_window_size: Option<usize>

Number of candidates per source before fusion. Default: search size.

weights: Option<Vec<f32>>

Per-source weights for score-based fusion methods. Default: equal weights (1.0 each).

Trait Implementations

impl Clone for RankingExpression

fn clone(&self) -> RankingExpression

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RankingExpression

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

Formats the value using the given formatter.

impl PartialEq for RankingExpression

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