Enum Fusion 

#[non_exhaustive]
pub enum Fusion {
    ReciprocalRank {
        k: f64,
    },
    Weighted {
        semantic_weight: f64,
    },
    LexicalFirst,
}

How lexical and semantic results are combined.

Variants (Non-exhaustive)

Non-exhaustive enums could have additional variants added in future. Therefore, when matching against variants of non-exhaustive enums, an extra wildcard arm must be added to account for any future variants.

ReciprocalRank

Reciprocal rank fusion: each list adds 1 / (k + rank), ranks from 1. Needs no score calibration; k = 60 is the common choice.

Fields

k: f64

Weighted

(1 - semantic_weight) * lexical + semantic_weight * max(semantic, 0). Lexical scores are in [0, 1]; semantic ones are inner products, cosine for normalised vectors.

Fields

semantic_weight: f64

LexicalFirst

Lexical hits in their order, then semantic hits not found lexically.

Trait Implementations

impl Clone for Fusion

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for Fusion

impl Debug for Fusion

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

Formats the value using the given formatter.

impl Default for Fusion

fn default() -> Self

Returns the “default value” for a type.

impl PartialEq for Fusion

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

Equality operator ==.

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

Inequality operator !=.

impl StructuralPartialEq for Fusion