Enum VectorMetric 

pub enum VectorMetric {
    Cosine,
    Euclidean,
    DotProduct,
    Manhattan,
}

Vector distance/similarity metric for vector scan operations.

Variants

Cosine

Cosine similarity (1 - cosine_distance). Best for normalized embeddings.

Euclidean

Euclidean (L2) distance. Best when magnitude matters.

DotProduct

Dot product. Best for maximum inner product search.

Manhattan

Manhattan (L1) distance. Less sensitive to outliers.

Trait Implementations

impl Clone for VectorMetric

fn clone(&self) -> VectorMetric

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for VectorMetric

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

Formats the value using the given formatter.

impl PartialEq for VectorMetric

fn eq(&self, other: &VectorMetric) -> 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 Copy for VectorMetric

impl Eq for VectorMetric

impl StructuralPartialEq for VectorMetric