Enum DistanceMetric 

pub enum DistanceMetric {
    L2 = 0,
    Cosine = 1,
    InnerProduct = 2,
    Manhattan = 3,
    Chebyshev = 4,
    Hamming = 5,
    Jaccard = 6,
    Pearson = 7,
}

Distance metric selection.

Variants

L2 = 0

Euclidean (L2) squared distance.

Cosine = 1

Cosine distance (1 - cosine_similarity).

InnerProduct = 2

Negative inner product (for max-inner-product search via min-heap).

Manhattan = 3

Manhattan (L1) distance: sum of absolute differences.

Chebyshev = 4

Chebyshev (L-infinity) distance: max absolute difference.

Hamming = 5

Hamming distance for binary-like vectors (threshold > 0.5).

Jaccard = 6

Jaccard distance for binary-like vectors (threshold > 0.5).

Pearson = 7

Pearson distance: 1 - Pearson correlation coefficient.

Trait Implementations

impl Clone for DistanceMetric

fn clone(&self) -> DistanceMetric

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for DistanceMetric

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for DistanceMetric

fn deserialize<__D>( __deserializer: __D, ) -> Result<DistanceMetric, <__D as Deserializer<'de>>::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for DistanceMetric

fn eq(&self, other: &DistanceMetric) -> 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 Serialize for DistanceMetric

fn serialize<__S>( &self, __serializer: __S, ) -> Result<<__S as Serializer>::Ok, <__S as Serializer>::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Copy for DistanceMetric

impl Eq for DistanceMetric

impl StructuralPartialEq for DistanceMetric