Enum VectorDistance 

pub enum VectorDistance {
    Cosine,
    Euclidean,
    DotProduct,
}

Distance metric for vector similarity search.

Variants

Cosine

Cosine similarity distance (1 - cosine similarity)

Euclidean

Euclidean distance (L2 norm)

DotProduct

Dot-product (inner-product) distance.

Ranks by the inner product of two vectors: a larger inner product means greater similarity. The HNSW index treats smaller scores as closer, so the distance function returns the negated inner product (see dot_product_distance). For L2-normalized embeddings this ranks identically to VectorDistance::Cosine while skipping the per-vector normalization step.

Trait Implementations

impl Clone for VectorDistance

fn clone(&self) -> VectorDistance

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for VectorDistance

impl Debug for VectorDistance

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

Formats the value using the given formatter.

impl Default for VectorDistance

fn default() -> VectorDistance

Returns the “default value” for a type.

impl Eq for VectorDistance

impl PartialEq for VectorDistance

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