Enum EmbeddingVector 

pub enum EmbeddingVector {
    Dense(Vec<f64>),
    DenseF32(Vec<f32>),
    Sparse(HashMap<String, f64>),
}

An embedding vector for semantic similarity comparison.

Variants

Dense(Vec<f64>)

Dense vector from API-based embeddings (f64 for precision).

DenseF32(Vec<f32>)

Dense f32 vector (for HNSW index compatibility).

Sparse(HashMap<String, f64>)

Sparse TF-IDF vector (term → weight).

Implementations

impl EmbeddingVector

pub fn cosine_similarity(&self, other: &Self) -> f64

Compute cosine similarity between two vectors.

pub fn is_empty(&self) -> bool

Returns true if this vector is empty/zero.

pub fn to_f32_dense(&self) -> Option<Vec<f32>>

Convert to f32 dense vector (for HNSW index).

• DenseF32 → clone
• Dense → cast f64 to f32
• Sparse → returns None (not convertible)

pub fn dimensions(&self) -> usize

Get the dimensionality of the vector.

Trait Implementations

impl Clone for EmbeddingVector

fn clone(&self) -> EmbeddingVector

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for EmbeddingVector

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for EmbeddingVector

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for EmbeddingVector

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

where __S: Serializer,

Serialize this value into the given Serde serializer.