Struct EmbeddingModel 

pub struct EmbeddingModel {
    pub model: String,
    /* private fields */
}

Cohere embedding model wrapper

Fields

model: String

Model identifier

Implementations

impl EmbeddingModel

pub fn new(client: Client, model: &str, ndims: usize) -> Self

Creates a new embedding model instance

Arguments

• client - Cohere API client
• model - Model identifier
• ndims - Number of dimensions in the embedding vectors

Trait Implementations

impl Clone for EmbeddingModel

fn clone(&self) -> EmbeddingModel

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl EmbeddingFeaturesDyn for EmbeddingModel

fn ndims(&self) -> usize

Returns the number of dimensions for this embedding model

fn embed( &self, texts: Vec<String>, ) -> BoxPinFut<Result<(Vec<Embedding>, Usage), BoxError>>

Generates embeddings for a batch of texts

Arguments

• texts - Vector of text strings to embed

Returns

Future resolving to a vector of Embedding structs

https://docs.cohere.com/reference/embed Maximum number of texts per call is 96. Tecommend reducing the length of each text to be under 512 tokens for optimal quality.

fn embed_query( &self, text: String, ) -> BoxPinFut<Result<(Embedding, Usage), BoxError>>

Generates an embedding for a single query text

Arguments

• text - Query text to embed

Returns

Future resolving to a single Embedding struct