Struct CohereEmbeddingProvider 

pub struct CohereEmbeddingProvider { /* private fields */ }

Embedding provider backed by the Cohere embed API (v2).

Stores the API key, model, and dimension configuration. Calling [embed()] performs a real HTTP request when the http-embeddings feature is enabled. Without the feature, it returns an error. For local/offline embeddings, use LocalEmbedding.

Implementations

impl CohereEmbeddingProvider

pub fn new(api_key: impl Into<String>, model: Option<String>) -> Self

Create a new Cohere embedding provider.

model defaults to "embed-english-v3.0".

pub fn with_input_type(self, input_type: impl Into<String>) -> Self

Set the input type ("search_document" for indexing, "search_query" for querying).

pub fn with_dimensions(self, dimensions: usize) -> Self

Override the output dimension count.

pub fn model(&self) -> &str

Returns the model name.

pub fn input_type(&self) -> &str

Returns the current input type.

Trait Implementations

impl EmbeddingProvider for CohereEmbeddingProvider

fn embed<'life0, 'life1, 'async_trait>( &'life0 self, _text: &'life1 str, ) -> Pin<Box<dyn Future<Output = ArgentorResult<Vec<f32>>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Compute embedding vector for a single text.

fn dimension(&self) -> usize

Dimension of the embedding vectors produced by this provider.

fn embed_batch<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, texts: &'life1 [&'life2 str], ) -> Pin<Box<dyn Future<Output = ArgentorResult<Vec<Vec<f32>>>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait,

Compute embeddings for a batch of texts.