Struct CohereEmbedV4Provider 

pub struct CohereEmbedV4Provider { /* private fields */ }

Embedding provider backed by the Cohere v2 embed API (labeled “v4” here to disambiguate from the existing CohereEmbeddingProvider and to mirror the naming in higher-level integrations).

Differs from CohereEmbeddingProvider in that it exposes explicit input_type helpers (for_search_document, for_search_query) and supports embed-english-v3.0 / embed-multilingual-v3.0 at 1024 dims.

Implementations

impl CohereEmbedV4Provider

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

Create a new v4 provider with the default model (embed-english-v3.0).

pub fn with_model( api_key: impl Into<String>, model: impl Into<String>, dimensions: usize, ) -> Self

Create with an explicit model and dimension override.

pub fn for_search_document(self) -> Self

Configure this provider for indexing documents (search_document).

pub fn for_search_query(self) -> Self

Configure this provider for querying (search_query).

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

Set an arbitrary input_type string.

pub fn with_base_url(self, base_url: impl Into<String>) -> Self

Override the API base URL.

pub fn model(&self) -> &str

Returns the configured model name.

pub fn input_type(&self) -> &str

Returns the current input type.

pub fn build_payload(&self, texts: &[String]) -> Value

Build the request payload for the Cohere v2 embed endpoint.

Trait Implementations

impl EmbeddingProvider for CohereEmbedV4Provider

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.