Struct NomicEmbedProvider 

pub struct NomicEmbedProvider { /* private fields */ }

Embedding provider backed by the Nomic Atlas embeddings API.

Default model: nomic-embed-text-v1.5 (768 dims). The Nomic endpoint accepts an array of texts under the texts key and responds with { "embeddings": [ [...], ... ] }.

Implementations

impl NomicEmbedProvider

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

Create a new Nomic provider with the default model (nomic-embed-text-v1.5).

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 with_task_type(self, task_type: impl Into<String>) -> Self

Set the task_type (search_document, search_query, clustering, classification).

pub fn model(&self) -> &str

Returns the configured model name.

pub fn task_type(&self) -> &str

Returns the current task type.

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

Build the request payload for the Nomic embeddings API.

Trait Implementations

impl EmbeddingProvider for NomicEmbedProvider

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.