Skip to main content

EmbeddingService

lattice_embed

Trait EmbeddingService 

Source 
pub trait EmbeddingService: Send + Sync {
    // Required methods
    fn embed<'life0, 'life1, 'async_trait>(
        &'life0 self,
        texts: &'life1 [String],
        model: EmbeddingModel,
    ) -> Pin<Box<dyn Future<Output = Result<Vec<Vec<f32>>>> + Send + 'async_trait>>
       where Self: 'async_trait,
             'life0: 'async_trait,
             'life1: 'async_trait;
    fn supports_model(&self, model: EmbeddingModel) -> bool;
    fn name(&self) -> &'static str;

    // Provided methods
    fn embed_one<'life0, 'life1, 'async_trait>(
        &'life0 self,
        text: &'life1 str,
        model: EmbeddingModel,
    ) -> Pin<Box<dyn Future<Output = Result<Vec<f32>>> + Send + 'async_trait>>
       where Self: 'async_trait,
             'life0: 'async_trait,
             'life1: 'async_trait { ... }
    fn model_config(&self, model: EmbeddingModel) -> ModelConfig { ... }
}
Expand description

Stable: external consumers may depend on this; breaking changes require a SemVer bump.

Trait for embedding generation services.

This trait defines the interface for services that can convert text into vector embeddings. Implementations may use local models (native Rust) or remote APIs.

§Example

use lattice_embed::{EmbeddingService, EmbeddingModel, NativeEmbeddingService};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let service = NativeEmbeddingService::default();
    let embedding = service.embed_one("Hello, world!", EmbeddingModel::default()).await?;
    assert_eq!(embedding.len(), 384);
    Ok(())
}

Required Methods§

Source

fn embed<'life0, 'life1, 'async_trait>( &'life0 self, texts: &'life1 [String], model: EmbeddingModel, ) -> Pin<Box<dyn Future<Output = Result<Vec<Vec<f32>>>> + Send + 'async_trait>>
where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Stable: generate embeddings for multiple texts.

Returns a vector of embeddings, one for each input text, in the same order.

Source

fn supports_model(&self, model: EmbeddingModel) -> bool

Stable: check if the service supports a given model.

Source

fn name(&self) -> &'static str

Stable: get the name/identifier of this service.

Provided Methods§

Source

fn embed_one<'life0, 'life1, 'async_trait>( &'life0 self, text: &'life1 str, model: EmbeddingModel, ) -> Pin<Box<dyn Future<Output = Result<Vec<f32>>> + Send + 'async_trait>>
where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Stable: generate an embedding for a single text.

This is a convenience method that calls embed with a single-element slice.

Source

fn model_config(&self, model: EmbeddingModel) -> ModelConfig

Unstable: returns the effective ModelConfig for a given model on this service.

The default returns a config with no MRL truncation. NativeEmbeddingService overrides this to expose the configured output dimension so CachedEmbeddingService can include the actual dimension in cache keys.

Implementors§