Struct NativeEmbeddingService 

pub struct NativeEmbeddingService { /* private fields */ }

Unstable: model-loading API still evolving; signature may change as lattice-inference matures.

Pure-Rust local embedding service for one BERT-family or Qwen model configuration.

It memoizes the load result independently of cancellation. See docs/service.md for loading and architecture details.

Implementations

impl NativeEmbeddingService

pub fn new() -> Self

Unstable: constructor signature may change; use EmbeddingService trait for stable API.

pub fn with_model(model_type: EmbeddingModel) -> Self

Unstable: constructor signature may change; use EmbeddingService trait for stable API.

pub fn with_model_config(model_config: ModelConfig) -> Result<Self>

Unstable: create with explicit model config (model + optional MRL truncation dim).

pub fn with_model_from_env(model_type: EmbeddingModel) -> Result<Self>

Unstable: create with model config read from LATTICE_EMBED_DIM env var.

pub fn save_cache(&self) -> Result<usize>

Unstable: persistence API may be moved to a separate manager type.

pub fn cache_size(&self) -> usize

Unstable: internal diagnostic; may be removed or moved to metrics.

pub async fn ensure_loaded(&self) -> Result<()>

Unstable: preload the model without performing an encode pass.

Returns the same loading errors as the first embed call. See docs/service.md for preload behavior.

Trait Implementations

impl Default for NativeEmbeddingService

fn default() -> Self

Returns the “default value” for a type.

impl EmbeddingService for NativeEmbeddingService

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.

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

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

Stable: embed texts under a retrieval role, applying that role’s instruction.

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

Unstable: returns the effective configuration used for this model’s cache keys.

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

Stable: check if the service supports a given model.

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

Stable: get the name/identifier of this service.

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.

fn embed_query<'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: embed query texts after applying the model’s query instruction.

fn embed_passage<'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: embed passages after applying the model’s document instruction.