Struct GemmaEmbedding 

pub struct GemmaEmbedding { /* private fields */ }

Local embedding engine using quantized EmbeddingGemma model via candle.

Implementations

impl GemmaEmbedding

pub fn new(config: EmbeddingConfig) -> Result<Self, EmbeddingError>

Creates a new GemmaEmbedding from build-time prepared model files.

pub fn from_files( config: EmbeddingConfig, model_files: &ModelFiles, ) -> Result<Self, EmbeddingError>

Creates a GemmaEmbedding from pre-downloaded model files.

Trait Implementations

impl EmbeddingEngine for GemmaEmbedding

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

Returns the engine name (e.g., “gemma”, “remote”).

fn dimensions(&self) -> usize

Returns the output vector dimensions.

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

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

Computes an embedding vector for a single text input.

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

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

Computes embedding vectors for a batch of text inputs.