Struct BgeM3Provider 

pub struct BgeM3Provider { /* private fields */ }

BGE-M3 embedding provider.

Uses fastembed for ONNX inference. 1024-dimensional embeddings, supports 100+ languages.

Implementations

impl BgeM3Provider

pub fn new() -> Result<Self, EmbedError>

Create a new BGE-M3 provider with default settings.

pub fn with_cache_size(cache_size: usize) -> Result<Self, EmbedError>

Create a new BGE-M3 provider with custom cache size.

Trait Implementations

impl EmbeddingProvider for BgeM3Provider

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

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

Generate embeddings for a batch of texts.

fn dimensions(&self) -> usize

Vector dimensionality of this provider.

fn model_id(&self) -> &str

Human-readable model identifier.

fn max_batch_size(&self) -> usize

Maximum batch size supported.

fn embed_one<'life0, 'life1, 'async_trait>( &'life0 self, text: &'life1 str, ) -> Pin<Box<dyn Future<Output = Result<Embedding, EmbedError>> + Send + 'async_trait>>

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

Embed a single text (convenience method).