Skip to main content

Embedder

Trait Embedder 

Source
pub trait Embedder: Send + Sync {
    // Required methods
    fn embed_batch<'life0, 'life1, 'async_trait>(
        &'life0 self,
        texts: &'life1 [String],
    ) -> Pin<Box<dyn Future<Output = Result<Vec<Vec<f32>>>> + Send + 'async_trait>>
       where Self: 'async_trait,
             'life0: 'async_trait,
             'life1: 'async_trait;
    fn dimension(&self) -> usize;
}
Expand description

Abstraction over embedding backends.

Why: Decouple consumers from any one model so we can swap in remote APIs, quantised models, or deterministic mocks without changing call sites. What: a single primitive — embed_batch — plus a dimension accessor. Single-text callers should use the embed_one convenience helper. Test: covered by FastEmbedder and MockEmbedder tests below.

Required Methods§

Source

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

Embed a batch of texts. Returns one Vec<f32> per input, each of length self.dimension(). An empty input batch returns an empty Vec.

Source

fn dimension(&self) -> usize

Output dimension of the produced embeddings.

Implementors§