Trait ImageEmbeddingModel 

pub trait ImageEmbeddingModel: ModelInfo {
    // Required methods
    fn embed<'life0, 'async_trait>(
        &'life0 self,
        images: Vec<ImageInput>,
    ) -> Pin<Box<dyn Future<Output = Result<EmbedResult>> + Send + 'async_trait>>
       where Self: 'async_trait,
             'life0: 'async_trait;
    fn dimensions(&self) -> u32;

    // Provided method
    fn warmup<'life0, 'async_trait>(
        &'life0 self,
    ) -> Pin<Box<dyn Future<Output = Result<()>> + Send + 'async_trait>>
       where Self: Sync + 'async_trait,
             'life0: 'async_trait { ... }
}

A model that produces dense vector embeddings from images.

One vector is returned per input image, each of dimension dimensions. Implementations typically batch internally for GPU efficiency; callers should pass as large a batch as fits their latency budget.

Required Methods

fn embed<'life0, 'async_trait>( &'life0 self, images: Vec<ImageInput>, ) -> Pin<Box<dyn Future<Output = Result<EmbedResult>> + Send + 'async_trait>>

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

Embed a batch of images.

Errors

Returns an error if the provider fails to load any input, runs out of memory, or the upstream API rejects the request.

fn dimensions(&self) -> u32

The dimensionality of vectors produced by this model.

Provided Methods

fn warmup<'life0, 'async_trait>( &'life0 self, ) -> Pin<Box<dyn Future<Output = Result<()>> + Send + 'async_trait>>

where Self: Sync + 'async_trait, 'life0: 'async_trait,

Optional warmup hook (e.g. load weights into memory on first access). The default is a no-op.

Errors

Returns an error if the underlying model fails to initialize.

Implementors

impl ImageEmbeddingModel for InstrumentedImageEmbeddingModel