Skip to main content

Module multimodal

Module multimodal 

Source
Expand description

Multimodal embedding types and traits (image / audio / mixed-modality).

These types accompany the trait definitions for embedders that consume non-text inputs. Each trait sits alongside EmbeddingModel and returns an EmbedResult so remote providers can attach per-call usage counts.

Structs§

MultimodalInput
A heterogeneous input to a MultimodalEmbeddingModel.

Enums§

AudioInput
An audio input to a transcription or audio embedding model.
Modality
Modality labels reported by MultimodalEmbeddingModel::supported_modalities.
MultimodalBlock
One block of input to a MultimodalEmbeddingModel.

Traits§

AudioEmbeddingModel
A model that produces dense vector embeddings from audio.
ImageEmbeddingModel
A model that produces dense vector embeddings from images.
MultimodalEmbeddingModel
A model that produces a single dense vector from heterogeneous content (text + image + audio together).