Class MultiModalEmbeddingResponse (1.70.0)

MultiModalEmbeddingResponse(
    _prediction_response: typing.Any,
    image_embedding: typing.Optional[typing.List[float]] = None,
    video_embeddings: typing.Optional[
        typing.List[vertexai.vision_models.VideoEmbedding]
    ] = None,
    text_embedding: typing.Optional[typing.List[float]] = None,
)

The multimodal embedding response.

Attributes

Name Description
image_embedding List[float]
Optional. The embedding vector generated from your image.
video_embeddings List[VideoEmbedding]
Optional. The embedding vectors generated from your video.
text_embedding List[float]
Optional. The embedding vector generated from the contextual text provided for your image or video.