Class MultiModalEmbeddingModel (1.75.0)

MultiModalEmbeddingModel(model_id: str, endpoint_name: typing.Optional[str] = None)

Generates embedding vectors from images and videos.

Examples::

model = MultiModalEmbeddingModel.from_pretrained("multimodalembedding@001")
image = Image.load_from_file("image.png")
video = Video.load_from_file("video.mp4")

embeddings = model.get_embeddings(
    image=image,
    video=video,
    contextual_text="Hello world",
)
image_embedding = embeddings.image_embedding
video_embeddings = embeddings.video_embeddings
text_embedding = embeddings.text_embedding

Methods

MultiModalEmbeddingModel

MultiModalEmbeddingModel(model_id: str, endpoint_name: typing.Optional[str] = None)

Creates a _ModelGardenModel.

This constructor should not be called directly. Use {model_class}.from_pretrained(model_name=...) instead.

from_pretrained

from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.T

Loads a _ModelGardenModel.

Exceptions
Type	Description
`ValueError`	If model_name is unknown.
`ValueError`	If model does not support this class.

get_embeddings

get_embeddings(
    image: typing.Optional[vertexai.vision_models.Image] = None,
    video: typing.Optional[vertexai.vision_models.Video] = None,
    contextual_text: typing.Optional[str] = None,
    dimension: typing.Optional[int] = None,
    video_segment_config: typing.Optional[
        vertexai.vision_models.VideoSegmentConfig
    ] = None,
) -> vertexai.vision_models.MultiModalEmbeddingResponse

Gets embedding vectors from the provided image.

Parameters
Name	Description
`image`	`Image` Optional. The image to generate embeddings for. One of `image`, `video`, or `contextual_text` is required.
`video`	`Video` Optional. The video to generate embeddings for. One of `image`, `video` or `contextual_text` is required.
`contextual_text`	`str` Optional. Contextual text for your input image or video. If provided, the model will also generate an embedding vector for the provided contextual text. The returned image and text embedding vectors are in the same semantic space with the same dimensionality, and the vectors can be used interchangeably for use cases like searching image by text or searching text by image. One of `image`, `video` or `contextual_text` is required.
`dimension`	`int` Optional. The number of embedding dimensions. Lower values offer decreased latency when using these embeddings for subsequent tasks, while higher values offer better accuracy. Available values: `128`, `256`, `512`, and `1408` (default).
`video_segment_config`	`VideoSegmentConfig` Optional. The specific video segments (in seconds) the embeddings are generated for.

Returns
Type	Description
`MultiModalEmbeddingResponse`	The image and text embedding vectors.