embed_images

Function

Calls the CLIP service to convert the image list provided by the user into vectors.

Prototype

def embed_images(images, batch_size)

Parameters

Parameter

Data Type

Required/Optional

Description

images

List[str]

Required

Image list. The list length range is [1, 1000], and the string length range is [1, 10 × 1024 × 1024]. Each image is a string encoded using Base64.

batch_size

Integer

Optional

Batch size. texts of batch_size is combined for embedding each time. The value range is [1, 1024]. The default value is 32. If the value of batch_size is too large, the server may return error code 500. In this case, you need to decrease the value of batch_size.

Return Value

Data Type

Description

List[List[float]]

Vector array after the conversion of images.

If images is an array whose length is 4 and the output of the embedding model is a 512-dimensional vector, the final output result is an array of size (4, 512).