Alibaba Cloud Model Studio:Multimodal embedding API details

Use an image URL

import dashscope
import json
from http import HTTPStatus
# In practice, replace the URL with your image URL.
image = "https://dashscope.oss-cn-beijing.aliyuncs.com/images/256_1.png"
input = [{'image': image}]
# Call the model API.
resp = dashscope.MultiModalEmbedding.call(
    model="tongyi-embedding-vision-plus",
    input=input
)

if resp.status_code == HTTPStatus.OK:
    result = {
        "status_code": resp.status_code,
        "request_id": getattr(resp, "request_id", ""),
        "code": getattr(resp, "code", ""),
        "message": getattr(resp, "message", ""),
        "output": resp.output,
        "usage": resp.usage
    }
    print(json.dumps(result, ensure_ascii=False, indent=4))

Use a local image

The following sample code shows how to convert a local image to the Base64 format and then call the model to generate an embedding.

import dashscope
import base64
import json
from http import HTTPStatus
# Read the image and convert it to Base64. In practice, replace xxx.png with your image file name or path.
image_path = "xxx.png"
with open(image_path, "rb") as image_file:
    # Read the file and convert it to Base64.
    base64_image = base64.b64encode(image_file.read()).decode('utf-8')
# Set the image format.
image_format = "png"  # Modify this based on the actual format, such as jpg or bmp.
image_data = f"data:image/{image_format};base64,{base64_image}"
# Input data.
input = [{'image': image_data}]

# Call the model API.
resp = dashscope.MultiModalEmbedding.call(
    model="tongyi-embedding-vision-plus",
    input=input
)
if resp.status_code == HTTPStatus.OK:
    result = {
        "status_code": resp.status_code,
        "request_id": getattr(resp, "request_id", ""),
        "code": getattr(resp, "code", ""),
        "message": getattr(resp, "message", ""),
        "output": resp.output,
        "usage": resp.usage
    }
    print(json.dumps(result, ensure_ascii=False, indent=4))