Multimodal-Embedding API详情

使用图片URL

import dashscope
import json
from http import HTTPStatus
# 实际使用中请将url地址替换为您的图片url地址
image = "https://dashscope.oss-cn-beijing.aliyuncs.com/images/256_1.png"
input = [{'image': image}]
# 调用模型接口
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))

使用本地图片

您可以参考以下示例代码，将本地图片转换为Base64格式后调用multimodal-embedding-v1模型进行向量化处理。

import dashscope
import base64
import json
from http import HTTPStatus
# 读取图片并转换为Base64,实际使用中请将xxx.png替换为您的图片文件名或路径
image_path = "xxx.png"
with open(image_path, "rb") as image_file:
    # 读取文件并转换为Base64
    base64_image = base64.b64encode(image_file.read()).decode('utf-8')
# 设置图像格式
image_format = "png"  # 根据实际情况修改，比如jpg、bmp 等
image_data = f"data:image/{image_format};base64,{base64_image}"
# 输入数据
input = [{'image': image_data}]

# 调用模型接口
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))