Multimodal-Embedding API详情

生成图片Embedding示例

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))

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))

生成视频Embedding示例

多模态向量化模型目前仅支持以URL形式输入视频文件，暂不支持直接传入本地视频。

import dashscope
import json
from http import HTTPStatus
# 实际使用中请将url地址替换为您的视频url地址
video = "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250107/lbcemt/new+video.mp4"
input = [{'video': video}]
# 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))
    

生成文本Embedding示例

import dashscope
import json
from http import HTTPStatus

text = "通用多模态表征模型示例"
input = [{'text': text}]
# 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))

生成融合Embedding示例

import dashscope
import json
import os
from http import HTTPStatus

# 多模态融合向量：将文本、图片、视频融合成一个融合向量
# 适用于跨模态检索、图搜等场景
text = "这是一段测试文本，用于生成多模态融合向量"
image = "https://dashscope.oss-cn-beijing.aliyuncs.com/images/256_1.png"
video = "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250107/lbcemt/new+video.mp4"

# 输入包含文本、图片、视频，模型会将它们融合成一个融合向量
input_data = [
    {
        "text": text,
        "image": image,
        "video": video
    }
]

# 使用 qwen3-vl-embedding 生成融合向量
resp = dashscope.MultiModalEmbedding.call(
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3-vl-embedding",
    input=input_data,
    # 可选参数：指定向量维度（支持 2560、2048、1536、1024、768、512、256，默认 2560）
    # parameters={"dimension": 1024}
)

print(json.dumps(resp, ensure_ascii=False, indent=4))