Alibaba Cloud Model Studio:Multimodal embeddings API

Image embedding

import dashscope
import json
from http import HTTPStatus
# Replace this 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))

import dashscope
import base64
import json
from http import HTTPStatus
# Read the image and convert it to Base64. 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))

Video embedding

The multimodal embedding model currently accepts video input only via URL. Passing local video files directly is not supported.

import dashscope
import json
from http import HTTPStatus
# Replace this with your video URL.
video = "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250107/lbcemt/new+video.mp4"
input = [{'video': video}]
# 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))
    

Text embedding

import dashscope
import json
from http import HTTPStatus

text = "General multimodal representation model example"
input = [{'text': text}]
# 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))

Fused embedding

import dashscope
import json
import os
from http import HTTPStatus

# Multimodal fused embedding: Combines text, image, and video into a single fused embedding.
# Ideal for applications like cross-modal retrieval and image search.
text = "This is a test text for generating a multimodal fused embedding."
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"

# The input contains text, an image, and a video. Set enable_fusion=True to generate a single fused embedding.
input_data = [
    {"text": text},
    {"image": image},
    {"video": video}
]

# Use qwen3-vl-embedding to generate a fused embedding.
resp = dashscope.MultiModalEmbedding.call(
    # If the environment variable is not set, provide your DashScope API Key directly, e.g., api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3-vl-embedding",
    input=input_data,
    enable_fusion=True,
    # Optional parameter: Specify the embedding dimension. Supported values are 2560, 2048, 1536, 1024, 768, 512, and 256. The default is 2560.
    # parameters={"dimension": 1024}
)

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

Multi-image fused embedding

This example shows how to use the qwen3-vl-embedding model to fuse multiple images and text into a single embedding. To perform this multi-image fusion, pass multiple image items. This method is ideal for comprehensive semantic retrieval of products using multi-angle images and text descriptions.

import dashscope
import json
import os
from http import HTTPStatus

# Multi-image + text fused embedding: Fuses multiple product images and a description text into a single embedding.
# Suitable for comprehensive semantic retrieval using multi-angle product images and a text description.
text = "White sports shoes, lightweight and breathable, suitable for running and daily wear."
image1 = "https://dashscope.oss-cn-beijing.aliyuncs.com/images/256_1.png"
image2 = "https://img.alicdn.com/imgextra/i3/O1CN01rdstgY1uiZWt8gqSL_!!6000000006071-0-tps-1970-356.jpg"

# Pass multiple image items for multi-image fusion. `enable_fusion=True` fuses all inputs into a single embedding.
input_data = [
    {"text": text},
    {"image": image1},
    {"image": image2}
]

resp = dashscope.MultiModalEmbedding.call(
    # If the environment variable is not set, provide your DashScope API Key directly, e.g., api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3-vl-embedding",
    input=input_data,
    enable_fusion=True
)

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