Alibaba Cloud Model Studio:Multimodal embedding API details

Generate image embeddings

import dashscope
import json
from http import HTTPStatus
# Replace the URL with the URL of your image.
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 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))

Generate video embeddings

The multimodal embedding model currently supports video file input only as a URL. Passing local videos directly is not supported.

import dashscope
import json
from http import HTTPStatus
# Replace the URL with the URL of your video.
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))
    

Generate text embeddings

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))

Generate fused embeddings

import dashscope
import json
import os
from http import HTTPStatus

# Multimodal fused embedding: Fuses text, an image, and a video into a single fused embedding.
# Suitable for scenarios such as 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. The model will fuse them into a single fused embedding.
input_data = [
    {
        "text": text,
        "image": image,
        "video": video
    }
]

# Use qwen3-vl-embedding to generate the fused embedding.
resp = dashscope.MultiModalEmbedding.call(
    # If you have not configured the environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3-vl-embedding",
    input=input_data,
    # Optional parameter: Specify the vector dimension (supported values: 2560, 2048, 1536, 1024, 768, 512, 256; default: 2560)
    # parameters={"dimension": 1024}
)

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