Alibaba Cloud Model Studio：Multimodal-Embedding API詳情

圖片向量化樣本

import dashscope
import json
from http import HTTPStatus
# 實際使用中請將url地址替換為您的圖片url地址
image = "https://dashscope.oss-cn-beijing.aliyuncs.com/images/256_1.png"
input = [{'image': image}]
# 調用模型介面
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
# 讀取圖片並轉換為Base64,實際使用中請將xxx.png替換為您的圖片檔案名稱或路徑
image_path = "xxx.png"
with open(image_path, "rb") as image_file:
    # 讀取檔案並轉換為Base64
    base64_image = base64.b64encode(image_file.read()).decode('utf-8')
# 設定映像格式
image_format = "png"  # 根據實際情況修改，比如jpg、bmp 等
image_data = f"data:image/{image_format};base64,{base64_image}"
# 輸入資料
input = [{'image': image_data}]

# 調用模型介面
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))

視頻向量化樣本

多模態向量化模型目前僅支援以URL形式輸入視頻檔案，暫不支援直接傳入本地視頻。

import dashscope
import json
from http import HTTPStatus
# 實際使用中請將url地址替換為您的視頻url地址
video = "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250107/lbcemt/new+video.mp4"
input = [{'video': video}]
# 調用模型介面
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))
    

文本向量化樣本

import dashscope
import json
from http import HTTPStatus

text = "通用多模態表徵模型樣本"
input = [{'text': text}]
# 調用模型介面
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))

融合向量化樣本

import dashscope
import json
import os
from http import HTTPStatus

# 多模態融合向量：將文本、圖片、視頻融合成一個融合向量
# 適用於跨模態檢索、圖搜等情境
text = "這是一段測試文本，用於產生多模態融合向量"
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"

# 輸入包含文本、圖片、視頻，通過 enable_fusion 參數產生融合向量
input_data = [
    {"text": text},
    {"image": image},
    {"video": video}
]

# 使用 qwen3-vl-embedding 產生融合向量
resp = dashscope.MultiModalEmbedding.call(
    # 若沒有配置環境變數，請用百鍊API Key將下行替換為：api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3-vl-embedding",
    input=input_data,
    enable_fusion=True,
    # 選擇性參數：指定向量維度（支援 2560、2048、1536、1024、768、512、256，預設 2560）
    # parameters={"dimension": 1024}
)

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

多圖融合向量化樣本

以下樣本展示如何使用 qwen3-vl-embedding 模型，將多張圖片與文本融合為 1 個向量。傳入多個 image 條目即可實現多圖融合，適用於商品多角度圖片+描述文本的綜合語義檢索情境。

import dashscope
import json
import os
from http import HTTPStatus

# 多圖+文本融合向量：將多張商品圖片和描述文本融合為 1 個向量
# 適用於商品多角度圖片+描述文本的綜合語義檢索
text = "白色運動鞋，輕量透氣，適合跑步和日常穿著"
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"

# 傳入多個 image 條目實現多圖融合，enable_fusion=True 將所有輸入融合為 1 個向量
input_data = [
    {"text": text},
    {"image": image1},
    {"image": image2}
]

resp = dashscope.MultiModalEmbedding.call(
    # 若沒有配置環境變數，請用百鍊API Key將下行替換為：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))