Alibaba Cloud Model Studio：Multimodal-Embedding API詳情

產生圖片Embedding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))

產生視頻Embedding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))
    

產生文本Embedding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))

產生融合Embedding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，模型會將它們融合成一個融合向量
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,
    # 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))