Alibaba Cloud Model Studio：Detail API penyematan multimodal

Gunakan URL citra

import dashscope
import json
from http import HTTPStatus
# Dalam praktiknya, ganti URL dengan URL citra Anda.
image = "https://dashscope.oss-cn-beijing.aliyuncs.com/images/256_1.png"
input = [{'image': image}]
# Panggil API model.
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))

Gunakan citra lokal

Kode contoh berikut menunjukkan cara mengonversi citra lokal ke format Base64 lalu memanggil model untuk menghasilkan penyematan.

import dashscope
import base64
import json
from http import HTTPStatus
# Baca citra dan konversi ke Base64. Dalam praktiknya, ganti xxx.png dengan nama file atau path citra Anda.
image_path = "xxx.png"
with open(image_path, "rb") as image_file:
    # Baca file dan konversi ke Base64.
    base64_image = base64.b64encode(image_file.read()).decode('utf-8')
# Atur format citra.
image_format = "png"  # Ubah ini sesuai format aktual, seperti jpg atau bmp.
image_data = f"data:image/{image_format};base64,{base64_image}"
# Data input.
input = [{'image': image_data}]

# Panggil API model.
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))