glm4v-flash.py

import base64
import re
from typing import Optional
from openai import OpenAI


client = OpenAI(base_url='https://open.bigmodel.cn/api/paas/v4', api_key='')

def describe_image(prompt: str, image: bytes | str) -> Optional[str]:
    """ 图像描述 """
    encoded_image = base64.b64encode(image).decode('utf-8')

    response = client.chat.completions.create(
        model='glm-4v-flash',
        temperature=0.95,
        top_p=0.70,
        messages=[{'role': 'user', 'content': [
            {'type': 'image_url', 'image_url': {'url': encoded_image}},
            {'type': 'text', 'text': prompt},
        ]}],
    )

    completion_message = response.choices[0].message
    response_text: str = completion_message.content
    response_text = re.sub(r'\s\S\n', '', response_text)
    return response_text


if __name__ == '__main__':
    prompt = '尽可能少的字数描述图片主体是什么, 里面物品有什么. 给人的感觉如何. 不要描述物品放置的目的.'
    image = open('image/dog.jpg', 'rb').read()
    description = describe_image(prompt, image)
    print(description)