图片理解

import os, json, urllib.request, urllib.error

BASE = os.environ["MOSSHUB_API_BASE"].rstrip("/")
KEY = os.environ["MOSSHUB_API_KEY"]
MODEL = "YOUR_MODEL_ID"

def chat(messages, **options):
    body = {"model": MODEL, "messages": messages, "stream": False, **options}
    request = urllib.request.Request(
        BASE + "/v1/chat/completions",
        data=json.dumps(body, ensure_ascii=False).encode("utf-8"),
        headers={"Authorization": "Bearer " + KEY,
                 "Content-Type": "application/json"}, method="POST")
    try:
        with urllib.request.urlopen(request, timeout=60) as response:
            result = json.load(response)
    except urllib.error.HTTPError as error:
        raise RuntimeError(f"HTTP {error.code}: {error.read().decode('utf-8')}") from error
    choices = result.get("choices", [])
    if not choices or not isinstance(choices[0].get("message"), dict):
        raise RuntimeError("未返回有效消息，请检查错误信息与模型能力")
    if choices[0].get("finish_reason") == "length":
        raise RuntimeError("回答因输出上限而截断，请调整预算后重试")
    return choices[0]["message"]

image_url = os.environ["MOSSHUB_IMAGE_URL"]
if not image_url.startswith("https://"):
    raise ValueError("请提供可公开访问的 HTTPS 图片地址")
message = chat([{"role": "user", "content": [
    {"type": "text", "text": "描述这张图片的主要内容，并列出三个可见细节。"},
    {"type": "image_url", "image_url": {"url": image_url}},
]}])
content = message.get("content")
if not isinstance(content, str):
    raise RuntimeError("当前返回不是文本，请检查消息与模型能力")
print(content)