视觉理解

curl https://api.yelu.ai/v1/chat/completions \
  -H "Authorization: Bearer $YELU_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"model\":\"gpt-4o-mini\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"描述图片并列出可见文字。\"},{\"type\":\"image_url\",\"image_url\":{\"url\":\"$IMAGE_URL\",\"detail\":\"auto\"}}]}],\"max_completion_tokens\":300}"

const response = await fetch('https://api.yelu.ai/v1/chat/completions', {
  method: 'POST',
  headers: { Authorization: `Bearer ${process.env.YELU_API_KEY}`, 'Content-Type': 'application/json' },
  body: JSON.stringify({
    model: 'gpt-4o-mini',
    messages: [{ role: 'user', content: [
      { type: 'text', text: '描述图片并列出可见文字。' },
      { type: 'image_url', image_url: { url: process.env.IMAGE_URL, detail: 'auto' } },
    ] }],
    max_completion_tokens: 300,
  }),
});
if (!response.ok) throw new Error(await response.text());
console.log((await response.json()).choices[0].message.content);

import os
import requests

response = requests.post(
    "https://api.yelu.ai/v1/chat/completions",
    headers={"Authorization": f"Bearer {os.environ['YELU_API_KEY']}"},
    json={
        "model": "gpt-4o-mini",
        "messages": [{"role": "user", "content": [
            {"type": "text", "text": "描述图片并列出可见文字。"},
            {"type": "image_url", "image_url": {"url": os.environ["IMAGE_URL"], "detail": "auto"}},
        ]}],
        "max_completion_tokens": 300,
    },
    timeout=120,
)
response.raise_for_status()
print(response.json()["choices"][0]["message"]["content"])