マルチモーダル — 画像と文書の理解

resp = client.chat.completions.create(
    model="gpt-4o",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "How many cats are in this image?"},
            {"type": "image_url", "image_url": {"url": "https://.../cats.png"}}
        ]
    }],
)