图像输入(vision)

from openai import OpenAI

client = OpenAI(
    api_key="sk-你的密钥",
    base_url="https://www.ruapi.ai/v1",
)

response = client.chat.completions.create(
    model="claude-opus-4-8",  # vision 模型;准确名称见价格页
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "图里是什么?请简要描述。"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg"
                    },
                },
            ],
        }
    ],
)

print(response.choices[0].message.content)

import base64
from openai import OpenAI

client = OpenAI(
    api_key="sk-你的密钥",
    base_url="https://www.ruapi.ai/v1",
)

# 把本地文件编码成 base64
with open("screenshot.jpg", "rb") as f:
    b64 = base64.b64encode(f.read()).decode("utf-8")

data_uri = f"data:image/jpeg;base64,{b64}"

response = client.chat.completions.create(
    model="claude-opus-4-8",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "识别这张截图里的所有文字。"},
                {"type": "image_url", "image_url": {"url": data_uri}},
            ],
        }
    ],
)

print(response.choices[0].message.content)