Python 이미지 인식

from openai import OpenAI

client = OpenAI(api_key="sk-xxx", base_url="https://api.crazyrouter.com/v1")

response = client.chat.completions.create(
    model="gpt-5.5",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "이 이미지의 내용을 설명해 주세요"},
            {
                "type": "image_url",
                "image_url": {
                    "url": "https://example.com/photo.jpg"
                }
            }
        ]
    }]
)

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

import base64
from openai import OpenAI

client = OpenAI(api_key="sk-xxx", base_url="https://api.crazyrouter.com/v1")

# 로컬 이미지를 읽어 base64로 변환
with open("photo.jpg", "rb") as f:
    image_data = base64.b64encode(f.read()).decode("utf-8")

response = client.chat.completions.create(
    model="gpt-5.5",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "이 이미지에는 무엇이 있나요?"},
            {
                "type": "image_url",
                "image_url": {
                    "url": f"data:image/jpeg;base64,{image_data}"
                }
            }
        ]
    }]
)

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

response = client.chat.completions.create(
    model="gpt-5.5",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "이 두 이미지의 차이를 비교해 주세요"},
            {"type": "image_url", "image_url": {"url": "https://example.com/img1.jpg"}},
            {"type": "image_url", "image_url": {"url": "https://example.com/img2.jpg"}}
        ]
    }]
)

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

response = client.chat.completions.create(
    model="claude-opus-4-8",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "이 이미지를 자세히 설명해 주세요"},
            {
                "type": "image_url",
                "image_url": {
                    "url": f"data:image/png;base64,{image_data}"
                }
            }
        ]
    }],
    max_tokens=1024
)

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