Analyze Images with GPT Vision API

from openai import OpenAI
import base64
from pathlib import Path

client = OpenAI()

def encode_image(image_path: str) -> str:
    """Encode a local image to base64."""
    return base64.b64encode(Path(image_path).read_bytes()).decode()

def analyze_image(image_path: str, question: str) -> str:
    """Ask a question about a local image."""
    base64_image = encode_image(image_path)

    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[
            {
                "role": "user",
                "content": [
                    {"type": "text", "text": question},
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": f"data:image/png;base64,{base64_image}",
                            "detail": "high"
                        }
                    }
                ]
            }
        ],
        max_tokens=1000
    )
    return response.choices[0].message.content

# Analyze a screenshot
result = analyze_image(
    "screenshot.png",
    "Describe the UI layout and suggest improvements."
)
print(result)

# Compare two images
def compare_images(path1: str, path2: str) -> str:
    return client.chat.completions.create(
        model="gpt-4o",
        messages=[{
            "role": "user",
            "content": [
                {"type": "text", "text": "Compare these two images."},
                {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{encode_image(path1)}"}},
                {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{encode_image(path2)}"}}
            ]
        }]
    ).choices[0].message.content