gpt4v.py

import base64
from openai import OpenAI


class GPT4Vision:
    def __init__(self):
        self.client = OpenAI()

    def encode_image(self, image_path):
        """
        Encode the image to base64 format.

        :param image_path: Path to the image file.
        :return: Base64 encoded string of the image.
        """
        with open(image_path, "rb") as image_file:
            return base64.b64encode(image_file.read()).decode('utf-8')

    def describe(self, image_path, user_message):
        """
        Get a description of the image using OpenAI's GPT-4 Vision API.

        :param image_path: Path to the image file.
        :param user_message: Custom text message to send as user input.
        :return: The API response.
        """
        base64_image = self.encode_image(image_path)

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