gpt4v.py

import cv2
import base64
import requests

import numpy as np


META_PROMPT = '''
- For any marks mentioned in your answer, please highlight them with [].
'''
API_URL = "https://api.openai.com/v1/chat/completions"


def encode_image_to_base64(image: np.ndarray) -> str:
    """
    Encodes an image into a base64-encoded string in JPEG format.

    Parameters:
        image (np.ndarray): The image to be encoded. This should be a numpy array as
            typically used in OpenCV.

    Returns:
        str: A base64-encoded string representing the image in JPEG format.
    """
    success, buffer = cv2.imencode('.jpg', image)
    if not success:
        raise ValueError("Could not encode image to JPEG format.")

    encoded_image = base64.b64encode(buffer).decode('utf-8')
    return encoded_image


def compose_headers(api_key: str) -> dict:
    return {
        "Content-Type": "application/json",
        "Authorization": f"Bearer {api_key}"
    }


def compose_payload(image: np.ndarray, prompt: str) -> dict:
    base64_image = encode_image_to_base64(image)
    return {
        "model": "gpt-4-vision-preview",
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "role": "system",
                        "content": [
                            META_PROMPT
                        ]
                    },
                    {
                        "type": "text",
                        "text": prompt
                    },
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": f"data:image/jpeg;base64,{base64_image}"
                        }
                    }
                ]
            }
        ],
        "max_tokens": 800
    }


def prompt_image(api_key: str, image: np.ndarray, prompt: str) -> str:
    headers = compose_headers(api_key=api_key)
    payload = compose_payload(image=image, prompt=prompt)
    response = requests.post(url=API_URL, headers=headers, json=payload).json()

    if 'error' in response:
        raise ValueError(response['error']['message'])
    return response['choices'][0]['message']['content']