vision_api.py

import streamlit as st
import os, base64, requests

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")

def get_transcribed_text(base64_image):

    headers = {
        "Content-Type": "application/json",
        "Authorization": f"Bearer {OPENAI_API_KEY}"
    }
    image_prompt = (
        "Understand and interpret the image properly, there could be "
        "handwritten notes or scribbles beside the electronic text. "
        "Once you have sufficient understanding of the image, "
        "transcribed them into text. If the content is a question, "
        "convert the question into text."
    )
    print(image_prompt)

    payload = {
        "model": "gpt-4-vision-preview",
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                    "type": "text",
                    "text": image_prompt
                    },
                    {
                    "type": "image_url",
                    "image_url": {
                        "url": f"data:image/jpeg;base64,{base64_image}"
                    }
                    }
                ]
            }
        ],
        "max_tokens": 300
    }

    response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
    transcribed_msg = response.json()["choices"][0]["message"]["content"]

    return transcribed_msg