app.py

import gradio as gr
import requests
import json
import base64

API_KEY = "your_api_key"  # Replace with your actual API key

def encode_image_to_base64(image):
    encoded_image = base64.b64encode(image).decode("utf-8")
    return encoded_image

def extract_text_from_image(encoded_image):
    url = "https://api.openai.com/v1/images/generations"
    headers = {
        "Content-Type": "application/json",
        "Authorization": f"Bearer {API_KEY}",
    }
    data = {
        "prompt": "Extract the text from the document image.",
        "image": encoded_image,
        "n": 1,
        "size": "1024x1024",
    }
    response = requests.post(url, headers=headers, data=json.dumps(data))
    extracted_text = response.json()["data"][0]["text"]
    return extracted_text

def summarize_text(text):
    url = "https://api.openai.com/v1/completions"
    headers = {
        "Content-Type": "application/json",
        "Authorization": f"Bearer {API_KEY}",
    }
    data = {
        "prompt": f"Summarize the following text:\n\n{text}\n\nSummary:",
        "max_tokens": 100,
        "n": 1,
        "stop": None,
        "temperature": 0.7,
    }
    response = requests.post(url, headers=headers, data=json.dumps(data))
    summary = response.json()["choices"][0]["text"]
    return summary

def document_summarizer(image):
    encoded_image = encode_image_to_base64(image)
    extracted_text = extract_text_from_image(encoded_image)
    summary = summarize_text(extracted_text)
    return summary

iface = gr.Interface(
    fn=document_summarizer,
    inputs=gr.inputs.Image(type="file", label="Upload Document Image"),
    outputs="text",
    title="Document Image Summarizer",
    description="Upload an image of a document and get a summary of its content.",
)

iface.launch()