app.py

import gradio as gr
import openai
import os
from PIL import Image
import base64
import io

# Ensure you have your OpenAI API key set as an environment variable
openai.api_key = os.getenv("OPENAI_API_KEY")

def image_to_base64(image):
    buffered = io.BytesIO()
    image.save(buffered, format="JPEG")
    img_str = base64.b64encode(buffered.getvalue()).decode()
    return img_str

def extract_and_summarize(image):
    # Convert image to base64
    image_base64 = image_to_base64(image)
    
    # Prepare the prompt for GPT-4
    prompt = [
        {
            "role": "system",
            "content": "You are a helpful assistant. Summarize the text content of the document image provided."
        },
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Here is an image of a document. Please summarize its content."},
                {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{image_base64}"}}
            ]
        }
    ]
    
    # Call GPT-4 API for summarization
    response = client.chat.completions.create(
        model="gpt-4o",
        messages=prompt,
        temperature=0.0,
        max_tokens=300,
    )
    
    # Extract summary from GPT-4 response
    summary = response.choices[0].message.content
    
    return summary

# Define Gradio interface
iface = gr.Interface(
    fn=extract_and_summarize,
    inputs=gr.Image(type="pil", label="Upload Document Image"),
    outputs=gr.Textbox(label="Summarized Text"),
    title="Document Summarizer",
    description="Upload an image of a document and get a summarized text."
)

# Launch the interface
iface.launch()