app.py

import gradio as gr
import pytesseract
from PIL import Image
import json

def extract_fields(image):
    try:
        raw_text = pytesseract.image_to_string(image)
        lines = raw_text.split('\n')
        result = {}

        for line in lines:
            line = line.strip()
            if ':' in line:
                key, value = line.split(':', 1)
                result[key.strip()] = value.strip()
            elif len(line.split()) >= 2:
                result["line_" + str(len(result))] = line

        return json.dumps(result, indent=2)
    except Exception as e:
        return {"error": str(e)}

gr.Interface(
    fn=extract_fields,
    inputs=gr.Image(type="pil"),
    outputs="json",
    title="Smart KYC OCR (Tesseract)",
    description="Upload Aadhaar or PAN image to extract key-value KYC fields using Tesseract OCR."
).launch()