app.py

import gradio as gr
import fitz  # PyMuPDF
from transformers import pipeline
import re

# Use faster summarization model
summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")

def extract_text_from_pdf(pdf_file):
    try:
        doc = fitz.open(pdf_file.name)  # FIXED: Use .name instead of .read()
        text = ""
        for page in doc:
            text += page.get_text()
        return text
    except Exception as e:
        return None

def chunk_text(text, max_words=500):
    words = text.split()
    return [" ".join(words[i:i + max_words]) for i in range(0, len(words), max_words)]

def simplify_summary(summary):
    summary = re.sub(r"(Mayo Hospital|Lahore Hospital|Dr\.\s+\w+)+.*", "", summary, flags=re.IGNORECASE)
    return "🩺 In simple terms:\n" + summary.strip()

def process_report(pdf_file):
    raw_text = extract_text_from_pdf(pdf_file)
    if not raw_text:
        return "❌ Could not read PDF file.", ""
    
    chunks = chunk_text(raw_text, max_words=600)
    summaries = []
    for chunk in chunks:
        try:
            result = summarizer(chunk, max_length=150, min_length=30, do_sample=False)
            summaries.append(result[0]['summary_text'])
        except:
            continue

    if not summaries:
        return "❌ Summarization failed. Try a smaller or clearer PDF.", ""

    full_summary = " ".join(summaries)
    return full_summary, simplify_summary(full_summary)

demo = gr.Interface(
    fn=process_report,
    inputs=gr.File(label="Upload Medical Report PDF"),
    outputs=[
        gr.Textbox(label="AI-Generated Summary", lines=8),
        gr.Textbox(label="Simplified Explanation", lines=8)
    ],
    title="🏥 Medical Report Summarizer",
    description="Upload a medical report PDF to get an AI summary and non-medical explanation."
)

if __name__ == "__main__":
    demo.launch()