app.py

import gradio as gr
from transformers import pipeline
from PyPDF2 import PdfReader
from docx import Document
from fpdf import FPDF
import os

# Load summarization pipeline
summarizer = pipeline("summarization")

# Function to read text from different file types
def extract_text(file):
    text = ""
    if file.name.endswith(".pdf"):
        reader = PdfReader(file.name)
        for page in reader.pages:
            text += page.extract_text()
    elif file.name.endswith(".docx"):
        doc = Document(file.name)
        for para in doc.paragraphs:
            text += para.text + "\n"
    else:
        text = file.read().decode("utf-8")
    return text

# Function to summarize and return as PDF or Word
def summarize_file(file, output_format):
    text = extract_text(file)
    if not text.strip():
        return None, "File is empty or could not be read."
    
    summarized = summarizer(text, max_length=150, min_length=40, do_sample=False)[0]["summary_text"]
    
    output_path = "/tmp/summary_output"
    if output_format == "PDF":
        pdf = FPDF()
        pdf.add_page()
        pdf.set_auto_page_break(auto=True, margin=15)
        pdf.set_font("Arial", size=12)
        for line in summarized.split("\n"):
            pdf.multi_cell(0, 10, line)
        output_file = f"{output_path}.pdf"
        pdf.output(output_file)
    else:
        doc = Document()
        doc.add_heading("Summary", 0)
        doc.add_paragraph(summarized)
        output_file = f"{output_path}.docx"
        doc.save(output_file)

    return output_file, "Success"

# Gradio interface
iface = gr.Interface(
    fn=summarize_file,
    inputs=[
        gr.File(label="Upload a text, Word, or PDF file"),
        gr.Radio(["PDF", "Word"], label="Choose output format")
    ],
    outputs=[
        gr.File(label="Download Summary"),
        gr.Textbox(label="Status")
    ],
    title="Smart Text Summarizer",
    description="Upload a .txt, .docx, or .pdf file and get the summary back as a Word or PDF file."
)

iface.launch()