app.py

import gradio as gr
from transformers import pipeline
import PyPDF2
import docx

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

def read_pdf(file):
    try:
        reader = PyPDF2.PdfReader(file.name)
        text = ""
        for page in reader.pages:
            text += page.extract_text() or ""
        return text
    except Exception:
        return "Failed to read PDF."

def read_docx(file):
    try:
        doc = docx.Document(file.name)
        return "\n".join([para.text for para in doc.paragraphs])
    except Exception:
        return "Failed to read Word document."

def summarize_file(pdf_file, docx_file, text_input):
    if pdf_file:
        text = read_pdf(pdf_file)
    elif docx_file:
        text = read_docx(docx_file)
    elif text_input:
        text = text_input
    else:
        return "Please upload a file or enter some text."

    if not text.strip():
        return "No valid text found to summarize."

    if len(text) > 3000:
        text = text[:3000]

    summary = summarizer(text, max_length=150, min_length=30, do_sample=False)[0]["summary_text"]
    return summary

with gr.Blocks() as demo:
    gr.Markdown("## 🧠 Smart Text Summarizer")

    with gr.Row():
        pdf_input = gr.File(label="Upload PDF", file_types=[".pdf"])
        docx_input = gr.File(label="Upload Word File", file_types=[".docx"])

    text_input = gr.Textbox(lines=8, label="Or Paste Text Here")

    summarize_button = gr.Button("Summarize")

    output = gr.Textbox(lines=8, label="Summary")

    summarize_button.click(
        summarize_file,
        inputs=[pdf_input, docx_input, text_input],
        outputs=output
    )

demo.launch()