import gradio as gr
from transformers import pipeline
import fitz

# Light summarization model (Free Spaces compatible)
summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")

def summarize_pdf(pdf_file):
    if pdf_file is None:
        return "Please upload a PDF file."

    try:
        doc = fitz.open(pdf_file.name)
    except:
        return "PDF can't be opened."

    text = ""
    for page in doc:
        text += page.get_text()

    if len(text) < 100:
        return "PDF me enough text nahi mila."

    # Split text into smaller chunks
    chunks = []
    words = text.split()
    chunk_size = 400

    for i in range(0, len(words), chunk_size):
        chunk = " ".join(words[i:i+chunk_size])
        chunks.append(chunk)

    final_summary = ""

    for chunk in chunks:
        try:
            s = summarizer(chunk, max_length=150, min_length=40, do_sample=False)
            final_summary += s[0]["summary_text"] + "\n\n"
        except:
            continue

    return final_summary


iface = gr.Interface(
    fn=summarize_pdf,
    inputs=gr.File(type="filepath", label="Upload PDF"),
    outputs="text",
    title="PDF Notes AI",
    description="Lightweight PDF summarizer — Free Space compatible."
)

iface.launch()
import gradio as gr
import fitz
from transformers import pipeline

summarizer = pipeline("summarization")

def pdf_summarizer(file):
    doc = fitz.open(file.name)
    text = ""
    for page in doc:
        text += page.get_text()
    doc.close()
    summary = summarizer(text, max_length=150, min_length=50, do_sample=False)
    return summary[0]['summary_text']

with gr.Blocks(css=".gradio-container {background: linear-gradient(135deg,#ff7e5f,#6a11cb);} ") as demo:

    gr.Markdown(
        """
        <h1 style='text-align:center; color:white;'>📘 PDF Notes AI</h1>
        <p style='text-align:center; color:white;'>Upload any PDF and get instant AI-powered notes.</p>
        """
    )

    with gr.Column(scale=1):
        pdf_file = gr.File(label="Upload PDF", file_types=[".pdf"])
        btn = gr.Button("Generate Summary", variant="primary")
        output = gr.Textbox(label="Summary Output")

        btn.click(pdf_summarizer, inputs=pdf_file, outputs=output)
import gradio as gr
import fitz  # pymupdf
from transformers import pipeline

# Summarizer pipeline
summarizer = pipeline("summarization")

def pdf_summarizer(file):
    doc = fitz.open(file.name)
    text = ""
    for page in doc:
        text += page.get_text()
    doc.close()

    summary = summarizer(text, max_length=150, min_length=50, do_sample=False)
    return summary[0]['summary_text']

with gr.Blocks(css=".gradio-container {background: linear-gradient(135deg,#ff7e5f,#6a11cb);} ") as demo:

    gr.Markdown(
        """
        <h1 style='text-align:center; color:white;'>📘 PDF Notes AI</h1>
        <p style='text-align:center; color:white;'>Upload any PDF and get instant AI-powered notes.</p>
        """
    )

    with gr.Column(scale=1):
        pdf_file = gr.File(label="Upload PDF", file_types=[".pdf"])
        btn = gr.Button("Generate Summary", variant="primary")
        output = gr.Textbox(label="Summary Output")

        btn.click(pdf_summarizer, inputs=pdf_file, outputs=output)

demo.launch()