Delete app.py

app.py

@@ -1,49 +0,0 @@
-import gradio as gr
-import torch
-from transformers import pipeline
-from PyPDF2 import PdfReader
-from pathlib import Path
-
-# 1. Pick the best small Google model for abstractive summarisation
-SUMMARISER = pipeline(
-    "summarization",
-    model="google/pegasus-xsum",
-    device=0 if torch.cuda.is_available() else -1,
-    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
-)
-
-# 2. Helper: extract raw text from uploaded PDF
-def pdf_to_text(pdf_file):
-    reader = PdfReader(pdf_file.name)
-    text = "".join(page.extract_text() or "" for page in reader.pages)
-    return text.strip()
-
-# 3. Core summarisation logic
-def summarise_pdf(pdf_file):
-    if pdf_file is None:
-        return "❗ Please upload a PDF file."
-    text = pdf_to_text(pdf_file)
-    if not text:
-        return "❗ Could not extract text from this PDF."
-
-    # Pegasus-XSUM works best with ≤512 tokens; chunk if needed
-    max_chunk = 450  # tokens ≈ 1800 chars
-    chunks = [text[i : i + max_chunk] for i in range(0, len(text), max_chunk)]
-    summaries = [SUMMARISER(chunk, max_length=64, min_length=16, do_sample=False)[0]["summary_text"] for chunk in chunks]
-
-    return "\n".join(summaries)
-
-# 4. Gradio UI
-iface = gr.Interface(
-    fn=summarise_pdf,
-    inputs=gr.Textbox(label="Upload PDF", lines=3),
-    outputs=gr.Textbox(label="Summary", lines=10),
-    title="PDF Summariser – Google Pegasus-XSUM",
-    description="Upload any PDF and get a concise abstractive summary in seconds.",
-   # allow_flagging="never",
-)
-
-# 5. Launch (use queue for HF Spaces)
-if __name__ == "__main__":
-    iface.launch(debug=True)
-