app.py

import gradio as gr
from PyPDF2 import PdfReader
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model_name = "ArtifactAI/led_large_16384_arxiv_summarization"
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

def summarize_pdf_abstract(pdf_file):
    try:
        reader = PdfReader(pdf_file)
        abstract_text = ""
        for page in reader.pages:
            if "Abstract" in page.extract_text() or "Introduction" in page.extract_text():
                abstract_text = page.extract_text()
                break

        inputs = tokenizer(abstract_text, return_tensors="pt")
        outputs = model.generate(**inputs)
        summary = tokenizer.decode(outputs[0])

        return {"summary": summary}

    except Exception as e:
        raise Exception(str(e))

interface = gr.Interface(
    fn=summarize_pdf_abstract,
    inputs=[gr.File(label="Upload PDF")],
    outputs=[gr.Textbox(label="Summary")]
)

interface.launch(share=True)