summarizer.py

from transformers import pipeline
import PyPDF2

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

def extract_text_from_pdf(file):
    # Check if file is a path (string) or file-like object
    if isinstance(file, str):
        with open(file, "rb") as f:
            reader = PyPDF2.PdfReader(f)
            text = "".join([page.extract_text() or "" for page in reader.pages])
    else:
        reader = PyPDF2.PdfReader(file)
        text = "".join([page.extract_text() or "" for page in reader.pages])
    return text.strip()

def summarize_text(text, max_length=130, min_length=30):
    if len(text.strip()) == 0:
        return "No valid text found in the PDF."
    summary = summarizer_pipeline(text[:3000], max_length=max_length, min_length=min_length, do_sample=False)
    return summary[0]['summary_text']