utils.py

import os
import fitz  # PyMuPDF

def extract_text_from_file(file_obj):
    name = file_obj.name
    if name.endswith(".pdf"):
        doc = fitz.open(stream=file_obj.read(), filetype="pdf")
        return "\n".join(page.get_text() for page in doc)
    elif name.endswith(".txt"):
        return file_obj.read().decode("utf-8")
    else:
        return ""