read_files.py

import PyPDF2
from docx import Document

def read_pdf(file):
    reader = PyPDF2.PdfReader(file)
    num_pages = len(reader.pages)
    text = ""
    for page_num in range(num_pages):
        page = reader.pages[page_num]
        text += page.extract_text()
    return text

def read_docx(file):
    doc = Document(file)
    text = ""
    for paragraph in doc.paragraphs:
        text += paragraph.text + "\n"
    return text