import os
import sqlite3
from docx import Document

# Initialize tokenizer

def read_file(file_path):
    """Read text from Word or Text files."""
    if file_path.endswith('.docx'):
        doc = Document(file_path)
        return "\n".join([para.text for para in doc.paragraphs])
    elif file_path.endswith('.txt'):
        with open(file_path, 'r', encoding='utf-8') as f:
            return f.read()
    else:
        raise ValueError("Unsupported file format. Only .docx and .txt are allowed.")