documents/loader.py

import pypdf  # Changed from PyPDF2
from PIL import Image
import pytesseract

class DocumentLoader:
    def load_pdf(self, file_path):
        text = ""
        with open(file_path, 'rb') as file:
            pdf_reader = pypdf.PdfReader(file)  # Changed here
            for page in pdf_reader.pages:
                text += page.extract_text()
        return text
    
    def load_image(self, file_path):
        image = Image.open(file_path)
        text = pytesseract.image_to_string(image)
        return text