utils/document_loader.py

import os
from langchain_community.document_loaders import PDFPlumberLoader

def load_pdf(file_path):
    loader = PDFPlumberLoader(file_path)
    document = loader.load()
    return document

def create_unique_ids(documents):
    return [f"{doc.metadata['source']}_page_{doc.metadata['page']}" for doc in documents]