from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.document_loaders import PyPDFLoader

import logging

logger: logging.Logger = logging.getLogger("pdf_loader")


def load_pdf(file_path):
    loader = PyPDFLoader(file_path)
    splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
    documents = loader.load_and_split(splitter)
    logger.info(f"Loaded and Split into {len(documents)} documents from {file_path}")

    return documents