loader.py

# loader.py
from langchain.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter

def load_and_split_pdf(pdf_path):
    loader = PyPDFLoader(pdf_path)
    docs = loader.load()

    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
    return splitter.split_documents(docs)