from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.document_loaders import PyPDFLoader
def load_pdf(file_path):
	loader = PyPDFLoader(file_path)
	pages = loader.load()
	print(f"Loaded {len(pages)} documents from {file_path}")
	splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
	splits = splitter.split_documents(pages)
	documents = []
	metadatas = []
 
	for split in splits:
		documents.append(split.page_content)
		metadatas.append(split.metadata)
     
	return (documents, metadatas)