chunk.py

from langchain_community.document_loaders import PyMuPDFLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_core.vectorstores import VectorStore

loader = PyMuPDFLoader("sample.pdf")
splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
docs = loader.load_and_split(splitter)

from