data_parsing.py

from langchain.text_splitter import RecursiveCharacterTextSplitter

text_splitter = RecursiveCharacterTextSplitter(
    chunk_size = 1000, ### YOUR CODE HERE, # the character length of the chunk
    chunk_overlap = 100, ### YOUR CODE HERE, # the character length of the overlap between chunks
    length_function = len ### YOUR CODE HERE, # the length function - in this case, character length (aka the python len() fn.)
)