study-buddy / app /rag /chunker.py
GitHub Actions
deploy d092bea3608b7a29952f16357fda39b7a29e399b
2e818da
Raw
History Blame Contribute Delete
374 Bytes
from typing import List
from langchain_text_splitters import RecursiveCharacterTextSplitter
def chunk_text(text: str, chunk_size: int = 512, overlap: int = 64) -> List[str]:
splitter = RecursiveCharacterTextSplitter(
chunk_size=chunk_size,
chunk_overlap=overlap,
separators=["\n\n", "\n", ". ", " "],
)
return splitter.split_text(text)