diff --git a/splitter.py b/splitter.py index c2cdcb0..4687bca 100644 --- a/splitter.py +++ b/splitter.py @@ -1,7 +1,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter -def chunk_text(text: str, chunk_size: int = 1000, chunk_overlap: int = 200, separators: list[str] | None = None) -> list[str]: +def chunk_text(text: str, chunk_size: int = 500, chunk_overlap: int = 100, separators: list[str] | None = None) -> list[str]: if separators is None: separators = ["\n\n", "\n", " ", ""] splitter = RecursiveCharacterTextSplitter(chunk_size=chunk_size, chunk_overlap=chunk_overlap, separators=separators)