From 07c5b07617372d0d8dd135d991ce515baab4d25a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=D0=9A=D0=B8=D1=80=D0=B8=D0=BB=D0=BB=20=D0=A0=D0=BE=D0=BC?= =?UTF-8?q?=D0=B0=D0=BD=D0=BE=D0=B2?= Date: Wed, 3 Jun 2026 08:44:03 +0000 Subject: [PATCH] Add chunker.py --- chunker.py | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 chunker.py diff --git a/chunker.py b/chunker.py new file mode 100644 index 0000000..78a3f00 --- /dev/null +++ b/chunker.py @@ -0,0 +1,11 @@ +"""Simple text splitter using RecursiveCharacterTextSplitter. +""" + +from langchain_text_splitters import RecursiveCharacterTextSplitter + +class Chunker: + def __init__(self, chunk_size: int = 500, chunk_overlap: int = 50): + self.splitter = RecursiveCharacterTextSplitter(chunk_size=chunk_size, chunk_overlap=chunk_overlap) + + def split(self, text: str) -> list[str]: + return self.splitter.split_text(text)