From 95c6d65bf42a8e662aa8085190a5961dfde0fd3e 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=9A=D1=83=D1=82?=
 =?UTF-8?q?=D0=BB=D0=B0=D1=85=D0=BC=D0=B5=D1=82=D0=BE=D0=B2?=
 <kirillkutlahmetov10@gmail.com>
Date: Thu, 28 May 2026 10:30:55 +0000
Subject: [PATCH] add chunker.py

---
 chunker.py | 27 +++++++++------------------
 1 file changed, 9 insertions(+), 18 deletions(-)

diff --git a/chunker.py b/chunker.py
index 82d8a8f..5648121 100644
--- a/chunker.py
+++ b/chunker.py
@@ -1,26 +1,17 @@
 """
 Chunking utilities for the RAG agent.
 
-Uses RecursiveCharacterTextSplitter from langchain-text-splitters with a chunk size of 500 and overlap of 100.
+Uses RecursiveCharacterTextSplitter from langchain.text_splitter to split documents into
+chunks of 500 characters with an overlap of 100 characters. The splitter is exposed as a
+singleton instance so that it can be reused across the project.
 """
 
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 
-# Global splitter instance
-splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)
+# Singleton splitter configuration
+CHUNKER = RecursiveCharacterTextSplitter(
+    chunk_size=500,
+    chunk_overlap=100,
+)
 
-
-def split_document(text: str):
-    """Split a document into chunks.
-
-    Parameters
-    ----------
-    text: str
-        Full text of the document.
-
-    Returns
-    -------
-    list[str]
-        List of chunk strings.
-    """
-    return splitter.split_text(text)
+__all__ = ["CHUNKER"]