From ff1a0979166d3baaeea38af2f21823fac08ce683 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?= Date: Thu, 28 May 2026 13:32:36 +0000 Subject: [PATCH] =?UTF-8?q?=D0=A3=D0=B4=D0=B0=D0=BB=D0=B8=D1=82=D1=8C=20ch?= =?UTF-8?q?unker.py?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- chunker.py | 26 -------------------------- 1 file changed, 26 deletions(-) delete mode 100644 chunker.py diff --git a/chunker.py b/chunker.py deleted file mode 100644 index e99eb22..0000000 --- a/chunker.py +++ /dev/null @@ -1,26 +0,0 @@ -""" -Chunking utilities for the RAG agent. - -This module provides a single function `get_text_splitter` that returns a -:class:`langchain.text_splitter.RecursiveCharacterTextSplitter` configured to -split documents into chunks of 500 characters with an overlap of 100. - -The splitter is used by :mod:`agent` when ingesting files. -""" - -from langchain.text_splitter import RecursiveCharacterTextSplitter - - -def get_text_splitter() -> RecursiveCharacterTextSplitter: - """Return a configured text splitter. - - The splitter uses a chunk size of 500 characters and an overlap of 100 - characters. These values are chosen to balance context length with the - ability to retrieve relevant passages during semantic search. - """ - return RecursiveCharacterTextSplitter( - chunk_size=500, - chunk_overlap=100, - ) - -# End of chunker.py