From fdfcfa4b82ad0c094b2ecdc1ceff6920d84098b3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=9C=D0=B0=D1=80=D0=B0=D1=82=20=D0=A4=D0=B0=D0=B7=D1=8B?=
 =?UTF-8?q?=D0=BB=D0=BE=D0=B2?= <maratfazylov19@gmail.com>
Date: Thu, 14 May 2026 16:54:05 +0000
Subject: [PATCH] add chunker

---
 chunker.py | 7 +++++++
 1 file changed, 7 insertions(+)
 create mode 100644 chunker.py

diff --git a/chunker.py b/chunker.py
new file mode 100644
index 0000000..f9876e6
--- /dev/null
+++ b/chunker.py
@@ -0,0 +1,7 @@
+from langchain_text_splitter import RecursiveCharacterTextSplitter
+from langchain.schema import Document
+
+def get_chunks(content: str, title: str):
+    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    texts = splitter.split_text(content)
+    return [Document(page_content=t, metadata={"title": title, "content": t}) for t in texts]