From bd777ed02cfdd281215b7b23ed3bad9fd6a1b574 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: Fri, 15 May 2026 08:39:58 +0000
Subject: [PATCH] add chunker

---
 chunker.py | 12 ++++++++++++
 1 file changed, 12 insertions(+)
 create mode 100644 chunker.py

diff --git a/chunker.py b/chunker.py
new file mode 100644
index 0000000..974a8a0
--- /dev/null
+++ b/chunker.py
@@ -0,0 +1,12 @@
+from langchain_text_splitter import RecursiveCharacterTextSplitter
+
+def get_chunks(content, title):
+    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    texts = splitter.split_text(content)
+    return [
+        {
+            "page_content": t,
+            "metadata": {"title": title}
+        }
+        for t in texts
+    ]