From 0a34ac365b66ff71bb97fe76366f19627db13961 Mon Sep 17 00:00:00 2001
From: Cocoon-Break <54054995+kuishou68@users.noreply.github.com>
Date: Fri, 10 Apr 2026 08:05:55 +0000
Subject: [PATCH] fix(chunking): preserve sentence order in NlpSentenceChunking

Using list(set(sens)) destroys sentence order and incorrectly deduplicates.
Fix: return the sentences list directly.
---
 crawl4ai/chunking_strategy.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/crawl4ai/chunking_strategy.py b/crawl4ai/chunking_strategy.py
index f46cb667c..31f8abdb5 100644
--- a/crawl4ai/chunking_strategy.py
+++ b/crawl4ai/chunking_strategy.py
@@ -86,7 +86,7 @@ def chunk(self, text: str) -> list:
         sentences = sent_tokenize(text)
         sens = [sent.strip() for sent in sentences]
 
-        return list(set(sens))
+        return sens
 
 
 # Topic-based segmentation using TextTiling