diff --git a/crawl4ai/chunking_strategy.py b/crawl4ai/chunking_strategy.py index f46cb667c..a0bfe1bf4 100644 --- a/crawl4ai/chunking_strategy.py +++ b/crawl4ai/chunking_strategy.py @@ -71,7 +71,6 @@ def __init__(self, **kwargs): """ Initialize the NlpSentenceChunking object. """ - from crawl4ai.le.legacy.model_loader import load_nltk_punkt load_nltk_punkt() def chunk(self, text: str) -> list: @@ -86,7 +85,7 @@ 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