diff --git a/openagent_eval/diagnosis/chunking.py b/openagent_eval/diagnosis/chunking.py index dedf887..794fc47 100644 --- a/openagent_eval/diagnosis/chunking.py +++ b/openagent_eval/diagnosis/chunking.py @@ -159,7 +159,7 @@ def _check_content_gaps( "will", "about", "into", "your", "some", "than", } question_words = set( - w.lower() for w in re.findall(r"\b[a-zA-Z]{4,}\b", question) + w.lower() for w in re.findall(r"\b[^\W\d_]{4,}\b", question) ) - stop_words if not question_words: return issues