Update app.py

app.py

@@ -9,8 +9,11 @@ kw_model = KeyBERT(model)
 
 # 🔍 Helper: Clean keywords from text (split on commas, newlines)
 def clean_keywords(text):
-    keywords = re.split(r"[,\n]", text.lower())
-    return set(kw.strip() for kw in keywords if kw.strip())
+    # Lowercase, remove special characters, and split on space/comma
+    text = re.sub(r"[^a-zA-Z0-9\s]", " ", text.lower())
+    words = re.split(r"\s+", text)
+    return set(w for w in words if w and len(w) > 2)  # ignore very short words
+
 
 # 🔍 Main function
 def extract_keywords(job_desc, resume_text, analyze_with_jd):