Update app.py

app.py

@@ -17,6 +17,7 @@ import pandas as pd
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 from transformers import AutoTokenizer, AutoModelForQuestionAnswering
+#import re
 
 """# data - text"""
 
@@ -30,10 +31,10 @@ def remove_symbols(text):
     cleaned_text = "".join([char for char in text if char not in remove_chars])
 
     # Remove non-ASCII characters
-    pattern_ascii = r'[^\x00-\x7F]'  # Matches any character outside the ASCII range
-    filtered_text = re.sub(pattern_ascii, '', cleaned_text)
+    #pattern_ascii = r'[^\x00-\x7F]'  # Matches any character outside the ASCII range
+    #filtered_text = re.sub(pattern_ascii, '', cleaned_text)
 
-    return filtered_text
+    return cleaned_text
 
 def context_func(message):
   # Create a TF-IDF vectorizer