Update app.py

app.py

@@ -16,28 +16,33 @@ try:
 except Exception as e:
     print(f"Failed to load models: {e}")
 
+def preprocess_text(text):
+    """
+    Preprocess text by lowercasing and removing special characters.
+    """
+    text = text.lower()
+    text = re.sub(r'[^a-z0-9\s]', '', text)
+    return text
+
 def load_and_preprocess_text(filename):
     """
     Load and preprocess text from a file, removing empty lines and stripping whitespace.
     """
     try:
         with open(filename, 'r', encoding='utf-8') as file:
-            segments = [line.strip() for line in file if line.strip()]
+            segments = [preprocess_text(line.strip()) for line in file if line.strip()]
         print("Text loaded and preprocessed successfully.")
         return segments
     except Exception as e:
         print(f"Failed to load or preprocess text: {e}")
         return []
 
-segments = load_and_preprocess_text(filename)
+segments = load_and_preprocess_text(filena
 
 def find_relevant_segments(user_query, segments, top_k=5):
-    """
-    Find the top-k most relevant text segments for a user's query using cosine similarity among sentence embeddings.
-    """
     try:
-        # Lowercase the query for better matching
-        lower_query = user_query.lower()
+        # Preprocess and lowercase the query for better matching
+        lower_query = preprocess_text(user_query)
         # Encode the query and the segments
         query_embedding = retrieval_model.encode(lower_query)
         segment_embeddings = retrieval_model.encode(segments)
@@ -51,6 +56,7 @@ def find_relevant_segments(user_query, segments, top_k=5):
         print(f"Error in finding relevant segments: {e}")
         return []
 
+
 def generate_response(user_query, relevant_segments):
     """
     Generate a response providing song recommendations based on mood.