Update app.py

app.py

@@ -40,18 +40,46 @@ def load_and_preprocess_text(filename):
 
 segments = load_and_preprocess_text(filename)
 
-def find_relevant_segment(user_query, segments):
+def find_relevant_segment(user_query, segments, similarity_threshold=0.5):
+    """
+    Find the most relevant text segment based on a user query.
+    Parameters:
+    - user_query (str): The user's query.
+    - segments (list[str]): List of text segments to search within.
+    - similarity_threshold (float): Minimum similarity required to consider a segment relevant.
+    Returns:
+    - str: The most relevant text segment.
+    """
     try:
-        lower_query = user_query.lower()
-        query_embedding = retrieval_model.encode(lower_query)
+        query_embedding = retrieval_model.encode(user_query)
         segment_embeddings = retrieval_model.encode(segments)
         similarities = util.pytorch_cos_sim(query_embedding, segment_embeddings)[0]
         best_idx = similarities.argmax()
-        return segments[best_idx]
+        if similarities[best_idx].item() >= similarity_threshold:
+            return segments[best_idx]
+        else:
+            return "Sorry, I couldn't find a specific match. Here are some general tips to help you:"
     except Exception as e:
-        print(f"Error in finding relevant segment: {e}")
+        print(f"Error finding relevant segment: {e}")
         return ""
 
+def clean_up_response(response, segment):
+    """
+    Clean up the generated response to ensure it is tidy and presentable.
+    Parameters:
+    - response (str): The initial response generated by the model.
+    - segment (str): The segment used to generate the response.
+    Returns:
+    - str: A cleaned and formatted response.
+    """
+    sentences = response.split('.')
+    cleaned_sentences = [sentence.strip() for sentence in sentences if sentence.strip() and sentence.strip().lower() not in segment.lower()]
+    cleaned_response = '. '.join(cleaned_sentences).strip()
+    if cleaned_response and not cleaned_response.endswith((".", "!", "?")):
+        cleaned_response += "."
+    return cleaned_response
+
+
 def generate_response_with_context(user_query, relevant_segment):
     """
     Generate a response based on a user query and a relevant segment.