Update app.py

app.py

@@ -13,10 +13,9 @@ def preprocess_text(text):
     cleaned_chunks = []
     
     for chunk in chunks:
-        chunk.strip()
-
-    if chunk != "":
-      cleaned_chunks.append(chunk)
+        chunk = chunk.strip()
+        if chunk != "":
+            cleaned_chunks:append(chunk)
 
     return cleaned_chunks
 cleaned_chunks = preprocess_text(info_text)
@@ -24,10 +23,11 @@ cleaned_chunks = preprocess_text(info_text)
 # Load the pre-trained embedding model that converts text to vectors
 model = SentenceTransformer('all-MiniLM-L6-v2')
 
+chunk_embeddings = create_embeddings(cleaned_chunks) # Complete this line
+
 def create_embeddings(text_chunks):
-    chunk_embeddings = model.encode(cleaned_chunks, convert_to_tensor=True) # Replace ... with the text_chunks list
+    chunk_embeddings = model.encode(text_chunks, convert_to_tensor=True) # Replace ... with the text_chunks list
     return chunk_embeddings
-chunk_embeddings = create_embeddings(cleaned_chunks) # Complete this line
 
 # Define a function to find the most relevant text chunks for a given query, chunk_embeddings, and text_chunks
 def get_top_chunks(query, chunk_embeddings, text_chunks):
@@ -47,13 +47,22 @@ def query_model(question):
     """
     Process a question, find relevant information, and generate a response.
     """
-    if question == "":
+    if question.strip() == "":
         return "Welcome to GreenGuide! Ask me anything about eco-friendly hotels, restaurants, and things to do in NYC."
-    relevant_segment = find_relevant_segment(question, segments)
-    if not relevant_segment:
-        return "Could not find specific information. Please refine your question."
-    response = generate_response(question, relevant_segment)
+
+    top_chunks = get_top_chunks(question, chunk_embeddings, cleaned_chunks)
+
+    response = "Here are the most relevant results:\n\n"
+    for i, chunk in enumerate(top_chunks, start=1):
+        response += f"{i}. {chunk}\n\n"
+
     return response
+    
+    # relevant_segment = find_relevant_segment(question, segments)
+    # if not relevant_segment:
+    #     return "Could not find specific information. Please refine your question."
+    # response = generate_response(question, relevant_segment)
+    # return response
 
 
 def display_iframe():