added food and attractions

app.py

@@ -13,6 +13,12 @@ with open("weather.txt", "r", encoding="utf-8") as file:
 with open("luggage.txt", "r", encoding="utf-8") as file:
   # Read the entire contents of the file and store it in a variable
   luggage_text = file.read()
+with open("attraction.txt", "r", encoding="utf-8") as file:
+  # Read the entire contents of the file and store it in a variable
+  attraction_text = file.read()
+with open("food.txt", "r", encoding="utf-8") as file:
+  # Read the entire contents of the file and store it in a variable
+  food_text = file.read()
 
 #STEP 3 FROM SEMATIC SEARCH
 def preprocess_text(text):
@@ -37,6 +43,8 @@ def preprocess_text(text):
 # Call the preprocess_text function and store the result in a cleaned_chunks variable
 cleaned_chunks_weather = preprocess_text(weather_text) # Complete this line
 cleaned_chunks_luggage = preprocess_text(luggage_text)
+cleaned_chunks_attraction = preprocess_text(attraction_text)
+cleaned_chunks_food = preprocess_text(food_text)
 
 #STEP 4 FROM SEMATIC SEARCH
 # Load the pre-trained embedding model that converts text to vectors
@@ -55,6 +63,8 @@ def create_embeddings(text_chunks):
 # Call the create_embeddings function and store the result in a new chunk_embeddings variable
 chunk_embeddings_weather = create_embeddings(cleaned_chunks_weather) # Complete this line
 chunk_embeddings_luggage = create_embeddings(cleaned_chunks_luggage)
+chunk_embeddings_attraction = create_embeddings(cleaned_chunks_attraction)
+chunk_embeddings_food = create_embeddings(cleaned_chunks_food)
 
 #STEP 5 FROM SEMATIC SEARCH
 # Define a function to find the most relevant text chunks for a given query, chunk_embeddings, and text_chunks
@@ -93,11 +103,17 @@ client = InferenceClient("Qwen/Qwen2.5-72B-Instruct")
 def respond(message, history,use_spanish, destinations, season, luggage_types, luggage_size, food_prefs):
     top_weather = get_top_chunks(message, chunk_embeddings_weather, cleaned_chunks_weather)
     top_luggage = get_top_chunks(message, chunk_embeddings_luggage, cleaned_chunks_luggage)
+    top_attraction = get_top_chunks(message, chunk_embeddings_attraction, cleaned_chunks_attraction)
+    top_food = get_top_chunks(message, chunk_embeddings_food, cleaned_chunks_food)
     print(top_weather)
     print(top_luggage)
+    print(top_attraction)
+    print(top_food)
     
     str_top_weather = "\n".join(top_weather)
     str_top_luggage = "\n".join(top_luggage)
+    str_top_attraction = "\n".join(top_attraction)
+    str_top_food = "\n".join(top_food)
 
     lang = "Spanish" if use_spanish else "English"
     ctx = (
@@ -107,7 +123,7 @@ def respond(message, history,use_spanish, destinations, season, luggage_types, l
         f"Luggage: {', '.join(luggage_types)} of size {luggage_size}\n"
         f"Food: {', '.join(food_prefs)}\n"
     )
-    
+
     messages = [{"role": "system", "content": f"You're a friendly and gen z chatbot. Base your response on the provided context: {top_weather} and {top_luggage}."}]
 
     if history: