Update app.py

app.py

@@ -7,9 +7,17 @@ import torch
 
 # STEP 2 FROM SEMANTIC SEARCH
 # Open the water_cycle.txt file in read mode with UTF-8 encoding
-with open("mom_phrases.txt", "r", encoding="utf-8") as file:
+with open("cool_mom_phrases.txt", "r", encoding="utf-8") as file:
   # Read the entire contents of the file and store it in a variable
-  phrases_text = file.read()
+  cool_mom_text = file.read()
+
+with open("tutor_mom_phrases.txt", "r", encoding="utf-8") as file:
+  # Read the entire contents of the file and store it in a variable
+  tutor_mom_text = file.read()
+
+with open("strict_mom_phrases.txt", "r", encoding="utf-8") as file:
+  # Read the entire contents of the file and store it in a variable
+  strict_mom_text = file.read()
 
 # STEP 3 FROM SEMANTIC SEARCH
 def preprocess_text(text):
@@ -37,7 +45,9 @@ def preprocess_text(text):
   return cleaned_chunks
 
 # Call the preprocess_text function and store the result in a cleaned_chunks variable
-cleaned_chunks = preprocess_text(phrases_text) # Complete this line
+cleaned_cool_chunks = preprocess_text(cool_mom_text) # Complete this line
+cleaned_tutor_chunks = preprocess_text(tutor_mom_text)
+cleaned_strict_chunks = preprocess_text(strict_mom_text)
 
 #STEP 4 FROM SEMANTIC SEARCH
 # Load the pre-trained embedding model that converts text to vectors
@@ -59,7 +69,9 @@ def create_embeddings(text_chunks):
   return chunk_embeddings
 
 # Call the create_embeddings function and store the result in a new chunk_embeddings variable
-chunk_embeddings = create_embeddings(cleaned_chunks) # Complete this line
+cool_chunk_embeddings = create_embeddings(cleaned_cool_chunks) # Complete this line
+tutor_chunk_embeddings = create_embeddings(cleaned_tutor_chunks)
+strict_chunk_embeddings = create_embeddings(cleaned_strict_chunks)
 
 #STEP 5 FROM SEMANTIC SEARCH
 # Define a function to find the most relevant text chunks for a given query, chunk_embeddings, and text_chunks
@@ -96,21 +108,18 @@ def get_top_chunks(query, chunk_embeddings, text_chunks):
   # Return the list of most relevant chunks
   return top_chunks
 
-print(get_top_chunks("How are you", chunk_embeddings, cleaned_chunks))
-
 # STEP 6 FROM SEMANTIC SEARCH
 # Call the get_top_chunks function with the original query
-top_results = get_top_chunks("How does water get into the sky?", chunk_embeddings, cleaned_chunks) # Complete this line
-
-# Print the top results
-print(top_results)
-
+#top_cool_results = get_top_chunks(message, cool_chunk_embeddings, cleaned_cool_chunks) # Complete this line
+#top_tutor_results = get_top_chunks(message, tutor_chunk_embeddings, cleaned_tutor_chunks)
+#top_tiger_results = get_top_chunks(message, tiger_chunk_embeddings, cleaned_tiger_chunks)
 
 client = InferenceClient("Qwen/Qwen2.5-72B-Instruct")
 
 def respond(message, history):
-    best_chunks = get_top_chunks(message, chunk_embeddings, cleaned_chunks)
-    print(best_chunks)
+    top_cool_results = get_top_chunks(message, cool_chunk_embeddings, cleaned_cool_chunks) # Complete this line
+    top_tutor_results = get_top_chunks(message, tutor_chunk_embeddings, cleaned_tutor_chunks)
+    top_strict_results = get_top_chunks(message, strict_chunk_embeddings, cleaned_strict_chunks)
     str_chunks = "\n".join(best_chunks)
     messages = [{"role": "system", "content": f"You are chatbot that plays the role of the user's mom. Base your response on the provided context: {str_chunks}"}, 
                {"role": "user",