Update app.py

app.py

@@ -7,10 +7,10 @@ import torch
 
 #STEP 2 FROM SEMATIC SEARCH
 # Open the water_cycle.txt file in read mode with UTF-8 encoding
-with open("water_cycle.txt", "r", encoding="utf-8") as file:
+with open("weather.txt", "r", encoding="utf-8") as file:
   # Read the entire contents of the file and store it in a variable
-  water_cycle_text = file.read()
-print(water_cycle_text)
+  weather_text = file.read()
+
 
 #STEP 3 FROM SEMATIC SEARCH
 def preprocess_text(text):
@@ -18,7 +18,7 @@ def preprocess_text(text):
   cleaned_text = text.strip()
 
   # Split the cleaned_text by every newline character (\n)
-  chunks = cleaned_text.split("\n")
+  chunks = cleaned_text.split("***")
 
   # Create an empty list to store cleaned chunks
   cleaned_chunks = []
@@ -40,7 +40,7 @@ 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(water_cycle_text) # Complete this line
+cleaned_chunks = preprocess_text(weather_text) # Complete this line
 
 #STEP 4 FROM SEMATIC SEARCH
 # Load the pre-trained embedding model that converts text to vectors
@@ -98,7 +98,9 @@ def get_top_chunks(query, chunk_embeddings, text_chunks):
 
 #STEP 6 FROM SEMATIC SEARCH
 # Call the get_top_chunks function with the original query
-top_results = get_top_chunks("How do you make banana bread?", chunk_embeddings, cleaned_chunks)
+top_weather = get_top_chunks("How do you make banana bread?", chunk_embeddings, cleaned_chunks)
+
+
 
 # Print the top results
 print(top_results)
@@ -107,11 +109,11 @@ print(top_results)
 client = InferenceClient("Qwen/Qwen2.5-72B-Instruct")
 
 def respond(message, history):
-    top_results = get_top_chunks(message, chunk_embeddings, cleaned_chunks)
-    print(top_results)
-    str_top_results = "\n".join(top_results)
+    top_weather = get_top_chunks(message, chunk_embeddings, cleaned_chunks)
+    print(top_weather)
+    str_top_weather = "\n".join(top_weather)
     
-    messages = [{"role": "system", "content": f"You're a friendly and gen z chatbot. Base your response on the provided context: {top_results}."}]
+    messages = [{"role": "system", "content": f"You're a friendly and gen z chatbot. Base your response on the provided context: {top_weather}."}]
 
     if history:
         messages.extend(history)
@@ -128,4 +130,6 @@ def respond(message, history):
     
 chatbot = gr.ChatInterface(respond, type = 'messages')
 chatbot.launch(debug = True) 
+    
+