Refine generate_response

app.py

@@ -11,7 +11,8 @@ retrieval_model_name = 'all-MiniLM-L6-v2'  # Using a pre-trained model from Hugg
 
 openai.api_key = os.environ["OPENAI_API_KEY"]
 
-system_message = "You are an assistant specialized in distilling the user input into a to-do list of specific items. You will then output those items in a numbered list."
+# Update the system message to provide more guidance on generating a to-do list
+system_message = "You are an assistant specialized in creating detailed to-do lists based on user input. Parse the input for tasks and generate a comprehensive list of actionable items. Output the items in a numbered list."
 
 # Initial system message to set the behavior of the assistant
 messages = [{"role": "system", "content": system_message}]
@@ -63,17 +64,15 @@ def find_relevant_segment(user_query, segments):
         print(f"Error in finding relevant segment: {e}")
         return ""
 
-def generate_response(user_query, relevant_segment):
+def generate_response(user_query):
     """
     Generate a response emphasizing the bot's capability in providing scheduling information.
     """
     try:
-        # Use relevant segment in the message to the model
-        user_message = f"Here's a to do list based on what you said: {relevant_segment}"
-
         # Append user's message to messages list
-        messages.append({"role": "user", "content": user_message})
+        messages.append({"role": "user", "content": user_query})
         
+        # Call OpenAI API to generate a to-do list based on the user query
         response = openai.ChatCompletion.create(
             model="gpt-4",
             messages=messages,
@@ -103,13 +102,8 @@ def query_model(question):
     if question == "":
         return "Hello! I am your time manager Timify! Please enter what you need to do today."
     
-    # Find the most relevant example segment
-    relevant_segment = find_relevant_segment(question, segments)
-    if not relevant_segment:
-        return "Could not find specific information. Please refine your requirements."
-    
-    # Generate a response using the relevant example
-    response = generate_response(question, relevant_segment)
+    # Generate a response using the user query directly
+    response = generate_response(question)
     return response
 
 # Define the welcome message and specific topics the chatbot can provide information about
@@ -140,6 +134,5 @@ with gr.Blocks(theme='freddyaboulton/test-blue') as demo:
             submit_button = gr.Button("Submit")
             submit_button.click(fn=query_model, inputs=question, outputs=answer)
     
-
 # Launch the Gradio app to allow user interaction
 demo.launch(share=True)