Update app.py

app.py

@@ -11,58 +11,80 @@ conversation_history = [
     {"role": "system", "content": "You are an assistant in a trivia game focused on Nigerian music."}
 ]
 
+# Function to count tokens (approximation)
+def count_tokens(messages):
+    return sum(len(message["content"].split()) for message in messages)
+
 # Function to get the initial LLM output and start the conversation
 def start_trivia_game():
     # Initial message to start the game
-    initial_message = "Start a Trivia on Nigeria music. Assess the answer and provide the percentage score"
-    
+    initial_message = "Start a Trivia on Nigerian music. Make 'None of the Above' an option available so that if the answer to the question is not in the options, users can choose 'None of the above'. Assess the answer and provide the percentage score. The highest percentage is 100%."
+
     # Add the initial message to the conversation history
     conversation_history.append({"role": "user", "content": initial_message})
-    
+
     # Get completion from the LLM for the initial question
     completion = client.chat.completions.create(
         model="llama-3.1-70b-versatile",
         messages=conversation_history,
         temperature=1,
-        max_tokens=1024,
+        max_tokens=2048,
         top_p=1,
         stream=True,
         stop=None,
     )
-    
+
     llm_output = ""
     for chunk in completion:
         llm_output += chunk.choices[0].delta.content or ""
-    
+
     # Add the assistant's response to the conversation history
     conversation_history.append({"role": "assistant", "content": llm_output})
-    
+
     return llm_output
 
 # Function to handle user response and continue the conversation
 def continue_trivia_game(user_response):
     # Add user's response to the conversation history
     conversation_history.append({"role": "user", "content": user_response})
-    
+
+    # Token limit management
+    max_tokens = 2048  # Maximum token limit for the LLM (example value)
+    current_tokens = count_tokens(conversation_history)
+
+    while current_tokens > max_tokens:
+        # Remove the oldest user-assistant pair
+        if len(conversation_history) > 2:
+            conversation_history.pop(1)  # Removing the second item as the first is the system message
+            conversation_history.pop(1)  # Remove the corresponding assistant response
+        current_tokens = count_tokens(conversation_history)
+
     # Get completion from the LLM for the user's response
-    completion = client.chat.completions.create(
-        model="llama-3.1-70b-versatile",
-        messages=conversation_history,
-        temperature=1,
-        max_tokens=1024,
-        top_p=1,
-        stream=True,
-        stop=None,
-    )
-    
-    llm_output = ""
-    for chunk in completion:
-        llm_output += chunk.choices[0].delta.content or ""
-    
-    # Add the assistant's response to the conversation history
-    conversation_history.append({"role": "assistant", "content": llm_output})
-    
-    return llm_output
+    try:
+        completion = client.chat.completions.create(
+            model="llama-3.1-70b-versatile",
+            messages=conversation_history,
+            temperature=1,
+            max_tokens=2048,
+            top_p=1,
+            stream=True,
+            stop=None,
+        )
+
+        llm_output = ""
+        for chunk in completion:
+            llm_output += chunk.choices[0].delta.content or ""
+
+        # Add the assistant's response to the conversation history
+        conversation_history.append({"role": "assistant", "content": llm_output})
+
+        return llm_output
+    except Exception as e:
+        # Check for specific rate limit error
+        if "rate_limit_exceeded" in str(e):
+            return "You've reached the maximum number of requests. Please wait a few minutes before trying again."
+        else:
+            return f"An error occurred Try again in 10 minutes: {str(e)}"
 
 # Start the game and get the initial LLM output
 initial_output = start_trivia_game()
@@ -70,22 +92,21 @@ initial_output = start_trivia_game()
 # Using gr.Blocks to create the interface
 with gr.Blocks() as demo:
     # Title and Description
-    gr.Markdown("# TriviaVilla\n A simple trivia game on Nigerian Music using LLama 3.1 LLM.")
-    
+    gr.Markdown("# TriviaVilla\n A simple trivia game on Nigerian Music Industry using LLama 3.1 LLM.")
+
     # LLM Output Textbox
     llm_output = gr.Textbox(label="LLM Output", placeholder="The output from the LLM will appear here", lines=10, value=initial_output)
-    
+
     # User Response Textbox
     user_response = gr.Textbox(label="Your Response", placeholder="Type your response here", lines=3)
-    
+
     # Button to submit the user's response and update the LLM output
     submit_button = gr.Button("Submit")
-    
+
     # Function to update the LLM output upon submission
     def update_llm_output(user_input):
-        # Update the LLM output and return it
         return continue_trivia_game(user_input)
-    
+
     # Define interactions
     submit_button.click(fn=update_llm_output, inputs=user_response, outputs=llm_output)