fix rate limit

webpages/buff_bot.py

@@ -21,11 +21,11 @@ def buffbot():
     with st.expander("See Source Code"):
         with open(__file__, "r", encoding="utf-8") as f:
             st.code(f.read(), language="python")
-
+    st.divider()
     # Select AI model for chatbot
     model_options = ["llama3.2:1b", "deepseek-chat", ]
     # on_change callback to clear chat history when model is changed
-    selected_model = st.selectbox("**👉 Please select a model to start**", model_options, on_change=clear_chat)
+    selected_model = st.selectbox("**👉Please select a model to start**", model_options, on_change=clear_chat)
 
     # Initialize session state to store chat history and message count
     if "messages" not in st.session_state:
@@ -85,31 +85,37 @@ def buffbot():
         with st.chat_message(message["role"], avatar=avatar):
             st.markdown(message["content"])
 
-    # Get user input
-    if prompt := st.chat_input("Type your message here..."):
-        # Add user message to chat history
-        st.session_state.messages.append({"role": "user", "content": prompt})
-        # Display user message with cowboy avatar
-        with st.chat_message("user", avatar="🤠"):
-            st.markdown(prompt)
+    if st.session_state.message_count < MAX_USER_MESSAGES:
+        # Get user input
+        if prompt := st.chat_input("Type your message here..."):
+            # Add user message to chat history
+            st.session_state.messages.append({"role": "user", "content": prompt})
+            st.session_state.message_count += 1
+            # Display user message with cowboy avatar
+            with st.chat_message("user", avatar="🤠"):
+                st.markdown(prompt)
 
-        # Generate reply 
-        with st.chat_message("assistant", avatar="🦬"):
-            with st.spinner('Thinking...'):
-                # Call the selected model API to generate a response
-                stream = client.chat.completions.create(
-                    model=selected_model,
-                    messages=[
-                        {"role": m["role"], "content": m["content"]}
-                        for m in st.session_state.messages
-                    ],
-                    stream=True, # stream the response
-                )
-            # Display the response from the model API
-            response = st.write_stream(stream)
-        # Add the AI assistant response to the chat history
-        st.session_state.messages.append({"role": "assistant", "content": response})
+            # Generate reply 
+            with st.chat_message("assistant", avatar="🦬"):
+                with st.spinner('Thinking...'):
+                    # Call the selected model API to generate a response
+                    stream = client.chat.completions.create(
+                        model=selected_model,
+                        messages=[
+                            {"role": m["role"], "content": m["content"]}
+                            for m in st.session_state.messages
+                        ],
+                        stream=True, # stream the response
+                    )
+                # Display the response from the model API
+                response = st.write_stream(stream)
+            # Add the AI assistant response to the chat history
+            st.session_state.messages.append({"role": "assistant", "content": response})
 
+    else:
+        st.warning("You have reached the maximum number of messages allowed.\
+            Please switch to another model to continue chatting.")
+        
     # Clear chat history
     if st.button("Clear Chat"):
         clear_chat()