Updated limits

Added limits to prompt input and token output to prevent overload.

app.py

@@ -1,6 +1,7 @@
 """ Simple Chatbot
 @author: Nigel Gebodh
 @email: nigel.gebodh@gmail.com
+@website: https://ngebodh.github.io/
 """
 import numpy as np
 import streamlit as st
@@ -13,10 +14,13 @@ load_dotenv()
 # #===========================================
 # updates = '''
 # Updates
-# +01/08/2026
+# + 01/10/2026
+# - Updated cooldown
+
+# + 01/08/2026
 # - Updated logging info
 
-# +10/10/2025
+# + 10/10/2025
 # - Update the model options since Gemma-2-9B-it 
 #    is no longer supported. Replaced with GPT-OSS-120B
 
@@ -54,7 +58,7 @@ from datetime import datetime
 try:
     LOGGER_TOOL_WEBHOOK = os.environ.get("LOGGER_TOOL_URL")
 except Exception as e:
-    print(f"❌ Error in loading LOGGER_TOOL_WEBHOOK: {e}")
+    print(f"❌ Error in loading LOGGER_TOOL_WEBHOOK")
 
     
 
@@ -93,7 +97,7 @@ def log_to_webhook(
     try:
         requests.post(LOGGER_TOOL_WEBHOOK, json=payload, timeout=3)
     except Exception as e:
-        print("Logging failed:", e)
+        print("Logging failed")
 
 #  --------------------------------------------
 
@@ -112,6 +116,7 @@ def get_session_info():
     data = {
         "timezone": time.tzname,
         "platform": sys.platform,
+        "rand": uuid.uuid4().hex,
     }
     raw = json.dumps(data, sort_keys=True)
     return hashlib.sha256(raw.encode()).hexdigest()[:12]
@@ -137,21 +142,14 @@ def reset_conversation():
     st.session_state.messages = []
     st.session_state.session_info["conversation_id"] = str(uuid.uuid4())
 
+#  --------------------------------------------
 
 
 
 
-
-
-
-
-
-
-
-
-
-
-
+#==========================================================
+# Limits
+#  --------------------------------------------
 
 API_CALL_LIMIT = 20 # Define the limit
 
@@ -161,6 +159,15 @@ if 'api_call_count' not in st.session_state:
 
 
 
+REQUEST_COOLDOWN = 2  # seconds between requests
+
+if "last_request_time" not in st.session_state:
+    st.session_state.last_request_time = 0
+#  --------------------------------------------
+
+
+    
+
 model_links_hf ={
       "Gemma-3-27B-it":{
                       "inf_point":"https://router.huggingface.co/nebius/v1",
@@ -404,8 +411,19 @@ if prompt := st.chat_input(f"Hi I'm {selected_model}, ask me a question "):
     # Add user message to chat history
     st.session_state.messages.append({"role": "user", "content": prompt})
 
+    #Cooldown check
+    now = time.time()
+    elapsed = now - st.session_state.last_request_time
+    
+    if elapsed < REQUEST_COOLDOWN:
+        wait_time = round(REQUEST_COOLDOWN - elapsed, 1)
+        st.warning(f"⏳ Please wait before sending another request.")
+        st.stop()
+
+    st.session_state.last_request_time = now
 
 
+    
     if st.session_state.api_call_count >= API_CALL_LIMIT:
         
         # Add the warning to the displayed messages, but not to the history sent to the model
@@ -431,7 +449,7 @@ if prompt := st.chat_input(f"Hi I'm {selected_model}, ask me a question "):
                         ],
                         temperature=temp_values,#0.5,
                         stream=True,
-                        max_tokens=3000,
+                        max_tokens=1500, #3000,
                     )
 
                     response = st.write_stream(stream)