feat: added a wait timer

app.py

@@ -1,3 +1,5 @@
+import time
+
 import gradio as gr
 import aiohttp
 import asyncio
@@ -58,7 +60,6 @@ async def chat_with_server(chat_history, api_key, base_url, selected_type, selec
         if assistant_msg is not None and not assistant_msg.startswith("Assistant is thinking"):
             api_messages.append({'role': 'assistant', 'content': assistant_msg})
 
-    # Use custom_model if selected_type is 'custom' or 'open_router', otherwise use selected_model
     model = custom_model if selected_type in ['custom', 'open_router'] else selected_model
 
     payload = {
@@ -71,35 +72,36 @@ async def chat_with_server(chat_history, api_key, base_url, selected_type, selec
         'stream': True,
     }
 
-    # Initialize typing animation
+    start_time = time.time()
+
     if chat_history:
-        chat_history[-1][1] = "Assistant is thinking"
+        chat_history[-1][1] = "Assistant is thinking (0 sec)"
         yield chat_history
 
     async with aiohttp.ClientSession() as session:
         try:
-            # Start the server request asynchronously
             response_task = asyncio.create_task(session.post(
                 f'{api_url}/v1/chat/completions',
                 headers=headers,
                 json=payload,
-                timeout=900
+                timeout=1200
             ))
 
-            # Typing animation variables
             dots_count = 0
             assistant_message = ''
 
             while not response_task.done():
-                # Update typing animation
+                elapsed_time = time.time() - start_time
+                minutes, seconds = divmod(int(elapsed_time), 60)
+                time_str = f"{minutes} min {seconds} sec" if minutes > 0 else f"{seconds} sec"
+
                 dots = '.' * ((dots_count % 3) + 1)
                 dots_count += 1
                 if chat_history:
-                    chat_history[-1][1] = f"Assistant is thinking{dots}"
+                    chat_history[-1][1] = f"Assistant is thinking ({time_str}){dots}"
                     yield chat_history
-                await asyncio.sleep(0.5)  # Wait before updating again
+                await asyncio.sleep(0.5)
 
-            # Now get the response
             response = await response_task
             if response.status != 200:
                 error_message = f"Error {response.status}: {await response.text()}"
@@ -108,7 +110,6 @@ async def chat_with_server(chat_history, api_key, base_url, selected_type, selec
                 return
 
             assistant_message = ''
-            # Read the streaming response
             async for line in response.content:
                 line = line.decode('utf-8').strip()
                 if line == '':
@@ -124,10 +125,8 @@ async def chat_with_server(chat_history, api_key, base_url, selected_type, selec
                             if 'content' in delta:
                                 content = delta['content']
                                 assistant_message += content
-                                # Update the assistant's message in the chat
                                 chat_history[-1][1] = assistant_message
                                 yield chat_history
-            # Final update to the conversation
             yield chat_history
 
         except Exception as e: