Update app.py

app.py

@@ -1,4 +1,5 @@
 import gradio as gr
+import time
 from optimum.intel import OVModelForCausalLM
 from transformers import AutoTokenizer, pipeline
 
@@ -12,6 +13,9 @@ pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 def respond(message):
     try:
+        # Record the start time
+        start_time = time.time()
+        
         # Only use the current message as input (no history)
         input_text = f"User: {message}"
 
@@ -26,6 +30,10 @@ def respond(message):
         )
         reply = response[0]['generated_text'].strip()
         
+        # Calculate inference time
+        inference_time = time.time() - start_time
+        print(f"Inference time: {inference_time:.4f} seconds")
+        
         # Return as a tuple (user message, bot reply)
         return [(message, reply)]