Update app.py

app.py

@@ -76,6 +76,10 @@ def interact(user_input, history, interaction_count):
         if tokenizer is None or model is None:
             raise ValueError("Tokenizer or model is not initialized.")
         
+        # Concatenate a final message if max interactions are reached
+        if interaction_count >= MAX_INTERACTIONS - 1:
+            user_input += " This is the last message. Please respond accordingly."
+
         messages = history + [{"role": "user", "content": user_input}]
         
         # Ensure roles alternate correctly
@@ -88,11 +92,6 @@ def interact(user_input, history, interaction_count):
         # Check if the maximum number of interactions has been reached
         interaction_count += 1
         print(f"Interaction count: {interaction_count}")  # Print the interaction count
-        if interaction_count >= MAX_INTERACTIONS:
-            farewell_message = "Thank you for the conversation! Have a great day!"
-            history.append({"role": "assistant", "content": farewell_message})
-            formatted_history = [(entry["content"], None) if entry["role"] == "user" else (None, entry["content"]) for entry in history if entry["role"] in ["user", "assistant"]]
-            return "", formatted_history, history, interaction_count
         
         # Generate response using selected model
         input_ids = tokenizer(prompt, return_tensors='pt').input_ids.to("cuda")
@@ -106,7 +105,7 @@ def interact(user_input, history, interaction_count):
         formatted_history = [(entry["content"], None) if entry["role"] == "user" else (None, entry["content"]) for entry in history if entry["role"] in ["user", "assistant"]]
         return "", formatted_history, history, interaction_count
     except Exception as e:
-        if torch.cuda.is_available():
+        if torch.cuda.is available():
             torch.cuda.empty_cache()
         print(f"Error during interaction: {e}")
         raise gr.Error(f"An error occurred during interaction: {str(e)}")