Update app.py

app.py

@@ -468,8 +468,8 @@ def generate_answer(message, choice, retrieval_mode, selected_model):
                 logging.debug(f"Phi-3.5 Prompt: {prompt}")
 
                 response = selected_model(prompt, **{
-                    "max_new_tokens": 128,  # Increased to handle longer responses
-                    "return_full_text": False,
+                    "max_new_tokens": 160,  # Increased to handle longer responses
+                    "return_full_text": True,
                     "temperature": 0.7,  # Adjusted to avoid cutting off
                     "do_sample": True,   # Allow sampling to increase response diversity
                 })