Update app.py

app.py

@@ -537,7 +537,7 @@ def get_response_from_llama(query, model, selected_docs, file_type, num_calls=1,
             # Generate content with streaming enabled
             for response in client.chat_completion(
                 messages=messages,  # Pass messages in the required format
-                max_new_tokens=1000,  # Reduced to ensure we stay within token limits
+                max_tokens=1000,  # Reduced to ensure we stay within token limits
                 temperature=temperature,
                 stream=True,
                 repetition_penalty=1.1,