Update app.py

app.py

@@ -65,13 +65,13 @@ def respond(message, history, model, access_level):
     try:
         # Call the chat completion method with the correct format
         response_message = client.chat_completion(
-          model=model,
-          messages=full_message,  # Use the correct parameter name
-          max_tokens=512,
-          temperature=0.7,
-          top_p=0.95,
-          stream=False
-         )
+            model=model,
+            inputs=full_message,  # Use the concatenated string
+            max_tokens=512,
+            temperature=0.7,
+            top_p=0.95,
+            stream=False  # Disable streaming
+        )
         response = response_message['choices'][0]['text']  # Access the content directly
     except Exception as e:
         return f"Error during model inference: {str(e)}", history