-
Notifications
You must be signed in to change notification settings - Fork 5.7k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Feature Request]: partial error message from code executor #2060
Comments
Just to clarify, do you mean you want the code executors to only return specific part of the call stack in error message? If that's the case, you can take a look at the code executors' implementations in Let @jackgerrits and me know if you are stuck. We can also discuss if we should add this to our code executor roadmap #1421 |
Yes, thanks, that's exactly what I was interested in, I think it's useful because in some cases when there are errors, for example when loading very large csv files, the error is in the column format "AcolumnBcolumnCcolumnD....ColumnZ is not considered intger " so even if you use a timeout you could run out of all your available per minute tokens with just one error message. |
Thanks for confirming. Would you like to give it a try? A good place to start is |
Yes I will try |
Can you please try reproing your issues in 0.4 and create a new issue if it is still a problem for you. Thanks! |
Feature Request
Is it possible to include just a part of the error when a code is executed? For example if I have in a roleplay one of the two agents that executing the code finds:
Traceback (most recent call last):
File "/home/matt/anaconda3/envs/coder/lib/python3.11/site-packages/autogen/oai/completion.py", line 224, in _get_response
response = openai_completion.create(request_timeout=request_timeout, **config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/matt/anaconda3/envs/coder/lib/python3.11/site-packages/openai/api_resources/chat_completion.py", line 25, in create
return super().create(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/matt/anaconda3/envs/coder/lib/python3.11/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 153, in create
response, _, api_key = requestor.request(
^^^^^^^^^^^^^^^^^^
File "/home/matt/anaconda3/envs/coder/lib/python3.11/site-packages/openai/api_requestor.py", line 226, in request
resp, got_stream = self._interpret_response(result, stream)
Can I decide to send to the other agent just the last line? In this case:
File "/home/matt/anaconda3/envs/coder/lib/python3.11/site-packages/openai/api_requestor.py", line 226, in request
resp, got_stream = self._interpret_response(result, stream)
The text was updated successfully, but these errors were encountered: