-
Notifications
You must be signed in to change notification settings - Fork 5.1k
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
Fixes “The model produced invalid content” error when calling functions #3429
Draft
davorrunje
wants to merge
10
commits into
microsoft:0.2
Choose a base branch
from
davorrunje:fix-model-produced-invalid-content
base: 0.2
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
+273
−4
Draft
Changes from all commits
Commits
Show all changes
10 commits
Select commit
Hold shift + click to select a range
d552c05
Fixes the issue caused the following error introduced by more strict …
davorrunje 7b65662
update tests
davorrunje 31e4db9
fix
davorrunje 0e76c51
Merge branch 'microsoft:main' into fix-model-produced-invalid-content
davorrunje e81a6c6
removed names from assistant role only
davorrunje f7caf75
Merge branch 'fix-model-produced-invalid-content' of https://github.c…
davorrunje 8321c81
Merge branch 'microsoft:main' into fix-model-produced-invalid-content
davorrunje abc708f
Merge branch 'main' into fix-model-produced-invalid-content
davorrunje 96658f9
Merge branch 'microsoft:main' into fix-model-produced-invalid-content
davorrunje a698c8b
Merge branch '0.2' into fix-model-produced-invalid-content
ekzhu File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@marklysze here is an example of failing completion call
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks @davorrunje, is it possible to get the AutoGen code that would have generated this?
As an update: I ran the params through OpenAI's API (
response = completions.create(**params)
) and it ran through okay and returned a function call.With my agent's termination check it failed on checking the content for the termination keyword as
content
isNone
:is_termination_msg=lambda x: True if "FINISH" in x["content"] else False
The exception:
argument of type 'NoneType' is not iterable
Updating my termination expression corrected that:
is_termination_msg=lambda x: True if x["content"] and "FINISH" in x["content"] else False
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@marklysze I marked the PR as a draft as I am not sure yet what kind of workaround is the best one. The issue seems to be on the OpenAPI side and it is more common with GPT-4o-mini than older models. Maybe we should remove names only if we get an exception? Even changing the system message a little bit helps sometimes. The list of possible workarounds is (https://community.openai.com/t/bizarre-issue-preventing-response-from-gpt-4o-mini-the-model-produces-invalid-content/875432):
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks @davorrunje, appreciate the detail and the note on the draft.
It is definitely tricky because removing the name is a considerable change and could affect people's existing code - at the very least I'd suggest it is made as an option and defaults to existing behaviour of leaving it in.
From the list you provided, I think the third point would be the safest to do to minimise the impact on the validity of the messages. In the following linked LinkedIn post they added a message "DO NOT PRODUCE INVALID CONTENT" and that seemed to fix it! :).
LinkedIn Post on this being intermittent behaviour.
I would love to be able to replicate it, have you got any other examples that you can get to throw an exception?
I wonder if rather than change the messages to start with, we run inference and if it throws that specific exception then it adjusts the messages (perhaps with 3rd option above) and tries again up to x times.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yes, I think we need to add a simple hack first and see how it goes. I see this error quite often when working with function calls and GPT-4o and GPT-4o-mini. I'll try adding a message as suggested first.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Okay, not sure if it's possible but if you do get the exception and are able to get the params["messages"] it would be interesting to see if it is replicated.
See how you go with the additional message.