Skip to content
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

deepl plugin returns text in unicode escape sequence #541

Closed
yurnov opened this issue Feb 28, 2024 · 4 comments
Closed

deepl plugin returns text in unicode escape sequence #541

yurnov opened this issue Feb 28, 2024 · 4 comments

Comments

@yurnov
Copy link
Contributor

yurnov commented Feb 28, 2024

I enabled deepl plugin and found unexpected result, instead of readable text I got unicode escape sequence:
image

So, the answer is \u043e\u0445\u043e\u043f\u043b\u0435\u043d\u043d\u044f that is Cyrillic охоплення, but from the end-user perspective, it's wired.

yurnov added a commit to yurnov/chatgpt-telegram-bot that referenced this issue Feb 28, 2024
reason for this change is avoiding to get unicode escape characters in response for non-ANSI characters

potential fix for issue n3d1117#541
@yurnov
Copy link
Contributor Author

yurnov commented Feb 28, 2024

PR with fix created, please find #542, working fine for me:

image

@yurnov
Copy link
Contributor Author

yurnov commented Mar 7, 2024

I found that it's known bug for non-English functions calls in GPT-3.5 Turbo models that is fixed in gpt-3.5-turbo-0125.

Anyway, a PR #542 can be merged anyway as it fix issue for older model and don't bring any issue with a newer one.

@n3d1117
Copy link
Owner

n3d1117 commented Mar 11, 2024

Good work @yurnov and thanks for fixing! PR is merged now

@n3d1117 n3d1117 closed this as completed Mar 11, 2024
@yurnov
Copy link
Contributor Author

yurnov commented Mar 11, 2024

Thanks @n3d1117 a lot for accepting this PR

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants