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

token length('150') exceeded #252

Open
zczuprik opened this issue Aug 11, 2024 · 1 comment
Open

token length('150') exceeded #252

zczuprik opened this issue Aug 11, 2024 · 1 comment

Comments

@zczuprik
Copy link

zczuprik commented Aug 11, 2024

First thanks for the great work @jekalmin!

Looking for a bit of help... Connected faster-whisper and piper to Home Assistant and it is working just fine when trying to manage specific devices in the house.

However I'm getting frequently the message from Assist:
"Something went wrong: token length('150') exceeded. Increase maximum token to avoid the issue."

Quick example:
Roll up shutter 08 - works
Roll up shutter 09 - works
Roll up shutter 10 - works
Roll up shutter 11 - works
Roll up shutter 08,09 and 10 - works

Roll up shutter 08,09,10 and 11 - gives the above error message
Roll up all shutters - gives the above error message

Not sure which component gives back the error message, therefore no idea where to try to increase the token limit.
Thanks for any idea, I'm new to these technologies.

Zoli

@jekalmin
Copy link
Owner

jekalmin commented Dec 1, 2024

Sorry for late reply.
Try increasing Maximum Token to return in response.
It's because of the length of LLM's response of function calling is greater than what you set in Maximum Token to return in response.

1

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