-
Notifications
You must be signed in to change notification settings - Fork 51
Open
Description
In our new and fancy world of LLMs and OpenAI, we have rate limits by number of message-tokens per minute, which means the bucket needs to be increased by a somewhat arbitrary number. Obviously, I could just call "check_rate" sequentially in a loop a few hundred times, but that seems... A little silly.
Would it be possible to expand the public API a little, and allow us to pass in an optional number-by-which-to-increase-the-number-of-tokens-in-the-bucket?
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
No labels