You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
For those instances in which we're using models/providers with severe token-per-minute limitations, or in which their APIs can get overloaded, it would be cool if there was a way to specify a "throttle" parameter to specify a limit on the max token-per-minute rate.
The text was updated successfully, but these errors were encountered:
Version
Command-line (Python) version
Suggestion
For those instances in which we're using models/providers with severe token-per-minute limitations, or in which their APIs can get overloaded, it would be cool if there was a way to specify a "throttle" parameter to specify a limit on the max token-per-minute rate.
The text was updated successfully, but these errors were encountered: