Closed josephtutera closed 1 year ago
Hi, Thanks for checking the repo.
The library is separated from the openai library, so it must work. You just need to feed it the prompts and parameters you are using with a context manager.
But, I have not updated the library for months, I don't know if there are any modifications in the system.
I suggest you test it first.
Until then, I can't guarantee that the current rate limiting implementation is still correct.
Thanks.
I'll give it a try!
Thanks
This worked on Azure, just FYI
Hey! I am currently building with GPT-4 and our API endpoint uses the Azure OpenAI service. We need to implement a ratelimiter like the one you have here as we run many calls in parallel. Will this work with the Azure Endpoints?
Thanks!