I’m looking for a way to access current usage and limits so that the app I’m building can adjust itself based on how much is available. Basically, the amount of history for the prompt, the frequency at which the system will perform completions, etc. needs to be able to adjust on its own so that it lowers the risk of going over the quota.
I also need to be able to initialize the fine-tuning of an already fine-tuned model, from within my application. I’ve been looking, but it doesn’t seem like there’s a way to do this right now. Maybe it can be done using the raw API, but I don’t see documentation there. The only fine-tuning documentation shows the CLI tool as the way to fine-tune.
I’m terrible at figuring out how to directly interface with an API, which is why I rely so heavily on bindings, but if there aren’t any, and there is at least a direct way to access it through the API, that at least would make it possible for me to complete this application, especially with some hand holding on how to write the code to directly interface with the API without bindings.