Bart Shappee
Bart Shappee
> Strange. It's definitely configured in the server as https://gitlab.com. However, it did work when I passed it in as a command line function. > > Is there a situation...
> Thanks for the fix! > > Instead of this implementation, what if we changed the `completion_cost` function in llm.py to return `0.00` when working with local models? Is there...
I added the localhost check so that there was at least a warning in the log, if not a local model, so that we aren't logging $0 even if there...