tjohnman

In some of my attempts to create a UI what I did was monitor the token usage and when it was 512 tokens from the limit, send a separate API...

This is important for me, too. Is it a bug, or are we supposed to set the configuration in some other way?

It should be easy to add support to any service that provides an OpenAI-compatible API, such as Perplexity, or LiteLLM for local models.

> Hey, I have a similar ? problem. This is not the first time that I install this, but this time it´s giving me trouble. When I try to open...

Historically, Japanese servers used the Shift JIS encoding. Over the years I've seen servers use Mac OS Roman, Latin 1, Shift JIS and UTF-8. But as far as I know,...