How to use internal AI endpoints?

[evantobin (evan)]

I was able to get this to work by doing DISCOURSE_ALLOWED_INTERNAL_HOSTS: localhost as an environment variable to connect to my LiteLLM sidecar hosted at localhost:4000. I also have a pull request to add vertex AI auth here: DEV: add Google Vertex AI LLM provider by evantobin · Pull Request #41350 · discourse/discourse · GitHub