Catch rate limiting errors

[scottyeager]

Might be nice to catch errors like this:

Error: error getting completion: failed to get completion: POST "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions": 429 Too Many Requests [{
  "error": {
    "code": 429,
    "message": "Resource has been exhausted (e.g. check quota).",
    "status": "RESOURCE_EXHAUSTED"
  }
}

And display a nicer error:

# Yer getting rate limited, mate