Seems like support for Azure OpenAI broke.

As far as I can see, the engine config is no longer parsed and used in the code anywhere, as it were earlier (#58).

It looks like the engine parameter is needed on openai.ChatCompletion instead of model when using AzureOpenAI, as per this Azure example:

completion = openai.ChatCompletion.create(
  engine="my-deployment",
  messages = message_text,
  temperature=0.7,
  max_tokens=800,
  top_p=0.95,
  frequency_penalty=0,
  presence_penalty=0,
  stop=None
)