Support defaulting to infinity or -1 for completions

[swg]

Hello,

As per llama.cpp help:

-n N, --n_predict N number of tokens to predict (default: 128, -1 = infinity)

The OpenAI docs state that the /completions endpoint defaults to 16, but is optional:
max_tokens integer Optional Defaults to 16
https://platform.openai.com/docs/api-reference/completions/create#completions/create-max_tokens

However, /chat/completions defaults to infinity, and is again optional:
max_tokens integer Optional Defaults to inf
https://platform.openai.com/docs/api-reference/chat/create#chat/create-max_tokens

This pull request modifies the fast_api example, the main server and supporting python lib to allow passing a 'null' which will default to infinity, mimicking the OpenAI API.

[peturparkur]

The type signature for max_tokens: Optional[Union[int, None]] doesn't make any sense.
Optional[T] is equivalent/alias of Union[T, None]

[K-Mistele]

Hey guys, seems like there's a related error in #983 where if you don't specify the max_tokens and then send a prompt larger than n_ctx you run into a TypeError due to server attempting to add the default value of max_tokens which is None to the number of tokens from the prompt.

[abetlen]

@K-Mistele yup, I added a few commits to hopefully fix that in the server error handler.

@swg thanks for the contribution! Sorry it took so long to merge.

[K-Mistele]

With these fixes what is now the proper way to set an unlimited number of response tokens?

[abetlen]

@K-Mistele passing None / null for max_tokens should work everywhere now and is recommended as it matches the OpenAI spec.