Feature: count tokens before calling '/v1/chat/completions'

[GPTLocalhost]

We recently integrated Microsoft Word with LocalAI through a local Word Add-in. You can see a demo of the integration here. We're planning to add a feature that allows users to see how many tokens are left before calling '/v1/chat/completions'. The question is:

Is it possible for LocalAI to count the tokens of the prompt 
before calling '/v1/chat/completions'? Any insights would be greatly appreciated.

For OpenAI models, this cookbook might be a direction. For other models with different tokenizers, it is not as clear how to implement such a function.