Support stream_options for openAI API

[Binyang2014]

According to openAI doc: https://platform.openai.com/docs/api-reference/chat/create#chat-create-stream_options. The API provide the stream_options which can get token usage info for stream request. Please support this option for better rate-limit control

[Minxiangliu]

My alternative approach here is to use the AutoTokenizer from the transformers library to calculate the number of tokens.

from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('model....')
len(tokenizer.tokenize(content))