Stephen Hodgson

> Hi everyone. It seems the streaming feature for the Assistant API has just been released. Is it possible to start working on its support? > > Here is the...

- https://github.com/openai/openai-openapi/issues/208

So it seems they actually use a completely different API surface for this which is quite a breaking change. So I won't be adding this until OpenAI-DotNet 8.0.0 ``` OpenAI-Beta:...

I wasn't planning on tracking these individually.

> I wonder if there is some way we could consume the OpenAI API spec so that when new properties get released it can be partially automated? > > https://github.com/openai/openai-openapi/blob/master/openapi.yaml...

Sorry I haven't had time to get around to it. I'll see what I can do this weekend.

Most of the work is done. Just finishing up streaming support and fixing a few bugs with tool cache

Is there anything preventing you from using GPT-3-Encoder-Sharp with this package?

Honestly, I would rather OpanAI add an endpoint specifically to do this. They have their own [tokenizer utility page](https://platform.openai.com/tokenizer) that gives you an idea about how many tokens but the...

but encoder for gpt-4 is different