Zakey Faieq

As a first step, I've added a PR that allows for Edge Runtime route handlers to stream function-calling responses from OpenAI. #154

I've taken a crack at the problem here: #178 . @yutakobayashidev That PR does exactly what you asked for

> @Zakinator123 This is great! For example, would it be possible to access the weather API when get_current_weather is called and implement our own weather UI based on the response?...

I just put up a PR that allows for streaming function responses to be streamed back to clients (who then can parse the JSON once the response is finished). #154

@Royal-lobster This PR probably solves your issue: #154

> It would be nice to parse the response from OpenAI differently, when it comes to function calling. Since it won't be a stream response. 🤔 Function calling responses are...

> I was toying with this separately and the responses not coming back as streams really messed with my head. I think it'd be better to keep the endpoint as...

Just FYI for everyone, I'm working on cleaning up the PR, hopefully will have some updates pushed up by this evening.

One issue I'm wrestling with is that function calling is very OpenAI specific, which has me leaning towards creating a brand new hook (e.g. `useOpenAIChat`), especially since `useChat` _technically_ is...

> @Zakinator123 I'm a fan of a new `mode: 'functions'` param for `useChat` instead of a mostly-duplicate hook. > > thank you for your work on this! @MaxLeiter I've made...