Hi everyone. As many of you probably know, the OpenAI API times out after 60 seconds. I know other platforms have been able to get around this. If I call the API directly through the new CallAPI feature, could I avoid the timeout? Also… I’ve seen other platforms that can return results one word at a time rather than after the complete result has been pulled. Any ideas how?
I was reading about this the other day, that’s what they call “streaming”.
However, as I understand, you might incur many more updates that way, if you want to update the result every time the API returns a new part in the result (if you do it through Make/Zapier).
I don’t know how it would work with Call API. Since you’re not changing the URL to call, I don’t know if Glide caches the result or not, there might be a chance you won’t get the full answer.