Completions requesting gpt-4 models timeout (Error: Gateway timeout.) about open-ai

[testgonzo]

There is apparently an undocumented 600 second (10 minute) timeout parameter as per:

https://community.openai.com/t/frequent-api-timeout-errors-recently/106903/8?u=fp

[orhanerday]

This issue is OpenAI API related, I can't do anything about it. We can wait to solve the issue by OpenAI.

[testgonzo]

1. Does the $client->setTimeout(x) functionality described in #31 for completion endpoint address question (2) posed in the opening post of this thread for completion, chat, and all endpoints?

2. Appears completions timedout in this manner do not return any data to function call. Is there a way to have calls timedout this way return a specific message indicating library timeout occurred (as opposed to OpenAI timeout)?

3. Would it be helpful to start a thread in this github in which we can all share our experiences with OpenAI timeout issues to help collectively track API performance? Sort of like a "down detector" for OpenAI.