Why Are The API Calls not working! or taking forever? A feedback from OpenAI would be appreciated, you guys have all the resources in the world and it seems like you’re ignoring all of your developers issues. API calls should be rock solid! Upgrade your systems or whatever you have to do but it’s almost embarrassing. OpenAI Please Respond!
1 Like
Not open AI memeber here, but chat GPT has a major outage currently and even api has been behaving erratically today. Definitely some problem is going on. Only the incident report will be able to tell what the problem was.
1 Like
My responses are also not working with API calls. I keep getting timed out:
code: ‘ETIMEDOUT’,
syscall: ‘connect’,
address: ‘52.152.96.252’,
port: 443,
1 Like
Respectfully: what makes you guys think that opening 394825902 threads with the same topic that is already being discussed everywhere would be of some help for your particular use case? It just makes the community messier.
I know that everyone believes that their problem is the most relevant one and should be fixed ASAP. But this is a developers community. We help each other. We try to extract common insights/knowledge from each other’s experience. This is not customer support. And we are responsible for keeping it clean and tidy. At least, we are responsible for reading the existing topics and identify that our current issue is the same one that is already being discussed. In a lot of threads.
If we want to send a message to OpenAI (such as this super helpful message: “Your systems are failing, this is embarrassing, you’re ignoring your developers, please respond to me and ignore the others”), we have other channels to do so. It would be nice if we could all accept this contract and act accordingly.
Finally, developing an application is not creating a wrapper to OpenAI’s API and call it a day. OpenAI’s API has issues because of the amazing growth that they’re experiencing. But even if it didn’t: you need to handle errors. Things can fail, break or stop functioning. And you need to be ready for this. Retries with backoff / Fallback strategies is the way to go on this regard. And this is our responsibility. It has nothing to do with OpenAI.
2 Likes
Respectfully,
if the API is timing out for the past 6 hours (for me) it’s not my fault or anyone’s fault.
Things should expand as the resources are being used up to the limit, if that’s the case.
This was expected to happen.
Correct and these are Beta offerings:
1. Beta Services
This section governs your use of services or features that OpenAI offers on an alpha, preview, early access, or beta basis (“Beta Services”). Beta Services are offered “as-is” to allow testing and evaluation.
OpenAI makes no representations or warranties for Beta Services, including any warranty that Beta Services will be generally available, uninterrupted or error-free, or that Content will be secure or not lost or damaged. Except to the extent prohibited by law, OpenAI expressly disclaims all warranties for Beta Services, including any implied warranties of merchantability, satisfactory quality, fitness for a particular purpose, non-infringement, or quiet enjoyment, and any warranties arising out of any course of dealing or usage of trade.
Reference:
1 Like
If your API call times out, that’s already indicating something. You should probably consider having your own client timeout when you’re doing calls to it.
I did not say anywhere in my message that an API timeout is your fault. But having a proper strategy to handle errors is your full responsibility. Especially taking OpenAI’s terms of use into consideration.
3 Likes