Is anyone else getting this error: “The server had an error while processing your request. Sorry about that!”
It happens randomly and then when I rerun everything works fine. Is this a gpt-4 beta rollout problem, or is this an overall api endpoint problem?
i was getting them a bunch yesterday and the day before, i’m actually unable to get the node completions functions to work outside of the quickstart example, but the python one is working great with a more complex prompt setup.
just keep running or add error handling to pause and rerun for the time being maybe, if losing service of the script is a problem.
Yes. I second this concern, as it has been a constant challenge yesterday. We basically had to stop building zapier integrations yesterday because of this.
yeah, im getting this too. “RateLimitError: The server had an error while processing your request. Sorry about that!” Same pythonscript im using to chat with gpt works fine with 3.5. Any ideas, or should i just go back to using 3.5 til they fix this?
Oh, and i make perhaps one request every 10s or so, dont think I am over any limits at all.
yes, I get this for like every third request. If not this, then a false rate limit error. Back to 3.5 for the time being
same here, I get the “RateLimitError: The server had an error while processing your request. Sorry about that!” randomly. Any idea when this issue will be fixed?
Yes. Using the GPT-4 model we are seeing about 10% of requests are failing with this error.