Hi everyone, I'm sending consecutive requests to gpt3. The total number of requests would be anywhere in between 50-100. Between each request, I'm adding a 2 second sleep timer, yet I get this issue, I need to execute these requests together to get the required output.
I'm on a paid plan, using text-davinci-003 without finetuning, if anyone knows how to counter this issue, please do let me know.
Thanks !
#openai.error.RateLimitError: The server had an error while processing your request. Sorry about that
ionic gyro