I encountered many RateLimitError errors when I accessed the Completion interface today, but I actually did not call frequently, only about a few times a minute.
error message:
openai.error.RateLimitError: The server had an error while processing your request. Sorry about that!
my request:
response = openai.Completion.create(
model="text-davinci-003",
prompt=query,
temperature=0.9,
max_tokens=1200,
top_p=1,
frequency_penalty=0.0,
presence_penalty=0.0,
stop=["#"]
)
my env:
- Python 3.7.5
- ubuntu 16.04
I encountered many
RateLimitErrorerrors when I accessed the Completion interface today, but I actually did not call frequently, only about a few times a minute.error message:
my request:
my env: