#davinci-003 keeps getting "The server had an error while processing your request. Sorry about that!"

19 messages · Page 1 of 1 (latest)

tawdry scaffold
#

This has been happening all day long...

cunning latch
tawdry scaffold
#

openai.error.RateLimitError: The server had an error while processing your request. Sorry about that!

#

I am currently using batch prompt to send 7 requests thru openai.Completion.create(engine='text-davinci-003',prompt=prompt_list,top_p=1,temperature=0.6,max_tokens=100,n=1)

cunning latch
#

RateLimitError is an error that occurs when the rate limit of a given endpoint is exceeded. This usually happens when an endpoint is receiving too many requests in a short period of time.

tawdry scaffold
bitter scroll
#

@cunning latch I'm facing similar error
openai.error.RateLimitError: The server had an error while processing your request. Sorry about that!
I'm sending almost 10 requests and between each request I am adding 2 seconds timer, what would be the best way to handle this issue if you'd know. Because after the current set of requests, I'll be at least sending 40-50 requests for another task which is similar in all the cases but the input differs a bit.
any idea how to solve it.
Thanks !

cunning latch
bitter scroll
#

I'm still on my 18$ free trial,
I've added my payment method too but I have yet to purchase any credits.
As of now I've only spent 5$ and I'm getting this rate limit

cunning latch
bitter scroll
#

on their platform or in this discord group ?

cunning latch
bitter scroll
#

Thanks

cunning latch
fiery magnet
#

that may be not always because you reach the limit, the server sometimes overloaded. just send the request again and again in your code until it gets the response

#

usually no more than three times

#

you can set the max attempt times

#

like this

image.png