Continuous gpt3 api 500 error: The server had an error while processing your request. Sorry about that!

API
1

I created a Python script that loops through a list of text strings (each string is about 2000 characters in length) and summarizes each string. See the code for the response below (This prompt is within a for loop):

response = openai.Completion.create( model="text-davinci-003", max_tokens=2000, prompt = f"Summarize the following text: {text_list[i]}", temperature=0.5, frequency_penalty=1.5, presence_penalty=-1.5, n=1 )

It works for maybe 1 or 2 items in the text list but then I receive an error: “openai.error.APIError: The server had an error while processing your request. Sorry about that!”

This happens consistently even when I use different api keys, prompts, accounts. Any idea what is happening?

2 Likes
2

Is there a typo f"in the above?

Is that f supposed to be there?

3

Yes, it is an f-string. I was able to get around the issue by using the curie model but have not been able to solve the original error

1 Like
4

Getting this issue now… very annoying.

5

Can you check your error ? Is it an APIError or a ReadLimit ?

Cause the Readlimit might be due to repeated calls to the API to get the completion for each string

6

When you loop and post to the OpenAI, you will get these errors if you do not slow down the loop.

Normally, when I loop while posting to the OpenAI API, I use a 2 second delay in the loop; but I think one second is OK. Without any delay, you will get an error.

7

I’m using 5-second sleep, and it just happened to me multiple times just now. I did make about 300 requests yesterday - don’t know if it had anything to do with that. Other than that, I just get this error when trying and had to add it to the try, exception statements: openai.error.RateLimitError: The server had an error while processing your request. Sorry about that!

8

Also, I notice that this thread was dead for 14 days, but around 30 minutes ago, the same time this error occurred to me, someone new posted that this error is showing up. This makes me think that it’s happening to more than one of us right now.

1 Like
9

I’m experiencing the same problem even if I wait more than 5 seconds between every call.

10

I have the same problem. And I did not continuously prompt.

11

I have the same problem as well. Along with very flow response times.

1 Like
12

It’s probably because people are spamming ChatGPT right now. They are severely limiting our API access to give more power to ChatGPT’s side.

13

Same here, any update from OpenAI team ?

14

It’s not anything to do with the API, it happens in Playground as well.

15

Same here ! Premium / free account : “The server had an error while processing your request. Sorry about that!”

1 Like
16

Same here. Tried several workarounds, but the issue persists.

17

Yes, I’m experiencing the same issue.

18

same here with payment plan added and still getting same response.

19

I am also getting this error.

20

Same here for several hours very consistently:

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

Using python 3.10
python openapi client 0.26.4

I’m located in EEST (+2 GMT) Anyone else seeing this? Could it be a local issue?