Support for Handling error e.g. HTTP 429

[adewandaru]

Hi.. thanks for the nice library!

I have a small question.. Is there a good way to handle error returned by openai api response?
For example, when you're running out of Quota, it will reply with HTTP 429 response.

Thanks.

[njerschow]

Here's how I do it:

try {
    await openai.complete({
        engine: 'davinci',
        prompt: 'this is a test',
        maxTokens: 5,
        temperature: 0.9,
        topP: 1,
        presencePenalty: 0,
        frequencyPenalty: 0,
        bestOf: 1,
        n: 1,
        stream: false,
        stop: ['\n', "testing"]
    });
 } catch(e) {
     console.error("[ERROR] OpenAI responded with status: " + e.response.status)
     if (e.response.status === 429) {
         console.log("OpenAI Quota exceeded")
         //handle this case
     }
 }

disclaimer: This is untested code

[adewandaru]

Thanks much for the pointer.

[AlexanderKozhevin]

It's strange but I'm gettting this error frequently.
Taking into account that I have enough quota limit