About Error handling

[ZeroDeng01]

Hi, when I am using Azure openai chatgpt, I refer to the example of Error handling and cannot catch the error code 429. Every time the 429 code appears, the program will run into the default code block. I am not sure whether it is a problem with my operation or The content returned by azure openai is different from that of openai.
go-openai failed to serialize error messages correctly.THANKS!

func OpenaiErrorAndCode(openaierr error) (code int, err error) {
	var openaiError = &openai.APIError{}
	if errors.As(openaierr, &openaiError) {
		switch openaiError.HTTPStatusCode {
		case 400:
			return 400, errors.New("xxxxxxx")
		case 401:
			return 401, errors.New("xxxxxxx")
		case 429:
			return 429, errors.New("xxxxxxx")
		case 500:
			return 500, errors.New("xxxxxxx")
		default:
				return 500, errors.New("unknown：" + openaierr.Error())
		}
	}
	return 500, openaierr
}

stream, err := client.CreateChatCompletionStream(ctx, req)
if err != nil {
	fmt.Printf("ChatCompletionStream error: %v\n", err)
	_,openaierr := appError.OpenaiErrorAndCode(err)
	fmt.Printf(openaierr.Error())
}

The json returned by azure openai is as follows：

{
    "error": {
        "code": "429",
        "message": "Requests to the Creates a completion for the chat message Operation under Azure OpenAI API version 2023-03-15-preview have exceeded token rate limit of your current OpenAI S0 pricing tier. Please retry after 20 seconds. Please go here: https://aka.ms/oai/quotaincrease if you would like to further increase the default rate limit."
    }
}

[vvatanabe]

@ZeroDeng01 I want you to use curl to log output the details (-v or --verbose)
Note: if you attach logs, please hide the secret.

[ZeroDeng01]

@vvatanabe hello,The following is the log of my request. I have modified the key, ip, domain name, etc. to prevent the loss of key and other information,Hope this helps you debug related issues.THANKS!

curl https://myhost.openai.azure.com/openai/deployments/gpt-35-turbo0301/chat/completions?api-version=2023-03-15-preview \
>   -H "Content-Type: application/json" \
>   -H "api-key: my azure key" \
-d '{">   -d '{"messages":[{"role":"system","content":"You are an AI assistant that helps people find information."},{"role":"user","content":"hello"}],
>   "max_tokens":800,
>   "temperature":0.7,
>   "frequency_penalty":0,
>   "presence_penalty":0,
>   "top_p":0.95,
>   "stop":null,
>   "stream":true
> }' -v
*   Trying 20.61.x.x:443...
* TCP_NODELAY set
* Connected to myhost.openai.azure.com (20.61.x.x) port 443 (#0)
* ALPN, offering h2
* ALPN, offering http/1.1
* successfully set certificate verify locations:
*   CAfile: /etc/ssl/certs/ca-certificates.crt
  CApath: /etc/ssl/certs
* TLSv1.3 (OUT), TLS handshake, Client hello (1):
* TLSv1.3 (IN), TLS handshake, Server hello (2):
* TLSv1.2 (IN), TLS handshake, Certificate (11):
* TLSv1.2 (IN), TLS handshake, Server key exchange (12):
* TLSv1.2 (IN), TLS handshake, Server finished (14):
* TLSv1.2 (OUT), TLS handshake, Client key exchange (16):
* TLSv1.2 (OUT), TLS change cipher, Change cipher spec (1):
* TLSv1.2 (OUT), TLS handshake, Finished (20):
* TLSv1.2 (IN), TLS handshake, Finished (20):
* SSL connection using TLSv1.2 / ECDHE-RSA-AES256-GCM-SHA384
* ALPN, server accepted to use h2
* Server certificate:
*  subject: C=US; ST=WA; L=Redmond; O=Microsoft Corporation; CN=westeurope.api.cognitive.microsoft.com
*  start date: Mar 24 11:39:30 2023 GMT
*  expire date: Mar 18 11:39:30 2024 GMT
*  subjectAltName: host "myhost.openai.azure.com" matched cert's "*.openai.azure.com"
*  issuer: C=US; O=Microsoft Corporation; CN=Microsoft Azure TLS Issuing CA 01
*  SSL certificate verify ok.
* Using HTTP2, server supports multi-use
* Connection state changed (HTTP/2 confirmed)
* Copying HTTP/2 data in stream buffer to connection buffer after upgrade: len=0
* Using Stream ID: 1 (easy handle 0x56102dd037c0)
> POST /openai/deployments/gpt-35-turbo0301/chat/completions?api-version=2023-03-15-preview HTTP/2
> Host: myhost.openai.azure.com
> user-agent: curl/7.68.0
> accept: */*
> content-type: application/json
> api-key: my azure key
> content-length: 277
>
* Connection state changed (MAX_CONCURRENT_STREAMS == 20)!
* We are completely uploaded and fine
< HTTP/2 429
< content-length: 368
< content-type: application/json
< retry-after: 17
< apim-request-id: 8282fe77-229a-4d8b-8ebb-8781dca6dde2
< strict-transport-security: max-age=31536000; includeSubDomains; preload
< x-content-type-options: nosniff
< policy-id: DeploymentRatelimit-Token
< x-ms-region: West Europe
< date: Wed, 07 Jun 2023 15:24:59 GMT
<
* Connection #0 to host myhost.openai.azure.com left intact
{"error":{"code":"429","message": "Requests to the Creates a completion for the chat message Operation under Azure OpenAI API version 2023-03-15-preview have exceeded token rate limit of your current OpenAI S0 pricing tier. Please retry after 17 seconds. Please go here: https://aka.ms/oai/quotaincrease if you would like to further increase the default rate limit."}}

[vvatanabe]

@ZeroDeng01 I made a pull request to fix this problem.
#345

[ZeroDeng01]

@vvatanabe You’ve been a big help. I just saw your pull and I feel like it will help me. After the pull request is approved and a new version is released, I will experience and test it. Thank you again!😁