Code error 500 with api gpt-4-vision-preview

API Bugs
1

Hello
I am currently performing image recognition with gpt-4-vision-preview. It is working , but I frequently encounter error code 500. Is this a server overload issue with OpenAI or is it
due to a response time problem with my server, or something else?
Thanks for help

openai.error.APIError: The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if you keep seeing this error. (Please include the request ID a969655ea84e5f988be3e937bd24e707 in your email.) {
“error”: {
“message”: “The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if you keep seeing this error. (Please include the request ID a969655ea84e5f988be3e937bd24e707 in your email.)”,
“type”: “server_error”,
“param”: null,
“code”: null
}
} 500 {‘error’: {‘message’: ‘The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if you keep seeing this error. (Please include the request ID a969655ea84e5f988be3e937bd24e707 in your email.)’, ‘type’: ‘server_error’, ‘param’: None, ‘code’: None}} {‘Date’: ‘Sat, 11 Nov 2023 04:00:37 GMT’, ‘Content-Type’: ‘application/json’, ‘Content-Length’: ‘365’, ‘Connection’: ‘keep-alive’, ‘openai-processing-ms’: ‘5899’, ‘x-ratelimit-limit-requests’: ‘100’, ‘x-ratelimit-limit-tokens’: ‘150000’, ‘x-ratelimit-remaining-requests’: ‘98’, ‘x-ratelimit-remaining-tokens’: ‘148977’, ‘x-ratelimit-reset-requests’: ‘28m10.247s’, ‘x-ratelimit-reset-tokens’: ‘409ms’, ‘x-request-id’: ‘a969655ea84e5f988be3e937bd24e707’, ‘strict-transport-security’: ‘max-age=15724800; includeSubDomains’, ‘CF-Cache-Status’: ‘DYNAMIC’, ‘Server’: ‘cloudflare’, ‘CF-RAY’: ‘8243a0f71e94007a-CDG’, ‘alt-svc’: ‘h3=“:443”; ma=86400’}

2

Je pense avoir trouvé le bug, le problÚme venait apparemment de la taille des images transmises , en diminuant la taille des fichiers , format jpg, le problÚme semble avoir été résolu

4

I had a similar issue. It could be your image was big. Notice, the rate limit with token information in the service response. The image is converted to tokens and then the model will act on it.
Sometimes the error is encountered when the OpenAI platform is bustling and cannot find a server to serve your request.

5

Finally, I solved the problem. It wasn’t due to the size of the image
as I initially thought, but rather a somewhat complicated issue
related to the client-server transit in Flask (Python). From a web
page (client), I was making a request to my server, which then queried
the gpt-4-vision-preview API by providing it with a link to download
the image, also provided by the Flask server (Python). The API was
supposed to then send back the image analysis to my server, which
would then return the response to the client (web page). It was the
back and forth between the API (gpt4 server) and my server that was
causing the bug. I had to modify the request architecture so that the
exchanges go through the client before being returned
 and now there
are no more bugs.

1 Like