Gpt-4-vision-preview model API response 500

API
,
1

Does anyone experence today API Error: Error code: 500 while trying use GPT-4-VISION via API?

No changes on request or content, and yesterday the same requests were working.

OpenAI API returned an API Error: Error code: 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 req_822027b59bad0b0eeff258302409b5a4 in your email.)’, ‘type’: ‘server_error’, ‘param’: None, ‘code’: None}}

Status page doesn’t show any incidents:
image

1 Like
2

It seems to be chatting OK, but incredibly slow - about 10 tokens a second.

Saying the normal stuff:

Prompt: If I send you an image, will you be able to see the contents and interpret for me?
I’m sorry for any confusion, but as a text-based AI, I don’t
have the capability to view or interpret images. However, I can
certainly help answer questions or provide information based on
a description you give me. What would you like to know about
the image?
[Finish reason: stop, 5.31 seconds. Counted 55 tokens.]
Prompt: I have enabled your multi-modal GPT-4 computer vision, so that in the future, you will be able to answer about images that have been uploaded.
That’s fantastic! With multi-modal capabilities, I’ll be able
to assist you with image-related queries as well. Feel free to
upload an image, and I’ll do my best to provide you with the
information or interpretation you need. How can I assist you
with your image today?
[Finish reason: stop, 5.71 seconds. Counted 57 tokens.]

1 Like
3

Attaching request

[{"role": "system", "content": [{"type": "text", "text": "Please provide a direct answer without any introductory phrases. Maximum words 50. Provide in markdown format."}]}, {"role": "user", "content": [{"type": "text", "text": "What is content type of this web page image?"}, {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAIBAQEBAQIBAQECAgICAgQDAgICAgUEBAMEBgUGBgYFBgYGBwkIBgcJBwYGCAsICQoKCgoKBggLDAsKDAkKCgr/
...
H//Z", "detail": "high"}}]}]
1 Like
4

I have managed identify problem, which cause error 500.
Previously I called (python 3.11):

query = (
     {"role": "system",
         "content": [
             {"type":  ...
)

completion = client.chat.completions.create(
            model=MODEL,
            messages=[query],
            max_tokens=MAX_TOKENS,
        )

solved problem changed:

query = [
     {"role": "system",
         "content": [
             {"type":  ...
]

completion = client.chat.completions.create(
            model=MODEL,
            messages=query,
            max_tokens=MAX_TOKENS,
        )

Strange that it worked before with API. So there should be some update on OpenAI API service