500 The server had an error processing your request. image_url

API
1

I’m using gpt-4o model to analyze image documents. I have an API working with no problem locally, but when it’s in production, after a day of being deployed i start getting 500 error from OpenAI server, specifically when running
const run = await client.beta.threads.createAndRunPoll({ assistant_id: assistantId, thread: { messages: [ { role: 'user', content: [ { type: 'text', text: content }, { type: 'image_url', image_url: { url: fileAddress, detail: 'high' } }, ], }, ], }, });
Being content a simple instruction and fileAddress the address of an image in a S3 Bucket.

Someone has a idea of what could be happening? I run the API locally, and send a request that runs the exact same code, and i dont get the error. Also the assistants are working fine in the Playground.

2

500 - The server had an error while processing your request Cause: Issue on our servers.
Solution: Retry your request after a brief wait and contact us if the issue persists. Check the status page.

https://platform.openai.com/docs/guides/error-codes/api-errors

I might try another URL for the image as maybe the S3 Bucket is causing a problem?

3

Its not the S3 bucket, since the same request made locally works fine, also the api in production does work, but only for 12-14 hours after being deployed, after this time OpenAI starts responding with 500 error. This only happens with the createAndRunPoll request, since in my code i make a client.files.create request with no problem.

1 Like
4

Gotcha. Might be best to reach out to help.openai.com to let them know.

5

Is this an error from OpenAI?

6

Yes, it’s 500 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.

7

Any resolution for this?

I get the same error consistently when calling gpt-4o with an image_url…