Our backend service using Azure OpenAI APIs was unexpectedly getting this kind of responses for around 2 hours for all incoming requests:
error_code=OperationNotSupported
error_message='The embeddings operation does not work with the specified model, text-embedding-ada-002. Please choose different model and try again. You can learn more about which models can be used with each operation here: https://go.microsoft.com/fwlink/?linkid=2197993.' error_param=None error_type=None message='OpenAI API error received' stream_error=False"
We are using python with openai package, doing something like this:
openai.Embedding.create(input=text, engine=model)
Problem is that I'm unable to find any details about this and the outage took around 2 hours. In Azure monitoring, this was marked as "client error", however on our side nothing has changed - backend code is the same as well as access tokens. There was no new deployment, nor any spike in traffic. Also Azure's logs and healthchecks weren't showing anything helpful... Any idea what this could be?