Find answers from the community

Updated 8 months ago

I'm getting an error about embed rate

At a glance

The community member is experiencing an error related to embed rate limits from Azure OpenAI. They were previously able to use a batch size of 500 without issue, but now encounter a rate limit error that suggests they must wait 24 hours. However, the community member was able to resolve the issue by reducing the batch size to 100, rather than waiting 24 hours as suggested. The community member has two unanswered questions: 1) Did Azure OpenAI recently reduce the maximum batch size? and 2) Why does the error message say the wait time is 86400 seconds (24 hours) when that was not the case?

In the comments, another community member states that they do not know the answers to these questions, as the information is coming directly from Azure.

Useful resources
I'm getting an error about embed rate limits from Azure OpenAI that I wasn't getting before, and openai seems to say to tell me I have to wait 24hrs. This is with a embed batch size of 500. Doesn't happen with size 100.

However, I didn't have to wait 24 hours. I just reduced batch size and it worked.

Unanswered questions:
  1. Did Azure OpenAI recently reduce max batch size?
  2. Why does it say 86400s when it's not true?
Plain Text
2024-06-06 14:54:59,932 - llama_index.embeddings.openai.utils - WARNING - Retrying llama_index.embeddings.openai.base.get_embeddings in 0.6736039165786247 seconds as it raised RateLimitError: Error code: 429 - {'error': {'code': '429', 'message': 'Requests to the Embeddings_Create Operation under Azure OpenAI API version 2024-02-15-preview have exceeded call rate limit of your current OpenAI S0 pricing tier. Please retry after 86400 seconds. Please go here: https://aka.ms/oai/quotaincrease if you would like to further increase the default rate limit.'}}.
L
1 comment
I don't know the answer to either of these -- this is coming directly from azure
Add a reply
Sign up and join the conversation on Discord