Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

RateLimitIssue with 30k per minute on Azure OpenAI #15

Open
hoangvnh24 opened this issue Oct 2, 2024 · 2 comments
Open

RateLimitIssue with 30k per minute on Azure OpenAI #15

hoangvnh24 opened this issue Oct 2, 2024 · 2 comments

Comments

@hoangvnh24
Copy link

I am running the demo code using Azure Open AI, tier pay as you go, the limit is 30k per minute. However, with such a large limit, my prompt was "Build a Cargo game in Python" The system keeps giving me RateLimitErrors. I believe that 30k per minute is quite large already. Not sure if the system is technically feasible if it cannot run with the above token rate limit.

@minhngh
Copy link
Collaborator

minhngh commented Oct 2, 2024

Hi hoangvnh24,

Thank you for your concern. This issue may stem from your Azure OpenAI key, which can be easily fixed by increasing the TPM. Also, you can check whether the key you're using is shared with anyone. Technically, our method will run seamlessly from phase to phase, which can lead to a noticeable number of requests within a short time.

@hoangvnh24
Copy link
Author

hoangvnh24 commented Oct 6, 2024

Hi there, what is the new TPM you are suggesting to request from Azure? Let's say 100k TPM? Let me know about this with more details if you can. I am just afraid that if we ask for more tokens, the designed system might be too expensive/inefficient to run?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants