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

feature: LLM Tracing, tracking token usages and access control in kubeai #342

Open
meetzuber opened this issue Dec 7, 2024 · 1 comment

Comments

@meetzuber
Copy link

Hi

I came to know about kubeAI its very nice integration of GenAI tools. only access control and usages tracking is missing which is also a important part of LLMOps.

deploying langfuse instance and logging all metrics and tokens in langfuse with user details will be a good idea.

  1. litellm or any other application can be used for sending traces to langfuse, loadbalancing, model failover etc.
  2. user management can be done by litellm or open-webui, where users can create there own tokens and use them.
  3. using this Billing can be done based on token used by team/user.
  4. daily/monthly budget or limits can be set using litellm.

Tools mentioned above are just for reference which I use, but can be replaced with any other tool which will be stable and easy to integrate in exiting framework.

Thanks :)

@nstogner
Copy link
Contributor

nstogner commented Dec 7, 2024

Thanks for the suggestions @meetzuber!

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