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

Cost and Tokens Metrics in OpenSearch Dashboard #782

Open
DiljithNair opened this issue Nov 14, 2024 · 2 comments
Open

Cost and Tokens Metrics in OpenSearch Dashboard #782

DiljithNair opened this issue Nov 14, 2024 · 2 comments

Comments

@DiljithNair
Copy link

Would like to have a metrics in the OpenSearch dashboard of the qnabot to show the cost incurred by the bot in real-time along with the number of tokens (input and output) used by the foundational model used.

A OpenSearch visualization using qnabot logs showing the cost incurred and tokens consumed by the bot to analysts to make data driven decisions and tweaks to the bot.

@abhirpat
Copy link
Member

Thank you for reporting this @DiljithNair. We will get back to you.

@abhirpat
Copy link
Member

abhirpat commented Jan 22, 2025

Hi @DiljithNair, to view costs incurred from Bedrock and other services in AWS, we recommend using
AWS Cost Explorer as mentioned in the implementation guide. Additionally, please see this blog on
Improve visibility into Amazon Bedrock usage and performance with Amazon CloudWatch, which discusses your use-case of capturing LLM token usage as well. Please let us know if you have any questions.

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

No branches or pull requests

2 participants