Skip to content

Having only single llm call in case of extracting token usage metrics from the ChatNVIDIA connector#390

Open
niyatisingal wants to merge 1 commit intodevelopfrom
dev/nsingal/fix-perf-regression
Open

Having only single llm call in case of extracting token usage metrics from the ChatNVIDIA connector#390
niyatisingal wants to merge 1 commit intodevelopfrom
dev/nsingal/fix-perf-regression

Conversation

@niyatisingal
Copy link
Collaborator

@niyatisingal niyatisingal commented Feb 27, 2026

Description

Checklist

  • I am familiar with the Contributing Guidelines.
  • All commits are signed-off (git commit -s) and GPG signed (git commit -S).
  • New or existing tests cover these changes.
  • The documentation is up to date with these changes.
  • If adjusting docker-compose.yaml environment variables have you ensured those are mimicked in the Helm values.yaml file.

@niyatisingal niyatisingal self-assigned this Feb 27, 2026
@niyatisingal niyatisingal force-pushed the dev/nsingal/fix-perf-regression branch 4 times, most recently from 56e92cf to 29c05c8 Compare February 27, 2026 12:39
Signed-off-by: Niyati Singal <nsingal@nvidia.com>
@niyatisingal niyatisingal force-pushed the dev/nsingal/fix-perf-regression branch from 29c05c8 to 48c2d6d Compare February 27, 2026 12:42
and hasattr(gen.message, "usage_metadata")
and gen.message.usage_metadata
):
meta = gen.message.usage_metadata
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Since we are still relying on metadata to get token information.

Was our ChatNvidia wrapper not processing this information in astream mode even though it was returned by llm?

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

Successfully merging this pull request may close these issues.

2 participants