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.

Sign up for GitHub

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

Jump to bottom

[bug report] Double incrementing te_request_count metric in successful single openai_embed requests #480

Open
aarongreen-datadog opened this issue Jan 29, 2025 · 0 comments · May be fixed by #486
Open

[bug report] Double incrementing te_request_count metric in successful single openai_embed requests #480

aarongreen-datadog opened this issue Jan 29, 2025 · 0 comments · May be fixed by #486

Comments

@aarongreen-datadog
Copy link

aarongreen-datadog commented Jan 29, 2025 •
edited
Loading

As mentioned in the title, I believe this line is a bug and should actually be te_request_success. We're setting up observability for TEI, and we use the openai-compatible /v1/embeddings endpoint, and I noticed weird numbers coming from the metrics, which led me to finding this line as the likely culprit.

I think the same bug might exist in the following functions in the HTTP and grpc APIs:
HTTP

GRPC
@aarongreen-datadog aarongreen-datadog changed the title [bug report] Double incrementing te_request_count metric in successful openai_embed requests [bug report] Double incrementing te_request_count metric in successful single openai_embed requests Jan 29, 2025
@kozistr kozistr linked a pull request Feb 6, 2025 that will close this issue
Open
5 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Fix double incrementing te_request_count metric kozistr/text-embeddings-inference
1 participant
@aarongreen-datadog