-
Notifications
You must be signed in to change notification settings - Fork 1.2k
[MLOB-2411] Add Distributed Proxy/Gateway Service Guide for LLM Observability #28593
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
[MLOB-2411] Add Distributed Proxy/Gateway Service Guide for LLM Observability #28593
Conversation
Preview links (active after the
|
Created DOCS-10979 for documentation team review |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks Sam, this is looking great! Can we also add a section with one paragraph under Advanced Tracing? https://docs.datadoghq.com/llm_observability/setup/sdk/python/#advanced-tracing
Co-authored-by: Barry Eom <[email protected]>
Co-authored-by: Barry Eom <[email protected]>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks so much for drafting this! Let me know if you have any questions about my comments or if any of my changes affects the accuracy of your draft.
|
||
## Enabling LLM Observability for a proxy or gateway service | ||
|
||
To enable LLM Observability for a proxy or gateway service that might be called from several different ML applications, you can enable LLM Observability without specifying an ML application name. In its place, specify the service name. This can be used to [filter out spans in LLM observability specific to the proxy or gateway service](#observing-llm-gateway-and-proxy-services). |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
To enable LLM Observability for a proxy or gateway service that might be called from several different ML applications, you can enable LLM Observability without specifying an ML application name. In its place, specify the service name. This can be used to [filter out spans in LLM observability specific to the proxy or gateway service](#observing-llm-gateway-and-proxy-services). | |
To enable LLM Observability for a proxy or gateway service used by multiple ML applications, you can configure it without specifying an ML application name. Instead, set the service name. This allows you to [filter spans specific to that proxy or gateway service within LLM observability](#observing-llm-gateway-and-proxy-services). |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
To confirm, are you filtering out spans from that proxy or gateway, or filtering to only show spans from that proxy or gateway?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
filtering to only show spans from that proxy or gateway
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for considering my suggestions! I left a few more, but they don't block this PR.
Co-authored-by: Esther Kim <[email protected]>
Co-authored-by: Esther Kim <[email protected]>
✅ Documentation Team ReviewThe documentation team has approved this pull request. Thank you for your contribution! |
/merge --delay -@ tomorrow at 9am EST |
View all feedbacks in Devflow UI.
Arguments errors:
If you need support, contact us on Slack #devflow with those details! |
/merge --cancel |
View all feedbacks in Devflow UI.
This merge request is not in the queue and can't be unqueued To get help about command usage, write If you need support, contact us on Slack #devflow with those details! |
/merge |
View all feedbacks in Devflow UI.
Added to the queue but the mergequeue is not enabled for now.
This pull request was merged directly. |
What does this PR do? What is the motivation?
Merge instructions
Merge readiness:
For Datadog employees:
Merge queue is enabled in this repo. Your branch name MUST follow the
<name>/<description>
convention and include the forward slash (/
). Without this format, your pull request will not pass in CI, the GitLab pipeline will not run, and you won't get a branch preview. Getting a branch preview makes it easier for us to check any issues with your PR, such as broken links.If your branch doesn't follow this format, rename it or create a new branch and PR.
To have your PR automatically merged after it receives the required reviews, add the following PR comment:
Additional notes