docs: add OpenTelemetry GenAI instrumentation sample #13238
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Motivation and Context
Currently, Semantic Kernel does not ship an example of how to adopt the new OpenTelemetry GenAI semantic conventions.
This makes it difficult for developers to instrument SK-based applications with end-to-end observability (latency, token usage, error rates, tool-call spans, and retrieval latency).
This PR contributes a documentation/sample entry showing how to instrument SK with OpenTelemetry using the
SkOtel
library.The goal is to provide the community with a ready-to-run reference that aligns with the OTel GenAI spec.
Description
samples/
demonstrating OTel GenAI instrumentation for SK.AddSemanticKernelTelemetry
middleware and a DelegatingHandler.sk-chat
) plus Dockerized Collector → Tempo → Prometheus → Grafana stack.This contribution is docs/sample only — no changes are made to SK core runtime code.
Contribution Checklist