Skip to content

docs: add OpenTelemetry GenAI instrumentation sample #13238

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

docs: add OpenTelemetry GenAI instrumentation sample #13238

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 28 additions & 0 deletions docs/OPENTELEMETRY_GENAI.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
# OpenTelemetry GenAI instrumentation sample

The community project [otel-genai-bridges](https://github.com/dineshkumarkummara/otel-genai-bridges) includes a .NET library (`SkOtel`) and sample (`dotnet/samples/sk-chat`) that instrument Semantic Kernel applications using the [OpenTelemetry Generative AI semantic conventions](https://github.com/open-telemetry/semantic-conventions/tree/main/docs/gen-ai).

## Highlights

- `AddSemanticKernelTelemetry` extension registers telemetry options, middleware, and a DelegatingHandler.
- Middleware captures prompts, completions, tool invocations, latency, token usage, cost, and RAG retrieval latency.
- Docker Compose stack (OpenTelemetry Collector → Tempo/Prometheus → Grafana) and dashboards are provided out of the box.

## Quick start

```bash
# Clone the repository
git clone https://github.com/dineshkumarkummara/otel-genai-bridges.git
cd otel-genai-bridges

# Launch the collector, Tempo, Prometheus, Grafana, and both sample apps
./scripts/run_all.sh
```

The Semantic Kernel sample listens on `http://localhost:7080`. Send prompts to `/chat` or `/rag` with `curl` to generate telemetry.

![Grafana token throughput panel](https://github.com/dineshkumarkummara/otel-genai-bridges/raw/main/docs/screenshots/grafana-tokens.png)

The Grafana dashboard (http://localhost:3000/d/genai-overview) surfaces latency, token usage, error rates, tool-call counts, and RAG retrieval latency. Tempo provides trace waterfalls showing prompt/response events and tool execution spans.

For more details or to contribute, visit the repository: https://github.com/dineshkumarkummara/otel-genai-bridges.
Loading