Skip to content

Add Microsoft Foundry to OTel instrumentation guide #35459

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

Closed
Kyle-Verhoog wants to merge 2 commits into from
Closed

Add Microsoft Foundry to OTel instrumentation guide #35459

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3b1a6d1
Add Microsoft Foundry setup guide to OTel instrumentation docs
Kyle-Verhoog Mar 21, 2026
1c9d2c3
Update content/en/llm_observability/instrumentation/otel_instrumentat…
Kyle-Verhoog Mar 23, 2026
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
30 changes: 30 additions & 0 deletions content/en/llm_observability/instrumentation/otel_instrumentation.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,35 @@

This environment variable ensures that `strands-agents` emits traces following the OpenTelemetry v1.37+ semantic conventions for generative AI, which are required by LLM Observability.

#### Using Microsoft Foundry

Check warning on line 57 in content/en/llm_observability/instrumentation/otel_instrumentation.md

View workflow job for this annotation

GitHub Actions / vale

Datadog.headings 

'Using Microsoft Foundry' should use sentence-style capitalization.

[Microsoft Foundry][9] (formerly Azure AI Foundry) emits OpenTelemetry GenAI traces that follow the v1.37+ semantic conventions, including the Foundry Agents Service, Semantic Kernel, and LangChain (through `langchain-azure-ai`).

Check notice on line 59 in content/en/llm_observability/instrumentation/otel_instrumentation.md

View workflow job for this annotation

GitHub Actions / vale

Datadog.sentencelength 

Suggestion: Try to keep your sentence length to 25 words or fewer.

To send Microsoft Foundry traces to LLM Observability, configure the OpenTelemetry exporter in your application:

```python
from azure.ai.projects import AIProjectClient
from azure.identity import DefaultAzureCredential
from opentelemetry import trace
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter

provider = TracerProvider()
provider.add_span_processor(BatchSpanProcessor(OTLPSpanExporter()))
trace.set_tracer_provider(provider)
```

Set the following environment variables:

```
OTEL_EXPORTER_OTLP_TRACES_PROTOCOL=http/protobuf
OTEL_EXPORTER_OTLP_TRACES_ENDPOINT={{< region-param key="otlp_trace_endpoint" code="true" >}}
OTEL_EXPORTER_OTLP_TRACES_HEADERS=dd-api-key=<YOUR_API_KEY>,dd-otlp-source=llmobs
```

Then enable tracing on your Foundry client with the `enable_telemetry` method from the `azure-core-tracing-opentelemetry` package. For more details, see the [Microsoft Foundry tracing documentation][9].

### Instrumentation

To generate traces compatible with LLM Observability, do one of the following:
Expand Down Expand Up @@ -506,4 +535,5 @@
[6]: /llm_observability/evaluations/external_evaluations
[7]: https://strandsagents.com/latest/
[8]: /account_management/rbac/data_access/
[9]: https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/trace-agent-framework

Loading