Skip to content

Python: docs(observability): add Langfuse example #1544

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
jannikmaierhoefer wants to merge 2 commits into from
Closed

Python: docs(observability): add Langfuse example #1544

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
57020a7
docs(observability): add Langfuse example
jannikmaierhoefer Oct 17, 2025
a9533f9
Merge branch 'main' into patch-1
eavanvalkenburg Dec 10, 2025
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
38 changes: 38 additions & 0 deletions python/samples/getting_started/observability/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -254,6 +254,44 @@ ENABLE_OTEL=true OTLP_ENDPOINT=http://localhost:4317 python 01-zero_code.py

Once your sample finishes running, navigate to <http://localhost:18888> in a web browser to see the telemetry data. Follow the [Aspire Dashboard exploration guide](https://learn.microsoft.com/en-us/dotnet/aspire/fundamentals/dashboard/explore) to authenticate to the dashboard and start exploring your traces, logs, and metrics!

## Langfuse Dashboard

[Langfuse](https://langfuse.com/) is an open-source LLM and AI agent observability tool. The Microsoft Agent Framework can export OpenTelemetry spans to Langfuse for evaluation and debugging.

### Configure Langfuse

```bash
pip install agent-framework langfuse
```

Next, set your Langfuse credentials as environment variables. You can retrieve your Langfuse API keys by [self-hosting Langfuse](https://langfuse.com/self-hosting) or using [Langfuse Cloud](https://cloud.langfuse.com/).

```bash
LANGFUSE_PUBLIC_KEY=pk-lf-...
LANGFUSE_SECRET_KEY=sk-lf-...
LANGFUSE_HOST=https://cloud.langfuse.com
```

Next, initialize the Langfuse client and enable observability in the Agent Framework:

```python
from agent_framework.observability import setup_observability
from langfuse import get_client

langfuse = get_client()
setup_observability(enable_sensitive_data=True)
```

For a complete integration guide, please take a look at the [Langfuse documentation](https://langfuse.com/integrations/frameworks/microsoft-agent-framework).
Copy link
Contributor

@TaoChenOSU TaoChenOSU Dec 10, 2025 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Some explanation on how agent framework connects to langfuse will be helpful.


### See traces in Langfuse

Now, all agent executions can be viewed in the Langfuse UI:

![Example trace in Langfuse](https://langfuse.com/images/cookbook/integration_microsoft-agent-framework/microsoft-agent-framework-example-race.png)
Copy link
Member

@eavanvalkenburg eavanvalkenburg Dec 10, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this link no longer works @jannikmaierhoefer


[Example Trace in Langfuse](https://cloud.langfuse.com/project/cloramnkj0002jz088vzn1ja4/traces/232de211-7fcf-45c8-b415-6af0e8cd6eaa)

## Console output

You won't have to deploy an Application Insights resource or install Docker to run Aspire Dashboard if you choose to inspect telemetry data in a console. However, it is difficult to navigate through all the spans and logs produced, so **this method is only recommended when you are just getting started**.
Expand Down
Loading