Hello Arize team. I have an AI application that is written in .NET, how would you suggest the best way to integrate it with Phoenix?
Phoenix does not provide a native .NET client, but you can integrate your .NET AI application with Phoenix by using OpenTelemetry (OTEL) to manually instrument your code and export traces to Phoenix鈥檚 OTLP HTTP endpoint. You should use the OpenTelemetry .NET SDK, set the exporter endpoint to http://<phoenix_host> :6006/v1/traces, and follow the OpenInference semantic conventions for span attributes to ensure Phoenix can recognize your data. Evaluation metrics, however, can only be sent via the Python client at this time; .NET can only send traces, not evals or metrics directly. For embedding visualization, you must upload embeddings as datasets using the Python client, as this is not supported via .NET tracing alone.For a working .NET example and further details, see the discussion and code snippets in this Slack thread. For OpenInference semantic conventions, refer to this specification.Would you like a step-by-step example or code snippet for .NET integration?Sources:
- Slack thread: .NET integration with Phoenix
馃挕聽Hint: Mention RunLLM in the thread for followups.
Hi Chris, the bot here is correct -- in terms of just setting up your phoenix instance, there's a number of ways to do so here. & then from there you'll want to manually instrument your application - the best resources I can recommend for getting started there is this external example set & our documentation for how to setup tracing. Hope this helps a little bit and points you in the right direction! Feel free to ask any other question or share any issues you run into!
