This example shows how to use @arizeai/openinference-instrumentation-openai to instrument a simple Node.js application with OpenAI
Our example will export spans data simultaneously on Console and arize-phoenix, however you can run your code anywhere and can use any exporter that OpenTelemetry supports.
If running and exporting to phoenix. You will also be able to add feedback to your spans via the chat interface.
First, startup the backend as described in the backend README.
Second, run the development server of the frontend as described in the frontend README.
Open http://localhost:3000 with your browser to see the result.
Ensure that Docker is installed and running. Run the command docker compose up to spin up services for the backend and Phoenix. Once those services are running, open http://localhost:6006 to view spans and feedback in Phoenix. When you're finished, run docker compose down to spin down the services.
To learn more about Arize Phoenix, take a look at the following resources:
You can check out the Phoenix GitHub repository - your feedback and contributions are welcome!