Quickstart: Tracing
Learn how to trace your LLM application and run evaluations in Arize
To trace your LLM app and start troubleshooting your LLM calls, you'll need to do the following:
You can also dive right into examples below.
Python: Colab Link
JS/TS: Github
Install our tracing packages
Run the following commands below to install our open source tracing packages, which works on top of OpenTelemetry. This example below uses openai, and we support many LLM providers (see full list).
Using pip
Using conda
Get your API keys
Go to your space settings in the left navigation, and create a key using the button below.

Add our tracing code
Arize is an OpenTelemetry collector, which means you can configure your tracer and span processor. For more OTEL configurability, see how to set your tracer for auto instrumentors.
The package we are using is arize-otel, which is a lightweight convenience package to set up OpenTelemetry and send traces to Arize.
Python and JS/TS examples are shown below.
The following code snippet showcases how to automatically instrument your OpenAI application.
Set OpenAI Key:
To test, let's send a chat request to OpenAI:
Now start asking questions to your LLM app and watch the traces being collected by Arize.
Run your LLM application
Once you've executed a sufficient number of queries (or chats) to your application, you can view the details on the LLM Tracing page.

To continue with this guide, go to the trace evaluations guide to add evaluation labels to your traces!
Next steps
Dive deeper into the following topics to keep improving your LLM application!
Last updated
Was this helpful?