Last updated
Last updated
In this example we will instrument a small program that uses the framework to protect their LLM calls.
Sign up for Phoenix:
Install packages:
Connect your application to your cloud instance:
Initialize the GuardrailsAIInstrumentor before your application code.
From here, you can run Guardrails as normal:
Now that you have tracing setup, all invocations of underlying models used by Guardrails (completions, chat completions, embeddings) will be streamed to your running Phoenix for observability and evaluation. Additionally, Guards will be present as a new span kind in Phoenix.
Sign up for an Arize Phoenix account at
Your Phoenix API key can be found on the Keys section of your .
For details on customizing a local terminal deployment, see .
See for more details
Pull latest Phoenix image from :
For more info on using Phoenix with Docker, see
By default, notebook instances do not have persistent storage, so your traces will disappear after the notebook is closed. See or use one of the other deployment options to retain traces.
Instrument LLM applications that use the Guardrails AI framework