Instrument LLM applications that use the Guardrails AI framework
In this example we will instrument a small program that uses the Guardrails AI framework to protect their LLM calls.
Launch Phoenix
Install packages:
pipinstallarize-phoenix
Launch Phoenix:
import phoenix as pxpx.launch_app()
Connect your notebook to Phoenix:
from phoenix.otel import registertracer_provider =register( project_name="my-llm-app", # Default is 'default')
By default, notebook instances do not have persistent storage, so your traces will disappear after the notebook is closed. See Persistence or use one of the other deployment options to retain traces.
Launch your local Phoenix instance:
python3-mphoenix.server.mainserve
For details on customizing a local terminal deployment, see Terminal Setup.
Install packages:
pipinstallarize-phoenix-otel
Connect your application to your instance using:
from phoenix.otel import registertracer_provider =register( project_name="my-llm-app", # Default is 'default' endpoint="http://localhost:6006",)
from phoenix.otel import registertracer_provider =register( project_name="my-llm-app", # Default is 'default' endpoint="http://localhost:6006",)
For more info on using Phoenix with Docker, see Docker
If you don't want to host an instance of Phoenix yourself or use a notebook instance, you can use a persistent instance provided on our site. Sign up for an Arize Phoenix account athttps://app.phoenix.arize.com/login
Install packages:
pipinstallarize-phoenix-otel
Connect your application to your cloud instance:
import osfrom phoenix.otel import register# Add Phoenix API Key for tracingos.environ["PHOENIX_CLIENT_HEADERS"]="api_key=...:..."# configure the Phoenix tracerregister( project_name="my-llm-app", # Default is 'default' endpoint="https://app.phoenix.arize.com/v1/traces",)
Your Phoenix API key can be found on the Keys section of your dashboard.
Initialize the GuardrailsAIInstrumentor before your application code.
from openinference.instrumentation.guardrails import GuardrailsInstrumentorGuardrailsInstrumentor().instrument(tracer_provider=tracer_provider)
Run Guardrails
From here, you can run Guardrails as normal:
from guardrails import Guardfrom guardrails.hub import TwoWordsimport openaiguard =Guard().use(TwoWords(),)response =guard( llm_api=openai.chat.completions.create, prompt="What is another name for America?", model="gpt-3.5-turbo", max_tokens=1024,)print(response)
Observe
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.