Hugging Face smolagents

How to use the SmolagentsInstrumentor to trace smolagents by Hugging Face

smolagents is a minimalist AI agent framework developed by Hugging Face, designed to simplify the creation and deployment of powerful agents with just a few lines of code. It focuses on simplicity and efficiency, making it easy for developers to leverage large language models (LLMs) for various applications.

Phoenix provides auto-instrumentation, allowing you to track and visualize every step and call made by your agent.

Google Colab

Launch Phoenix

We have several code samples below on different ways to integrate with smolagents, based on how you want to use Phoenix.

Phoenix Developer Edition

Sign up for Phoenix:

Sign up for an Arize Phoenix account at https://app.phoenix.arize.com/login

Install packages:

pip install arize-phoenix-otel

Connect your application to your cloud instance:

import os
from phoenix.otel import register

# Add Phoenix API Key for tracing
PHOENIX_API_KEY = "ADD YOUR API KEY"
os.environ["PHOENIX_CLIENT_HEADERS"] = f"api_key={PHOENIX_API_KEY}"
os.environ["PHOENIX_COLLECTOR_ENDPOINT"] = "https://app.phoenix.arize.com"

# configure the Phoenix tracer
tracer_provider = register(
  project_name="my-llm-app", # Default is 'default'
)

Your Phoenix API key can be found on the Keys section of your dashboard.

Command Line

Launch your local Phoenix instance:

pip install arize-phoenix
phoenix serve

For details on customizing a local terminal deployment, see Terminal Setup.

Install packages:

pip install arize-phoenix-otel

Connect your application to your instance using:

from phoenix.otel import register

tracer_provider = register(
  project_name="my-llm-app", # Default is 'default'
  endpoint="http://localhost:6006/v1/traces",
)

See Quickstart: Deployment for more details

Docker

Pull latest Phoenix image from Docker Hub:

docker pull arizephoenix/phoenix:latest

Run your containerized instance:

docker run -p 6006:6006 arizephoenix/phoenix:latest

This will expose the Phoenix on localhost:6006

Install packages:

pip install arize-phoenix-otel

Connect your application to your instance using:

from phoenix.otel import register

tracer_provider = register(
  project_name="my-llm-app", # Default is 'default'
  endpoint="http://localhost:6006/v1/traces",
)

For more info on using Phoenix with Docker, see Docker

Notebook

Install packages:

pip install arize-phoenix

Launch Phoenix:

import phoenix as px
px.launch_app()

Connect your notebook to Phoenix:

from phoenix.otel import register

tracer_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.

Install

pip install openinference-instrumentation-smolagents smolagents

Setup

Add your HF_TOKEN as an environment variable:

os.environ["HF_TOKEN"] = "<your_hf_token_value>"

Initialize the SmolagentsInstrumentor before your application code:

from openinference.instrumentation.smolagents import SmolagentsInstrumentor

SmolagentsInstrumentor().instrument(tracer_provider=tracer_provider)

Create & Run an Agent

Create your Hugging Face Model, and at every run, traces will be sent to Phoenix.

from smolagents import (
    CodeAgent,
    ToolCallingAgent,
    ManagedAgent,
    DuckDuckGoSearchTool,
    VisitWebpageTool,
    HfApiModel,
)

model = HfApiModel()

agent = ToolCallingAgent(
    tools=[DuckDuckGoSearchTool(), VisitWebpageTool()],
    model=model,
)
managed_agent = ManagedAgent(
    agent=agent,
    name="managed_agent",
    description="This is an agent that can do web search.",
)
manager_agent = CodeAgent(
    tools=[],
    model=model,
    managed_agents=[managed_agent],
)
manager_agent.run(
    "If the US keeps its 2024 growth rate, how many years will it take for the GDP to double?"
)

Observe

Now that you have tracing setup, all invocations and steps of your Agent will be streamed to your running Phoenix for observability and evaluation.

Resources

• OpenInference package

• Working examples