Smolagents Tracing

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

colab.research.google.com

Install

pip install openinference-instrumentation-smolagents smolagents

Setup

Add your HF_TOKEN as an environment variable:

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

Connect your application to Phoenix with the register function:

Create & Run an Agent

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

from smolagents import (
    CodeAgent,
    InferenceClientModel,
    ToolCallingAgent,
    VisitWebpageTool,
    WebSearchTool,
)

model = InferenceClientModel()

managed_agent = ToolCallingAgent(
    tools=[WebSearchTool(), VisitWebpageTool()],
    model=model,
    name="managed_agent",
    description="This is an agent that can do web search.",
)
managed_agent.run("Based on the latest news, what is happening in extraterrestrial life?")

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

⌘I

Developer Tools

MCP

LLM Providers

TypeScript

Python

Java

Platform

Sandboxes

Evaluation Integrations

Coding Agents

Smolagents Tracing

Google Colab

Install

Setup

Create & Run an Agent

Observe

Resources

Google Colab

​Install

​Setup

​Create & Run an Agent

​Observe

​Resources

Install

Setup

Create & Run an Agent

Observe

Resources