Smol Agents - Future AGI Documentation

1. Installation

First install the traceAI and necessary dependencies.

pip install traceAI-smolagents smolagents

2. Set Environment Variables

Set up your environment variables to authenticate with both FutureAGI and OpenAI.

import os

os.environ["OPENAI_API_KEY"] = "your-openai-api-key"
os.environ["FI_API_KEY"] = "your-futureagi-api-key"
os.environ["FI_SECRET_KEY"] = "your-futureagi-secret-key"

3. Initialize Trace Provider

Set up the trace provider to create a new project in FutureAGI, establish telemetry data pipelines .

from fi_instrumentation import register
from fi_instrumentation.fi_types import ProjectType

trace_provider = register(
    project_type=ProjectType.OBSERVE,
    project_name="smolagents",
)

4. Instrument your Project

Instrument your Project with SmolagentsInstrumentor . This step ensures that all interactions with the Agents are tracked and monitored.

from traceai_smolagents import SmolagentsInstrumentor

SmolagentsInstrumentor().instrument(tracer_provider=trace_provider)

5. Interact with Smol Agents

Interact with you Smol Agents as you normally would. Our Instrumentor will automatically trace and send the telemetry data to our platform.

from smolagents import (
    CodeAgent,
    DuckDuckGoSearchTool,
    OpenAIServerModel,
    ToolCallingAgent,
)

model = OpenAIServerModel(model_id="gpt-4o")
agent = ToolCallingAgent(
    tools=[DuckDuckGoSearchTool()],
    model=model,
    max_steps=3,
    name="search",
    description=(
        "This is an agent that can do web search. "
        "When solving a task, ask him directly first, he gives good answers. "
        "Then you can double check."
    ),
)
manager_agent = CodeAgent(
    tools=[DuckDuckGoSearchTool()],
    model=model,
    managed_agents=[agent],
)
manager_agent.run(
    "How many seconds would it take for a leopard at full speed to run through Pont des Arts? "
    "ASK YOUR MANAGED AGENT FOR LEOPARD SPEED FIRST"
)