​
Prerequisites

Install dependencies: 
pip install "quotientai>=0.4.6" "smolagents>=1.15.0" "openinference-instrumentation-smolagents==0.1.14"
Set environment variables: 
export OPENAI_API_KEY=your-openai-api-key
export QUOTIENT_API_KEY=your-quotient-api-key

​
Sample Integration

quotient_trace_smolagents.py
import requests
from openinference.instrumentation.smolagents import SmolagentsInstrumentor

from quotientai import QuotientAI

quotient = QuotientAI()
quotient.tracer.init(
    app_name="smolagents-weather-app",
    environment="dev",
    instruments=[SmolagentsInstrumentor()],
)

from smolagents import ToolCallingAgent, LiteLLMModel, tool

@tool
def search_wikipedia(query: str) -> str:
    """Fetch a summary of a Wikipedia page."""
    url = f"https://en.wikipedia.org/api/rest_v1/page/summary/{query}"
    response = requests.get(url)
    response.raise_for_status()
    data = response.json()
    title = data["title"]
    extract = data["extract"]
    return f"Summary for {title}: {extract}"

@quotient.trace('smolagents-wikipedia-agent')
def main() -> None:
    model = LiteLLMModel(model_id="gpt-4o")

    agent = ToolCallingAgent(
        tools=[search_wikipedia],
        model=model,
    )
    agent.run("What happened in the 2024 US election?")

if __name__ == "__main__":
    main()

​
Notes

  • The instrumentor traces tool invocation latency and model calls so you can spot bottlenecks.
  • Wrap additional helper functions with start_span if you need more granular insight.
Back: Agent Framework Integrations