Smolagents example connecting to Sap Generative AI Hub via LiteLLM

How Smolagents work

Installation

%pip install “smolagents[toolkit] litellm”

Credentials for SAP Gen AI Hub

Get the service key from your SAP BTP tenant with AI subscription.

Add the following variables from the service key in a file called “.env” and put it in the same folder where you run the notebook:

AICORE_AUTH_URL="https://* * * .authentication.sap.hana.ondemand.com/oauth/token"
AICORE_CLIENT_ID=" *** "
AICORE_CLIENT_SECRET=" *** "
AICORE_RESOURCE_GROUP=" *** "
AICORE_BASE_URL="https://api.ai.***.cfapps.sap.hana.ondemand.com/

Run the Smolagents with LiteLLM and SAP LLMs

from dotenv import load_dotenv
from smolagents import CodeAgent, LiteLLMModel, tool

Load your credentials as environment variables that Litellm can use automatically.

load_dotenv()

Define the agent tool

@tool
def get_weather(city: str) -> str:
    """Retrieves the current weather report for a specified city.
    Args:
        city (str): The name of the city to retrieve weather information for.
            Examples: "New York", "London", "Tokyo".
    """
    city_normalized = city.lower().replace(" ", "")

    mock_weather_db = {
        "newyork": "The weather in New York is sunny with a temperature of 25°C.",
        "london": "It's cloudy in London with a temperature of 15°C.",
        "tokyo": "Tokyo is experiencing light rain and a temperature of 18°C.",
    }

    if city_normalized in mock_weather_db:
        return mock_weather_db[city_normalized]
    else:
        return f"The weather in {city} is sunny with a temperature of 20°C."

Define the model

model = LiteLLMModel(model_id="sap/gpt-5")

Define the agent

agent = CodeAgent(tools=[get_weather], model=model)

Run the agent

response = agent.run("What is the weather like in London?")
print(response)