Switching models (llm/slm) dynamically

[jamesmkfoo23]

To add a model to a kernel, the model provider needs to be specified.

from semantic_kernel import Kernel
from semantic_kernel.connectors.ai.open_ai import AzureChatCompletion, AzureTextCompletion

kernel = Kernel()

# Register multiple models
kernel.add_service(
    AzureChatCompletion(
        service_id="gpt4o",
        deployment_name="gpt-4o",
        endpoint="https://<your-endpoint>.openai.azure.com/",
        api_key="<your-key>",
    )
)

What if we wanted to switch models dynamically which includes other providers (eg: Gemini/or other SLM)?

Azure AI Foundry SDK makes this possible, just so long as the model can be deployed onto Azure AI Foundry. I don't think this is possible for SLMs though

    agent = project_client.agents.create_agent(
        model=os.environ["MODEL_DEPLOYMENT_NAME"],  # Model deployment name
        name="my-agent",  # Name of the agent
        instructions="You politely help with math questions. Use the Code Interpreter tool when asked to visualize numbers.",  # Instructions for the agent
        tools=code_interpreter.definitions,  # Attach the tool
    )

Would this be possible using Semantic Kernel?