semantic-kernel/python/notebooks/00-getting-started.ipynb

Setup

Step 1: Import Semantic Kernel SDK from pypi.org

In [ ]:

!python -m pip install semantic-kernel==0.9.6b1

In [ ]:

from semantic_kernel import Kernel

kernel = Kernel()

Configure the service you'd like to use via the Service Enum.

In [ ]:

from services import Service

# Select a service to use for this notebook (available services: OpenAI, AzureOpenAI, HuggingFace)
selectedService = Service.OpenAI

Option 1: using OpenAI

Step 2: Add your OpenAI Key key to a .env file in the same folder (org Id only if you have multiple orgs):

OPENAI_API_KEY="sk-..."
OPENAI_ORG_ID=""

Use "keyword arguments" to instantiate an OpenAI Chat Completion service and add it to the kernel:

Option 2: using Azure OpenAI

Step 2: Add your Azure Open AI Service key settings to a .env file in the same folder:

AZURE_OPENAI_API_KEY="..."
AZURE_OPENAI_ENDPOINT="https://..."
AZURE_OPENAI_DEPLOYMENT_NAME="..."

Use "keyword arguments" to instantiate an Azure OpenAI Chat Completion service and add it to the kernel:

In [ ]:

from semantic_kernel.utils.settings import azure_openai_settings_from_dot_env, openai_settings_from_dot_env

service_id = None
if selectedService == Service.OpenAI:
    from semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion

    api_key, org_id = openai_settings_from_dot_env()
    service_id = "default"
    kernel.add_service(
        OpenAIChatCompletion(service_id=service_id, ai_model_id="gpt-3.5-turbo-1106", api_key=api_key, org_id=org_id),
    )
elif selectedService == Service.AzureOpenAI:
    from semantic_kernel.connectors.ai.open_ai import AzureChatCompletion

    deployment, api_key, endpoint = azure_openai_settings_from_dot_env()
    service_id = "default"
    kernel.add_service(
        AzureChatCompletion(service_id=service_id, deployment_name=deployment, endpoint=endpoint, api_key=api_key),
    )

Run a Semantic Function

Step 3: Load a Plugin and run a semantic function:

In [ ]:

plugin = kernel.add_plugin(parent_directory="../../samples/plugins", plugin_name="FunPlugin")

In [ ]:

from semantic_kernel.functions import KernelArguments

joke_function = plugin["Joke"]

joke = await kernel.invoke(joke_function, KernelArguments(input="time travel to dinosaur age", style="super silly"))
print(joke)