semantic-kernel/samples/notebooks/python/01-basic-loading-the-kernel.ipynb

Basic Loading of the Kernel

To run the notebooks we recommend using Poetry and starting a shell with a virtual environment prepared to use SK.

See DEV_SETUP.md for more information.

In [ ]:

!python -m pip install -r requirements.txt

In [ ]:

import semantic_kernel as sk
from semantic_kernel.ai.open_ai import AzureTextCompletion, OpenAITextCompletion

You can instantiate the kernel in a few ways, depending on your use case.

In [ ]:

# Simple instance
kernel_1 = sk.Kernel()

In [ ]:

# Instance with a custom logger
my_logger = sk.NullLogger()
kernel_2 = sk.Kernel(log=my_logger)

In [ ]:

# Instance with a custom configuration
my_config = sk.KernelConfig()
kernel_2 = sk.Kernel(config=my_config)

When using the kernel for AI requests, the kernel needs some settings like URL and credentials to the AI models.

The SDK currently supports OpenAI and Azure OpenAI, other services will be added over time.

If you need an Azure OpenAI key, go here.

In [ ]:

kernel = sk.Kernel()

kernel.config.add_text_backend(               # We are adding a text service
    "Azure_curie",                            # The alias we can use in prompt templates' config.json
    AzureTextCompletion(
        "my-finetuned-Curie",                 # Azure OpenAI *Deployment ID*
        "https://contoso.openai.azure.com/",  # Azure OpenAI *Endpoint*
        "...your Azure OpenAI Key..."         # Azure OpenAI *Key*
    )
)

kernel.config.add_text_backend(               # We are adding a text service
    "OpenAI_davinci",                         # The alias we can use in prompt templates' config.json
    OpenAITextCompletion(
        "text-davinci-003",                   # OpenAI Model Name
        "...your OpenAI API Key...",          # OpenAI API key
        "...your OpenAI Org ID..."            # *optional* OpenAI Organization ID
    )
)

When working with multiple services and multiple models, the first service defined is also the "default" used in these scenarios:

• a prompt configuration doesn't specify which AI service to use
• a prompt configuration requires a service unknown to the kernel

The default can be set and changed programmatically:

In [ ]:

kernel.config.set_default_text_backend("Azure_curie")

Great, now that you're familiar with setting up the Semantic Kernel, let's see how we can use it to run prompts.