mirror of https://github.com/microsoft/semantic-kernel.git synced 2026-10-12 11:19:56 +00:00

Files

T

d019485568 Python: Update notebooks and add samples for streaming and multiple responses (#1489 )

### Motivation and Context
The python notebooks are pinned to 0.2.7.dev0 while the latest pip
package for python is 0.3.1.dev0. This PR updates the notebooks to pull
the 0.3.1.dev0 and adds 2 new notebooks demonstrating new features added
to SK between these versions.


### Description
- All notebooks depend on semantic-kernel==0.3.1.dev0
- Added a notebook demonstrating streaming completion responses
- Added a notebook demonstrating multiple responses per prompt
(including streaming them)


### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [ ] The code builds clean without any errors or warnings
- [ ] The PR follows SK Contribution Guidelines
(https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
- [ ] The code follows the .NET coding conventions
(https://learn.microsoft.com/dotnet/csharp/fundamentals/coding-style/coding-conventions)
verified with `dotnet format`
- [ ] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄

---------

Co-authored-by: Lee Miller <[email protected]>
Co-authored-by: Shawn Callegari <[email protected]>

2023-07-08 03:22:42 +00:00

4.6 KiB

Raw Blame History

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 semantic-kernel==0.3.1.dev0

In [ ]:

import semantic_kernel as sk
from semantic_kernel.connectors.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)

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.add_text_completion_service(               # 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 name*
        "https://contoso.openai.azure.com/",  # Azure OpenAI *Endpoint*
        "...your Azure OpenAI Key..."         # Azure OpenAI *Key*
    )
)

kernel.add_text_completion_service(               # 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.set_default_text_completion_service("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.

4.6 KiB Raw Blame History

Basic Loading of the Kernel

4.6 KiB

Raw Blame History