mirror of https://github.com/microsoft/semantic-kernel.git synced 2026-10-12 02:19:06 +00:00

Files

T

History

Evan Mattson 8381e50e8b Python: Introduce the new function calling abstraction, FunctionChoiceBehavior (#6910 )

### Motivation and Context

The current `FunctionCallBehavior` has allowed us to utilize auto
function calling for OpenAI type models. As we proceed to support more
AI connectors, that differ from OpenAI models, we need to be able to
handle functions for all models that support function calling.

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

In this PR:
- We introduce a new function calling abstraction called
`FunctionChoiceBehavior` which has three types: Auto, Required, and
None.
- One is able to configure the `function_choice_behavior` along with
fully qualified function names (e.g., plugin1.function1),
`maximum_auto_invoke_attempts` or `auto_invoke_kernel_functions` in yaml
and JSON prompts. We have a new concept example showing how to do this
for for yaml and JSON prompts.
- If the fully qualified names are specified in the config file, they
take precedence over the filters, if specified at a later point.
- To make sure this isn't a breaking change, we still handle the
previous `FunctionCallBehavior`, but so we can make decisions on the new
`FunctionChoiceBehavior` we map the `FunctionCallBehavior` to
`FunctionChoiceBehavior`. Each time `FunctionCallBehavior` is updated,
`FunctionChoiceBehavior` will be updated, too.
- The `_process_tool_call()` method in the
`open_ai_chat_completion_base` needs to maintain the argument name as
`function_call_behavior` as we cannot introduce a breaking change.
- All concept samples have been converted to use
`FunctionChoiceBehavior`.
- New unit tests have been added for `FunctionChoiceBehavior` and we
still currently support `FunctionCallBehavior` tests to make sure we
haven't broken the backwards compatibility.
- Added `deprecated` typing decorators to classes/methods to alert users
that it would be best to transition to `FunctionChoiceBehavior` even
though `FunctionCallBehavior` is still supported.
- The `FunctionCallingStepwisePlanner` was updated to use the new
`FunctionChoiceBehavior`.
- Closes #6496, #6458
- Addresses #6626 

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄

2024-06-27 20:34:59 +00:00

bookings_plugin

Python: new pre-commit actions and pre-commit as GHA (#6376 )

2024-05-28 15:28:04 +00:00

booking_sample_settings.py

Python: further improvements to checks and docs in dev_setup (#6445 )

2024-05-31 13:06:41 +00:00

README.md

Python: Fix sample plugin path for Windows. Re-enable samples CI tests. (#6691 )

2024-06-13 15:48:16 +00:00

restaurant_booking.py

Python: Introduce the new function calling abstraction, FunctionChoiceBehavior (#6910 )

2024-06-27 20:34:59 +00:00

README.md

Restaurant - Demo Application

This sample provides a practical demonstration of how to leverage features from the Semantic Kernel to build a console application. Specifically, the application utilizes the Business Schedule and Booking API through Microsoft Graph to enable a Large Language Model (LLM) to book restaurant appointments efficiently. This guide will walk you through the necessary steps to integrate these technologies seamlessly.

Prerequisites

Python 3.10, 3.11, or 3.12.
Microsoft 365 Business License to use Business Schedule and Booking API.
Azure Entra Id administrator account to register an application and set the necessary credentials and permissions.

Function Calling Enabled Models

This sample uses function calling capable models and has been tested with the following models:

Model type	Model name/id	Model version	Supported
Chat Completion	gpt-3.5-turbo	0125	✅
Chat Completion	gpt-3.5-turbo	1106	✅
Chat Completion	gpt-3.5-turbo-0613	0613	✅
Chat Completion	gpt-3.5-turbo-0301	0301	❌
Chat Completion	gpt-3.5-turbo-16k	0613	✅
Chat Completion	gpt-4	0613	✅
Chat Completion	gpt-4-0613	0613	✅
Chat Completion	gpt-4-0314	0314	❌
Chat Completion	gpt-4-turbo	2024-04-09	✅
Chat Completion	gpt-4-turbo-2024-04-09	2024-04-09	✅
Chat Completion	gpt-4-turbo-preview	0125-preview	✅
Chat Completion	gpt-4-0125-preview	0125-preview	✅
Chat Completion	gpt-4-vision-preview	1106-vision-preview	✅
Chat Completion	gpt-4-1106-vision-preview	1106-vision-preview	✅

ℹ️ OpenAI Models older than 0613 version do not support function calling.

ℹ️ When using Azure OpenAI, ensure that the model name of your deployment matches any of the above supported models names.

Configuring the sample

Please make sure either your environment variables or your .env file contains the following:

"BOOKING_SAMPLE_CLIENT_ID"
"BOOKING_SAMPLE_TENANT_ID"
"BOOKING_SAMPLE_CLIENT_SECRET"
"BOOKING_SAMPLE_BUSINESS_ID"
"BOOKING_SAMPLE_SERVICE_ID"

If wanting to use the .env file, you must pass the env_file_path parameter with a valid path:

booking_sample_settings = BookingSampleSettings(env_file_path=env_file_path)

This will tell Pydantic settings to also load the .env file instead of just trying to load environment variables.

Create an App Registration in Azure Active Directory

Go to the Azure Portal.
Select the Azure Active Directory service.
Select App registrations and click on New registration.
Fill in the required fields and click on Register.
Copy the Application (client) Id for later use.
Save Directory (tenant) Id for later use..
Click on Certificates & secrets and create a new client secret. (Any name and expiration date will work)
Copy the client secret value for later use.
Click on API permissions and add the following permissions:
- Microsoft Graph
  - Application permissions
    - BookingsAppointment.ReadWrite.All
  - Delegated permissions
    - OpenId permissions
      - offline_access
      - profile
      - openid

Create Or Use a Booking Service and Business

Go to the Bookings Homepage website.
Create a new Booking Page and add a Service to the Booking (Skip if you don't ).
Access Graph Explorer

Run the following query to get the Booking Business Id:

GET https://graph.microsoft.com/v1.0/solutions/bookingBusinesses

Copy the Booking Business Id for later use.

Run the following query and replace it with your Booking Business Id to get the Booking Service Id

GET https://graph.microsoft.com/v1.0/solutions/bookingBusinesses/{bookingBusiness-id}/services

Copy the Booking Service Id for later use.

Running the sample

Either run the sample in an IDE, like VSCode, or via the command line.

Example of a conversation

User > Please book a restaurant for me.

Assistant > Sure, I can help you with that. Could you please provide me with the following information:

Name of the restaurant you would like to book.

Date and time of the reservation.

Number of people in your party.

Your name.

Your email address.

Your phone number.

Once I have all this information, I will proceed with the booking.

User > I would like to book a table at the restaurant "The French Laundry" on the 15th of March at 7:00 PM for 4 people. My name is John Doe, my email address is [email protected], and my phone number is 123-456-7890.

System > Do you want to book a table at The French Laundry on 15/03/2023 19:00:00 for 4 people?

System > Please confirm by typing 'yes' or 'no'.

User > yes

Assistant > Great! I have successfully booked a table for you at "The French Laundry" on the 15th of March at 7:00 PM for 4 people.

Your reservation has been made under the name John Doe.

If you have any further questions or need to make any changes to your reservation, please let me know.

User > List my current bookings

Assistant > You currently have one booking:

Restaurant: The French Laundry

Date and Time: 15th of March at 7:00 PM

Party Size: 4 people

If you need any further assistance or if there's anything else I can help you with, please let me know.

User > Cancel my booking

System > [Cancelling a reservation for 4 at The French Laundry on 2023-03-15 at 19:00:00]

Assistant > I have successfully canceled your booking at "The French Laundry" on the 15th of March at 7:00 PM for 4 people.

If you have any other questions or need further assistance, please let me know.

README.md Unescape Escape

Restaurant - Demo Application

Prerequisites

Function Calling Enabled Models

Configuring the sample

Create an App Registration in Azure Active Directory

Create Or Use a Booking Service and Business

Running the sample

Example of a conversation

README.md