mirror of
https://github.com/microsoft/semantic-kernel.git
synced 2026-10-12 11:19:56 +00:00
Evan Mattson
51675d2607
### Motivation and Context We currently handle OpenAPI plugins via the kernel, but in a pretty simple way. The changes in this PR are allowing one to define multiple server paths for an operation as well as configure security on the operations either at the operation level or at the "global" spec level (these are included as metadata in the kernel function parameter `additional_parameters` dict). The OpenAPI plugin is graduating from an experimental state to a preview state. This, in turn, removes the `experimental` tag from some public facing methods. In the near future, all `experimental` tags will be removed once we're confident there are no other underlying changes required. Closes #9719 <!-- 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 Adds support for OpenAPI plugin: - allow for multiple servers for an API operation - allows one to define security configuration at the spec level as well as per operation level - fixes a bug where the `excluded_operations` on the execution settings were never checked during REST API operation building - adds the deprecated tag to the `OpenAI plugin` code as it was deprecated by OpenAI and we never handled it in SK Python. - renames some model class to remove the `operation` portion of the name. - adds ability to specify a callback to be able to skip certain api operations based on name, method, or description - removes the experimental tag from public facing methods. - allows one to pass in a parsed OpenAPI spec to the plugin add method - adds unit tests <!-- 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 - [ ] I didn't break anyone 😄
Semantic Kernel Demo Applications
Demonstration applications that leverage the usage of one or many SK features
| Type | Description |
|---|---|
| assistants_group_chat | A sample Agent demo that shows a chat functionality with an OpenAI Assistant agent. |
| booking_restaurant | A sample chat bot that leverages the Microsoft Graph and Bookings API as a Semantic Kernel plugin to make a fake booking at a restaurant. |
| guided_conversations | A sample showing a framework for a pattern of use cases referred to as guided conversations. |
| processes_with_dapr | A sample showing the Semantic Kernel process framework used with the Python Dapr runtime. |
| telemetry_with_application_insights | A sample project that shows how a Python application can be configured to send Semantic Kernel telemetry to Application Insights. |