mirror of
https://github.com/microsoft/semantic-kernel.git
synced 2026-10-12 11:19:56 +00:00
Evan Mattson
5e632fd1b2
### Motivation and Context OpenAI / Azure OpenAI released the ability to specify the `parallel_tool_calls` = True | False boolean attribute on the prompt execution settings in July. This was never brought into SK Python. Further, there appears to be a pesky bug related to function calling where enabling parallel tool calls can cause 500s. The only way to get around this is to disable parallel function calling. This has been both tested on the Azure Chat Completion and OpenAI Chat Completion code and works well -- the chat history shows the synchronous function calls if multiple tool calls are required. <!-- 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 Add the `parallel_tool_calls` attribute on the OpenAIChatPromptExecutionExecution settings, which are also used by the AzureChatCompletionClass. - Closes #9478 - Adds unit tests for this prompt execution setting <!-- 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 😄