mirror of
https://github.com/microsoft/semantic-kernel.git
synced 2026-10-12 11:19:56 +00:00
Mark WallaceandDmytro Struk
a7566b6654
### Contribution Checklist - [ ] The code builds clean without any errors or warnings - [ ] 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 - [ ] All unit tests pass, and I have added new tests where possible - [ ] I didn't break anyone 😄 ## Summary This pull request updates PromptTemplateConfig to support multiple AI models, providing greater flexibility in configuring AI services for semantic functions. The Completion property has been removed and replaced with a Models collection that contains AIRequestSettings objects. The SetAIConfiguration and SetAIService methods in SemanticFunction have been updated to use the first AIRequestSettings object in the Models list. SKFunctionTests1 and KernelTests have also been updated to use the Models property of PromptTemplateConfig and to reflect these changes. ## Changes - Added PromptTemplateConfigExtensions.cs file - Modified StepwisePlanner.cs file - Modified AIRequestSettings.cs file - Modified PromptTemplateConfig.cs file - Added unit tests to ensure proper deserialization of PromptTemplateConfig with multiple models - Updated SKFunctionTests1 to use Models property of PromptTemplateConfig - Updated KernelTests to use Models property of PromptTemplateConfig and add OpenAIRequestSettings object to Models list instead of setting it directly to Completion property - Updated test cases to reflect changes --- *Powered by [Microsoft Semantic Kernel](https://github.com/microsoft/semantic-kernel)* --------- Co-authored-by: Dmytro Struk <[email protected]>
16 lines
360 B
JSON
16 lines
360 B
JSON
{
|
|
"schema": 1,
|
|
"description": "Turns natural language into Python command line scripts. Reads variables from args, operates on stdin, out",
|
|
"models": [
|
|
{
|
|
"max_tokens": 256,
|
|
"temperature": 0.0,
|
|
"top_p": 0.0,
|
|
"presence_penalty": 0.0,
|
|
"frequency_penalty": 0.0,
|
|
"stop_sequences": [
|
|
"# Done"
|
|
]
|
|
}
|
|
]
|
|
} |