.Net: Sample Code Showcasing Usage of Reasoning Models in OpenAI and AzureOpenAI

[joslat]

Motivation and Context

1. Required: showing usage of reasoning effort.
2. Problem: Controlling reasoning effort - no sample
3. Scenario: Using reasoning effort to benefit from the new amazing models :)

Description

This pull request adds sample code that demonstrates how to leverage reasoning models in a ChatCompletion on AzureOpenAI and OpenAI.

This implementation how to leverage LLM Reasoning capabilities but also complements the phenomenal code from Roger Barreto (@RogerBarreto), further strengthening Semantic Kernel overall solution.

Contribution Checklist

• The code builds clean without any errors or warnings
• The PR follows the SK Contribution Guidelines and the pre-submission formatting script raises no violations
• All unit tests pass, and I have added new tests where possible
• I didn't break anyone 😄

[joslat]

@RogerBarreto I saw there was no sample, so "giving back" a bit ;)
Also, what do you think of the example use cases? Would you change/adjust them to properly use the "reasoning effort"?

[RogerBarreto]

Thanks for the sample and contribution @joslat.
I'm tagging @crickman as one of our Agent expert to have a look in the demo and comment. As we are approaching GA on the agents would be interesting to have your optinion and changes that bring a good Agent with latest reasoning capabilities to our Demo collections.

[joslat]

@RogerBarreto & @crickman any feedback? :)
If not, I think it fits the quality gate so we could approve, after all it's an example on "how to use the new reasoning effort parameter", that's all ;)

[crickman]

Thanks for the sample and contribution @joslat. I'm tagging @crickman as one of our Agent expert to have a look in the demo and comment. As we are approaching GA on the agents would be interesting to have your optinion and changes that bring a good Agent with latest reasoning capabilities to our Demo collections.

@RogerBarreto - The core of the demo isn't really agent specific. I've recommended to @joslat that it be refactored as a focused sample.

[joslat]

@crickman I think this is it, simplest implementation possible as a concept sample, ChatCompletion only.
Unsure about the configuration stuff, there I need guidance-support though. The rest is done.

[joslat]

Some TODO after an alignment/sync with @RogerBarreto:

• I will update the branch and rebuild as some code has changed and is specific to Azure/OpenAI. (like OpenAIPromptExecutionSettings)
• I will add a max tokens to circumvent an issue with this.
• I will create two examples, one for OpenAI, other for AzureOpenAI.
• I will leave the examples as simple and clear as possible.

Do I miss anything @RogerBarreto?

[RogerBarreto]

@joslat

Update the PR Description and Title to the simplified latest changes. Thanks!

[RogerBarreto]

Sounds good! Thanks!

[RogerBarreto]

ONe of the files in the PR changes the solution file, it's not needed.

[joslat]

ONe of the files in the PR changes the solution file, it's not needed.

also done :)