DOC: add Example sections to KernelFunction.from_prompt and invoke

[Shoumik Chakravarty (shoumikchakravarty-dev)]

Add illustrative code examples to two public methods in KernelFunction:

• from_prompt: shows creating a prompt-based function and registering it with the kernel
• invoke: shows async invocation with KernelArguments using OpenAIChatCompletion

Both examples follow the existing Google-style docstring convention used throughout the module.

Motivation and Context

Please help reviewers and future users, providing the following information:

1. The from_prompt and invoke methods are the primary entry points for defining and running prompt-based functions in Semantic Kernel, yet their docstrings contain only a one-line description or a parameter list — no usage examples.
2. Developers exploring the Semantic Kernel Python SDK through IDE tooltips, help(), or generated API docs currently see no usage examples for from_prompt and invoke
3. Any scenario where a developer is getting started with Semantic Kernel's Python SDK and wants to understand how to define a prompt-based function and invoke it with arguments — without leaving their IDE or the API reference
4. No open issue. This is a proactive documentation improvement spotted while exploring the Python SDK codebase.

Description

This PR adds illustrative code examples to two public methods in
KernelFunction that currently have minimal docstrings:

• from_prompt: shows creating a prompt-based function and registering
  it with the kernel
• invoke: shows async invocation with KernelArguments using
  OpenAIChatCompletion

Both examples follow the existing Google-style docstring convention
used throughout the module. No logic changes.

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 (Documentation only PR)
• I didn't break anyone 😄 (Documentation only PR)

[Copilot]

Pull request overview

Adds usage examples to two key public KernelFunction entry points in the Python SDK so developers can discover common workflows (creating prompt-based functions and invoking them) directly from docstrings / generated API docs.

Changes:

• Expanded KernelFunction.from_prompt docstring with an example that creates a prompt function and registers it with a Kernel.
• Expanded KernelFunction.invoke docstring with an async example invoking a prompt function using KernelArguments and OpenAIChatCompletion.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Shoumik Chakravarty (shoumikchakravarty-dev)]

Hello Gatekeepers , This is my first submission to update on the Kernel function documents. Please review & let me know if this needs any changes.

[Copilot]

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated 1 comment.

[Copilot]

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated no new comments.

[Shoumik Chakravarty (shoumikchakravarty-dev)]

Hi SergeyMenshykh , apologies for the direct ping — CODEOWNERS points at microsoft/octo-semantickernel-pr-python and I noticed you've been active in this area recently. This PR has 7 pending workflow approvals blocking human review; would you (or someone you can route me to) be able to trigger the runs? Happy to rebase if the branch has gone stale. Thanks!

[github-actions]

Python Test Coverage Report •

File	Stmts	Miss	Cover	Missing
functions
kernel_function.py	205	53	74%	111, 113, 320, 335–339, 392, 418–423, 480, 482, 484, 486–487, 489–490, 494–502, 506–507, 509–527, 529
TOTAL	28967	5639	80%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
4074	23 💤	0 ❌	0 🔥	2m 14s ⏱️

[Evan Mattson (moonbox3)]

Please have a look at the CI/CD failures.

[Shoumik Chakravarty (shoumikchakravarty-dev)]

Please have a look at the CI/CD failures.

Hi Evan Mattson (@moonbox3) — took care of the CI failures; there was an ruff-format issue with the embedded docstring code, which is now fixed. waiting for the integration test check to be finished.

[Copilot]

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated no new comments.

[Shoumik Chakravarty (shoumikchakravarty-dev)]

Evan Mattson (@moonbox3) - I think the python-integration-tests-check workflow is waiting on maintainer approval to run. Could you trigger it when you get a moment? Thanks!

[Shoumik Chakravarty (shoumikchakravarty-dev)]

Hi Evan Mattson (@moonbox3) / SergeyMenshykh — friendly check-in on this one. Applied the ruff-format fixes from your earlier feedback and CI is green on the checks that run automatically. The python-integration-tests-check workflow is still pending workflow approval — happy to make any additional changes if you want to see anything else before we get it moving. Thanks!

[Shoumik Chakravarty (shoumikchakravarty-dev)]

The current failing test (tests/unit/connectors/mcp/test_mcp.py) is unrelated to this PR — the root cause is:
ImportError: cannot import name 'streamablehttp_client' from 'mcp.client.streamable_http'

My PR only touches docstring formatting in KernelFunction.from_prompt and KernelFunction.invoke — no MCP code paths or dependencies are touched. Likely a version pin issue in uv.lock.

Happy to rebase against latest main if the dependency has been updated there. Let me know how you'd like to proceed.

[Shoumik Chakravarty (shoumikchakravarty-dev)]

Rebased against latest main. Automated CI is running; python-integration-tests-check is again pending workflow approval. Standing by for review.