feat: Added support for Azure OpenAI and other LLMs in Semantic Kernel

[oliverlabs]

Description

See google-a2a/A2A#505 for more information and background as the previous PR was closed due to the move of a2a-examples folder to a new repo.

Key changes:

1. Enum-based Service Selection: added a ChatServices enum with AZURE_OPENAI and OPENAI options for clear service identification.

2. Added explicity service configuration functions:

• get_chat_completion_service(): Main function to get a service by enum value
• _get_azure_openai_chat_completion_service(): Handles Azure OpenAI configuration
• _get_openai_chat_completion_service(): Handles OpenAI configuration

3. Added auto-detection with fallback using auto_detect_chat_service() function.

4. Provided .envexample file for environment variable examples

5. Updated the Readme file with instructions on how to define the variables for each service.

Thanks @moonbox3 for suggestions.

This change makes it possible to add other LLM chat completion services in future.

Cheers,
Oliver

---

Before submitting your PR, there are a few things you can do to make sure it goes smoothly:

• Follow the CONTRIBUTING Guide.
• Make your Pull Request title in the https://www.conventionalcommits.org/ specification.
• Ensure the tests and linter pass (Run nox -s format from the repository root to format)
• Appropriate docs were updated (if necessary)

Fixes #45 🦕

[oliverlabs]

@moonbox3, could you please review?

[jland-redhat]

Left one small comment you can change if you want. There is no current pattern so I will let @moonbox3 comment on which way he wants to go since he ins the maintainer.

But a fan of the new code changes. I know there were a lot of changes but this looks pretty clean to me.

[oliverlabs]

Left one small comment you can change if you want. There is no current pattern so I will let @moonbox3 comment on which way he wants to go since he ins the maintainer.

But a fan of the new code changes. I know there were a lot of changes but this looks pretty clean to me.

Thanks for reviewing this change, @jland-redhat. I really appreciate it. I agree about note markdown formatting. I was just following the pattern that was already set in the readme :) I fixed all instances of this now. Cheers.

[moonbox3]

Thanks for working on this -- a couple of small comments.