Add Apple Silicon and macOS setup notes to AI Agent on CPU path

[GurmanSinghDuklu]

Before submitting a pull request for a new Learning Path, please review Create a Learning Path

• [ ✅] I have reviewed Create a Learning Path

Please do not include any confidential information in your contribution. This includes confidential microarchitecture details and unannounced product information.

• [ ✅] I have checked my contribution for confidential information

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of the Creative Commons Attribution 4.0 International License.

[GurmanSinghDuklu]

For context on why I added this and what it covers:

This Learning Path currently targets Arm servers running Ubuntu 22.04 LTS. Apple Silicon Macs are Arm-based too, so I added a section covering the setup differences I ran into while following these steps end to end on an M-series MacBook Pro:

• Installing dependencies with Homebrew instead of apt
• A Python 3.10+ requirement for llama-cpp-agent, since macOS ships with an older system Python by default
• Installing llama-cpp-python without the Linux-specific --extra-index-url flag, since a prebuilt wheel for macOS arm64 is available directly from PyPI
• The huggingface-cli to hf rename in newer versions of huggingface_hub
• A fix for a Xet transfer error that interrupted the model download partway through
• Disabling Metal explicitly when building llama.cpp, to keep CPU-only performance measurement consistent with the rest of the Learning Path

I previewed the change locally with Hugo 0.130.0, matching the version pinned in this repo's workflows, to confirm it renders correctly against the existing page.

One style note: I used sentence case for my new heading per the writing-style-review guidelines, though the existing headings on this page use Title Case. Happy to match the existing style instead if that's preferred.

Thanks for taking a look, and let me know if you'd like any changes.