[Demos] Adding OctoAI API Examples (Hosted Llama solution)

[tmoreau89]

What does this PR do?

OctoAI provides hosted models for Llama2, LlamaGuard, CodeLlama, and embedding models among many other open source models.

This PR introduces demo examples that are ports of existing notebooks that originally used a mix of Replicate hosted Llama2, Huggingface-based Embedding model, and Anyscale hosted Llama-Guard. As a substitute, we're using OctoAI to host the Llama models and Embedding models, thus simplifying the demos and notebooks.

Note also that the RAG example originally relied on hosting Llama locally; now we're just relying on OctoAI here to host the Llama model.

Feature/Issue validation/testing

All python notebooks were run on a Macbook M1 laptop successfully.

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline,
  Pull Request section?
• Was this discussed/approved via a Github issue? Please add a link
  to it if that's the case.
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?

Thanks for contributing 🎉!

[HamidShojanazeri]

Thanks @tmoreau89 for the PR! LGTM, shall we add an update in README to mention, the support for OctoAI APIs as well?

[tmoreau89]

Sure, I can make that change, thanks @HamidShojanazeri

[tmoreau89]

@HamidShojanazeri updated the docs PTAL, thank you!

[HamidShojanazeri]

Thanks @tmoreau89!