update VideoSummary, LiveData, llama-on-prem for Llama 3

[jeffxtang]

What does this PR do?

VideoSummary: show how to ask Llama 3 to generate a summary of a long (almost 3 hours) youtube video (Yann LeCun vs Lex Fridman) content with 140+k chars or ~30k words or 40k tokens, exceeding Llama 3's 8k context length limit. https://github.com/meta-llama/llama-recipes/blob/demos4llama3v3/recipes/use_cases/VideoSummary.ipynb

LiveData: How to ask Llama 3 questions about recent live data via the live search API and LlamaIndex https://github.com/meta-llama/llama-recipes/blob/demos4llama3v3/recipes/use_cases/LiveData.ipynb

llama-on-prem.md: https://github.com/meta-llama/llama-recipes/blob/demos4llama3v3/recipes/inference/model_servers/llama-on-prem.md

Fixes # (issue)

Feature/Issue validation/testing

Please describe the tests that you ran to verify your changes and relevant result summary. Provide instructions so it can be reproduced. Please also list any relevant details for your test configuration.

• [ ] Test A Logs for Test A

• [ ] Test B Logs for Test B

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 🎉!

[albertodepaola]

Link to the actual recipe, for easier parsing: https://github.com/meta-llama/llama-recipes/blob/demos4llama3v3/recipes/use_cases/VideoSummary.ipynb

[albertodepaola]

nit: would be good to add the open in colab style link, from other notebooks as well.

good ideas! added.

[fbnav]

Looks great, thanks for putting this together!