Add LlamaCppEmbeddingFunction class for document embedding

[AveryUALibrary]

Description of changes

Implementation of Issue 2409

Summarize the changes made by this PR.

• Improvements & Bug fixes
  • ...
• New functionality
  • Implements llama cpp local model embedding

Test plan

How are these changes tested?

• [ ] Tests pass locally with pytest for python, yarn test for js, cargo test for rust

Documentation Changes

Are all docstrings for user-facing APIs updated if required? Do we need to make documentation changes in the docs repository?

[github-actions[bot]]

Reviewer Checklist

Please leverage this checklist to ensure your code review is thorough before approving

Testing, Bugs, Errors, Logs, Documentation

• [ ] Can you think of any use case in which the code does not behave as intended? Have they been tested?
• [ ] Can you think of any inputs or external events that could break the code? Is user input validated and safe? Have they been tested?
• [ ] If appropriate, are there adequate property based tests?
• [ ] If appropriate, are there adequate unit tests?
• [ ] Should any logging, debugging, tracing information be added or removed?
• [ ] Are error messages user-friendly?
• [ ] Have all documentation changes needed been made?
• [ ] Have all non-obvious changes been commented?

  System Compatibility

• [ ] Are there any potential impacts on other parts of the system or backward compatibility?
• [ ] Does this change intersect with any items on our roadmap, and if so, is there a plan for fitting them together?

  Quality

• [ ] Is this code of a unexpectedly high quality (Readability, Modularity, Intuitiveness)

[tazarov]

@AveryUALibrary, thanks for this. Here are a few more things we need to get done (happy to add any/all of those to your fork):

• Docs
• Tests
• Utility to fetch models - llama.CPP uses GGUF format, if I'm not mistaken; for most parts, these files are also hosted on HF, so maybe we can either add instructions but, better yet, use either direct HTTP calls to fetch the models or use HF tooling for that (if applicable).

[AveryUALibrary]

@AveryUALibrary, thanks for this. Here are a few more things we need to get done (happy to add any/all of those to your fork):

• Docs
• Tests
• Utility to fetch models - llama.CPP uses GGUF format, if I'm not mistaken; for most parts, these files are also hosted on HF, so maybe we can either add instructions but, better yet, use either direct HTTP calls to fetch the models or use HF tooling for that (if applicable).

The current implementation now contains updated docs and automatic fetching of hugging face models using Llama.from_pretrained. No clue on how to implement testing for Chroma.