[ENH] Implements a new embedding function for ChromaDB that uses the modern google-genai library (the recommended replacement for google.generativeai).

[yrangana]

This PR adds a new embedding function that uses the modern google-genai library for ChromaDB.

Improvements & Bug fixes
Addresses dependency on deprecated google.generativeai package
Ensures compatibility with the latest Google Generative AI API
Fixes response structure handling to properly extract embeddings

New functionality

• Adds GoogleGenAiEmbeddingFunction class that implements ChromaDB's EmbeddingFunction interface
• Uses text-embedding-004 as the default model (Google's recommended embedding model)
• Maintains the original GoogleGenerativeAiEmbeddingFunction for backward compatibility
• Provides comprehensive error handling and validation for API key configuration
• Supports the same vector spaces (cosine, l2, ip) as the original implementation

Test plan
How are these changes tested?

• Tests pass locally with pytest for python
• Manually tested embedding generation
• Verified compatibility with existing ChromaDB collections
• Confirmed proper error handling when API keys are missing or invalid
• Tested with various document types and lengths to ensure consistent embedding generation

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

• All docstrings have been updated with comprehensive descriptions and parameter details
• The main class docstring clearly indicates this is using the newer google-genai package
• The documentation repository should be updated to include:

[github-actions]

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)

[jairad26]

thank you for the PR! Could you also add the js embedding function to match, and add the google_genai.json to match? No worries if not, I can add to the PR as well if youre ok with that. Also could you prepend the PR title with [ENH]

[yrangana]

Im not familiar with JS function @jairad26, Can you add it pls. I have renamed the title. Thank you