embedding_functions: add azure_ad_token_provider support to OpenAIEmbeddingFunction

[wuxu92]

Description of changes

Fixes #5080

Test plan

manually 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 section?

first time to contribution to chromadb, let me know if improvements are needed.

[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)

[propel-code-bot]

Add Azure AD Token Provider Support to OpenAIEmbeddingFunction

This PR introduces support for providing an Azure Active Directory token provider to the OpenAIEmbeddingFunction class. This enables authentication via Azure AD tokens when using the embedding function with Azure-hosted OpenAI endpoints, without requiring an explicit API key.

Key Changes

• Added azure_ad_token_provider argument to OpenAIEmbeddingFunction constructor and internal usage.
• Updated parameter documentation and input validation to support Azure AD authentication.
• Conditionally select between API key and Azure AD flow based on api_type.
• Pass azure_ad_token_provider in AzureOpenAI client instantiation.
• Refactored imports and parameter validation for clarity.

Affected Areas

• chromadb/utils/embedding_functions/openai_embedding_function.py
• OpenAIEmbeddingFunction class (init, documentation, client setup)

This summary was automatically generated by @propel-code-bot