[ENH] Support using schema embedding function for dense vectors, allow document source key for sparse

[jairad26]

Description of changes

Summarize the changes made by this PR.

• Improvements & Bug fixes
  • This PR adds support for using the embedding function defined in the schema on a collection during _embed. This lets auto embedding via schema occur on inserts and queries
• New functionality
  • ...

Test plan

How are these changes tested?
added tests in stacked pr for e2e schema tests

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

Migration plan

Are there any migrations, or any forwards/backwards compatibility changes needed in order to make sure this change deploys reliably?

Observability plan

What is the plan to instrument and monitor this change?

Documentation Changes

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

[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]

• [ENH] Embed query strings in search api #5599
• [ENH] Add Schema to js client #5621
• [TST] Add schema e2e tests #5616
• [ENH] Support using schema embedding function for dense vectors, allow document source key for sparse #5617 👈 (View in Graphite)
• [ENH] Add hosted splade embedding function to python and js #5610
• main

This stack of pull requests is managed by Graphite. Learn more about stacking.

[propel-code-bot]

Enhance Schema Embedding Logic and Sparse Embedding Function Registration

This pull request introduces support for leveraging the embedding function defined in the schema on a collection during the _embed process. It allows schema-level embedding functions to be used automatically for dense vector generation during inserts and queries. The update also improves how sparse embedding functions can utilize the document source key and adds a decorator to facilitate custom sparse embedding function registration.

Key Changes

• Added support in CollectionCommon to use the schema's embedding function for dense embeddings, both for inserts and queries.
• Modified the _apply_sparse_embeddings_to_metadatas method in CollectionCommon to use the document value if the sparse embedding config is set to reference the document key.
• Added EMBEDDING_KEY and DOCUMENT_KEY handling in relevant sections of chromadb/api/models/CollectionCommon.py.
• Introduced register_sparse_embedding_function decorator to streamline registration of custom sparse embedding functions in chromadb/utils/embedding_functions/__init__.py.
• Minor signature update for sparse_known_embedding_functions with # type: ignore.
• Updated internal logic to prefer schema-defined embedding functions if set, falling back to client or configuration embedding functions.

Affected Areas

• chromadb/api/models/CollectionCommon.py
• chromadb/utils/embedding_functions/__init__.py

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