PGVectorStore: query with metadata filters only

[vlreinier]

Description

This pull request introduces the ability to query PostgreSQL using only metadata filters in LlamaIndex. Previously, queries could only be executed using an embedding or a query_str. The new functionality expands query options, making the system more flexible and allowing metadata filtering as a standalone query mechanism.

Key changes include:

A new VectorStoreQueryMode type named FILTERS has been added.
A filters_top_k parameter has been added to the VectorStoreQuery class.
Additionally, modifications were made to the PGVectorStore class to support the new FILTERS query mode. These changes are isolated to LlamaIndex Core.

Version Bump?

Did I bump the version in the pyproject.toml file of the package I am updating? (Except for the llama-index-core package)

• Yes
• No

Type of Change

Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

How Has This Been Tested?

Has been tested on the forked branch.

• I added new unit tests to cover this change
• I believe this change is already covered by existing unit tests

Suggested Checklist:

• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• I have added Google Colab support for the newly added notebooks.
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• I ran make format; make lint to appease the lint gods

[logan-markewich]

I kind if disagree with this change. We are adding a new enum value that is only used by single vector store. The user experience with these modes is already not great across vector stores, this makes it even worse.

I would prefer that we implement the get_nodes() / aget_nodes() function, that allows you to pass in either node ids or filters to get a list of nodes. This method is on the base class, but has only been implemented in a handful of vector stores so far (there is also delete_nodes() / adelete_nodes() and clear() / aclear())

[logan-markewich]

oh nice, get nodes is already implemented, just checked

[logan-markewich]

If you want to handle empty queries, that doesn't need to be its own mode. We can adjust the default query mode to work with or without a query string

Or, you can just use the get_nodes method described above

[vlreinier]

Understandable. The get_nodes solution seems to be sufficient. however I still think it adds some value because of the way llama-index builds the table columns. For each column a query mode is available except for metadata.