metadata and generic filters in vector search #689
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
montanalow
approved these changes
Jun 5, 2023
There was a problem hiding this comment.
I think there is a quickly growing need to move to a builder pattern, to prevent having to duplicate this functionality for example on a text_search or fuzzy_search function. We need a better API that more cleanly encapsulates recall, ranking and filtering, reranking and refiltering, and finally passing as an input to another SQL function or recalling from the database to the application.
| ) | ||
|
|
||
| if metadata_filter: | ||
| cte_select_statement += ( | ||
| " AND documents.metadata @> {metadata_filter}".format( |
There was a problem hiding this comment.
This is nice. We should also add a GIN index to documents.metadata.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I have added two filters to vector_search:
metadata_filteruses basic containment operator@>andgeneric_filtertakes pretty much anything that the user wants to filter ondocumentstable using SQL syntax.generic_filtershould give us quite a bit of coverage including timestamps and nested metadata.Added three tests.