Encode state-level city metadata as "null" string#369
Open
leekahung wants to merge 2 commits into
Open
Conversation
Vertex AI Search drops JSON null struct fields on import, so state-level
docs lost their city field and the city: ANY("null") retriever filter
matched nothing. Emit the literal string "null" instead.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What type of PR is this? (check all applicable)
Description
Vertex AI Search drops
struct_datafields whose value is JSONnullon import. State-level law docs were generated with{"city": null}, so they landed in the datastore with nocityfield at all. The retriever filters those docs withcity: ANY("null"), which matches the literal string"null"— not a missing field — so state-level statutes (ORS 90, 91, 105, etc.) returned zero results.This emits the literal string
"null"for state-level docs instead of JSONnull, so the metadata matches the filter.Note: this fixes the generator for future corpus builds. The currently-affected datastore (
city-state-law-search-05082026-edition) was already repaired in place by patching its bucketmetadata.jsonland re-importing.Related Tickets & Documents
QA Instructions, Screenshots, Recordings
cd backend && uv run pytest tests/test_generate_metadata_jsonl.py— all pass. State-level entries now serialize as{"city": "null", "state": "or"}.Added/updated tests?
Documentation
Architecture.mdhas been updated