nogueiraguh 587a809156 feat: auto-detect embedding dimensions per table in consult endpoint ...

- Detect VECTOR_DIMENSION_COUNT per table before querying
- Map dimensions to correct embedding model (1536→small, 3072→large)
- Cache query embeddings by dimension to avoid redundant API calls
- All tables now searchable regardless of which model generated them

2026-03-11 03:12:57 -03:00

278 KiB

Raw Blame History

View Raw