mirror of
https://github.com/vectorize-io/hindsight.git
synced 2026-09-14 19:31:49 +08:00
0b6b5261a2
Managed PostgreSQL distributions install the pg_search functions (score, boolean, match) under a schema of their choosing — pgsearch rather than paradedb on the distribution in #3757 — so the hardcoded paradedb. qualification made the pg_search backend unusable there without a custom image or wrapper functions. Adds HINDSIGHT_API_TEXT_SEARCH_EXTENSION_PG_SEARCH_FUNCTION_SCHEMA (default paradedb, validated as a plain PG identifier since it is interpolated into raw SQL) and threads it through both builders that qualify those calls: the memory-recall BM25 arm and the knowledge-pages arm. Index creation needs no change — USING bm25(...) resolves the access method globally. The pdb tokenizer pseudo-types stay fixed; they come from ParadeDB's own install DDL and are independent of the extension's target schema. Fixes #3757.