Or you can use Postgres to store the original text, the metadata and the embedding in a single table and then do hybrid queries against them (with pre- or post-filtering, optimized automatically).
Shameless plug:
BM25 search implemented in PL/pgSQL: https://github.com/jankovicsandras/plpgsql_bm25
faster BM25 search algorithms in Python: https://github.com/jankovicsandras/bm25opt