Wirestack
pg_pinecone 0.12.1 embeds a Postgres text column with a hosted model (November 8, 2026)
pg_pinecone 0.12.1 embeds a text column with a hosted model, so no vector column is needed. Starter and Builder embedding tokens doubled.
3 of 3 free copies left this month.Unlimited with Pro
What changed
Pinecone's release notes for November 8, 2026 say pg_pinecone can now embed a table's text column with a hosted model, such as gemini-embedding-2, so you can search by meaning without a vector column. It is available in v0.12.1.
You name the model when you track the table, as shown in the guide:
SELECT pinecone.track_docs('notes',
text_columns => '{"body": {"language": "en", "embed": {"model": "gemini-embedding-2"}}}',
metadata_columns => ARRAY['category']);Then search with mode => 'embed':
SELECT n.id, n.body, s.score
FROM pinecone.search_docs('notes', 'finding information by concept instead of exact words',
mode => 'embed', k => 3) s
JOIN notes n ON n.id = s.id::bigint
ORDER BY s.rank;