You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
docs(docker): use pgvector image for Postgres compose
Plain postgres:17 cannot load the vector extension required for semantic
search (#830). Switch to pgvector/pgvector:pg17 and document the requirement.
Co-authored-by: Cursor <cursoragent@cursor.com>
Copy file name to clipboardExpand all lines: docs/semantic-search.md
+1Lines changed: 1 addition & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -263,6 +263,7 @@ The sqlite-vec extension is loaded per-connection. Vector tables are created laz
263
263
### Postgres (cloud)
264
264
265
265
-**Vector storage**: [pgvector](https://github.com/pgvector/pgvector) with HNSW indexing
266
+
-**Local Docker**: use `docker-compose-postgres.yml` (`pgvector/pgvector:pg17`). Plain `postgres:17` lacks the extension; run `CREATE EXTENSION IF NOT EXISTS vector;` on any external instance before first migration.
266
267
-**Chunk metadata table**: Created via Alembic migration (`search_vector_chunks` with `BIGSERIAL` primary key)
267
268
-**Embedding table**: `search_vector_embeddings` created at runtime (dimension-dependent, same pattern as SQLite)
268
269
-**Index**: HNSW index on the embedding column for fast approximate nearest-neighbour queries
0 commit comments