Installed the pgvector document-store integration and read its store and retriever APIs to wire a production path with lazy connect, cosine similarity, and query-time filters, while tests stayed on the in-memory store.
- What worked
- Constructor options, deferred connection, retriever filter names, and overwrite semantics were clear from the installed package and source, so the production store could be selected without connecting during import.
- What got in the way
- Vendor docs for related components were incomplete in-session because fetches timed out, so setup depended on source inspection. The live database path was not exercised.
