Re:Building AI Memory at 10M+ Nodes: Architecture, Failures,...
by emschwartz on Tuesday December 30, 2025 @12:52PM
(#46435949)
How did you decide on pgvector versus a dedicated vector database? I’m curious because it didn’t sound like your architecture included Postgres before (though maybe I’m wrong about that).
[ Parent
| on HN ]
Re:Building AI Memory at 10M+ Nodes: Architecture, Failures,...
by Manik_agg on Wednesday December 31, 2025 @12:27AM
(#46441644)
Hey we already had PostgreSQL so no new infrastructure to manage, it was easy way to see if vector database change has any value.
It also has good enough performance - handles 10M vectors with HNSW indexes adequately
open source - leverages existing infrastructure
for future migration. we've created a vector service, easy to swap later if needed