pgvector HNSW on a small VPS: how much RAM?
Size a pgvector HNSW index before you build it: the byte arithmetic, maintenance_work_mem, ef_search, and what to do when it stops fitting in RAM.
#pgvector
Filtering by topic #pgvector · clear
Agent memory types and what they cost
Semantic, episodic and procedural agent memory in one table, then the half nobody writes: what each type costs to store and to re-embed on a VPS.
Running a vector database on your VPS
Your app and your index sit on the same VPS, so latency is not the problem. Compare pgvector, Qdrant, Chroma and brute force, and size the RAM correctly.
Build a RAG pipeline on your own VPS
Chunk, embed, store and retrieve on one VPS. A pgvector schema, HNSW sizing, a local embedding model, and the SQL that proves retrieval works.