Notes on embeddable vector search, ANN indexes, and shipping retrieval in Rust.https://memista.skelfresearch.com/en-ushttps://memista.skelfresearch.com/blog/persistence-patterns-vector-indexes/https://memista.skelfresearch.com/blog/persistence-patterns-vector-indexes/An in-memory vector index is easy. An in-memory vector index that survives a crash, a deploy, and a schema change is the actual work.Fri, 29 May 2026 00:00:00 GMThttps://memista.skelfresearch.com/blog/hnsw-vs-flat-embeddable/https://memista.skelfresearch.com/blog/hnsw-vs-flat-embeddable/A flat index is honest. HNSW is fast. For embeddable workloads, the choice is rarely either-or — it's about where in your data's life each one earns its keep.Thu, 21 May 2026 00:00:00 GMThttps://memista.skelfresearch.com/blog/when-you-dont-need-a-vector-db/https://memista.skelfresearch.com/blog/when-you-dont-need-a-vector-db/Most retrieval workloads fit on one box. Here is how to know yours is one of them — and what 'no vector DB' actually buys you.Tue, 12 May 2026 00:00:00 GMT