hnsw-vector-search

Builds HNSW vector indexes in SurrealDB and queries them with the KNN nearest-neighbor distance operator, covering metric and storage-type selection, index construction settings, and conversion of raw distances into thresholded similarity scores. Use when the user wants semantic search, RAG retrieval, embedding lookups, or recommendation matching in SurrealDB, or asks about HNSW index parameters, cosine versus euclidean distance, or nearest-neighbor search effort. Not for generating embeddings, choosing an embedding model, other vector databases, or keyword full-text search.

Version

v1.0.2

Size

14 KB

Updated

2026-10-10

Your client verifies the signature before reading. This explicit manual read is available on every plan. Free automatically loads five chosen skills; paid plans automatically load relevant skills across the library.