456
Dictionary

Vector Index

A data structure that makes nearest-neighbor search fast.

1 min readupdated 2026-07-04

/ quick answer

A vector index (HNSW, IVF, ScaNN) organizes embeddings so you can find the top-k neighbors in milliseconds instead of scanning every row. Trade-off: build time and memory. A data structure that makes nearest-neighbor search fast.

A data structure that makes nearest-neighbor search fast. A vector index (HNSW, IVF, ScaNN) organizes embeddings so you can find the top-k neighbors in milliseconds instead of scanning every row. Trade-off: build time and memory. In practice: pgvector's HNSW index on a 1M-row table returns top-10 neighbors in ~5ms. This dictionary node is part of the Onexial knowledge graph and links to related concepts, workflows and tools below.
Definition
A vector index (HNSW, IVF, ScaNN) organizes embeddings so you can find the top-k neighbors in milliseconds instead of scanning every row. Trade-off: build time and memory.
Example
pgvector's HNSW index on a 1M-row table returns top-10 neighbors in ~5ms.
Related Tool Stacks
/ frequently asked

What is Vector Index?

A vector index (HNSW, IVF, ScaNN) organizes embeddings so you can find the top-k neighbors in milliseconds instead of scanning every row. Trade-off: build time and memory.

What is an example of Vector Index?

pgvector's HNSW index on a 1M-row table returns top-10 neighbors in ~5ms.

Why does Vector Index matter for AI and automation?

A data structure that makes nearest-neighbor search fast. It connects to the workflows, prompts and tool stacks linked on this page, so you can move from definition to execution without leaving Onexial.