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.
↳ connected nodes
Tool Stack↳ linked
RAG Starter Stack
Minimum viable stack to ship a production RAG chatbot.
Dictionary↳ linked
Retrieval
Selecting the most relevant chunks for a query before generation.
Dictionary↳ linked
RAG (Retrieval-Augmented Generation)
Inject external knowledge into an LLM at query time.
Dictionary↳ linked
Agentic RAG
RAG where an agent decides what to retrieve, when, and from which source — instead of a single static query.
Dictionary↳ linked
Embedding
A numerical vector representation of text, image or audio that captures meaning for similarity search.
Dictionary↳ linked
Reranker
A second-stage model that reorders retrieved chunks for precision.