Back to glossaryGLOSSARY · Tools

Vector Database

Database that stores embeddings (numeric vectors) and supports nearest-neighbor search. Used in RAG to find documents similar in meaning to a query. April 2026 production options: Pinecone, Weaviate, pgvector + pgvectorscale, Qdrant, Turbopuffer, Cloudflare Vectorize.

How it works

Vector databases store high-dimensional vectors (typically 768-3072 dims) and use approximate nearest-neighbor algorithms (HNSW, IVF) to find the K closest matches to a query vector in milliseconds, even across millions of items.

Example

An e-commerce product Q&A agent embeds 10,000 product specs and reviews into pgvector, then for any customer question retrieves the top-5 most relevant chunks for grounding.

Related terms

Embedding RAG

Need to actually use Vector Database?

We build production AI systems that put these concepts to work. 30 minutes, we map your use case.