Skip to content
ReviewRamble

The weekly brief

AI, reviewed, in your inbox.

  • New reviews of tools, models, MCP servers and repos, with the verdict up front
  • Re-checked prices and ratings when something changes
  • New analysis pieces as they are published

Models, agents, MCP servers and the tools actually worth your time.

One email a week. Unsubscribe with the link in any brief. How we use your email

Vector database

A vector database stores embeddings alongside their source records and finds the stored vectors closest to a query vector, usually with an approximate index so search stays fast across millions of items.

Also called: vector store, vector DB

By Divya Sharma · Checked Nov 15, 2026 · How we review

A normal database answers "find rows where status = open". A vector database answers "find the items most similar to this one", where similarity is measured between embeddings. It is the storage layer behind most retrieval-augmented generation systems, semantic search and recommendation features.

What it does

It holds each vector with an ID and metadata such as source, date or owner. It builds an index, often HNSW, for approximate nearest neighbor search. It also handles inserts, updates and deletes, and lets you combine similarity with metadata filtering.

Options

Some products are built only for vectors, such as Pinecone, Qdrant and Milvus. Others add vector search to a database you may already run, such as pgvector for Postgres. Libraries like Faiss provide the index without the database parts, so you handle storage, updates and filtering yourself. The vector databases guide compares them.

How it differs from a vector index

An index is the data structure that makes search fast. A database wraps that index with durability, access control, replication and an API. For a prototype with a few thousand vectors, an in-memory index or even a brute-force scan is often enough.

Limits

Results are approximate, so a small share of true neighbors can be missed. Many products also support keyword or hybrid search, which helps with exact terms that embeddings handle poorly.

Related terms

HNSW
HNSW (hierarchical navigable small world) is a graph-based index for approximate nearest neighbor search. It links vectors to their neighbors across several layers, so a search can hop quickly toward the closest matches.
Embedding
An embedding is a list of numbers (a vector) that represents a piece of text, an image or other data, produced so that items with similar meaning end up with vectors close together.
Approximate nearest neighbor search
Approximate nearest neighbor (ANN) search finds vectors close to a query without checking every stored vector. It gives up a guarantee of the exact best match in exchange for much faster search on large collections.
Vector search
Vector search finds items by comparing their embeddings to the embedding of a query and returning the closest ones, so results match on meaning rather than on shared keywords.
Metadata filtering
Metadata filtering limits a search to items whose stored attributes, such as date, author, language or access group, match given conditions, alongside or before ranking them by vector similarity.
Hybrid search
Hybrid search runs a keyword search and a vector search on the same query and merges the two ranked lists, so results can match on exact words as well as on meaning.

Sources