IonBin
All pages
Search
Concept

Vector database

A vector database stores embeddings for similarity search. It can support semantic retrieval and RAG, but is not required for every project. Compare it with keyword search or a small context-based approach using actual token volume, permissions, retrieval quality and operating cost.

Verified Oct 18, 2026 Review by Apr 16, 2027 3 sources

What it is

IBM describes a vector database as one that stores, manages and indexes high-dimensional vector data, so it can run similarity search at scale. Implementations include these overlapping categories:

  • dedicated vector databases;
  • extensions to databases you may already run, such as pgvector, an open-source extension that adds vector similarity search to Postgres;
  • managed services, such as Cloudflare Vectorize.

IonBin names examples to explain the categories, not to rank them.

How it works

  1. Embed each document chunk and store the vector with its text and metadata.
  2. At query time, embed the question with a compatible embedding model and search for similar vectors.
  3. Pass the matching chunks to the model as context for its answer (RAG).

Benefits

  • Indexes can accelerate semantic search over large collections; benchmark latency and recall at your scale.
  • Metadata filters (date, customer, product) narrow the results.
  • Managed options reduce server operations; an extension can keep vectors beside existing database records.

Limits and risks

  • Adds a system to secure, update and pay for.
  • Retrieval quality depends on chunking and embeddings, not just the database.
  • Moving to an incompatible embedding space usually requires regenerating the corpus vectors. Plan migration, index costs and rollback.
  • Approximate indexes trade recall for speed. Metadata filters also need careful testing and are not a substitute for access control.
  • For small collections, evaluate simpler approaches first (see do I need a vector database?).

Best-fit stacks

Stack 08

Dev, web & IT

Design, code, host and ship sites and internal tools, with an AI coding agent doing most of the typing.

Agent compatibility

Not tool-specific. See Agent-ready for connector support by tool.

Levels come from each tool's recorded, sourced compatibility. How the levels work.

Sources

  1. What is a vector database? · IBMreference accessed Oct 18, 2026
  2. Vectorize docs · Cloudflareofficial accessed Oct 18, 2026
  3. pgvector · pgvector projectofficial accessed Oct 18, 2026

Practitioner views are restated in our words and labeled as views, not measured results. Product facts come from official sources dated above.

Suggest an edit

IonBin's wiki isn't user-edited. Corrections go to our Directory Curator, who checks them against primary sources before anything changes. Spot something wrong or out of date on “Vector database”? Email us with a link to a primary source.

Suggest an edit by email or write to contact@ionbin.com