← Back to the A-Z glossary
AI glossary · P1

Vector database

A vector database stores embeddings and finds the texts closest to a question.

RAG 4 min read Updated 2026-05-22
— Definition

Vector database, in plain words

A vector database stores embeddings and finds the texts closest to a question.

Connect the vector database, embeddings, and semantic search.

A concrete example

You store each PDF excerpt as a vector, then search for the excerpts closest to the question.

Why it matters

It makes search fast once you have a lot of documents.

You see it in Pinecone, Qdrant, Weaviate, Supabase pgvector, or document-chatbot architectures.

Don't mix it up with

Embedding: An embedding turns a piece of text into a list of numbers so you can compare its meaning with other texts.

RAG: RAG lets an AI answer using documents pulled up at the moment you ask the question.

Common mistakes

  • Using a vector database for three simple documents.
  • Forgetting metadata like date, source, or access rights.
  • Believing it replaces a regular database.

Quick checklist

  • First I check whether the word names a concept, a tool, a risk, or a metric.
  • I tie it to a concrete case: You store each PDF excerpt as a vector, then search for the excerpts closest to the question.
  • I keep the main trap in mind: Using a vector database for three simple documents.

Quick questions

What is Vector database in AI?

A vector database stores embeddings and finds the texts closest to a question.

Where will I run into Vector database?

You see it in Pinecone, Qdrant, Weaviate, Supabase pgvector, or document-chatbot architectures.

Which word should I read next?

Start with Embedding, RAG, Chunking.

Want to keep going in order?

Head back to the full glossary, search a word, then open only the pages that deserve more than a short definition.

Open the AI glossary