What is a vector database?

Documents become points in space, and search becomes finding the nearest neighbors. The idea behind AI search, animated.

A vector database searches by meaning instead of matching keywords. First, an embedding model reads each document and turns it into a long list of numbers. Those numbers are coordinates: every document becomes a point in a high-dimensional space, and documents with similar meaning land close together.

When you ask a question, it gets embedded the same way and lands in that same space, right next to the documents that talk about the same thing. Answering your query is now geometry: find the nearest neighbors. That trick powers semantic search, recommendations, and the retrieval step in AI assistants (RAG).

Remember this

  • Embeddings turn text into coordinates; similar meaning sits close together
  • A query is embedded the same way and lands near its answers
  • Search by meaning = nearest-neighbor lookup in vector space

Got a different question? SeaThru generates a fresh video for any topic where systems talk or data structures move.

Ask your own question →

Keep learning