What is a vector database?
A vector database stores data as embeddings, numerical vectors that capture meaning, and finds items that are most similar to a query vector. It powers semantic search, recommendations and retrieval-augmented generation by finding relevant content even when wording differs.
How it works
- Content is converted to embeddings.
- Vectors are indexed.
- A query is embedded.
- The database returns nearest neighbors.
Vector database vs knowledge graph
| Vector database | Knowledge graph | |
|---|---|---|
| Stores | Similarity | Relationships |
| Best for | "Find similar content" | "How are these connected?" |
Many enterprise AI systems use both.
