Vector Database

A database optimized for storing and querying high-dimensional vector embeddings used in similarity search and AI applications.

Traditional databases excel at exact matches and range queries. Vector databases are built for a different problem: finding items that are similar to a query vector. They store embeddings — numerical representations of text, images, or other data — and support approximate nearest neighbor search at scale.

How Vector Search Works: documents are converted to dots in 3D vector space, enabling similarity-based retrieval.

When you embed a user query and search for the closest document embeddings, you're doing semantic retrieval: matching by meaning, not keywords. Vector databases like Pinecone, pgvector, and Weaviate optimize for this. They use indexing structures (HNSW, IVF) to make similarity search fast even with millions of vectors. Essential for RAG, recommendations, and any application that needs "find things like this."

How Vector Search Works: documents are converted to dots in 3D vector space, enabling similarity-based retrieval.