Vector databases solve a hard problem: nearest-neighbor search in high-dimensional space at scale. A traditional database can find 'all rows where city = Tel Aviv' in milliseconds, but it can't find 'the 10 most semantically similar documents to this query.' Vector DBs use approximate nearest neighbor (ANN) algorithms (HNSW, IVF, ScaNN) that trade tiny accuracy for huge speed gains. The 2026 landscape: Pinecone (managed, dev-friendly), Weaviate (open-source, feature-rich), Postgres pgvector (in-place if you already use Postgres), Qdrant, Chroma. For most apps under 10M vectors, pgvector is enough; above that, dedicated vector DBs justify their cost in latency and operational simplicity.
GLOSSARY
What is Vector Database?
A database optimized for storing and searching embeddings — finding the nearest vectors to a query vector in milliseconds, even across billions of records.
RELATED TERMS
Embedding
A vector representation of text, image, or audio — a list of numbers that captures the semantic meaning, enabling 'find similar' searches.
RAG (Retrieval-Augmented Generation)
A technique that lets an LLM answer questions about information it wasn't trained on — by retrieving relevant documents at query time and stuffing them into the prompt.
Back to the AI Glossary