GlossaryIndexes
Vector database
A database optimized for storing and querying high-dimensional embedding vectors.
Vector databases store embeddings and serve approximate-nearest-neighbor (ANN) queries - given a query vector, return the K most similar stored vectors fast. Pinecone, Weaviate, Qdrant, Milvus, Chroma, and pgvector are the popular options. Choosing one depends on scale, metadata filtering needs, and whether you want self-host vs managed.