A specialized database optimized for storing and querying high-dimensional vector embeddings for similarity search. Vector databases enable efficient similarity search across large embedding spaces. They are commonly used in retrieval pipelines for AI applications. For more on AI system architectures, see our systems overview.
Vector databases enable efficient semantic search at scale, forming the retrieval layer in RAG architectures.
AI systems store document embeddings in vector databases and query them to find semantically similar content for retrieval-augmented generation.
Vector databases allow AI systems to quickly find relevant documents among millions of entries.