Vector Database
Technical InfrastructureA specialized database optimized for storing and searching embedding vectors — the backbone of semantic search and RAG systems.
A vector database stores numerical representations (embeddings) of content and enables fast similarity search. Instead of querying 'find documents containing the word X,' you query 'find documents whose meaning is closest to this query.'
Popular vector databases include Pinecone (fully managed), Weaviate (open-source), Chroma (lightweight, popular for prototyping), Qdrant, and Milvus. Traditional databases like PostgreSQL also offer vector extensions (pgvector).
Vector databases are essential infrastructure for RAG pipelines. You embed your documents, store the vectors in a vector database, and when a user asks a question, the database finds the most semantically relevant documents in milliseconds — even across millions of entries.
Real-World Example
When Perplexity instantly finds relevant sources for any question it's querying a massive vector database — matching your query's meaning against millions of pre-embedded web pages.
Related Terms
More in Technical Infrastructure
FAQ
What is Vector Database?
A specialized database optimized for storing and searching embedding vectors — the backbone of semantic search and RAG systems.
How is Vector Database used in practice?
When Perplexity instantly finds relevant sources for any question it's querying a massive vector database — matching your query's meaning against millions of pre-embedded web pages.
What concepts are related to Vector Database?
Key related concepts include Embedding, RAG (Retrieval-Augmented Generation), Semantic Search. Understanding these together gives a more complete picture of how Vector Database fits into the AI landscape.