Vector Database
A database optimized for similarity search over embedding vectors.
What is Vector Database?
A vector database is the storage layer behind RAG. In a private deployment, it sits next to the documents it indexes — not in a separate vendor tenant — so retrieval, permissions, and audit live in one boundary. See Vector Database and Private RAG.
Why it matters for on-premise & regulated AI
Your vector database is a compressed copy of your most sensitive documents — embeddings can be partially inverted back to text. Hosting it as a managed cloud service means your knowledge base lives outside your boundary regardless of where the LLM runs. Self-hosted vector stores (pgvector, Qdrant, Milvus) keep the index under the same controls as the source documents, which is why on-prem RAG architectures default to them.
Read the full guide: Vector Database — in-depth article →
Related terms
Putting Vector Database to work?
VDF AI runs governed AI agents on your own infrastructure — on-premises, sovereign cloud, or air-gapped. Book a working session to map the architecture.
Talk to VDF AI