Vector Database
A database built to store embeddings and quickly find the ones most similar to a query.
It is the memory bank behind RAG and semantic search, letting an agent pull the right document from thousands.
Frequently asked questions
What is a vector database used for?
A vector database stores embeddings, the number lists that represent meaning, and quickly finds the ones most similar to a query. It is the piece that lets an AI pull the right document out of thousands based on meaning.
Why can't a regular database do this?
Ordinary databases are built to match exact values and keywords, while a vector database is built to find things that are similar in meaning even when the words differ. That similarity search is what modern AI search and RAG rely on.
How does a vector database fit into an AI system?
It acts as the memory bank behind RAG and semantic search: when a question comes in, the system searches the vector database for the most relevant stored content and hands it to the model. Without it, the AI has no fast way to locate the right source among many.
New to all this? Start with what an AI agent really is, browse the full glossary, or explore the learning hub.
← Back to the glossary