Framework & Tool
Vector Database
Database optimised for storing and querying high-dimensional embedding vectors.
Definition
Vector databases index dense embeddings via approximate-nearest-neighbour algorithms (HNSW, IVF, ScaNN) and serve top-k similarity queries with low latency. They are the storage layer for RAG, recommendation systems and any embedding-driven workload.
Common use cases
- RAG
- Semantic search
- Recommendations