Vector Database
Also known as: Vector store, ANN index
A database tuned for fast approximate nearest-neighbor search over millions of high-dimensional vectors.
A specialized database optimized for storing, indexing, and querying high dimensional embedding vectors using approximate nearest neighbor (ANN) algorithms like HNSW or IVF.
In practice
Picking the right index (HNSW, IVF, ScaNN) and recall-vs-latency knob is a standard senior-level RAG interview question.
How it compares
Embeddings are the data; vector databases are the storage and retrieval layer for them.
Related topics
Practice questions
Related terms
Retrieval-Augmented Generation (RAG)
Fetch relevant docs at inference time and stuff them into the prompt so the model can answer from real data.
Embeddings
Dense numeric vectors that capture meaning; close vectors = similar text.
HNSW (Hierarchical Navigable Small World)
A graph-based ANN index with log-time approximate search, excellent recall/latency trade-off.
Cosine Similarity
Compare two vectors by the cosine of their angle; the default similarity metric for embedding search.
Hybrid Search
Combine BM25 (keywords) + dense embeddings (meaning); better recall than either alone.