Database Engineering

Vector Databases & Retrieval

Embeddings, cosine similarity, ANN and HNSW, metadata filtering, hybrid search — the storage layer under RAG.

Vector Search: Embeddings, Similarity and ANN

An embedding turns text into a point in a high-dimensional space where nearby means similar; vector search finds the k nearest points to a query, and the whole engineering problem is doing that sublinearly without losing too much recall.