Product

An embedding maps text or media into a dense vector so similarity and retrieval can be computed geometrically.

machine-learning

A technique for transforming graph-structured data into a continuous vector space while preserving its properties.

Inference

RAG retrieves relevant passages (often via embeddings) and conditions generation on them—reducing reliance on parametric memory alone.

Data

Semantic search retrieves by meaning (often via embeddings), not only keyword overlap.

Safety

A vector is a fixed-length array of numbers; embeddings represent meaning as vectors for search and clustering.

Data

A database or engine optimized for similarity search over embedding vectors, typically with metadata filters and hybrid lexical+vector queries for production RAG.