Embeddings

Numerical representations (high-dimensional vectors) that capture the meaning of a piece of text. The core idea: texts with similar meanings sit close together in this vector space, even when they don't share the same words.

This is what makes semantic search possible — you search by meaning, not by exact term matching. The choice of embedding model should match the domain (legal, biomedical, financial), because a generic model may not separate niche concepts well.