Embedding

A numerical representation of text (or images, audio, etc.) as a list of numbers called a vector. Embeddings capture semantic meaning: text with similar meaning produces vectors that are mathematically "close" to each other. "The cat sat on the mat" and "A feline rested on the rug" share almost no words but produce embeddings that are practically neighbors in vector space.

If that sounds abstract: imagine plotting every sentence ever written on a giant map, where sentences about similar things cluster together. The numbers are coordinates on that map. That's an embedding.

Why it matters for writers: Embeddings are the foundation of semantic search. Instead of matching exact keywords, systems compare query embeddings against document embeddings to find conceptually similar content. This is how AI-powered search, recommendation engines, and RAG pipelines work under the hood. See Retrieval-Augmented Generation for how embeddings get used in practice, and for why the way you structure your documents affects how well they get found.

Related terms: Vector Store · Similarity Search · Chunking