Technical

Embedding

A dense vector representation of text in a high-dimensional space where semantic similarity corresponds to geometric proximity. Used for search, clustering, and recommendation.

Explained at five levels

Level 1

Turning words into secret number codes so the computer can understand how similar or different things are.

Level 2

A way of converting text into numbers that capture meaning — similar words get similar numbers, so the AI can understand relationships.

Level 3

A dense vector representation of text in a high-dimensional space where semantic similarity corresponds to geometric proximity. Used for search, clustering, and recommendation.

Level 4

A learned mapping from discrete tokens or passages to continuous vectors in ℝⁿ, where cosine similarity approximates semantic relatedness. Fundamental to vector search, RAG retrieval, and representation learning.

Level 5

A function f: X → ℝⁿ mapping inputs to a metric space where the distance function approximates a target similarity — trained via contrastive loss, producing representations useful for nearest-neighbor retrieval, clustering, and downstream transfer.

Definitions are educational summaries. Terminology can vary by source and context.

Sources