Models & Architecture
Embedding
A way of turning words, images, or other data into lists of numbers that capture their meaning, so a computer can compare them.
An embedding represents a piece of data as a point in a high-dimensional space of numbers, arranged so that similar things land close together. That lets a computer measure how related two sentences or images are by measuring the distance between their embeddings. Embeddings are the backbone of semantic search, recommendations, and retrieval-augmented generation.
Reference: Wikipedia: Embedding
Related terms
Vector Database
A database built to store embeddings and quickly find the items most similar in meaning to a query.
Semantic Search
Search that matches on meaning rather than exact keywords, so related ideas surface even with different wording.
Retrieval-Augmented Generation
A technique that looks up relevant documents and feeds them to a model so its answers are grounded in real sources.
Tokenization
The step that chops text into tokens before a model can process it.