What is Embedding?
A mathematical representation of a text's meaning that enables semantic comparison.
// Explanation
An embedding converts text into a vector of numbers (a list of coordinates) that captures semantic meaning. Two texts that are similar in meaning will have close vectors, even if they use different words. It's the foundation of semantic search, recommendations, and RAG.
// Example
'Car' and 'automobile' have very close embeddings even though they're different words. 'Car' and 'pizza' have very distant embeddings. That's how semantic search works.