What Are Embeddings: From Words to Vectors
~12 min read
An embedding is a list of numbers that represents the MEANING of a piece of text — placed so that similar meanings end up close together in space, which is what makes semantic search possible.
What Are Embeddings: From Words to Vectors is a Pro topic
Sign in, then upgrade to Pro or Power to unlock this topic and the full AI Engineering curriculum.
Key points
- •An embedding is a fixed-length list of numbers (a vector) that represents a piece of text's MEANING, not its literal characters
- •Texts with similar meaning get placed close together in this numeric space — semantically related fruits cluster together, cities cluster elsewhere, entirely emerging from training rather than being manually assigned
- •Turning meaning into vectors converts a fuzzy human task (is this similar?) into a precise math problem (what's the distance between these two points?)
- •Real embedding spaces have hundreds or thousands of dimensions, not 2 or 3 — you can't visualize them, but distance still works the same way mathematically
- •This 'meaning as position' idea is the foundation for semantic search, recommendation, and RAG, where a query is embedded and compared to a document collection