01 / The Model
Embedding
A way of turning text into a list of numbers so that similar meanings sit close together. It is how a system finds the right passage without matching exact words.
How you’ll hear it
“How did it find “cancel” when I typed “end my contract”?”
“Embeddings. It matches on meaning, not wording.”
Avoid
Assuming semantic search is always right. Similar meaning is not the same as the right answer.
The longer version
An embedding represents a piece of text as numbers arranged so related ideas land near each other. Embeddings power semantic search, recommendations and the retrieval behind AI assistants. They make finding information more forgiving, and they can still surface passages that sound related but do not answer the question.