Glossary

Embedding

An embedding is a way of turning text into a list of numbers so a computer can measure how close two pieces of text are in meaning.

Computers do not understand words the way we do. An embedding turns a sentence into a long list of numbers that captures its meaning. Sentences that mean similar things get similar numbers. 'What time do you close?' and 'Closing time?' end up close together, even though they share almost no words.

This is what makes modern search feel smart. Instead of matching exact keywords, the system compares meanings. So a visitor can ask in Hinglish, in different words, or with a spelling mistake, and the right paragraph from your document can still be found. Embeddings are the quiet workhorse behind this.

You never see embeddings in fad.fyi, and you do not need to. You just feed files, links, text or Q&A. Behind the scenes, your fad works out which parts of your sources are closest in meaning to the visitor's question, and it answers from those parts only.