AI Vocabulary · 03 Working with AI
What is Embeddings?
Text turned into lists of numbers that capture meaning. The basis of semantic search and RAG.
An embedding is a list of numbers that represents the meaning of a piece of text. Texts with similar meaning get similar numbers, even if they use different words: "cancel my contract" and "how do I end my subscription" end up close together.
This makes search by meaning possible. Documents are converted into embeddings once and stored, often in a so-called vector database. A question is converted too, and the closest passages are found. That is the retrieval step of RAG.
Why it matters for you
If your AI search finds the wrong documents, the embeddings and how documents were split into pieces are worth checking. Good retrieval is often the hidden difference between a useful knowledge assistant and a frustrating one.
Own it
Embeddings are derived from your data. Know where they are stored, who hosts them, and whether you can export and rebuild them with another provider.
Where it comes from
The idea goes back to linguistics: in the 1950s, J. R. Firth argued that you can understand a word by the words it appears with, a principle known as distributional semantics. Neural networks turned that into numbers. Google's word2vec in 2013 made word embeddings fast and famous, including the much-cited example that king minus man plus woman lands close to queen (Mikolov et al.).
Related
Your AI Learning Hub
Learn the whole AI Vocabulary, step by step, and build with it. Build it. Own it.