Embedding
A way of turning text into a list of numbers that captures its meaning, so a computer can measure how similar two pieces of text are.
Embeddings power search, recommendations, and RAG. They are how AI finds "related" things by meaning, not keywords.
Frequently asked questions
What is an embedding, without the jargon?
An embedding turns a piece of text into a list of numbers that captures its meaning, so a computer can measure how similar two texts are. It is how software compares ideas by meaning rather than by matching exact words.
How does AI find related things by meaning instead of keywords?
Embeddings make it possible: because similar meanings produce similar numbers, the system can find content that is related even when the wording is completely different. That is what powers semantic search and recommendations.
Where do embeddings show up in tools I might use?
They quietly power search, recommendations, and RAG systems that answer questions about your documents. Any time a tool finds relevant results that do not share the exact keywords, embeddings are usually behind it.
New to all this? Start with what an AI agent really is, browse the full glossary, or explore the learning hub.
← Back to the glossary