Glossary
Embeddings
A way of turning text, images, or other data into lists of numbers that capture meaning, so a computer can measure how similar two things are.
An embedding is a numeric fingerprint of a piece of content. Things that mean similar things end up with similar numbers, so 'cancel my plan' and 'how do I end my subscription' land close together even though they share no words.
This is what makes modern search feel smart. Instead of matching keywords, you compare embeddings to find the closest matches by meaning, which is the first step in most retrieval and recommendation systems.
How we use it
We use embeddings to power semantic search and the retrieval layer behind grounded chatbots, so users find the right answer even when they don't use the exact wording.
Get in touch
Want to put this into practice?
If this concept is relevant to something you're building, a short note is the fastest way to get practical help.