What are embeddings?
Embeddings are lists of numbers that represent the meaning of text, images or other data, so similar items sit close together and can be found by similarity search.
In more detail
An embedding model turns a sentence into a vector, often hundreds or thousands of numbers long. 'Reset my password' and 'I can't log in' land near each other even though they share no words. That lets a system search by meaning instead of by keyword. Embeddings power RAG, duplicate detection, clustering and recommendations. They are tied to the model that made them, so changing embedding models means re-embedding everything. They also blur exact identifiers: a search for invoice number INV-20417 works better in a plain keyword index, which is why most production search combines both.
Example
A support team embeds 40,000 past tickets. When a new ticket arrives, the system pulls the five most similar solved ones, so the agent can see how those were handled.