How engines work
Embedding
An embedding is a numeric representation of a piece of text that places similar meanings close together. Embeddings let a system match a question to relevant passages even when they share no words.
In more detail
Practically, this means writing naturally about a subject works better than repeating an exact phrase — meaning is what gets matched, not the string.
Guides that cover this
Related terms
Vector search
Vector search finds documents by comparing embeddings rather than matching keywords, retrieving passages whose meaning is close to the question. It is the retrieval method behind most answer engines.
Semantic search
Semantic search retrieves results by meaning rather than by exact wording, so a page can be returned for a question that shares none of its words. It underpins how answer engines find material to answer from.
Retrieval-augmented generation
Retrieval-augmented generation is when a model searches for relevant documents and writes its answer from what it finds, rather than from training alone. It is why a page published this week can appear in an answer today.
Ready to Dominate AI Search?
Get started now
Allswap