Glossary · 4 · Grounding: content, retrieval and knowledge
Embedding
Also known as: Vector embedding, Semantic search
An embedding is a list of numbers — a vector — that represents the meaning of a piece of text, an image or other data, produced by an embedding model so that items with similar meaning end up close to each other in vector space.
- Intermediate
- Technical writers
- Developers
In one sentence
Embeddings explained: turning text into vectors that capture meaning — the basis of semantic search and retrieval-augmented generation.
Example
“Replace the filter cartridge” and “How do I change the filter?” use different words, but their embeddings are close, so a semantic search finds the right topic.
Explained in context
Context cards connect this term with others to answer one question. Also in British English and German.
- Semantic platform operator: the functional roleWho runs the graphs, the inference, the semantic view and the vector index — and keeps them in step with the approved model?UKDeutsch
- From knowledge graphs to adaptive semantics: the pathway mapHow does a DITA and iiRDS knowledge architecture get from governed semantics to a model that learns from AI agent use — and who does what on the way?UKDeutsch
Why it matters on your learning path
- Technical writers: Embeddings are why AI search finds content by meaning, not keywords — but consistent terminology still improves results.
- Developers: Choose an embedding model for your languages and domain; re-embed content when you switch models.