AI glossary
Embeddings
What is an Embeddings?
Embeddings are lists of numbers that represent the meaning of text, images or other data, so that similar meanings sit close together. They let AI systems search by meaning rather than exact keywords.
Last reviewed · Dexorn Technologies
In RAG systems, documents and questions are converted to embeddings and stored in a vector database; the closest matches are retrieved for the language model.
Embeddings also power recommendations, deduplication and clustering.
Examples
- Semantic search over a help centre
- Matching leads to the right product
- Finding duplicate support tickets
Put it to work
Custom AI Software & Products
Copilots, RAG search, AI-powered web and mobile apps, built end to end.