analytics-dictionary / term / ai
Embeddings
Embeddings are numerical representations of text or other data that capture meaning, so similar things are close together.
Written by Reflective Data experts · updated Oct 5, 2026
They make semantic search possible: finding documents that mean the same thing as a question, even if they share no words. Embeddings are the backbone of most RAG systems.
They are usually stored in a vector database or a vector-enabled search index.
related
Retrieval-augmented generation (RAG)Vector database
// how we can help
We build company brains, agent harnesses and AI bots on top of data you can trust. AI services → · The data platform behind it