Home · Glossary · Embedding
Enterprise AI glossary · Generative AI & LLMs

Embedding

A dense numeric vector representation of a piece of text (or image, or audio) such that semantically similar inputs produce vectors close in the embedding space.

Definition

What Embedding means in practice

An embedding is a fixed-length vector — typically 384 to 1024 dimensions — produced by an embedding model from a piece of text. The geometric property that makes embeddings useful is that semantically similar inputs produce vectors close in the embedding space, so a similarity search becomes a nearest-neighbour lookup. In retrieval-augmented generation, document chunks are embedded once at ingestion time, query embeddings are computed at query time, and the nearest chunks are passed to the LLM as context. For sovereign deployments MindMap uses nomic-embed-text for English-primary corpora and BGE-M3 for multilingual workloads — both open-weights and locally deployable.

Go deeper
Generative AI for enterprise →

All 62 terms, in plain language

Sovereign AI, RAG, agentic AI, IDP, MLOps and the regulations that shape enterprise AI.

Browse the glossary →Talk to an engineer →