Vector Embedding
A high-dimensional numerical representation of text, image, or other content that places semantically similar items close together in vector space, enabling similarity search and clustering.
How it works
A vector embedding is the output of an embedding model: typically a 384, 768, or 1536-dimensional floating-point array that captures the semantic meaning of a piece of content. Documents about the same topic produce embeddings that are close together by cosine similarity, even when they share no exact keywords. Embeddings are the substrate that makes RAG, semantic search, and document classification work. For UK enterprise deployments, the choice of embedding model matters: open-source models like BGE, E5, and Nomic can be run on private infrastructure with no third-party data export, while proprietary embeddings from OpenAI or Cohere require sending content to those providers. For regulated firms, the open-source on-premise route is usually the only viable architecture.
Related terms
Vector Database
A database optimised for storing and querying high-dimensional vector embeddings using approximate nearest-neighbour algorithms, used as the retrieval layer in RAG systems and semantic search.
Retrieval-Augmented Generation (RAG)
An architecture pattern that grounds language model outputs in retrieved documents from a private corpus, reducing hallucination and enabling answers based on the firm's own data rather than the model's training set.
Semantic Search
Search that ranks results by meaning rather than exact keyword match, using vector embeddings to retrieve semantically-similar content even when no terms overlap.
Want to see this technology in action?
Book a Discovery Call