Glossary
Embeddings
Dense numerical vector representations of text, images or audio that capture semantic similarity.
Definition
An embedding is a fixed-length vector of floating-point numbers (typically 768 or 1536 dimensions) produced by an embedding model — usually a transformer trained on contrastive objectives. Two pieces of text with similar meaning produce embeddings that are close in vector space. Embeddings power semantic search, recommendation systems, clustering, deduplication and the retrieval step in RAG.
Why it matters
Embedding-model choice and re-indexing strategy are easy to underestimate. Switching embedding models means re-embedding the entire corpus. Plan for that upgrade path from day one.
See also
RAG (Retrieval-Augmented Generation)
AI pattern where an LLM generates answers from documents retrieved at query time, rather than from training data alone.
Read →Vector Database
A database optimised for storing and querying high-dimensional vectors (embeddings) by similarity.
Read →LLM (Large Language Model)
A neural-network model trained on large text corpora to generate, summarise, classify and reason over text and code.
Read →Working on Embeddings?
Our AI Developmentteam ships this in production. Tell us your scope and we'll share a written recommendation and fixed quote within 48 hours.
AI Development →