Concept
aka vector embedding
aka embedding vector
Embedding
Dense numeric vector that represents text, an image, or other input in a learned semantic space.
Definition
Embeddings map discrete inputs (words, sentences, images) into a continuous high-dimensional vector space where semantically similar items lie close together. They power semantic search, retrieval-augmented generation, clustering, and recommendation. Modern embedding models output vectors of 256 to 4096 dimensions.
Common use cases
- Semantic search
- RAG
- Clustering
Related models
voyage
text-embedding-3-large