What Is an Embedding in AI? Vectors and RAG
AI-generated summary An embedding in AI is a numerical vector representing text or other data in a mathematical space and machine learning models use vector embeddings to measure relatedness between concepts, power semantic search, and retrieve relevant context in RAG systems. OpenAI says its third-generation embedding models set default output lengths at 1536 dimensions for text-embedding-3-small and 3072 dimensions for text-embedding-3-large while developers can call text-embedding-3-large with dimensions set to 1024, trading a small amount of accuracy for compatibility and smaller storage footprints.