AI Fundamentals
Embeddings
Numerical representations of text, images, or other data that capture semantic meaning in a format AI can process.
Embeddings are dense numerical vectors that represent the meaning of text, images, or other data in a format that AI systems can process. Created by specialized models like OpenAI's text-embedding-ada-002, embeddings capture semantic relationships—similar concepts have similar vector representations. A 1,536-dimensional embedding can encode nuanced meaning, enabling applications like semantic search, clustering, and recommendation systems. Embeddings are fundamental to RAG systems, where they enable finding relevant documents based on meaning rather than keywords.