High-dimensional numeric representations that capture the semantic meaning of text, images, or other data. Elements with similar meaning end up close to each other in vector space, enabling similarity search.
In AIF-C01 (Domains 2 and 3) they're the foundation of RAG and semantic search. Amazon Bedrock offers embedding models (e.g., Titan Embeddings) to convert documents into vectors that are then stored in a vector database. In GENAI-L (Domain 3) the equivalent is Vertex AI's Embeddings API, used together with Vertex AI Vector Search for RAG.
Embeddings is a concept that can show up on the exam. Check the full guide to see it in context.