RAG & Search
Retrieval, embeddings, vector search and grounding.
Embeddings
An embedding is a dense vector produced by a model that maps content into a space where distance corresponds to semantic similarity.
Knowledge Base
An AI knowledge base is a managed corpus of trusted documents that a model retrieves from at query time to produce grounded, source-backed answers.
Retrieval-Augmented Generation (RAG)
Retrieval-Augmented Generation is a pattern in which relevant documents are retrieved from an external source and injected into an LLM's prompt so the model can answer with grounded, up-to-date, private information.
Semantic Search
Semantic search is retrieval where relevance is judged by conceptual similarity between the query and candidate documents, not by literal keyword overlap.
Vector Search
Vector search is a retrieval technique that ranks results by similarity between numeric embeddings, enabling meaning-based (semantic) matching rather than lexical matching.