A numerical representation of text, image, or audio as a vector, positioned so similar inputs land near each other. Powers semantic search, clustering, and find-related-items features.
Definition: A numerical representation of text, image, or audio as a vector, positioned so similar inputs land near each other. Powers semantic search, clustering, and find-related-items features.
A numerical representation of text, image, or audio as a vector in high-dimensional space, where similar inputs end up close together. The math behind semantic search, thematic clustering, and "find related items" features. For research, embeddings power tools that group open-ended responses or interview quotes by meaning rather than exact wording. See also RAG and AI-assisted thematic analysis.
A technique that enhances LLM responses by first retrieving relevant information from a specific knowledge base, then using that information to ground the model's output.
An AI system trained on vast amounts of text to predict and generate human-like language. Best understood as a concept-transformation engine rather than a knowledge database.
A trained system that maps input to output through learned patterns. In research practice usually a large language model, but the term also covers image, audio, and multi-modal systems.