Glossary of Terms

Key concepts in the world of AI search and RAG.

RAG (Retrieval-Augmented Generation)

A framework for retrieving relevant facts from an external knowledge base (like your website) to ground Large Language Models (LLMs) in accurate, up-to-date information.

Vector Database

A type of database that stores data as multi-dimensional vectors (embeddings) instead of rows and columns, enabling fast similarity-based search.

Semantic Search

A search technique that understands the intent and contextual meaning of a query, rather than just matching literal keywords.

Embedding

A mathematical representation of a piece of text (or image) as a vector of numbers, capturing its semantic meaning.

Hallucination

A phenomenon where an AI model generates factually incorrect or nonsensical information. RAG is used to minimize hallucinations.