AI
RAG (Retrieval-Augmented Generation)
A pattern where a language model is given retrieved documents at inference time to ground its response. The Vantage AI agent uses RAG against the workspace knowledge base.
Definition
Answer
What does "RAG (Retrieval-Augmented Generation)" mean?
A pattern where a language model is given retrieved documents at inference time to ground its response. The Vantage AI agent uses RAG against the workspace knowledge base.
Related terms
- Knowledge Base — Vantage's repository of uploaded specs, SOWs, and strategy documents.
- AI Grounding — The practice of constraining an AI response to a known set of source documents.