JR AI Intelligence · Concept
Retrieval-Augmented Generation (RAG)
Pattern that retrieves external documents and conditions a generative model on them.
RAG combines a retriever with a generator so answers can cite material outside the model’s fixed parameters. Job Resiliens teaches RAG as an Academy capability node linked to vector databases and advanced retrieval patterns — not as a vendor pitch.
In practice, teams use RAG when facts change faster than model training cycles: policy docs, product catalogs, internal wikis. The graph links this concept to related learning topics and use cases such as enterprise RAG. We do not invent benchmark scores; verify claims against the primary paper and your own evals.
Primary source: Lewis et al. (2020) Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Graph entity page · Explore Universe · Academy · Open in app