AI Glossary · Search & RAG
RAG (Retrieval-Augmented Generation)
Fetching relevant documents at query time and passing them to the model so answers cite trusted sources instead of relying on parametric memory.
Definition
What is RAG (Retrieval-Augmented Generation)?
RAG (Retrieval-Augmented Generation) is fetching relevant documents at query time and passing them to the model so answers cite trusted sources instead of relying on parametric memory.
- Category
- Search & RAG
- Glossary set
- 8 related terms
- Audience
- Enterprise AI leaders
Why does RAG (Retrieval-Augmented Generation) matter in enterprise AI?
RAG (Retrieval-Augmented Generation) matters in enterprise RAG because it affects retrieval quality, answer trust, citation accuracy, and how safely AI systems use governed knowledge.
Related terms in Search & RAG
- Chunking
- Splitting source documents into passages sized for retrieval and the model's context window. Chunk size and overlap are top-3 RAG quality levers.
- Enterprise Search
- Unified search across internal systems (SharePoint, wikis, tickets, CRM) — increasingly powered by embeddings and LLM answers with citations.
- GraphRAG
- RAG variant that retrieves over a knowledge graph and communities of entities; strong for multi-hop questions on connected enterprise data.
- Hybrid Search
- Combining keyword (BM25) and vector search to improve RAG relevance, especially for enterprise content with codes, IDs and jargon.
- Re-ranker
- A second-stage model (cross-encoder) that reorders top-k candidates from initial retrieval for sharper relevance — the fastest RAG quality win.
- Semantic Search
- Search based on meaning rather than keywords, powered by embeddings; the retrieval half of most RAG systems.