{
 "id": "https://redfinchadvisory.com/lexicon/rag",
 "slug": "rag",
 "prefLabel": "RAG",
 "altLabel": [
  "Retrieval-augmented generation"
 ],
 "hiddenLabel": [],
 "definition": "A technique for grounding that finds relevant text in your documents or data and adds it to the model's context, so the model writes its answer from that text without being changed.",
 "scopeNote": "",
 "tier": "core",
 "group": "Connections and systems",
 "broader": [],
 "narrower": [
  "https://redfinchadvisory.com/lexicon/vector-database"
 ],
 "related": [
  {
   "id": "https://redfinchadvisory.com/lexicon/fine-tuning",
   "type": "pair"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/knowledge-cutoff",
   "type": "related"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/geo",
   "type": "related"
  }
 ],
 "links": [
  {
   "id": "https://redfinchadvisory.com/lexicon/context",
   "label": "adds sources to",
   "direction": "out"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/grounding",
   "label": "usually done with",
   "direction": "in"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/knowledge-base",
   "label": "searched by",
   "direction": "in"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/embedding",
   "label": "power the search in",
   "direction": "in"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/retrieval-from-our-data",
   "label": "is the method behind",
   "direction": "out"
  }
 ],
 "modified": "2026-10-21",
 "markdown": "https://redfinchadvisory.com/lexicon/rag.md",
 "inScheme": {
  "id": "https://redfinchadvisory.com/lexicon",
  "version": "1.0",
  "currentAsOf": "2026-10-21"
 }
}