ORCIDGitHubLinkedIn
RSS Curriculum Vitae TR

Retrieval-Augmented Generation

Turkish equivalent: Getirim destekli üretimDomain: Large Language Models

A generation architecture that retrieves external information at request time and supplies selected evidence to a language model as additional context.

Boundaries

RAG does not update model parameters; it supplies external context at inference time and therefore depends heavily on retrieval and context-construction quality.

  • Hybrid Search
  • Reranking
  • Embedding
  • Grounding
  • Context Window

Source

  • https://arxiv.org/abs/2005.11401

Updated:

Related concepts

Large Language Models