Encyclopedia · 311 concepts
Learn this concept as a feed

NLP & Language · intermediate · concept 119 of 311 · Updated Nov 4, 2026

Retrieval-Augmented Generation (RAG)

Combining LLMs with external knowledge retrieval. Instead of relying solely on training data, RAG retrieves relevant documents and passes them to the LLM, reducing hallucinations and adding current information. Contextual retrieval prepends document context to each chunk before embedding, a simple fix for chunks that lose their meaning alone.

Interactive · 3D

Graph Types for AI Agents: retrieval structures compared →

One dataset modeled six ways: vector index, knowledge graph, and friends.

Top AI contributors on this

Key terms

RetrieverGeneratorVector searchChunkingContext windowContextual retrieval

Where you meet it in the real world

Enterprise chatbots, document Q&A, customer support, legal research