Home
Back to Glossary

RAG

Pages
7
References
6
Related Terms
4

Definition

RAG, or Retrieval-Augmented Generation, combines retrieved external information with generative model output.

Background

After the 2020 work by Lewis et al., RAG became a common design for grounding LLM answers in documents or knowledge bases.

Position

It sits next to Knowledge Graphs and memory systems as a way to feed external knowledge into LLM workflows.

Distinctions

  • RAG is an architecture for retrieval plus generation, not a knowledge representation by itself.
  • A Knowledge Graph structures knowledge; RAG retrieves information and uses it during generation.

Primary source-backed reference selected for this concept.

A concept map for RAG.

Page Context

  • AI agent memory platform created with Graphiti and MCP
    1. Executive Summary By combining Graphiti and MCP, AI agents can be provided with "memory that persists across conversation sessions" and "a standard point of contact from exte...
    Quote: AI agent memory platform created with Graphiti and MCP

    ai-systems

  • LLM Limits and Hallucinations: Factuality, Evaluation, and QA
    LLM Limits and Hallucinations: Factuality, Evaluation, and QA 1. Executive Summary LLMs generate plausible text, but they are not truth checkers. Training optimizes next-token p...
    Quote: LLM Limits and Hallucinations: Factuality, Evaluation, and QA

    ai-systems

  • How LLM Training, Fine-Tuning, RAG, and Agents Differ
    How LLM Training, Fine-Tuning, RAG, and Agents Differ 1. Executive Summary The most common mistake in LLM discussions is to treat pretraining, fine-tuning, prompting, RAG, tool ...
    Quote: How LLM Training, Fine-Tuning, RAG, and Agents Differ

    ai-systems

  • Research Log: LLM Limits, Hallucinations, and Evaluation Methods
    Research Log: LLM Limits, Hallucinations, and Evaluation Methods Environment - model: gpt-5.4-mini - skill: research-report - prompt source: ops/codex/prompts/daily-issue-resear...
    Quote: Research Log: LLM Limits, Hallucinations, and Evaluation Methods

    ai-systems

  • Research Log: LLM Training, Fine-Tuning, RAG, and Agents
    Research Log: LLM Training, Fine-Tuning, RAG, and Agents Environment - model: gpt-5.4-mini - skill: research-report - prompt source: ops/codex/prompts/daily-issue-research.md Re...
    Quote: Research Log: LLM Training, Fine-Tuning, RAG, and Agents

    ai-systems

  • LLM Limits and Hallucinations: Source Notes
    - Indirect Prompt Injection in the Wild: An Empirical Study of Prevalence, Techniques, and Objectives - Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented...
    Quote: LLM Limits and Hallucinations: Source Notes

    ai-systems

Pages