// ⌕ RAG & Vector Retrieval
Retrieval-Augmented Generation (RAG)
Retrieve relevant documents, then generate grounded answers.
检索增强生成 RAG 2020 Foundational core
IN PLAIN WORDS
Combine parametric memory with an updatable index: a retriever fetches passages and the generator conditions on them, reducing hallucination and enabling citations. Now refers to any retrieve-then-generate system.
Used in: Enterprise QA, Perplexity-style search, support bots
TIMELINE · prerequisites → this → what builds on it
01Original paper
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Patrick Lewis, Ethan Perez, Aleksandra Piktus, et al. · 2020
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
Related:ColBERT (Late Interaction)BM25
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
04Where the course teaches it
On learning paths:AI Application Engineer
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
rag)