Lesson 1 · 6 topics · 18 min · intermediate

How RAG Works: Retrieve, Then Generate

You will be able to

Describe retrieval-augmented generation as retrieve-then-generate, and where the pattern and the name come from.
Explain what retrieval adds over a model's training data: current, per-user and citable context.
Decide when a knowledge base is small enough to put in the prompt and when it needs retrieval.
Separate indexing from querying, and say which changes require re-indexing.
Explain why retrieval recall caps end-to-end answer accuracy.
Route a question to no search, a document index or a table (text-to-SQL).

Topics

Your review

Sign in to keep your quick-check answers. The ones you miss come back for review after 1, 3 and 7 days, until they stick.

Sources

AI Engineering · Chip Huyen, 2025
Chip Huyen. O'Reilly. Used: Ch. 6 "RAG and Agents": "RAG", "RAG Architecture", "RAG Beyond Texts" > "RAG with tabular data".
Hands-On Large Language Models · Jay Alammar & Maarten Grootendorst, 2024
Jay Alammar & Maarten Grootendorst. O'Reilly. Used: Ch. 8 "Semantic Search and Retrieval-Augmented Generation": "Retrieval-Augmented Generation (RAG)" > "Advanced RAG Techniques".
Reading Wikipedia to Answer Open-Domain Questions · Danqi Chen et al., 2017
Danqi Chen, Adam Fisch, Jason Weston & Antoine Bordes. arXiv:1704.00051 (ACL 2017). Used: Abstract (fetched 2026-10-23). Open source
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks · Patrick Lewis et al., 2020
Patrick Lewis, Ethan Perez, Aleksandra Piktus et al.. arXiv:2005.11401 (NeurIPS 2020). Used: Abstract (fetched 2026-10-23). Open source
Introducing Contextual Retrieval · Anthropic, 2024
Anthropic. Used: "A note on simply using a longer prompt" (fetched 2026-10-23). Open source

You will be able to

Describe retrieval-augmented generation as retrieve-then-generate, and where the pattern and the name come from.

Explain what retrieval adds over a model's training data: current, per-user and citable context.

Decide when a knowledge base is small enough to put in the prompt and when it needs retrieval.

Separate indexing from querying, and say which changes require re-indexing.

Explain why retrieval recall caps end-to-end answer accuracy.

Route a question to no search, a document index or a table (text-to-SQL).

Sources

AI Engineering · Chip Huyen, 2025

Chip Huyen. O'Reilly. Used: Ch. 6 "RAG and Agents": "RAG", "RAG Architecture", "RAG Beyond Texts" > "RAG with tabular data".

Hands-On Large Language Models · Jay Alammar & Maarten Grootendorst, 2024

Jay Alammar & Maarten Grootendorst. O'Reilly. Used: Ch. 8 "Semantic Search and Retrieval-Augmented Generation": "Retrieval-Augmented Generation (RAG)" > "Advanced RAG Techniques".

Reading Wikipedia to Answer Open-Domain Questions · Danqi Chen et al., 2017

Danqi Chen, Adam Fisch, Jason Weston & Antoine Bordes. arXiv:1704.00051 (ACL 2017). Used: Abstract (fetched 2026-10-23). Open source

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks · Patrick Lewis et al., 2020

Patrick Lewis, Ethan Perez, Aleksandra Piktus et al.. arXiv:2005.11401 (NeurIPS 2020). Used: Abstract (fetched 2026-10-23). Open source

Introducing Contextual Retrieval · Anthropic, 2024

Anthropic. Used: "A note on simply using a longer prompt" (fetched 2026-10-23). Open source