Best books for RAG Engineers
This list is about the retrieval side of a language model application. It starts with the search foundations that still decide what a retrieved passage is worth, then moves to the transformer and language model vocabulary you need to tune embeddings and rerankers, and ends with the production and evaluation questions that separate a demo from a system. Nothing here teaches one vector database; the choice changes faster than the principles. The books assume you can write Python and call an API.
9 books in 3 stages, about 2,230 pages (at least 56 hours of reading). The notes are ours, with no ratings or sales claims.
See the full RAG Engineer roadmap →Best courses for RAG Engineers →
How to choose your books
A short method, so you read the right book for where you are instead of the longest list.
Find your stage
Getting started · 3 books
Search foundations and model vocabulary. Read these to learn what a retrieval score measures and what an embedding model is doing before you change either one.
Jump to this stage ↓Doing the job · 5 books
The working pipeline: relevance tuning, LangChain-style integration, prompt design for retrieved text, and the production concerns that come with it. Use these as you build and evaluate your first system.
Jump to this stage ↓Senior and leading · 1 books
Architecture and cost. These books help you decide which parts of a retrieval system to build, which to buy, and how to keep the whole system measurable as the company depends on it.
Jump to this stage ↓
If you are unsure, start one stage lower than you think. Books in a later stage assume the working knowledge the earlier ones give you.
Begin with one book
Our starting pick
Hands-On Large Language Models
by Jay Alammar, Maarten Grootendorst · 2024
It walks through the components of a retrieval pipeline with working examples, so the terms in the later books have something concrete to attach to.
See the book ↓Then pick by your situation
Choose the next book by the problem in front of you, not by its place in the list.
If your retrieval results look plausible but you cannot say whether they got better
read Relevant Search (doing the job)
If you are deciding what goes into the prompt and what must stay out of it
read Prompt Engineering for LLMs (doing the job)
If you are choosing between building a retrieval layer and buying one
read AI Engineering (senior and leading)
Set a time budget
| Stage | Books | Pages | Reading | At 3 hrs a week |
|---|---|---|---|---|
| Getting started | 3 | ≥ 880 | ≥ 22 hrs | ≥ 7 wks |
| Doing the job | 5 | ≥ 1,000 | ≥ 25 hrs | ≥ 8 wks |
| Senior and leading | 1 | 350 | 9 hrs | 3 wks |
| All 3 stages | 9 | ≥ 2,230 | ≥ 56 hrs | ≥ 19 wks |
Treat this as a ceiling, not a target. Read one book at a time, apply it, then move on; read reference-style books in sections. Totals are approximate.
Judge any book before you buy it
Age
This list runs from 2008 (Introduction to Information Retrieval) to 2024 (Hands-On Large Language Models). Older books earn their place by teaching principles that do not change. For tools and platforms, buy the latest edition.
Level
Check the stage before the title. A book from a later stage will make sense only once you have faced the problems it solves.
Format
Some books suit reading start to finish; others work as references. Read the reference-style ones in sections, when a problem calls for them.
Fit
Ask what you will do differently the week after you finish. If you cannot answer, the book is for a different moment. Come back to it when the situation arrives.
Getting started
Search foundations and model vocabulary. Read these to learn what a retrieval score measures and what an embedding model is doing before you change either one.

Introduction to Information Retrieval
by Christopher D. Manning, Prabhakar Raghavan, Hinrich Schütze · 2008
~480 pages~12 hrs to read
The foundations of indexing, ranking and evaluation for search: inverted indexes, term weighting and precision and recall. Retrieval-augmented generation is still retrieval, and this book explains why the old measures still matter.
View book →
Natural Language Processing with Transformers
by Lewis Tunstall, Leandro von Werra, Thomas Wolf · 2022
How transformer models are trained, fine-tuned and used in practice, with working code. It gives you the model vocabulary you need before you tune an embedding or reranking model.
View book →
Start hereHands-On Large Language Models
by Jay Alammar, Maarten Grootendorst · 2024
~400 pages~10 hrs to read
Illustrated, practical chapters on embeddings, semantic search and prompting. It is a good first book on the components of a retrieval pipeline.
View book →
Doing the job
The working pipeline: relevance tuning, LangChain-style integration, prompt design for retrieved text, and the production concerns that come with it. Use these as you build and evaluate your first system.
Relevant Search: With Applications for Solr and Elasticsearch
by Doug Turnbull, John Berryman · 2016
~360 pages~9 hrs to read
How search relevance is tuned in practice: query understanding, ranking signals and measuring whether results improved. The evaluation habits transfer directly to RAG retrieval.
View book →Generative AI with LangChain
by Ben Auffarth · 2023
Building applications that combine language models with documents, tools and memory. Read it for the integration patterns and the places where they break.
View book →
Designing Machine Learning Systems
by Chip Huyen · 2022
~390 pages~10 hrs to read
How to take a model into production: data pipelines, monitoring, drift and iteration. Retrieval systems have the same failure modes, and this book shows how to plan for them.
View book →
Prompt Engineering for LLMs: The Art and Science of Building Large Language Model-Based Applications
by John Berryman, Albert Ziegler · 2024
~250 pages~6 hrs to read
Prompt design for applications rather than chat: structuring context, handling retrieved text and testing outputs. Use it to decide what goes into the prompt and what the model should never see.
View book →
Build a Large Language Model (From Scratch)
by Sebastian Raschka · 2024
Implements a small language model step by step, so you learn what the model actually does with its inputs. It is worth reading when you need to debug why a model ignored the context you gave it.
View book →
Senior and leading
Architecture and cost. These books help you decide which parts of a retrieval system to build, which to buy, and how to keep the whole system measurable as the company depends on it.

AI Engineering: Building Applications with Foundation Models
by Chip Huyen · 2024
~350 pages~9 hrs to read
An overview of building products on foundation models, including retrieval, evaluation and cost. Read it when you are deciding which parts of a system to build and which to buy.
View book →
Book links go to Amazon and are affiliate links. As an Amazon Associate I earn from qualifying purchases.
Frequently asked questions
Which book should a RAG Engineer read first?
Hands-On Large Language Models by Jay Alammar, Maarten Grootendorst. It walks through the components of a retrieval pipeline with working examples, so the terms in the later books have something concrete to attach to.
Do I need to read all 9 books?
No. The list is a menu, not a syllabus. Find your stage (getting started: 3, doing the job: 5, senior and leading: 1), begin with one book (we suggest Hands-On Large Language Models), then pick the next book by the problem you are facing at work. Come back to the others when the situation they cover arrives.
How long does it take to read these books?
The 6 books with a known page count add up to about 2,230 pages, roughly 56 hours at 1.5 minutes a page. At three hours a week that is about 19 weeks; at six hours a week, about 9. The list is meant to be read over time, one book at a time, not in one run.
Are these books up to date?
They range from 2008 (Introduction to Information Retrieval) to 2024 (Hands-On Large Language Models). Older titles are included because they teach principles that have not changed; for tools and platforms, we favor recent editions. Check the edition before you buy.
Related reading
Some links are affiliate links: we earn a small commission if you buy, at no cost to you. It does not change what we list.