Drew Farris

Drew Farris is a Principal at Booz Allen Hamilton. He specializes in artificial intelligence and machine learning, with over 14 years of experience building advanced analytics for public sector clients. Before joining Booz Allen, Drew worked with academic research teams and start-ups on information retrieval, natural language process-ing, and large-scale data management platforms. He hasco-authored several publications, including Booz Allen’s Field Guide to Data Science and Machine Intelligence Primer, and the Jolt Award-winning book Taming Text on computational text proc-essing. Drew is also a member of the Apache Software Foundation and has contribut-ed to open source projects like Apache Mahout, Lucene, and Solr.

books by Drew Farris

How Large Language Models Work

  • June 2025
  • ISBN 9781633437081
  • 200 pages
  • printed in black & white

How Large Language Models Work takes you inside an LLM, showing step-by-step how a natural language prompt becomes a clear, readable text completion. Written in plain language, you’ll learn how LLMs are created, why they make errors, and how you can design reliable AI solutions. Along the way, you’ll learn how LLMs “think,” how to design LLM-powered applications like agents and Q&A systems, and how to navigate the ethical, legal, and security issues.

Taming Text

  • December 2012
  • ISBN 9781933988382
  • 320 pages
  • printed in black & white

There is so much text in our lives, we are practically drowning in it. Fortunately, there are innovative tools and techniques for managing unstructured information that can throw the smart developer a much-needed lifeline. You'll find them in this book.

Taming Text is a practical, example-driven guide to working with text in real applications. This book introduces you to useful techniques like full-text search, proper name recognition, clustering, tagging, information extraction, and summarization. You'll explore real use cases as you systematically absorb the foundations upon which they are built.

Written in a clear and concise style, this book avoids jargon, explaining the subject in terms you can understand without a background in statistics or natural language processing. Examples are in Java, but the concepts can be applied in any language.