John Berryman, Albert Ziegler

Prompt Engineering for LLMs

The Art and Science of Building Large Language Model-Based Applications. Sprache: Englisch.
kartoniert , 250 Seiten
ISBN 1098156153
EAN 9781098156152
Veröffentlicht 31. Dezember 2024
Verlag/Hersteller O'Reilly Media
83,00 inkl. MwSt.
vorbestellbar (Versand mit Deutscher Post/DHL)
Teilen
Beschreibung

Large language models (LLMs) promise unprecedented benefits. Well versed in common topics of human discourse, LLMs can make useful contributions to a large variety of tasks, especially now that the barrier for interacting with them has been greatly reduced. Potentially, any developer can harness the power of LLMs to tackle large classes of problems previously beyond the reach of automation.
This book provides a solid foundation of LLM principles and explains how to apply them in practice. When first integrating LLMs into workflows, most developers struggle to coax useful insights from them. That's because communicating with AI is different from communicating with humans. This guide shows you how to present your problem in the model-friendly way called prompt engineering.
With this book, you'll: - Examine the user-program-AI-user model interaction loop - Understand the influence of LLM architecture and learn how to best interact with it - Design a complete prompt crafting strategy for an application that fits into the application context - Gather and triage context elements to make an efficient prompt - Formulate those elements so that the model processes them in the way that's desired - Master specific prompt crafting techniques including few-shot learning, and chain-of-thought prompting

Portrait

John Berryman is the founder and principal consultant of Arcturus Labs, where he specializes in LLM application development. His expertise helps businesses harness the power of advanced AI technologies. As an early engineer on GitHub Copilot, John contributed to the development of its completions and chat functionalities, working at the forefront of AI-assisted coding tools.
Before his work on Copilot, John built an impressive career as a search engineer. His diverse experience includes helping to develop next-generation search system for the US Patent Office, building search and recommendations for Eventbrite, and contributing to GitHub's code search infrastructure. John is also coauthor of Relevant Search (Manning), a book that distills his expertise in the field.
John's unique background, spanning both cutting-edge AI applications and foundational search technologies, positions him at the forefront of innovation in LLM applications and information retrieval.