LLMs in Enterprise: Design strategies, patterns, and best practices for large language model development
Author: Ahmed Menshawy (Author), Mahmoud Fahmy (Author)
Publisher finelybook 出版社: Packt Publishing
Publication Date 出版日期: 2025-09-19
Language 语言: English
Print length 页数: 564 pages
ISBN-10: 1836203071
ISBN-13: 9781836203070
Book Description
Integrate large language models into your enterprise applications with advanced strategies that drive transformation
Key Features
- Explore design patterns for applying LLMs to solve real-world enterprise problems
- Learn strategies for scaling and deploying LLMs in complex environments
- Get more relevant results and improve performance by fine-tuning and optimizing LLMs
- Purchase of the print or Kindle book includes a free PDF eBook
Book Description
The integration of large language models (LLMs) into enterprise applications is transforming how businesses use AI to drive smarter decisions and efficient operations. LLMs in Enterprise is your practical guide to bringing these capabilities into real-world business contexts. It demystifies the complexities of LLM deployment and provides a structured approach for enhancing decision-making and operational efficiency with AI.
Starting with an introduction to the foundational concepts, the book swiftly moves on to hands-on applications focusing on real-world challenges and solutions. You’ll master data strategies and explore design patterns that streamline the optimization and deployment of LLMs in enterprise environments. From fine-tuning techniques to advanced inferencing patterns, the book equips you with a toolkit for solving complex challenges and driving AI-led innovation in business processes.
By the end of this book, you’ll have a solid grasp of key LLM design patterns and how to apply them to enhance the performance and scalability of your generative AI solutions.
What you will learn
- Apply design patterns to integrate LLMs into enterprise applications for efficiency and scalability
- Overcome common challenges in scaling and deploying LLMs
- Use fine-tuning techniques and RAG approaches to enhance LLM efficiency
- Stay ahead of the curve with insights into emerging trends and advancements, including multimodality
- Optimize LLM performance through customized contextual models, advanced inferencing engines, and evaluation patterns
- Ensure fairness, transparency, and accountability in AI applications
Who this book is for
This book is designed for a diverse group of professionals looking to understand and implement advanced design patterns for LLMs in their enterprise applications, including AI and ML researchers exploring practical applications of LLMs, data scientists and ML engineers designing and implementing large-scale GenAI solutions, enterprise architects and technical leaders who oversee the integration of AI technologies into business processes, and software developers creating scalable GenAI-powered applications.
Table of Contents
- Introduction to Large Language Models
- LLMs in Enterprise: Applications, Challenges, and Design Patterns
- Advanced Fine-Tuning Techniques and Strategies for Large Language Models
- Retrieval-Augmented Generation Pattern
- Customizing Contextual LLMs
- The Art of Prompt Engineering for Enterprise LLMs
- Enterprise Challenges in Evaluating LLM Applications
- The Data Blueprint: Crafting Effective Strategies for LLM Development
- Managing Model Deployments in Production
- Accelerated and Optimized Inferencing Patterns
- Connected LLMs Pattern
- Monitoring LLMs in Production
- Responsible AI in LLMs
- Emerging Trends and Multimodality
About the Author
Ahmed Menshawy is the Vice President of AI Engineering at Mastercard. He leads the AI Engineering team to drive the development and operationalization of AI products, address a broad range of challenges and technical debts for ML pipelines deployment. He also leads a team dedicated to creating several AI accelerators and capabilities, including serving engines and feature stores, aimed at enhancing various aspects of AI engineering.
Mahmoud Fahmy is a Lead Machine Learning Engineer at Mastercard, specializing in the development and operationalization of AI products. His primary focus is on optimizing machine learning pipelines and navigating the intricate challenges of deploying models effectively for end customers.
