Generative AI Application Integration Patterns : Integrate Large Language Models into Your Applications / Juan Pablo Bustos, Luis Lopez Soria ; foreword by Dr. Ali Arsanjani.

Format:

Book

Author/Creator:

Bustos, Juan Pablo, author.

Soria, Luis Lopez, author.

Contributor:

Arsanjani, Ali, writer of foreword.

Series:

Expert insight.

Expert insight

Language:

English

Subjects (All):

Artificial intelligence.

Application software--Development.

Application software.

Physical Description:

1 online resource (219 p.)

Place of Publication:

Birmingham : Packt Publishing, Limited, 2024.

Summary:

Unleash the transformative potential of GenAI with this comprehensive guide that serves as an indispensable roadmap for integrating large language models into real-world applications. Gain invaluable insights into identifying compelling use cases, leveraging state-of-the-art models effectively, deploying these models into your applications at scale, and navigating ethical considerations. Key Features Get familiar with the most important tools and concepts used in real scenarios to design GenAI apps Interact with GenAI models to tailor model behavior to minimize hallucinations Get acquainted with a variety of strategies and an easy to follow 4 step frameworks for integrating GenAI into applications Book Description Explore the transformative potential of GenAI in the application development lifecycle. Through concrete examples, you will go through the process of ideation and integration, understanding the tradeoffs and the decision points when integrating GenAI. With recent advances in models like Google Gemini, Anthropic Claude, DALL-E and GPT-4o, this timely resource will help you harness these technologies through proven design patterns. We then delve into the practical applications of GenAI, identifying common use cases and applying design patterns to address real-world challenges. From summarization and metadata extraction to intent classification and question answering, each chapter offers practical examples and blueprints for leveraging GenAI across diverse domains and tasks. You will learn how to fine-tune models for specific applications, progressing from basic prompting to sophisticated strategies such as retrieval augmented generation (RAG) and chain of thought. Additionally, we provide end-to-end guidance on operationalizing models, including data prep, training, deployment, and monitoring. We also focus on responsible and ethical development techniques for transparency, auditing, and governance as crucial design patterns. What you will learn Concepts of GenAI: pre-training, fine-tuning, prompt engineering, and RAG Framework for integrating AI: entry points, prompt pre-processing, inference, post-processing, and presentation Patterns for batch and real-time integration Code samples for metadata extraction, summarization, intent classification, question-answering with RAG, and more Ethical use: bias mitigation, data privacy, and monitoring Deployment and hosting options for GenAI models Who this book is for This book is not an introduction to AI/ML or Python. It offers practical guides for designing, building, and deploying GenAI applications in production. While all readers are welcome, those who benefit most include: Developer engineers with foundational tech knowledge Software architects seeking best practices and design patterns Professionals using ML for data science, research, etc., who want a deeper understanding of Generative AI Technical product managers with a software development background This concise focus ensures practical, actionable insights for experienced professionals.

Contents:

Cover

Copyright

Foreword

Contributors

Table of Contents

Preface

Chapter 1: Introduction to Generative AI Patterns

From AI predictions to generative AI

Predictive AI vs generative AI use case ideation

A change in the paradigm

Predictive AI use case development

simplified lifecycle

Generative AI use case development

General generative AI concepts

Generative AI model architectures

Techniques available to optimize foundational models

Techniques to augment your foundational model responses

Constant evolution across the generative AI space

Introducing generative AI integration patterns

Summary

Chapter 2: Identifying Generative AI Use Cases

When to consider generative AI

Realizing business value

Identifying Generative AI use cases

Potential business-focused use cases

Generative AI deployment and hosting options

Chapter 3: Designing Patterns for Interacting with Generative AI

Defining an integration framework

Entry point

Prompt pre-processing

Inference

Results post-processing

Selecting from amongst multiple outputs

Refining generated outputs

Results presentation

Logging

Chapter 4: Generative AI Batch and Real-Time Integration Patterns

Batch and real-time integration patterns

Different pipeline architectures

Application integration patterns in the integration framework

Prompt preprocessing

Result post-processing

Result presentation

Use case example

search enhanced by GenAI

Batch integration

document ingestion

Real-time integration

search

Chapter 5: Integration Pattern: Batch Metadata Extraction

Use case definition

Architecture

Chapter 6: Integration Pattern: Batch Summarization

Use case definition

Chapter 7: Integration Pattern: Real-Time Intent Classification

Logging and monitoring

Summary

Chapter 8: Integration Pattern: Real-Time Retrieval Augmented Generation

Use case demo

The Gradio app

Chapter 9: Operationalizing Generative AI Integration Patterns

Operationalization framework

Data layer

A real-world example: Part 1

Training layer

A real-world example: Part 2

Inference layer

A real-world example: Part 3

Operations layer

CI/CD and MLOps

Monitoring and observability

Evaluation and monitoring

Notes:

Description based upon print version of record.

Alerting

OCLC-licensed vendor bibliographic record.

ISBN:

9781835887608

1835887600

OCLC:

1455134869