Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Save more on your purchases now! discount-offer-chevron-icon
Savings automatically calculated. No voucher code required.
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Generative AI Application Integration Patterns

You're reading from   Generative AI Application Integration Patterns Integrate large language models into your applications

Arrow left icon
Product type Paperback
Published in Sep 2024
Publisher Packt
ISBN-13 9781835887608
Length 218 pages
Edition 1st Edition
Languages
Arrow right icon
Authors (2):
Arrow left icon
Luis Lopez Soria Luis Lopez Soria
Author Profile Icon Luis Lopez Soria
Luis Lopez Soria
Juan Pablo Bustos Juan Pablo Bustos
Author Profile Icon Juan Pablo Bustos
Juan Pablo Bustos
Arrow right icon
View More author details
Toc

Table of Contents (13) Chapters Close

Preface 1. Introduction to Generative AI Patterns 2. Identifying Generative AI Use Cases FREE CHAPTER 3. Designing Patterns for Interacting with Generative AI 4. Generative AI Batch and Real-Time Integration Patterns 5. Integration Pattern: Batch Metadata Extraction 6. Integration Pattern: Batch Summarization 7. Integration Pattern: Real-Time Intent Classification 8. Integration Pattern: Real-Time Retrieval Augmented Generation 9. Operationalizing Generative AI Integration Patterns 10. Embedding Responsible AI into Your GenAI Applications 11. Other Books You May Enjoy
12. Index

Training layer

The Training layer is where your GenAI models come to learn how to behave in front of your customers, learning from the curated data and acquiring the skills needed to generate meaningful outputs. But it’s not just about training; it’s about governing, monitoring, understanding, and continuously improving these models. Model governance is a necessity for building trustworthy AI. Here are key strategies to consider:

  • Clear policies and guidelines: Establish a framework that defines how models are developed, deployed, monitored, and updated. Address ethical considerations like fairness, transparency, and accountability. Document your decision-making processes for model selection, hyperparameter tuning, and data handling.
  • Responsible AI practices: Implement techniques to detect and mitigate potential biases in your training data and model outputs. Regularly evaluate the impact of your models on different user groups and stakeholders. Consider...
lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at €18.99/month. Cancel anytime