Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Essential Guide to LLMOps

You're reading from   Essential Guide to LLMOps Implementing effective strategies for Large Language Models in deployment and continuous improvement

Arrow left icon
Product type Paperback
Published in Jul 2024
Publisher Packt
ISBN-13 9781835887509
Length 190 pages
Edition 1st Edition
Languages
Tools
Arrow right icon
Author (1):
Arrow left icon
Ryan Doan Ryan Doan
Author Profile Icon Ryan Doan
Ryan Doan
Arrow right icon
View More author details
Toc

Table of Contents (14) Chapters Close

Preface 1. Part 1: Foundations of LLMOps FREE CHAPTER
2. Chapter 1: Introduction to LLMs and LLMOps 3. Chapter 2: Reviewing LLMOps Components 4. Part 2: Tools and Strategies in LLMOps
5. Chapter 3: Processing Data in LLMOps Tools 6. Chapter 4: Developing Models via LLMOps 7. Chapter 5: LLMOps Review and Compliance 8. Part 3: Advanced LLMOps Applications and Future Outlook
9. Chapter 6: LLMOps Strategies for Inference, Serving, and Scalability 10. Chapter 7: LLMOps Monitoring and Continuous Improvement 11. Chapter 8: The Future of LLMOps and Emerging Technologies 12. Index 13. Other Books You May Enjoy

Operationalizing compliance and performance

Operationalizing performance, security, governance, legal, and regulatory compliance for LLMs involves creating a comprehensive system that spans various departments and functions within an organization. Integrating robust workflows, such as those managed by Apache Airflow, with strategic human review points, and ensuring compliance with data and model licensing, are key components of this system.

Operationalizing performance

For performance, establishing continuous integration/continuous deployment (CI/CD) pipelines managed by workflow orchestration tools such as Apache Airflow ensures that models are consistently evaluated against performance benchmarks. Directed acyclic graphs (DAGs) in Airflow can be programmed to automatically trigger performance evaluation tasks, such as running test suites that measure the LLM’s accuracy, recall, precision, and F1 scores against a validation set.

These DAGs can also include steps for...

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 $19.99/month. Cancel anytime
Banner background image