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
Data Science with .NET and Polyglot Notebooks

You're reading from   Data Science with .NET and Polyglot Notebooks Programmer's guide to data science using ML.NET, OpenAI, and Semantic Kernel

Arrow left icon
Product type Paperback
Published in Aug 2024
Publisher Packt
ISBN-13 9781835882962
Length 404 pages
Edition 1st Edition
Languages
Arrow right icon
Author (1):
Arrow left icon
Matt Eland Matt Eland
Author Profile Icon Matt Eland
Matt Eland
Arrow right icon
View More author details
Toc

Table of Contents (22) Chapters Close

Preface 1. Part 1: Data Analysis in Polyglot Notebooks
2. Chapter 1: Data Science, Notebooks, and Kernels FREE CHAPTER 3. Chapter 2: Exploring Polyglot Notebooks 4. Chapter 3: Getting Data and Code into Your Notebooks 5. Chapter 4: Working with Tabular Data and DataFrames 6. Chapter 5: Visualizing Data 7. Chapter 6: Variable Correlations 8. Part 2: Machine Learning with Polyglot Notebooks and ML.NET
9. Chapter 7: Classification Experiments with ML.NET AutoML 10. Chapter 8: Regression Experiments with ML.NET AutoML 11. Chapter 9: Beyond AutoML: Pipelines, Trainers, and Transforms 12. Chapter 10: Deploying Machine Learning Models 13. Part 3: Exploring Generative AI with Polyglot Notebooks
14. Chapter 11: Generative AI in Polyglot Notebooks 15. Chapter 12: AI Orchestration with Semantic Kernel 16. Part 4: Polyglot Notebooks in the Enterprise
17. Chapter 13: Enriching Documentation with Mermaid Diagrams 18. Chapter 14: Extending Polyglot Notebooks 19. Chapter 15: Adopting and Deploying Polyglot Notebooks 20. Index 21. Other Books You May Enjoy

Knowing where to go from here

AI orchestration is one of the new frontiers in AI. LLMs have made generative AI scenarios possible that were hard to imagine a decade ago. But, as we’ve seen, AI orchestration is not perfect. It can have a real financial cost, it can be sensitive to how you describe your capabilities, it can take additional time to execute, it can get answers to questions wrong, and it can be sensitive to change.

I believe we still need to see a few key innovations in AI orchestration.

First, we need to mature our testing practices for generative AI systems. Because the output of an LLM is non-deterministic and will change from request to request, interactions with LLMs are inherently hard to test in an automated manner.

There are some exciting innovations in this space, such as prompt flow, which helps automate the evaluation of LLM responses in an automated way. There are also a few LLM testing frameworks, such as DeepEval, which aims to test LLM outputs...

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