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 with Amazon Bedrock

You're reading from   Generative AI with Amazon Bedrock Build, scale, and secure generative AI applications using Amazon Bedrock

Arrow left icon
Product type Paperback
Published in Jul 2024
Publisher Packt
ISBN-13 9781803247281
Length 384 pages
Edition 1st Edition
Tools
Arrow right icon
Authors (2):
Arrow left icon
Shikhar Kwatra Shikhar Kwatra
Author Profile Icon Shikhar Kwatra
Shikhar Kwatra
Bunny Kaushik Bunny Kaushik
Author Profile Icon Bunny Kaushik
Bunny Kaushik
Arrow right icon
View More author details
Toc

Table of Contents (18) Chapters Close

Preface 1. Part 1: Amazon Bedrock Foundations
2. Chapter 1: Exploring Amazon Bedrock FREE CHAPTER 3. Chapter 2: Accessing and Utilizing Models in Amazon Bedrock 4. Chapter 3: Engineering Prompts for Effective Model Usage 5. Chapter 4: Customizing Models for Enhanced Performance 6. Chapter 5: Harnessing the Power of RAG 7. Part 2: Amazon Bedrock Architecture Patterns
8. Chapter 6: Generating and Summarizing Text with Amazon Bedrock 9. Chapter 7: Building Question Answering Systems and Conversational Interfaces 10. Chapter 8: Extracting Entities and Generating Code with Amazon Bedrock 11. Chapter 9: Generating and Transforming Images Using Amazon Bedrock 12. Chapter 10: Developing Intelligent Agents with Amazon Bedrock 13. Part 3: Model Management and Security Considerations
14. Chapter 11: Evaluating and Monitoring Models with Amazon Bedrock 15. Chapter 12: Ensuring Security and Privacy in Amazon Bedrock 16. Index 17. Other Books You May Enjoy

Unlocking prompt engineering techniques

The field of prompt engineering is an active area of research and innovation with new techniques and patterns emerging frequently, driven by the pursuit to improve the performance of the models and generate more natural human-like responses. In this section, we are going to look at some of the most common patterns.

Zero-shot prompting

Zero-shot refers to the ability of LLMs to generate reasonable responses to prompts that it has not been explicitly trained on. It relies solely on a descriptive prompt to specify the desired output, as depicted in Figure 3.4:

Figure 3.4 – Zero-shot prompting

Figure 3.4 – Zero-shot prompting

For instance, a zero-shot prompt to get a poem could be Write a rhyming poem with 4 stanzas about seasons changing.

The main advantage of this method is that it’s easier; prompt crafting can be done without providing examples in the input. However, output quality can vary without concrete examples to base...

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