Sign In Start Free Trial
Account

Add to playlist

Create a Playlist

Modal Close icon
You need to login to use this feature.
  • Book Overview & Buying Generative AI Application Integration Patterns
  • Table Of Contents Toc
Generative AI Application Integration Patterns

Generative AI Application Integration Patterns

By : Juan Pablo Bustos, Luis Lopez Soria
close
close
Generative AI Application Integration Patterns

Generative AI Application Integration Patterns

By: Juan Pablo Bustos, Luis Lopez Soria

Overview of this book

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.
Table of Contents (13 chapters)
close
close
7
Integration Pattern: Real-Time Intent Classification
11
Other Books You May Enjoy
12
Index

Results post-processing

Before presenting the raw outputs from GenAI models directly to end users, additional post-processing is often essential to refine and polish results. There are a few common techniques to improve quality, as we will see now.

Filtering inappropriate content – Despite making the best efforts during training, models will sometimes return outputs that are biased, incorrect, or offensive. Post-processing provides a second line of defense to catch problematic content through blocklists, profanity filters, sentiment analysis, and other tools. Flagged results can be discarded or rerouted to human review. This filtration ensures only high-quality content reaches users.

Models such as Google Gemini allow you to define a set of safety settings to set thresholds during generation, allowing you to stop generating content if those thresholds are exceeded. Additionally, it provides a set of safety ratings with your results, allowing you to determine the threshold...

CONTINUE READING
83
Tech Concepts
36
Programming languages
73
Tech Tools
Icon Unlimited access to the largest independent learning library in tech of over 8,000 expert-authored tech books and videos.
Icon Innovative learning tools, including AI book assistants, code context explainers, and text-to-speech.
Icon 50+ new titles added per month and exclusive early access to books as they are being written.
Generative AI Application Integration Patterns
notes
bookmark Notes and Bookmarks search Search in title playlist Add to playlist download Download options font-size Font size

Change the font size

margin-width Margin width

Change margin width

day-mode Day/Sepia/Night Modes

Change background colour

Close icon Search
Country selected

Close icon Your notes and bookmarks

Confirmation

Modal Close icon
claim successful

Buy this book with your credits?

Modal Close icon
Are you sure you want to buy this book with one of your credits?
Close
YES, BUY

Submit Your Feedback

Modal Close icon
Modal Close icon
Modal Close icon