Examples and Projects - Apple Intelligence for Masterminds

HOME BOOKS VIDEO COURSES

NEWSLETTER CONTACT

Apple Intelligence for Masterminds

How to Create Intelligent Applications for iPhones, iPads and Macs

1st Edition
January 2026
ISBN: 978-1-7779782-8-0

Examples and Projects

Although typing the examples can help reinforce what you are learning, it can also be time consuming. To make the process faster, you can download the source code in TXT format, access the complete Xcode projects, or open the specific examples you want to review using the links below.

Download TXT Files
139.0 KBytes

Download Projects
763 MBytes

Chapter 1 — App Development

There are no Examples in this Chapter

Chapter 2 — Apple Intelligence

There are no Examples in this Chapter

Chapter 3 — Xcode

There are no Examples in this Chapter

Chapter 4 — Integrated Tools

Listing 4-1: Processing an image generated by Image Playground

Listing 4-2: Specifying the instructions from the application

Listing 4-3: Configuring the Image Playground interface

Listing 4-4: Generating images programmatically

Listing 4-5: Generating multiple images programmatically

Listing 4-6: Assigning attributes to a text

Listing 4-7: Defining a TextEditor view that supports attributed text

Listing 4-8: Storing attributed strings

Listing 4-9: Setting up the model container

Listing 4-10: Listing notes

Listing 4-11: Adding notes

Listing 4-12: Displaying notes

Listing 4-13: Creating a Representable view for a UITextField view

Listing 4-14: Using a representable view to allow the user to type Genmojis

Listing 4-15: Loading and saving an NSAttributedString value

Listing 4-16: Representable view to provide the UITextView view

Listing 4-17: Letting the user save and load attributed text

Listing 4-18: Disabling Writing Tools

Listing 4-19: Creating a button to open the Writing Tools interface

Listing 4-20: Processing the text before and after is modified by Writing Tools

Listing 4-21: Interface to test delegate methods

Listing 4-22: Selecting the text to be edited by Writing Tools

Listing 4-23: Configuring the Writing Tools results

Listing 4-24: Detecting if Writing Tools is open

Chapter 5 — Foundation Models

Listing 5-1: Prompting the model

Listing 5-2: Persisting the session

Listing 5-3: Using Foundation Models to create a chat box

Listing 5-4: Creating a complex prompt with the Prompt structure

Listing 5-5: Providing instructions to the model

Listing 5-6: Processing partial responses

Listing 5-7: Asking the model to always choose the most probable output

Listing 5-8: Changing the model's temperature

Listing 5-9: Using guided generation

Listing 5-10: Making our structure generable

Listing 5-11: Processing the model's response

Listing 5-12: Helping the model to produce the right values

Listing 5-13: Processing structured responses

Listing 5-14: Using a predefined prompt

Listing 5-15: Streaming generable responses

Listing 5-16: Defining a dynamic schema

Listing 5-17: Selecting the properties to include in a dynamic schema

Listing 5-18: Defining a tool

Listing 5-19: Defining a generable structure to work with a tool

Listing 5-20: Using a tool

Listing 5-21: Creating a tool with MapKit

Listing 5-22: Streaming the results of a tool

Listing 5-23: Showing the attractions found by the tool on a map

Listing 5-24: Defining a function to check availability

Listing 5-25: Checking the model's availability

Listing 5-26: Checking availability before using the model

Listing 5-27: Checking for common errors

Listing 5-28: Checking for guardrails errors

Listing 5-29: Setting up more permissive guardrails

Listing 5-30: Counting tokens

Listing 5-31: Starting a new session

Listing 5-32: Defining the data model to store conversations

Listing 5-33: Injecting the data model into the environment

Listing 5-34: Loading previous conversations and creating new ones

Listing 5-35: Listing conversations

Listing 5-36: Managing conversations

Listing 5-37: Using an adapter to tag content

Listing 5-38: Reading Conda's version

Listing 5-39: Creating a new environment

Listing 5-40: Activating an environment

Listing 5-41: Installing toolkit's requirements

Listing 5-42: JSON format for a sample data

Listing 5-43: Executing the Python script to train the adapter

Listing 5-44: Exporting the adapter into a file

Listing 5-45: Creating a session with an adapter

Chapter 6 — Text Models

Listing 6-1: Determining if the language of the text is English

Listing 6-2: Detecting the language

Listing 6-3: Showing the level of probability for each language

Listing 6-4: Restricting the recognizer to two languages

Listing 6-5: Generating tokens

Listing 6-6: Processing tokens

Listing 6-7: Extracting the root form

Listing 6-8: Determining the token's type

Listing 6-9: Classifying words by their lexical class

Listing 6-10: Extracting names and locations

Listing 6-11: Reading the level of confidence

Listing 6-12: Detecting the mood

Listing 6-13: Reading a word's embedding

Listing 6-14: Calculating the distance between two words

Listing 6-15: Finding related words

Listing 6-16: Finding related sentences

Listing 6-17: Opening the translation interface

Listing 6-18: Showing the translation in our interface

Listing 6-19: Translating a text when the view appears

Listing 6-20: Translating the text entered by the user

Listing 6-21: Declaring the languages we want to use

Listing 6-22: Implementing the logic to use multiple languages

Listing 6-23: Allowing the user to select the languages

Listing 6-24: Automatically selecting the source language

Listing 6-25: Initializing our app with all the supported languages

Listing 6-26: Detecting all supported languages

Listing 6-27: Translating multiple texts

Listing 6-28: Performing asynchronous translations

Listing 6-29: Translating multiple languages

Chapter 7 — Vision Framework

Listing 7-1: Classifying an image

Listing 7-2: Analyzing multiple images

Listing 7-3: Showing all the images and their categories

Listing 7-4: Filtering images

Listing 7-5: Showing the images searched by the user

Listing 7-6: Finding the area of interest

Listing 7-7: Highlighting the area of interest

Listing 7-8: Finding relevant objects in an image

Listing 7-9: Listing the pictures to score

Listing 7-10: Showing the score

Listing 7-11: Reading a QR code

Listing 7-12: Reading only barcodes of type codabar

Listing 7-13: Recognizing text in an image

Listing 7-14: Translating text from an image

Listing 7-15: Displaying the document to analyze

Listing 7-16: Retrieving the document's whole text

Listing 7-17: Finding paragraphs in a text

Listing 7-18: Extracting key information

Listing 7-19: Extracting lists

Listing 7-20: Extracting tables

Listing 7-21: Extracting barcodes

Listing 7-22: Detecting faces

Listing 7-23: Determining the orientation of the face

Listing 7-24: Determining the quality of selfies

Listing 7-25: Detecting facial features

Listing 7-26: Finding people in an image

Listing 7-27: Detecting body joints

Listing 7-28: Determining if people are raising their hands

Listing 7-29: Identifying hand joints

Listing 7-30: Detecting if the hand is counting numbers

Listing 7-31: Applying a filter

Listing 7-32: Generating barcodes

Listing 7-33: Using a mask

Chapter 8 — Audio Models

Listing 8-1: Checking if it is possible to perform a transcription

Listing 8-2: Reporting the state of the transcriber

Listing 8-3: Transcribing an audio file

Listing 8-4: Starting the transcription

Listing 8-5: Defining properties to process audio streams

Listing 8-6: Setting up the transcriber

Listing 8-7: Start recording from the microphone

Listing 8-8: Generating a stream of audio from the microphone

Listing 8-9: Converting the audio format

Listing 8-10: Finishing the transcription

Listing 8-11: Starting and ending the transcription

Listing 8-12: Translating the transcription

Listing 8-13: Synthesizing text

Listing 8-14: Providing the text to synthesize

Listing 8-15: Modifying the standard voice

Listing 8-16: Retrieving a voice in the user's preferred language

Listing 8-17: Getting the list of voices available for the user

Listing 8-18: Selecting a voice

Listing 8-19: Selecting a premium voice

Listing 8-20: Selecting a premium voice when the view is loaded

Listing 8-21: Selecting a voice by the identifier

Listing 8-22: Responding to the state of the synthesizer

Listing 8-23: Starting and pausing the synthesizer

Listing 8-24: Defining an observer for audio analysis

Listing 8-25: Analyzing an audio file

Listing 8-26: Showing the results of audio analysis

Listing 8-27: Storing the time at which each sound is found

Listing 8-28: Showing the time and category of each sound

Listing 8-29: Analyzing live audio

Listing 8-30: Identifying the categories in real time

Listing 8-31: Controlling the analysis of live audio

Chapter 9 — Siri

Listing 9-1: Defining an app intent

Listing 9-2: Defining our app's observable object

Listing 9-3: Defining our app's interface

Listing 9-4: Defining a shortcut to run our intent

Listing 9-5: Returning a dialog for Siri

Listing 9-6: Using an enumeration to provide options

Listing 9-7: Customizing the options

Listing 9-8: Requesting a value for a parameter

Listing 9-9: Using an ambiguous prompt

Listing 9-10: Requesting a value when necessary

Listing 9-11: Showing multiple dialogs

Listing 9-12: Updating the data model to store a list of movies

Listing 9-13: Disambiguating a parameter

Listing 9-14: Asking users for specific values

Listing 9-15: Defining errors for an intent

Listing 9-16: Throwing errors from an intent

Listing 9-17: Registering a dependency

Listing 9-18: Defining an App Entity

Listing 9-19: Defining a query for an App Entity

Listing 9-20: Defining an intent to work with App Entities

Listing 9-21: Defining a search query

Listing 9-22: Updating the parameters in our shortcuts

Listing 9-23: Returning an array with all the movies in our data model

Listing 9-24: Shortcuts with parameters

Listing 9-25: Showing a snippet view

Listing 9-26: Designing a snippet view

Listing 9-27: Defining a snippet intent

Listing 9-28: Defining an app intent to trigger a snippet intent

Listing 9-29: Defining an interactive view

Listing 9-30: Defining the app intent for the interactive view

Listing 9-31: Storing ordered copies

Listing 9-32: Storing the orders in the movie's entity

Listing 9-33: Defining a query to search for movies by title

Listing 9-34: Triggering the snippet intent from the app intent

Listing 9-35: Implementing the snippet intent

Listing 9-36: Defining the interactive view

Listing 9-37: Defining the intent to process the orders

Listing 9-38: Confirming the order

Listing 9-39: Showing Siri tips

Chapter 10 — Additional Models

Listing 10-1: Loading the model

Listing 10-2: Processing an image

Listing 10-3: Loading the images

Listing 10-4: Getting a prediction

Listing 10-5: Adapting our class to work with the MNIST model

Listing 10-6: JSON request for the OpenAI API

Listing 10-7: Sending requests to the OpenAI API

Listing 10-8: Structure to process the JSON response from the API

Listing 10-9: Taking the user's prompt and showing the response from the model

Listing 10-10: Worker's code

Listing 10-11: Editing the Worker's code

Listing 10-12: Installing Node.js Version Manager

Listing 10-13: Listing version available of Node.js

Listing 10-14: Downloading the latest version of Node.js

Listing 10-15: Creating a Worker

Listing 10-16: Deploying a Worker

Listing 10-17: Installing OpenAI API

Listing 10-18: Accessing OpenAI models from the Worker

Listing 10-19: Using a Worker from our app

Listing 10-20: Sending the user's prompt from the Worker

Listing 10-21: Creating a JSON schema for the model

Listing 10-22: Parsing a JSON response

Listing 10-23: Structure to parse the JSON response

Listing 10-24: Using a Gateway

Chapter 11 — Neural Networks

Listing 11-1: Storing the values of a neural network

Listing 11-2: Performing the forward pass

Listing 11-3: Controlling the training process

Listing 11-4: Calculating the error with the Mean Squared Error function

Listing 11-5: Performing backpropagation

Listing 11-6: Optimizing the neural network

Listing 11-7: Testing optimization

Listing 11-8: Training the neural network

Listing 11-9: Creating scalars and vectors with the MLXArray class

Listing 11-10: Creating vectors of type Float32

Listing 11-11: Converting arrays of type Double

Listing 11-12: Creating a matrix

Listing 11-13: Creating pre-populated matrices and vectors

Listing 11-14: Reading the configuration and accessing the items of an array

Listing 11-15: Processing the items of a tensor

Listing 11-16: Performing operations on the values of a vector

Listing 11-17: Performing operations between two tensors

Listing 11-18: Performing the dot operation

Listing 11-19: Transposing a matrix

Listing 11-20: Calculating the softmax on the values of an output layer

Listing 11-21: Defining the network

Listing 11-22: Initializing the network

Listing 11-23: Defining the loss function

Listing 11-24: Training the network

Listing 11-25: Designing a network for the Iris dataset

Listing 11-26: Loading the Iris dataset

Listing 11-27: Defining the loss function for classification tasks

Listing 11-28: Defining the loss function for classification tasks

Listing 11-29: Applying the ReLU activation function

TABLE OF CONTENTS

Select Country

Paperback

$ 29.95 BUY NOW

Kindle

$ 9.99 BUY NOW

Apple Books

$ 9.99 BUY NOW

Google Books

$ 9.99 BUY NOW

Information

1st Edition

January 2026

ISBN: 978-1-7779782-8-0