Prompt engineering for iOS developers (How LLMs and GenAI work)

Prompt engineering for iOS developers

How LLMs work
Generative AI as a service
Prompt engineering patterns
Pair programming with AI tools

How LLMs work
Generative Pre-trained Transformer

How LLMs work - GPT architecture
Input processing
Input
Output
Decoder
Contextual and Session Handling
Safety and Content Filters
Bootstrap prompts

How LLMs work - Tokenisation
Swift is a powerful and intuitive programming language for all Apple platforms.

How LLMs work - Token Embeddings
-0.05,
0.017
…
-0.01
Vectors with 12288 dimensions (features) and positional encoding
-0.03,
0.118
…
-0.02
-0.01,
0.007
…
-0.004
…

This vector encapsulates the semantic meaning of Google, without the
semantics of the word Kotlin, and also includes the semantics of the
word Swift.
Google - Kotlin + Swift = ?

Google - Kotlin + Swift = Apple

apple, 0.426
spotify, 0.396
amazon, 0.393
net
fl
ix, 0.387
yahoo, 0.382
snapchat, 0.371
huawei, 0.368
Google - Kotlin + Swift =

How LLMs work - GPT architecture
Input processing
Transformer layer
Transformer layer
Transformer layer
120 layers (GPT4)
Next word prediction
Decoder
Input
Output
Input +
next word

Generative AI as a service - OpenAI API

{
"model": "gpt-3.5-turbo",
"messages": [{
"role": "user",
"content": "Describe Turin in one sentence"
}],
"temperature": 0.7
}
POST https://api.openai.com/v1/chat/completions

struct AIMessage: Codable {
let role: String
let prompt: String
}
struct AIRequest: Codable {
let model: String
let messages: [AIMessage]
let temperature: Double
}
extension AIRequest {
static func gpt3_5Turbo(prompt: String)
-
>
AIRequest {
.init(model: "gpt-3.5-turbo",
messages: [
.init(role: "user", prompt: prompt)
],
temperature: 0.7
)
}
}

}
@MainActor
func invoke(prompt: String) async throws
-
>
String {

let (data, response) = try await URLSession.shared.data(for: request)
guard let httpURLResponse = (response as? HTTPURLResponse) else {
throw AIServiceError.badResponse
}
guard 200
.
.
.
399 ~= httpURLResponse.statusCode else {
throw AIServiceError.httpError(
code: httpURLResponse.statusCode,
description: String(data: data, encoding: .utf8)
?
?
""
)
}
let aiResponse = try decoder.decode(AIResponse.self, from: data)
return aiResponse.choices.f
i
rst
?
.
message.content
?
?
""
}
let openAIURL = URL(string: "https:
/
/
api.openai.com/v1/chat/completions")!
var request = URLRequest(url: openAIURL)
for (f
i
eld, value) in conf
i
g {
request.setValue(value, forHTTPHeaderField: f
i
eld)
}
request.httpMethod = "POST"
request.httpBody = try encoder.encode(AIRequest.gpt3_5Turbo(prompt: prompt))
@MainActor
func invoke(prompt: String) async throws
-
>
String {

Generative AI as a service work - OpenAI API

Generative AI as a service work - OpenAI API pricing
Model Input Output
gpt-3.5-turbo $1.50 / 1M tokens $2.00 / 1M tokens
gpt-4 $30.00 / 1M tokens $60.00 / 1M tokens
gpt-4-32k $60.00 / 1M tokens $120.00 / 1M tokens

Generative AI as a service - Amazon Bedrock

Generative AI as a service work - Amazon Bedrock
Model Input Output
Titan Text Lite $0.30 / 1M tokens $0.40 / 1M tokens
Claude 3 Haiku $0.25 / 1M tokens $0.15 / 1M tokens
Titan Image
Generator
$0.005 / per image

AWS
API Gateway
Lambda
Bedrock
iOS app

def invoke_model(prompt: str)
:
try:
enclosed_prompt = "Human: " + prompt + "nnAssistant:"
body = {
"prompt": enclosed_prompt,
"max_tokens_to_sample": 500,
"temperature": 0.5,
"stop_sequences": ["nnHuman:"],
}
bedrock_runtime_client = boto3.client('bedrock
-
runtime')
response = bedrock_runtime_client.invoke_model(
modelId = "anthropic.claude
-
v2", body = json.dumps(body)
)
response_body = json.loads(response["body"].read())
completion = response_body["completion"]
return completion
except Exception as e:
raise e

def lambda_handler(event, context)
:
body = json.loads(event["body"])
prompt = body["content"]
if (event["headers"]["authorization"]
!
=
key)
:
return {
'statusCode': 401
}
try:
completion = invoke_model(prompt = prompt)
return {
'statusCode': 200,
'body': json.dumps({"content": completion})
}
return {
'statusCode': 400,
'body': json.dumps(str(e))
}

POST https://[uuid]...amazonaws.com/dev/completions
{
"content": "Describe Turin in one sentence"
}

def schedule_prompt_template(content: str)
-
>
str:
return f"""
<context>
.
.
.
/
/
Swift Heroes 2024 schedule
.
.
.
.
.
.
<
/
context>
Task for Assistent:
Find the most relevant answer in the context
<question>
{content}
<
/
question>
"""

def lambda_handler(event, context)
:
…
try:
templatedPrompt = prompt
if template
=
=
"schedule":
templatedPrompt = schedule_prompt_template(content = prompt)
elif template
=
=
"chat":
templatedPrompt = chat_context_template(content = prompt)
completion = invoke_claude(prompt = templatedPrompt)
return {
'statusCode': 200,
'body': json.dumps({"content": completion})
}
…

POST https://[uuid]...amazonaws.com/dev/completions
{
"content": "Describe Turin in one sentence”,
"template": “schedule"
}

@MainActor
func invokeBedrock(content: String, template: AITemplate = .schedule) async throws
-
>
String {
…
request.httpBody = try encoder.encode(BedrockAIRequest(content: content,
template: template.rawValue))
…
let bedrockResponse = try decoder.decode(BedrockAIResponse.self, from: data)
return bedrockResponse.content
}
let answer = try await aiService.invokeBedrock(content: text, template: .schedule)
struct BedrockAIRequest: Codable {
let content: String
let template: String
}
enum AITemplate: String {
case schedule, chat
}

Prompt engineering
The emerging skill set focused on designing and optimizing inputs for AI
systems to ensure they generate optimal outputs.

One-shot, Few-shot and Zero-shot prompts
Summarize all the talks between context tags
Provide output as an array of json objects with a title, one main topic, and an array of tags.
The tags should not repeat the main topic.
<example>
Title: "Inclusive design: crafting Accessible apps for all of us"
Abstract: "One of the main goals for an app developer should be to reach everyone. ...
<result>
{{
"title": "Inclusive design: crafting Accessible apps for all of us"
"topic": "Accessibility"
"tags": ["user experience", "design", "assistance", "tools", "SwiftUI", "Swift", "Apple"]
}}
</result>
<context>
// Swift Heroes 2024 schedule …
</context>
</example>

[
{
"title": "Building Swift CLIs that your users and contributors love",
"topic": "Swift CLIs",
"tags": ["terminal", "Tuist", "contributors"]
},
{
"title": "Macro Polo: A new generation of code generation",
"topic": "Swift Macros",
"tags": ["code generation", "modules", "examples"]
},
{
"title": "Typestate - the new Design Pattern in Swift 5.9",
"topic": "Typestate Design Pattern",
"tags": ["state machines", "memory ownership", "generics", "constraints", "safety"]
},
{
"title": "A Tale of Modular Architecture with SPM",
"topic": "Modular Architecture",
"tags": ["MVVM", "SwiftUI", "SPM"]
},
.
.
.
]

Persona and audience
How does async/await work in Swift?
Act as an Experienced iOS developer
Explain to 12 years old

Chain-of-thought
How does async/await work in Swift?
Act as an Experienced iOS developer
Explain to the Product manager
Follow this Chain-of-thought:
- Technical details using understandable to the audience analogy
- Bene
fi
ts relevant for the audience
- Additional things to consider

Pair programming with AI tools - Copilot

Pair programming with AI tools - Copilot Chat

Pair programming with AI tools - ChatGPT
Discovering Swift Packages
Converting from legacy code
Writing unit tests and generating test data
Multiplatform development
Brainstorming and evaluating ideas

Prompt engineering for iOS developers (How LLMs and GenAI work)

Related slideshows

More Related Content

Similar to Prompt engineering for iOS developers (How LLMs and GenAI work)

Similar to Prompt engineering for iOS developers (How LLMs and GenAI work) (20)

More from Andrey Volobuev

More from Andrey Volobuev (9)

Recently uploaded

Recently uploaded (20)

Prompt engineering for iOS developers (How LLMs and GenAI work)