Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig

by Christian Liebel

Slide 1

Slide 1 text

Christian Liebel @christianliebel Consultant Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig

Slide 2

Slide 2 text

Hello, it’s me. Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Christian Liebel X: @christianliebel Email: christian.liebel @thinktecture.com Angular & PWA Slides: thinktecture.com /christian-liebel

Slide 3

Slide 3 text

09:00–10:30 Block 1 10:30–11:00 Coffee Break 11:00–12:30 Block 2 Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Timetable

Slide 4

Slide 4 text

What to expect Focus on web app development Focus on Generative AI Up-to-date insights: the ML/AI field is evolving fast Live demos on real hardware Hands-on labs What not to expect Deep dive into AI specifics, RAG, model finetuning or training Stable libraries or specifications WebSD in Angular 1:1 Support Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Expectations

Slide 5

Slide 5 text

Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig DEMO

Slide 6

Slide 6 text

(Workshop Edition) Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Demo Use Case DEMO

Slide 7

Slide 7 text

Setup complete? (Node.js, Google Chrome, Editor, Git, macOS/Windows, 20 GB free disk space, 6 GB VRAM) Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Setup (1/2) LAB #0

Slide 8

Slide 8 text

git clone https://github.com/thinktecture/angular- days-2024-fall-genai.git cd angular-days-2024-fall-genai npm i npm start -- --open Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Setup (2/2) LAB #0

Slide 9

Slide 9 text

Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Generative AI everywhere Source: https://www.apple.com/chde/apple-intelligence/

Slide 10

Slide 10 text

Run locally on the user’s system Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Single-Page Applications Server- Logik Web API Push Service Web API DBs HTML, JS, CSS, Assets Webserver Webbrowser SPA Client- Logik View HTML/CSS View HTML/CSS View HTML/CSS HTTPS WebSockets HTTPS HTTPS

Slide 11

Slide 11 text

Make SPAs offline-capable Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Progressive Web Apps Service Worker Internet Website HTML/JS Cache fetch

Slide 12

Slide 12 text

Overview Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Generative AI Text OpenAI GPT Mistral … Speech OpenAI Whisper tortoise-tts … Images DALL·E Stable Diffusion … Audio/Music Musico Soundraw …

Slide 13

Slide 13 text

Slide 14

Slide 14 text

Examples Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Generative AI Cloud Providers

Slide 15

Slide 15 text

Drawbacks Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Generative AI Cloud Providers Require a (stable) internet connection Subject to network latency and server availability Data is transferred to the cloud service Require a subscription

Slide 16

Slide 16 text

Can we run GenAI models locally? Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig

Slide 17

Slide 17 text

Large: Trained on lots of data Language: Process and generate text Models: Programs/neural networks Examples: – GPT (ChatGPT, Bing Chat, …) – Gemini, Gemma (Google) – LLaMa (Meta AI) Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Large Language Models

Slide 18

Slide 18 text

Token A meaningful unit of text (e.g., a word, a part of a word, a character). Context Window The maximum amount of tokens the model can process. Parameters/weights Internal variables learned during training, used to make predictions. Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Large Language Models

Slide 19

Slide 19 text

Prompts serve as the universal interface Unstructured text conveying specific semantics Paradigm shift in software architecture Natural language becomes a first-class citizen Caveats Non-determinism and hallucination, prompt injections Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Large Language Models

Slide 20

Slide 20 text

Size Comparison Model:Parameters Size phi3:3b 2.2 GB mistral:7b 4.1 GB llama3:8b 4.7 GB gemma2:9b 5.4 GB gemma2:27b 16 GB llama3:70b 40 GB Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Large Language Models

Slide 21

Slide 21 text

https://webllm.mlc.ai/ Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig WebLLM DEMO

Slide 22

Slide 22 text

On NPM Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig WebLLM

Slide 23

Slide 23 text

npm i @mlc-ai/web-llm Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig LAB #1

Slide 24

Slide 24 text

(1/3) In app.component.ts, add the following lines: protected readonly progress = signal(0); protected readonly ready = signal(false); protected engine?: MLCEngine; Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Downloading a model LAB #2

Slide 25

Slide 25 text

(2/3) In app.component.ts (ngOnInit()), add the following lines: const model = 'Llama-3.2-3B-Instruct-q4f32_1-MLC'; this.engine = await CreateMLCEngine(model, { initProgressCallback: ({ progress }) => this.progress.set(progress) }); this.ready.set(true); Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Downloading a model LAB #2

Slide 26

Slide 26 text

(3/3) In app.component.html, add the following lines:

Ask Launch the app via npm start. The progress bar should begin to move. Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Downloading a model LAB #2

Slide 27

Slide 27 text

Storing model files locally Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Cache API Internet Website HTML/JS Cache with model files Hugging Face Note: Due to the Same-Origin Policy, models cannot be shared across origins.

Slide 28

Slide 28 text

Parameter cache Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Cache API

Slide 29

Slide 29 text

Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig WebAssembly (Wasm) – Bytecode for the web – Compile target for arbitrary languages – Can be faster than JavaScript – WebLLM uses a model-specific Wasm library to accelerate model computations

Slide 30

Slide 30 text

Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig WebGPU – Grants low-level access to the Graphics Processing Unit (GPU) – Near native performance for machine learning applications – Supported by Chromium-based browsers on Windows and macOS from version 113

Slide 31

Slide 31 text

– Grants web apps access to the device’s CPU, GPU and Neural Processing Unit (NPU) – In specification by the WebML Working Group at W3C – Implementation in progress in Chromium (behind a flag) – Even better performance compared to WebGPU Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig WebNN Source: https://webmachinelearning.github.io/webnn-intro/ DEMO

Slide 32

Slide 32 text

Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig WebNN: near-native inference performance Source: Intel. Browser: Chrome Canary 118.0.5943.0, DUT: Dell/Linux/i7-1260P, single p-core, Workloads: MediaPipe solution models (FP32, batch=1)

Slide 33

Slide 33 text

(1/3) In app.component.ts, add the following lines at the top of the class: protected readonly reply = signal(''); Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Model inference LAB #3

Slide 34

Slide 34 text

(2/3) In the runPrompt() method, add the following code: await this.engine!.resetChat(); this.reply.set('…'); const messages: ChatCompletionMessageParam[] = [ { role: "user", content: userPrompt } ]; const reply = await this.engine!.chat.completions.create({ messages }); this.reply.set(reply.choices[0].message.content ?? ''); Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Model inference LAB #3

Slide 35

Slide 35 text

(3/3) In app.component.html, add the following line:

{{ reply() }}

You should now be able to send prompts to the model and see the responses in the template. Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Model inference LAB #3

Slide 36

Slide 36 text

Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig

Slide 37

Slide 37 text

npm run build Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig LAB #4

Slide 38

Slide 38 text

1. In angular.json, increase the bundle size for the Angular project (property architect.build.configurations.production.budgets[0] .maximumError) to at least 5MB. 2. Then, run npm run build again. This time, the build should succeed. 3. If you stopped the development server, don’t forget to bring it back up again (npm start). Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Build issues LAB #4

Slide 39

Slide 39 text

(1/2) In app.component.ts, add the following signal at the top: protected readonly todos = signal([]); Add the following line to the addTodo() method: this.todos.update(todos => [...todos, { done: false, text }]); Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Todo management LAB #5

Slide 40

Slide 40 text

(2/2) In app.component.html, add the following lines to add todos from the UI: Add

{{ todo.text }}

Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Todo management LAB #5

Slide 41

Slide 41 text

In app.component.ts, add the following lines to toggleTodo(): this.todos.update(todos => todos.map((todo, todoIndex) => todoIndex === index ? { ...todo, done: !todo.done } : todo)); In app.component.html, add the following content to the

node: You should now be able to toggle the checkboxes. Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Todo management (extended) LAB #6

Slide 42

Slide 42 text

Concept and limitations The todo data has to be converted into natural language. For the sake of simplicity, we will add all TODOs to the prompt. Remember: LLMs have a context window (Mistral-7B: 8K). If you need to chat with larger sets of text, refer to Retrieval Augmented Generation (RAG). These are the todos: * Wash clothes * Pet the dog * Take out the trash Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Chat with data

Slide 43

Slide 43 text

System prompt Metaprompt that defines… – character – capabilities/limitations – output format – behavior – grounding data Hallucinations and prompt injections cannot be eliminated. You are a helpful assistant. Answer user questions on todos. Generate a valid JSON object. Avoid negative content. These are the user’s todos: … Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Chat with data

Slide 44

Slide 44 text

Flow System message •The user has these todos: 1. … 2. … 3. … User message •How many todos do I have? Assistant message •You have three todos. Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Chat with data

Slide 45

Slide 45 text

Using a system & user prompt Adjust the implementation in runPrompt() to include the system prompt: const systemPrompt = `Here's the user's todo list: ${this.todos().map(todo => `* ${todo.text} (${todo.done ? 'done' : 'not done'})`).join('\n')}`; const messages: ChatCompletionMessageParam[] = [ { role: "system", content: systemPrompt }, { role: "user", content: userPrompt } ]; Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Chat with data LAB #7

Slide 46

Slide 46 text

Techniques – Providing examples (single shot, few shot, …) – Priming outputs – Specify output structure – Repeating instructions – Chain of thought – … Success also depends on the model. Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Prompt Engineering https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/advanced-prompt-engineering

Slide 47

Slide 47 text

const systemPrompt = `You are a helpful assistant. The user will ask questions about their todo list. Briefly answer the questions. Don't try to make up an answer if you don't know it. Here's the user's todo list: ${this.todos().map(todo => `* ${todo.text} (this todo is ${todo.done ? 'done' : 'not done'})`).join('\n')} ${this.todos().length === 0 ? 'The list is empty, there are no todos.' : ''}`; Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Prompt Engineering LAB #8

Slide 48

Slide 48 text

Alternatives Prompt Engineering Retrieval Augmented Generation Fine-tuning Custom model Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Prompt Engineering Effort

Slide 49

Slide 49 text

Add the following line to the runPrompt() method: console.log(reply.usage); Ask a new question and check your console for performance statistics. Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Performance LAB #9

Slide 50

Slide 50 text

Comparison 22.98 33.96 19.08 38.75 564.63 0 100 200 300 400 500 600 WebLLM (Mistral-7b, M1) WebLLM (Mistral-7b, M3) OpenAI (GPT-4) Azure OpenAI (GPT-4) Groq (Mixtral-8x7b) Tokens/sec Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Performance WebLLM/Groq: Own tests (23.03.2024), OpenAI/Azure OpenAI: https://mcplusa.com/comparing-performance-of-openai-gpt-4-and-microsoft-azure-gpt-4/ (31.08.2023)

Slide 51

Slide 51 text

– Open-source text-to-image model – Generates 512x512px images from a prompt – WebSD: special version of Stable Diffusion for the web (2 GB in size) – No npm package this time Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Stable Diffusion Prompt: A guinea pig eating a watermelon

Slide 52

Slide 52 text

https://websd.mlc.ai/ Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Web Stable Diffusion DEMO

Slide 53

Slide 53 text

Live Demo Retrofitting AI image generation into an existing drawing application (https://paint.js.org) Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Web Stable Diffusion DEMO

Slide 54

Slide 54 text

Pros & Cons + Data does not leave the browser (privacy) + High availability (offline support) + Low latency + Stability (no external API changes) + Low cost – Lower quality – High system (RAM, GPU) and bandwidth requirements – Large model size, models cannot always be shared – Model initialization and inference are relatively slow – APIs are experimental Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Local AI Models

Slide 55

Slide 55 text

Mitigations Download model in the background if the user is not on a metered connection Helpful APIs: – Network Information API to estimate the network quality/determine data saver (negative standards position by Apple and Mozilla) – Storage Manager API to estimate the available free disk space Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Local AI Models

Slide 56

Slide 56 text

Mitigations Hybrid modes: – Allow the user to switch between cloud/local execution (availability, system requirements) – Deploy OSS model on internal/enterprise infrastructure (privacy) Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Local AI Models

Slide 57

Slide 57 text

Alternatives: Prompt API Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Local AI Models Operating System Website HTML/JS Browser Internet Apple Intelligence Gemini Nano

Slide 58

Slide 58 text

Alternatives: Prompt API – Exploratory API for local experiments and use case determination – Downloads Gemini Nano into Google Chrome – Model is shared across origins – Uses native APIs directly – Related APIs: Translation API, Writing Assistance APIs Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Local AI Models https://developer.chrome.com/docs/ai/built-in

Slide 59

Slide 59 text

Alternatives: Ollama – Local runner for AI models – Offers a local server a website can connect to → allows sharing models across origins – Supported on macOS and Linux (Windows in Preview) https://webml-demo.vercel.app/ https://ollama.ai/ Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Local AI Models

Slide 60

Slide 60 text

Alternatives: Hugging Face Transformers Pre-trained, specialized, significantly smaller models beyond GenAI Examples: – Text generation – Image classification – Translation – Speech recognition – Image-to-text Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Local AI Models

Slide 61

Slide 61 text

Alternatives: Transformers.js – Pre-trained, specialized, significantly smaller models beyond GenAI – JavaScript library to run Hugging Face transformers in the browser – Supports most of the models https://xenova.github.io/transformers.js/ Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Local AI Models

Slide 62

Slide 62 text

– Cloud-based models remain the most powerful models – Due to their size and high system requirements, local generative AI models are currently rather interesting for very special scenarios (e.g., high privacy demands, offline availability) – Small, specialized models are an interesting alternative (if available) – Large language models are becoming more compact and efficient – Vendors start shipping AI models with their devices – Devices are becoming more powerful for running AI tasks – Experiment with the AI APIs and make your Angular App smarter! Angular-Apps smarter machen mit Generative AI: lokal und offlinefähig Summary

Slide 63

Slide 63 text

Thank you for your kind attention! Christian Liebel @christianliebel [email protected]