Smartere Web-Apps mit Angular, WebLLM und Prompt API: lokal und offlinefähig

Slide 1

Slide 1 text

Christian Liebel @christianliebel Consultant Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig

Slide 2

Slide 2 text

Hello, it’s me. Smartere Web-Apps mit Angular, WebLLM und Prompt API 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 Smartere Web-Apps mit Angular, WebLLM und Prompt API 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 Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Expectations Huge downloads! High requirements! Things may break!

Slide 5

Slide 5 text

Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig DEMO

Slide 6

Slide 6 text

(Workshop Edition) Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Demo Use Case DEMO

Slide 7

Slide 7 text

Setup complete? (Node.js, Google Chrome Canary, Editor, Git, macOS/Windows, 20 GB free disk space, 6 GB VRAM) Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Setup (1/2) LAB #0

Slide 8

Slide 8 text

git clone https://github.com/thinktecture/angular- days-2025-spring-genai.git cd angular-days-2025-spring-genai npm i npm start -- --open Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Setup (2/2) LAB #0

Slide 9

Slide 9 text

Smartere Web-Apps mit Angular, WebLLM und Prompt API 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 Smartere Web-Apps mit Angular, WebLLM und Prompt API 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 Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Progressive Web Apps Service Worker Internet Website HTML/JS Cache fetch

Slide 12

Slide 12 text

Overview Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Generative AI Text OpenAI GPT Mistral … Audio/Music Musico Soundraw … Images DALL·E Firefly … Video Sora Runway … Speech Whisper tortoise-tts …

Slide 13

Slide 13 text

Slide 14

Slide 14 text

Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Media DEMO

Slide 15

Slide 15 text

Slide 16

Slide 16 text

Examples Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Generative AI Cloud Providers

Slide 17

Slide 17 text

Drawbacks Smartere Web-Apps mit Angular, WebLLM und Prompt API 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 18

Slide 18 text

Can we run GenAI models locally? Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig

Slide 19

Slide 19 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) Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Large Language Models

Slide 20

Slide 20 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. Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Large Language Models

Slide 21

Slide 21 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 Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Large Language Models

Slide 22

Slide 22 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 Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Large Language Models

Slide 23

Slide 23 text

https://webllm.mlc.ai/ Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig WebLLM DEMO

Slide 24

Slide 24 text

On NPM Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig WebLLM

Slide 25

Slide 25 text

npm i @mlc-ai/web-llm Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig LAB #1

Slide 26

Slide 26 text

(1/4) In app.component.ts, add the following lines: protected readonly progress = signal(0); protected readonly ready = signal(false); protected engine?: MLCEngine; Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Downloading a model LAB #2

Slide 27

Slide 27 text

(2/4) 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); Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Downloading a model LAB #2

Slide 28

Slide 28 text

(3/4) In app.component.html, change the following lines: @if(!ready()) { } Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Downloading a model LAB #2

Slide 29

Slide 29 text

(4/4) Launch the app via npm start. The progress bar should begin to move. Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Downloading a model LAB #2

Slide 30

Slide 30 text

Storing model files locally Smartere Web-Apps mit Angular, WebLLM und Prompt API 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 31

Slide 31 text

Parameter cache Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Cache API

Slide 32

Slide 32 text

Smartere Web-Apps mit Angular, WebLLM und Prompt API 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 33

Slide 33 text

Smartere Web-Apps mit Angular, WebLLM und Prompt API 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 34

Slide 34 text

webgpureport.org Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig WebGPU

Slide 35

Slide 35 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 Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig WebNN Source: https://webmachinelearning.github.io/webnn-intro/ DEMO

Slide 36

Slide 36 text

Smartere Web-Apps mit Angular, WebLLM und Prompt API 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 37

Slide 37 text

Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig WebNN Source: https://github.com/webmachinelearning/webnn/issues/375#issuecomment-2720701672

Slide 38

Slide 38 text

(1/4) In app.component.ts, add the following lines at the top of the class: protected readonly reply = signal(''); Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Model inference LAB #3

Slide 39

Slide 39 text

(2/4) In the runPrompt() method, add the following code: this.reply.set('…'); const chunks = languageModel === 'webllm' ? await this.inferWebLLM(userPrompt) : await this.inferPromptApi(userPrompt); for await (const chunk of chunks) { this.reply.set(chunk); } Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Model inference LAB #3

Slide 40

Slide 40 text

(3/4) In the inferWebLLM() method, add the following code: await this.engine!.resetChat(); const messages: ChatCompletionMessageParam[] = [{role: "user", content: userPrompt}]; const chunks = await this.engine!.chat.completions.create({messages, stream: true}); let reply = ''; for await (const chunk of chunks) { reply += chunk.choices[0]?.delta.content ?? ''; yield reply; } Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Model inference LAB #3

Slide 41

Slide 41 text

(4/4) In app.component.html, change the following line:

{{ reply() }}

You should now be able to send prompts to the model and see the responses in the template. Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Model inference LAB #3

Slide 42

Slide 42 text

Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig

Slide 43

Slide 43 text

npm run build Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig LAB #4

Slide 44

Slide 44 text

1. In angular.json, increase the bundle size for the Angular project (property architect.build.configurations.production.budgets[0] .maximumError) to at least 6MB. 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). Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Build issues LAB #4

Slide 45

Slide 45 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: const text = prompt() ?? ''; this.todos.update(todos => [...todos, { done: false, text }]); Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Todo management LAB #5

Slide 46

Slide 46 text

(2/2) In app.component.html, add the following lines to add todos from the UI: @for (todo of todos(); track $index) { {{ todo.text }} } Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Todo management LAB #5

Slide 47

Slide 47 text

@for (todo of todos(); track $index) { {{ todo.text }} } ⚠ Boo! This pattern is not recommended. Instead, you should set the changed values on the signal. But this messes up with Angular Material… Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Todo management (extended) LAB #6

Slide 48

Slide 48 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 Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Chat with data

Slide 49

Slide 49 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: … Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Chat with data

Slide 50

Slide 50 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. Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Chat with data

Slide 51

Slide 51 text

Using a system & user prompt Adjust the code in inferWebLLM() 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 } ]; Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Chat with data LAB #7

Slide 52

Slide 52 text

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

Slide 53

Slide 53 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.' : ''}`; Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Prompt Engineering LAB #8

Slide 54

Slide 54 text

Alternatives Prompt Engineering Retrieval Augmented Generation Fine-tuning Custom model Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Prompt Engineering Effort

Slide 55

Slide 55 text

Comparison 45 33 1200 0 200 400 600 800 1000 1200 1400 WebLLM (Llama3-8b, M4) Azure OpenAI (gpt-4o-mini) Groq (Llama3-8b) Tokens/sec Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Performance WebLLM/Groq: Own tests (14.11.2024), OpenAI/Azure OpenAI: https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/provisioned-throughput (18.07.2024)

Slide 56

Slide 56 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 Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Stable Diffusion Prompt: A guinea pig eating a watermelon

Slide 57

Slide 57 text

https://websd.mlc.ai/ Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Web Stable Diffusion DEMO

Slide 58

Slide 58 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 Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Local AI Models

Slide 59

Slide 59 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 Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Local AI Models

Slide 60

Slide 60 text

Mitigations Hybrid modes: – Allow the user to switch between cloud/local execution (availability, system requirements) – Deploy OSS model on internal/enterprise infrastructure (privacy) Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Local AI Models

Slide 61

Slide 61 text

Alternatives: Prompt API Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Local AI Models Operating System Website HTML/JS Browser Internet Apple Intelligence Gemini Nano

Slide 62

Slide 62 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 Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Local AI Models https://developer.chrome.com/docs/ai/built-in

Slide 63

Slide 63 text

https://www.google.com/chrome/canary/ about://flags Enables optimization guide on device à EnabledBypassPerfRequirement Prompt API for Gemini Nano à Enabled about://on-device-internals AI in the Browser Smarter Angular apps with WebGPU and WebNN Local AI Models

Slide 64

Slide 64 text

Add the following line to the inferPromptApi() method: const systemPrompt = ` The user will ask questions about their todo list. Here's the user's todo list: ${this.todos().map(todo => `* ${todo.text} (${todo.done ? 'done' : 'not done'})`).join('\n')}`; const session = await window.ai.languageModel.create({ systemPrompt }); const chunks = session.promptStreaming(userPrompt); let reply = ''; for await (const chunk of chunks) { reply += chunk; yield reply; } Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Local AI Models LAB #9

Slide 65

Slide 65 text

Alternatives: Ollama – Local runner for AI models – Offers a local server a website can connect to à allows sharing models across origins – Supported on macOS and Linux (Windows in Preview) https://webml-demo.vercel.app/ https://ollama.ai/ Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Local AI Models

Slide 66

Slide 66 text

Alternatives: Hugging Face Transformers Pre-trained, specialized, significantly smaller models beyond GenAI Examples: – Text generation – Image classification – Translation – Speech recognition – Image-to-text Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Local AI Models

Slide 67

Slide 67 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/ Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Local AI Models

Slide 68

Slide 68 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! Smartere Web-Apps mit Angular, WebLLM und Prompt API Lokal und offlinefähig Summary

Slide 69

Slide 69 text

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