In this talk we'll take a look at the awesome open source library Transformers.js which allows us to run pretrained models right in the browser with no need for servers! Additionally we'll explore how we've brought AI inference and LLMs into Supabase Edge Functions, allowing you to run certain AI workloads faster and more cost-efficiently on the Edge!
—
Thor 雷神 is a Software Developer at Supabase working on DevRel and DX. He's also the organiser of HackerHouse Taiwan, aiming to bring Software Engineer from around the globe together to work from and explore Taiwan.

AI progress is running away on the server-side, where the GPUs live, but the web platform is never that far behind. In this talk we're going to explore the incredible applications you can build in the browser today and in the near future.

You'll see how to build an offline-capable, speech to speech language translation app, a babelfish, using nothing but the web platform. Through this app we'll explore the different ways we can run AI models in the browser today and what may be built into the browser in the future. From low-level standards to high-level experiments, you'll learn how to work with AI on the web.

Bio: 

Phil is a developer relations engineer for Langflow at IBM and Google Developer Expert living in Melbourne, Australia. He loves working with JavaScript, TypeScript or Ruby to build web applications and tools to help developers. He once helped build a website that captured the world's favourite sandwich fillings. He has too many GitHub repositories.

Away from the keyboard, Phil listens to ska punk, hangs out with his miniature dachshund (also called Ruby), and is on a mission to discover the world's best beers.

Phil tweets at @philnash and you can find him elsewhere online at https://philna.sh.

A simple demonstration of how to start a chat with your own data using Supabase powered by OpenAI’s GPT models and retrieval augmented generation (RAG) as pgvector based on https://github.com/supabase-community/chatgpt-your-files

Web AI libraries and models crossed over 1 billion downloads in the last 2 years alone. If you're not yet using machine learning on the client side, now is the time to see what's possible and the benefits it can bring your business over cloud based solutions - such as lower costs, privacy for your end users, and low latency responses suitable for real-time applications.

Learn what's new with the state of Web AI at Google and discover new generative AI models you can run client-side in the browser entirely offline along with key updates from Chrome, TensorFlow.js, MediaPipe, Core ML, Visual Blocks, and beyond.

A must see talk for anyone working in the web space (or is using JavaScript) so you can bring your AI powered ideas to life faster than ever before.