WebAI: Building the next user experience in the browser
summary
Demonstrates a working client-side RAG pipeline that embeds chunks with huggingface transformers feature-extraction, stores vectors in an IndexedDB vector index and retrieves relevant context to feed a small LLM in the browser via WebGPU/WebAssembly. Implements a three-function agent (detect job description, map required skills to available courses, generate a learning path) and shows a live demo that composes personalized curricula. Notes practical limits: model size, RAM and index scale, but highlights privacy gains and experimental Chrome AI APIs and WebLLM as viable paths.
AI-written summary · about
chapters (8)
- 0:00Introduction to WebAI
- 3:12AI user experience shift
- 5:38Browser advantages for AI
- 8:10Retrieval Augmented Generation
- 14:54RAG implementation demo
- 17:22Agentic patterns in AI
- 20:53Model Context Protocol overview
- 22:43Call to React developers
related talks
02mDiscover Web AI: Client side Agents, Gen AI, and machine learning in the browser
29mClient side Web AI Agents Building smarter user experiences for a future age
38mEmpowering AI Education with Rag: Building Domain-Specific LLM Agents for Enhanced...
24mState of client side AI
21mUnlocking Client-Side AI in Your Web App
41mFrom RAGs to riches: Build an AI document interrogation app in 30 mins
33mLocal Models: How to Run AI in the Browser
53mAI Didn’t Kill the Web, It Moved in!