Empowering Vue Apps with AI
summary
Builds a JavaScript-only agent that augments LLM answers with site data: scrapes a page, splits into 400-char chunks with 20-char overlap, turns each chunk into OpenAI embeddings, stores vectors in Supabase vector DB, then retrieves the top eight matches above ~50% similarity and sends that context to Gemini for generation. Demonstrates live queries (correctly returns May 15–17 for the event) and shows browser-side models via Hugging Face / Sova Transformers for offline sentiment analysis, proving the approach works end-to-end.
AI-written summary · about
chapters (4)
related talks
49mBuilding AI Enabled Web Apps
22mClient side Web AI Agents: Building smarter user experiences for future agentic ...
29mClient side Web AI Agents Building smarter user experiences for a future age
01h 00mHow to work with generative AI in JavaScript
45mAn AI-Enabled Framework? Using LLMs to Put People First
27mAI-Generated React Server Components
42mAdd Useful AI to Your Web App (Not Just Chatbots)
57mSmart Chat App with Vue, AI and Serverless Function Solution LIVE