Bring AI-Based Search to Your Web App
summary
Demo shows a working face‑filter proof of concept using the Face Detection API and webcam to add glasses in-browser, plus a separate set of demos that actually index and query 10 million Wikipedia paragraphs via a vector database (Weaviate) and multilingual/vectorizers (Cohere, OpenAI) for semantic search, image lookup with CLIP, and on‑the‑fly GPT summarization. Live coding runs, queries return plausible results, and image matches find celebrities — so the talk is about concrete tools, demoed builds, and results that mostly work.
AI-written summary · about
chapters (10)
- 0:00Introduction to AI search
- 1:37The surge of machine learning
- 2:56Limitations of traditional search
- 4:25What is semantic search?
- 5:55Understanding vector embeddings
- 8:01Multimodal AI applications
- 8:55JavaScript and vector databases
- 10:23Live demo: Text search
- 17:37Live demo: Image search
- 20:27Conclusion and summary
related talks
31mBring AI based Search to Your Website
02mDiscover Web AI: Client side Agents, Gen AI, and machine learning in the browser
49mReal Time Face Detection through a Webcam Using AI
23mWebAI: Building the next user experience in the browser
11mAI-powered JavaScript applications
59mHow to add genuinely useful AI to your webapp (not just chatbots)
44mThe age of applied AI
01h 03mIt's All About AI