Advanced search for your e-commerce website
summary
Shows that replacing keyword search with semantic search via vector embeddings (GPT and Hugging Face models) yields immediate relevance gains, handles misspellings and image queries, and supports personalization and boolean filters; demo uses an authentic vector DB (V Discovery / Vantage) with real data and returns results almost instantly. Engineers report live indexing at 50 million documents, model embed time 20–80 ms, and end-to-end query <200 ms latency, and the demo works.
AI-written summary · about
chapters (14)
- 0:00AI in e-commerce intro
- 1:06AI tech impact optimism
- 2:32AI enhancements for e-commerce
- 3:15AI use cases for e-commerce
- 7:28Modern AI tools and vector DBs
- 8:31Semantic search challenges
- 10:17Vector databases intro
- 12:45Vectors power ML models
- 13:27Vector DBs revolution
- 16:16Vector similarity search
- 17:43Key considerations for vector database quality
- 19:48Rule-based to vector search
- 20:29Live demo: Vantage Discovery
- 26:46Q&A: DB performance & embeddings
related talks
30mSearch on Steroids — A Story of Semantics
32mBuilding semantic search using Deep Learning
22mAI-Powered Personalized Discovery with Graph Search and VLM-Enhanced Embeddings
39mAI-Powered Search in Modern E-Commerce
39mAI-powered Semantic Search; A story of broken promises?
22mThe Capabilities of Semantic Search
40mVespa.ai’s Personalized Search: Advanced Ranking & Tensor framework
27mMachine Learning for Advanced AI Search