{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/c3e5abc0287d4dd79c85d339ee183fd6\" frameborder=\"0\" width=\"1664\" height=\"1248\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1248,"width":1664,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1248,"thumbnail_width":1664,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/c3e5abc0287d4dd79c85d339ee183fd6-05ffeae5df7fc338.gif","duration":305.9559,"title":"Personal Google Search Engine Demo","description":"In this video, I’m excited to share my personal Google search engine that I built using vector databases and embedding models. I've been tracking all the content I've consumed over the last three years, and I demonstrate how my system scrapes and stores this data in a Postgres database on AWS. I also walk through the functionality of my application server, which allows me to query this content using vector similarity matching. Please take a look and let me know your thoughts!"}