{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/42d33ccb653641e0bbd7cf5823d66845\" frameborder=\"0\" width=\"1658\" height=\"1243\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1243,"width":1658,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1243,"thumbnail_width":1658,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/42d33ccb653641e0bbd7cf5823d66845-28df4bf95696103c.gif","duration":77.976,"title":"RAG enabled podcast search","description":"I’m feeling uncertain about my job search, and I wanted to show you a better way than traditional search. In the background, we take YouTube transcripts, chunk them into 1200 plus searchable segments, and store them in a vector database. When you type something like I feel overwhelmed and click Find episodes, the query is embedded and we run a hybrid search to return 2 to 3 minute clips with exact timestamps. If you click a result, you go to the YouTube video. You can also adjust semantic weights and the number of chunks to retrieve, and give feedback."}