<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/b0616294d9994c67a09ca40c090d781f&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/b0616294d9994c67a09ca40c090d781f-0e7e037916304304.gif</thumbnail_url><duration>172.006</duration><title>AI Music Recommender Playlist from Prompts 🎵</title><description>Hi, I am Rivang Boothu, and this is my presentation for the AI Music Recommender. I walk through how it takes a user vibe or description, searches a dataset with RAG, and generates a 24 song playlist. I explain how apps like Spotify let users enter a prompt to get recommendations based on BPM, dancability, rhythm, mood, genre, energy, tempo, valence, and similar features. I also describe how the system interprets the text into a vibe JSON and ranks songs by closeness to that representation. I begin a realistic way to test it.</description></oembed>