<?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/bddd8a4a6f214e3eac50fd17b82b69c1&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/bddd8a4a6f214e3eac50fd17b82b69c1-da3266dce67db94b.gif</thumbnail_url><duration>301.366</duration><title>RAG Song Recommendation System Demo 🎵</title><description>I demo my RAG-based song recommendation system. I run a Python module with an interactive menu, then enter mood, genre, and use cases like happy pop for workout, energetic music for a party, or concrete music for a trip. It takes some time because the connection is slow, and my Gemini rate limits were expired so it froze during recording. When it works, it returns song recommendations matching my prompts. I did not request any viewer action.</description></oembed>