<?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/7e0992c92ae642c399d70e72de0e8d42&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/7e0992c92ae642c399d70e72de0e8d42-e91978b2d0acab3a.gif</thumbnail_url><duration>297.545</duration><title>Context-Aware Media Agent Overview</title><description>In this video, I walk you through the context-aware media agent I built, which utilizes broadcast transcripts and technical manuals to provide answers based on prior context. I explain how we use ChromaDB for data storage and retrieval, employing a sentence transformer for embedding. I also demonstrate the hybrid search functionality that segments data into relevant categories. Please take a look and let me know your thoughts on the implementation!</description></oembed>