<?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/d76911e2d84440f58a7032df410bd317&quot; frameborder=&quot;0&quot; width=&quot;1108&quot; height=&quot;831&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>831</height><width>1108</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>831</thumbnail_height><thumbnail_width>1108</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/d76911e2d84440f58a7032df410bd317-e09585fa71f45f3a.gif</thumbnail_url><duration>146.0596</duration><title>Exploring Rav Engine X: A Modular Retrieval Augmented Generation Pipeline</title><description>In this video, I provide a quick walkthrough of the Rav Engine X, a modular production pipeline designed for retrieval-augmented generation. I explain how the system works, from uploading a PDF document to generating answers using vector similarity and a cross-encoder. You can view the retrieved context, final answers, and evaluation metrics, which can be exported as JSON or CSV files. I encourage you to try the live demo at radenginex.on.dander.com and explore the GitHub repository for the full code. Thank you for watching!</description></oembed>