<?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/e8d4c852300d46678484d22b9debb49a&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/e8d4c852300d46678484d22b9debb49a-1714969597665.gif</thumbnail_url><duration>268.441</duration><title>Exploring Retrieval Augmentation (RAG) with Langchain</title><description>In this video, I demonstrate how to use a rag chartboard to augment document generation. I explain the concept of KPI keys and the three models available through the GROP API. I also discuss the two types of document searches: general docs and Git repositories. I walk through the process of fetching and chunking a document, as well as using file filters for Git repositories. The video provides important context and instructions for viewers to understand and implement document augmentation.</description></oembed>