<?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/bc8ae9c8d28f41b69a8c43a6c851ea7c&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/bc8ae9c8d28f41b69a8c43a6c851ea7c-dcc1684ef39ff2b1.gif</thumbnail_url><duration>300.264</duration><title>Agentic Rag chatbot 📊</title><description>In this video, I discuss my submission for the Legendic Life Chat about an assignment focused on streamability and file uploads. I demonstrate uploading a quarterly result file and explain the company&apos;s plans for upcoming launches. I outline the architecture of the system, which includes three main agents: ingestion, retrieval, and LLM response. I also share my experience using the Google Flend T5 model and the Mistral model, highlighting the superior performance of Mistral. I encourage viewers to check the GitHub repository for the code and further details.</description></oembed>