<?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/7d196f914db442a592a66ec75c1f9efb&quot; frameborder=&quot;0&quot; width=&quot;1664&quot; height=&quot;1248&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1248</height><width>1664</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1248</thumbnail_height><thumbnail_width>1664</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/7d196f914db442a592a66ec75c1f9efb-286e016109901409.gif</thumbnail_url><duration>5018.9238</duration><title>Building an AI-Powered Research Assistant with Semantic Chunking and Indexing</title><description>In this video, I walk through the process of building an AI-powered MCP RAG server to help manage and index research papers effectively. We discuss the importance of semantic chunking and using the FAISS index for efficient information retrieval. I also highlight the need to ensure that our .env file is secure and not committed to the repository. I request viewers to follow along by testing the tools and implementing the phases as we develop the server. Overall, this session aims to equip you with the knowledge to create a robust system for handling academic research efficiently.</description></oembed>