<?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/cb6c432060f94d1eb4a384a1f03f3a0a&quot; frameborder=&quot;0&quot; width=&quot;1728&quot; height=&quot;1296&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1296</height><width>1728</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1296</thumbnail_height><thumbnail_width>1728</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/cb6c432060f94d1eb4a384a1f03f3a0a-aeaacd17af7d4ae2.gif</thumbnail_url><duration>80.21</duration><title>Google Drive RAG to Vector Database</title><description>This Loom demonstrates a simple RAG automation that converts a document from Google Drive into a vector database for an AI agent’s memory. The example takes a FAQ file, downloads it from Google Drive, and uses OpenAI Embeddings to turn it into a MINECON vector database under a namespace named FAQ. It then shows a chatbot that queries this vector database to retrieve relevant information, such as answering a user’s question about the return policy based on the document.</description></oembed>