<?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/7e9392e6ba2049299db590e544a34cd0&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/7e9392e6ba2049299db590e544a34cd0-4f8b9190df3ff992.gif</thumbnail_url><duration>322.349</duration><title>RAG Pipeline for PDF Document QA</title><description>Hi everyone, I am David. I am building a RAC system pipeline that can process BDF documents, extract key information, store embeddings in a vector database, and answer questions directly from the source. In the demo, it loads the saved index, retrieves answers in about 10 seconds, and shows the source PDFs. It can list products and descriptions, answer specific queries like the maximum dose for CyTVAR products, and find expired products with expiration dates and lot info. It also returns no answer when info is missing, like price. No action was requested from viewers.</description></oembed>