<?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/acfb9a8fcae24dea892a655974210c52&quot; frameborder=&quot;0&quot; width=&quot;1670&quot; height=&quot;1252&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1252</height><width>1670</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1252</thumbnail_height><thumbnail_width>1670</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/acfb9a8fcae24dea892a655974210c52-03018d144e60ea5c.gif</thumbnail_url><duration>74.368</duration><title>Adaptive Search Algorithm, Semantic vs Mini Search</title><description>This Loom demonstrates an adaptive search algorithm and how it behaves with semantic search enabled versus disabled. For a discourse graph with semantic search enabled, the presenter shows that results come from semantic search and minsearch is not used. They then show a case for discourse def where semantic search could not be enabled, so semantic returns zero and the system falls back to minsearch. The Loom includes running node search [49] and reviewing the resulting outputs after inserting the results.</description></oembed>