<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Semantic-Search on PersonalMediaVault</title><link>https://agustinsrg.github.io/pmv-site/tags/semantic-search/</link><description>Recent content in Semantic-Search on PersonalMediaVault</description><generator>Hugo</generator><language>en</language><atom:link href="https://agustinsrg.github.io/pmv-site/tags/semantic-search/index.xml" rel="self" type="application/rss+xml"/><item><title>Enabling semantic search</title><link>https://agustinsrg.github.io/pmv-site/docs/getting-started/enabling-semantic-search/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://agustinsrg.github.io/pmv-site/docs/getting-started/enabling-semantic-search/</guid><description>&lt;p>This document is a guide on how to enable semantic search for PersonalMediaVault.&lt;/p>
&lt;p>In order to enable semantic search for a vault, you need to perform 2 extra steps:&lt;/p>
&lt;ul>
&lt;li>Download an OpenClip embeddings models&lt;/li>
&lt;li>Enable semantic search by providing the path to the model&lt;/li>
&lt;/ul>
&lt;h2 id="download-openclip-embedding-model">Download OpenClip embedding model&lt;/h2>
&lt;p>The OpenClip model is required in order to transform text and images into a single representation.&lt;/p>
&lt;p>PersonalMediaVault needs a model compatible with &lt;a href="https://github.com/mlfoundations/open_clip">OpenClip&lt;/a> and &lt;a href="https://onnx.ai/">ONNX&lt;/a>.&lt;/p></description></item></channel></rss>