<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Tutorials &amp; Examples on Qdrant - Vector Search Engine</title><link>https://deploy-preview-2329--condescending-goldwasser-91acf0.netlify.app/documentation/tutorials-and-examples/</link><description>Recent content in Tutorials &amp; Examples on Qdrant - Vector Search Engine</description><generator>Hugo</generator><language>en-us</language><managingEditor>info@qdrant.tech (Andrey Vasnetsov)</managingEditor><webMaster>info@qdrant.tech (Andrey Vasnetsov)</webMaster><atom:link href="https://deploy-preview-2329--condescending-goldwasser-91acf0.netlify.app/documentation/tutorials-and-examples/index.xml" rel="self" type="application/rss+xml"/><item><title>Cloud Inference Hybrid Search</title><link>https://deploy-preview-2329--condescending-goldwasser-91acf0.netlify.app/documentation/tutorials-and-examples/cloud-inference-hybrid-search/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><author>info@qdrant.tech (Andrey Vasnetsov)</author><guid>https://deploy-preview-2329--condescending-goldwasser-91acf0.netlify.app/documentation/tutorials-and-examples/cloud-inference-hybrid-search/</guid><description>&lt;h1 id="hybrid-search-using-qdrant-cloud-inference">Hybrid Search Using Qdrant Cloud Inference&lt;/h1>
&lt;table>
 &lt;thead>
 &lt;tr>
 &lt;th>Time: 30 min&lt;/th>
 &lt;th>Level: Intermediate&lt;/th>
 &lt;/tr>
 &lt;/thead>
 &lt;tbody>
 &lt;/tbody>
&lt;/table>
&lt;p>In this tutorial, we&amp;rsquo;ll walkthrough building a &lt;strong>hybrid semantic search engine&lt;/strong> using Qdrant Cloud&amp;rsquo;s built-in &lt;a href="https://deploy-preview-2329--condescending-goldwasser-91acf0.netlify.app/documentation/cloud/inference/">inference&lt;/a> capabilities. You&amp;rsquo;ll learn how to:&lt;/p>
&lt;ul>
&lt;li>Automatically embed your data using &lt;a href="https://deploy-preview-2329--condescending-goldwasser-91acf0.netlify.app/documentation/cloud/inference/">cloud Inference&lt;/a> without needing to run local models,&lt;/li>
&lt;li>Combine dense semantic embeddings with &lt;a href="https://qdrant.tech/documentation/tutorials-search-engineering/reranking-hybrid-search/" target="_blank" rel="noopener nofollow">sparse BM25 keywords&lt;/a>, and&lt;/li>
&lt;li>Perform hybrid search using &lt;a href="https://deploy-preview-2329--condescending-goldwasser-91acf0.netlify.app/documentation/search/hybrid-queries/">Reciprocal Rank Fusion (RRF)&lt;/a> to retrieve the most relevant results.&lt;/li>
&lt;/ul>
&lt;h2 id="initialize-the-client">Initialize the Client&lt;/h2>
&lt;p>Initialize the Qdrant client after creating a &lt;a href="https://deploy-preview-2329--condescending-goldwasser-91acf0.netlify.app/documentation/cloud/">Qdrant Cloud account&lt;/a> and a &lt;a href="https://deploy-preview-2329--condescending-goldwasser-91acf0.netlify.app/documentation/cloud/create-cluster/">dedicated paid cluster&lt;/a>. Set &lt;code>cloud_inference&lt;/code> to &lt;code>True&lt;/code> to enable &lt;a href="https://deploy-preview-2329--condescending-goldwasser-91acf0.netlify.app/documentation/cloud/inference/">cloud inference&lt;/a>.&lt;/p></description></item></channel></rss>