The latest articles on DEV Community by Rajnish Raj (@rajnish_raj_7cd820516cd0d). https://dev.to/rajnish_raj_7cd820516cd0d https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F1690202%2Fe7bd2605-9566-4869-9da0-07c41236d286.png https://dev.to/rajnish_raj_7cd820516cd0d en Rajnish Raj Sat, 26 Jul 2025 05:19:41 +0000 https://dev.to/rajnish_raj_7cd820516cd0d/dask-search-through-2943-dsa-problem-using-natural-language-59gi https://dev.to/rajnish_raj_7cd820516cd0d/dask-search-through-2943-dsa-problem-using-natural-language-59gi <p><em>This is a submission for the <a href="https://dev.to/challenges/algolia-2025-07-09">Algolia MCP Server Challenge</a></em></p> <h2> What I Built </h2> <p>I built an AI-powered search engine that search through a database of about 3,000 DSA problems using natural language queries. Used Gemini API for AI responses and Algolia JavaScript API for fast, relevant search results.</p> <p><strong>Features</strong></p> <ul> <li>Search with a natural language query, not keywords</li> <li>automatic filter selection from query.</li> </ul> <h2> Demo </h2> <p>Live - <a href="https://dask-omega.vercel.app/" rel="noopener noreferrer">https://dask-omega.vercel.app/</a><br> Github - <a href="https://github.com/Rajnish8292/dask" rel="noopener noreferrer">https://github.com/Rajnish8292/dask</a><br> <iframe src="https://player.vimeo.com/video/1104666226" width="710" height="399"> </iframe> </p> <h2> How I Utilized the Algolia MCP Server </h2> <p>Algolia helps to filter search results based on facets and facetFilter and provide fast result.</p> <h2> Key Takeaways </h2> <p>I tried to apply multiple facetFilters at a single time, but that did not work well, so I took every possibility for facetFilter and then sent an array of requests to Aloglia for better results. <br> E.g<br> </p> <div class="highlight js-code-highlight"> <pre class="highlight plaintext"><code>// The issue with this method was that the first page often returned multiple hits with filters like "Google," "Array," and/or "Easy. facetFilters = [['google', 'zomato'], ['array', 'graph'], ['easy', hard]] // To overcome this problem, I break a single request into multiple requests facetFilterArray = [ [['google'], ['array'], ['easy']], [['google'], ['graph'], ['easy']], [['google'], ['array'], ['hard']], [['google'], ['graph'], ['hard']], [['Zomato'], ['array'], ['easy']], [['Zomato'], ['graph'], ['easy']], [['Zomato'], ['array'], ['hard']], [['Zomato'], ['graph'], ['hard']], ] </code></pre> </div> devchallenge algoliachallenge webdev ai