<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI on PAUL'S BLOG</title><link>https://paulyu.dev/categories/ai/</link><description>Recent content in AI on PAUL'S BLOG</description><generator>Hugo</generator><language>en</language><lastBuildDate>Wed, 08 Oct 2025 13:00:00 +0000</lastBuildDate><atom:link href="https://paulyu.dev/categories/ai/index.xml" rel="self" type="application/rss+xml"/><item><title>Local LLMs: Running Ollama and Open WebUI in Docker on Ubuntu</title><link>https://paulyu.dev/article/ollama-and-openwebui-containers/</link><pubDate>Wed, 08 Oct 2025 13:00:00 +0000</pubDate><guid>https://paulyu.dev/article/ollama-and-openwebui-containers/</guid><description>&lt;p&gt;&lt;a href="https://docs.ollama.com/"&gt;Ollama&lt;/a&gt; is a popular tool for running large language models (LLMs) locally on your machine. It provides a simple interface to interact with various models without needing an internet connection. &lt;a href="https://docs.openwebui.com"&gt;Open WebUI&lt;/a&gt; is a web-based user interface that allows you to interact with LLMs through a browser.&lt;/p&gt;
&lt;p&gt;I am working on an Ubuntu 24.04.3 LTS Desktop machine with decent hardware to run models locally, so my preference is to run Ollama as a local service rather than confining it to a container. This way, Ollama can take full advantage of my machine&amp;rsquo;s capabilities, especially the GPU.&lt;/p&gt;</description></item><item><title>Build a Weather MCP Server with Rust: Complete Tutorial for AI Integration</title><link>https://paulyu.dev/article/rust-mcp-server-weather-tutorial/</link><pubDate>Tue, 10 Jun 2025 13:00:00 +0000</pubDate><guid>https://paulyu.dev/article/rust-mcp-server-weather-tutorial/</guid><description>&lt;p&gt;Building AI tools that can access real-time data requires bridging the gap between language models and external APIs. The Model Context Protocol (MCP) makes this possible by providing a standard way for AI assistants to interact with data sources.&lt;/p&gt;
&lt;p&gt;In this tutorial, we&amp;rsquo;ll build a weather MCP server using Rust that connects to the National Weather Service API, giving any MCP-compatible AI assistant the ability to fetch live weather alerts and forecasts.&lt;/p&gt;</description></item><item><title>Soaring to New Heights with Kaito: The Kubernetes AI Toolchain Operator</title><link>https://paulyu.dev/article/soaring-with-kaito/</link><pubDate>Wed, 20 Mar 2024 14:00:00 +0000</pubDate><guid>https://paulyu.dev/article/soaring-with-kaito/</guid><description>&lt;p&gt;Earlier today at KubeCon Europe 2024, &lt;a href="https://twitter.com/jorgefpalma"&gt;Jorge Palma&lt;/a&gt; of the AKS team gave a &lt;a href="https://x.com/CloudNativeFdn/status/1770375558607647132?s=20"&gt;keynote talk on Kaito, the Kubernetes AI Toolchain Operator&lt;/a&gt;.&lt;/p&gt;
&lt;blockquote class="twitter-tweet"&gt;&lt;p lang="en" dir="ltr"&gt;Next keynote speaker &lt;a href="https://x.com/jorgefpalma?ref_src=twsrc%5Etfw"&gt;@jorgefpalma&lt;/a&gt; 🙌 we are truly living in the AI revolution &lt;a href="https://t.co/ATxLWUKDeD"&gt;pic.twitter.com/ATxLWUKDeD&lt;/a&gt;&lt;/p&gt;&amp;mdash; CNCF (@CloudNativeFdn) &lt;a href="https://x.com/CloudNativeFdn/status/1770375558607647132?ref_src=twsrc%5Etfw"&gt;March 20, 2024&lt;/a&gt;&lt;/blockquote&gt;
&lt;script async src="https://platform.x.com/widgets.js" charset="utf-8"&gt;&lt;/script&gt;


&lt;p&gt;This tool has been released as an &lt;a href="https://github.com/Azure/kaito"&gt;open-source project&lt;/a&gt; a few months back and you may or may not have heard of it.&lt;/p&gt;
&lt;p&gt;So if you don&amp;rsquo;t know, now you know&amp;hellip;&lt;/p&gt;
&lt;p&gt;You&amp;rsquo;re probably thinking, &amp;ldquo;but what is it, and what can it do for me?&amp;rdquo; 🤔&lt;/p&gt;</description></item></channel></rss>