<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Frameworks on Samarthya</title><link>https://samarthya.me/tags/frameworks/</link><description>Recent content in Frameworks on Samarthya</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© Samarthya 2018-2026. All rights reserved.</copyright><lastBuildDate>Mon, 26 Oct 2026 18:00:00 -0400</lastBuildDate><atom:link href="https://samarthya.me/tags/frameworks/index.xml" rel="self" type="application/rss+xml"/><item><title>AI in practice, part 1: Choosing the right framework</title><link>https://samarthya.me/posts/ai-in-practice-1-choosing-a-framework/</link><pubDate>Mon, 26 Oct 2026 18:00:00 -0400</pubDate><guid>https://samarthya.me/posts/ai-in-practice-1-choosing-a-framework/</guid><description>&lt;div class="lead text-neutral-500 dark:text-neutral-400 !mb-9 text-xl"&gt;&#10; &amp;ldquo;Which AI framework should I use?&amp;rdquo; has no single answer, because the names people throw around do&#10;completely different jobs. Put them on a map first, and the choice usually makes itself.&#10;&lt;/div&gt;&#10;&#10;&lt;p&gt;This series picks up where my earlier posts left off. Those covered the ideas: &lt;a href="https://samarthya.me/posts/genai/" &gt;what generative AI&#10;is&lt;/a&gt;, &lt;a href="https://samarthya.me/posts/language-model/" &gt;how transformers pay attention&lt;/a&gt;, &lt;a href="https://samarthya.me/posts/matrix-multiplication-to-gpus/" &gt;why GPUs matter&lt;/a&gt;,&#10;and two hands-on builds (&lt;a href="https://samarthya.me/posts/building-a-minimal-langchain-ollama-demo/" &gt;LangChain with Ollama&lt;/a&gt; and a&#10;&lt;a href="https://samarthya.me/posts/building-a-practical-retrieval-augmented-personal-assistant-rag/" &gt;RAG assistant&lt;/a&gt;). This part is the map&#10;that connects them.&lt;/p&gt;</description></item></channel></rss>