<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>rag on AgilePhD</title>
    <link>http://blog.agilephd.com/tags/rag/</link>
    <description>Recent content in rag on AgilePhD</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 19 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="http://blog.agilephd.com/tags/rag/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Building an LLM Application without a Framework</title>
      <link>http://blog.agilephd.com/posts/llm_no_framework/</link>
      <pubDate>Wed, 19 Aug 2026 00:00:00 +0000</pubDate>
      
      <guid>http://blog.agilephd.com/posts/llm_no_framework/</guid>
      <description>After rebuilding this script with LangChain a few times now, I wanted to try something different: skip the framework entirely and call the vendor SDKs directly. Partly out of curiosity, partly because I kept noticing that for a script this small (one PDF, one question, no agents, no multi-step tool calls), LangChain&amp;rsquo;s chains and retrievers were doing a fairly small amount of actual work under a fairly large amount of abstraction.</description>
    </item>
    
  </channel>
</rss>
