<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>RAG on Prakash&#39;s Blog 👨‍💻</title>
    <link>https://www.prakashbhandari.com.np/tags/rag/</link>
    <description>Recent content in RAG on Prakash&#39;s Blog 👨‍💻</description>
    <generator>Hugo -- 0.112.4</generator>
    <language>en</language>
    <lastBuildDate>Tue, 18 Feb 2025 16:20:01 +1100</lastBuildDate>
    <atom:link href="https://www.prakashbhandari.com.np/tags/rag/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Building a RAG Pipeline for Summarization and Q&amp;A with Llamaindex and OpenAI</title>
      <link>https://www.prakashbhandari.com.np/posts/building-rag-pipeline-for-summarization-and-q-and-a-with-llamaindex-and-openai/</link>
      <pubDate>Fri, 10 Jan 2025 10:22:49 +1100</pubDate>
      <guid>https://www.prakashbhandari.com.np/posts/building-rag-pipeline-for-summarization-and-q-and-a-with-llamaindex-and-openai/</guid>
      <description>In this post, I  will build a basic RAG pipeline using LlamaIndex, featuring both a Q&amp;amp;A Query Engine and a Summarization Query Engine. A Router (`RouterQueryEngine`) will dynamically select the most appropriate query engine to process each query. Here, I’ll walk through how to build a custom RAG pipeline using Python, LlamaIndex, and OpenAI models.</description>
    </item>
  </channel>
</rss>
