<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:wfw="http://wellformedweb.org/CommentAPI/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:sy="http://purl.org/rss/1.0/modules/syndication/" xmlns:slash="http://purl.org/rss/1.0/modules/slash/" xmlns:memo="https://memo.d.foundation/ns/feed/1">
  <channel>
    <title>rag - Dwarves Memo</title>
    <atom:link href="https://memo.d.foundation/topics/applied-llm/tags/rag/rss.xml" rel="self" type="application/rss+xml" />
    <link>https://memo.d.foundation/topics/applied-llm/tags/rag</link>
    <description>The newest notes tagged rag on Dwarves Memo.</description>
    <lastBuildDate>Wed, 21 Oct 2026 00:00:00 GMT</lastBuildDate>
    <language>en-US</language>
    <sy:updatePeriod>hourly</sy:updatePeriod>
    <sy:updateFrequency>1</sy:updateFrequency>
    <item>
      <title>Related notes by meaning: an embedding index won memo&apos;s Ask and lost the chat eval</title>
      <link>https://memo.d.foundation/memo-related-notes</link>
      <pubDate>Wed, 21 Oct 2026 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[Memo now picks the related notes Ask reads beside each article from a 522-note bge-m3 index instead of the folder a note sits in. The same index lost a blind 40-question eval for the web chat, so chat keeps its topic table for now.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/memo-related-notes</guid>
    </item>
    <item>
      <title>GraphRAG - building a knowledge graph for RAG system</title>
      <link>https://memo.d.foundation/llm/graphrag</link>
      <pubDate>Fri, 01 Nov 2024 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[nnhuyhoang]]></dc:creator>
      <description><![CDATA[In baseline Retrieval Augmented Generation (RAG), sometimes the result might not be accurate as expected since the query itself have multiple layers of reasoning or the answer requires traversing disparate pieces of information through their shared attributes in order to provide new synthesized insights. In this post, we will explore a new approach called GraphRAG which combines the strengths of knowledge graphs and large language models to improve the accuracy of RAG systems]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/llm/graphrag</guid>
    </item>
    <item>
      <title>Evaluating caching in RAG systems</title>
      <link>https://memo.d.foundation/llm/caching-with-rag-system</link>
      <pubDate>Fri, 09 Aug 2024 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[taynguyen]]></dc:creator>
      <description><![CDATA[Caching is a vital technique that boosts performance by storing frequently accessed information. Let's see how it works with RAG. In this article, we will know how cache could be implement in RAG system.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/llm/caching-with-rag-system</guid>
    </item>
    <item>
      <title>Evaluating search engine in RAG systems</title>
      <link>https://memo.d.foundation/llm/hybrid-search</link>
      <pubDate>Thu, 08 Aug 2024 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[datnguyennnx]]></dc:creator>
      <description><![CDATA[Hybrid search comes to solving problems in vector search and full-text search. Let's see how it works. In this article, we will know how hybrid search approach and how to evaluate each search method through metrics in information retrieval.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/llm/hybrid-search</guid>
    </item>
    <item>
      <title>Multimodal: in rag</title>
      <link>https://memo.d.foundation/llm/multimodal-in-rag</link>
      <pubDate>Fri, 28 Jun 2024 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[nnhuyhoang]]></dc:creator>
      <description><![CDATA[In spite of having taken the world by storm, Large Language Models(LLM) still has some limitations such as limited context window and a knowledge cutoff date. Retrieval-Augmented Generation(RAG) steps in to bridge this gap by allowing LLMs to access and utilize external knowledge sources beyond their training data. However, data is not text based only, it also can be image, audio, table in docs,...]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/llm/multimodal-in-rag</guid>
    </item>
    <item>
      <title>Building blocks of a RAG pipeline</title>
      <link>https://memo.d.foundation/llm/rag-building-blocks</link>
      <pubDate>Fri, 09 Jun 2023 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[zlatanpham]]></dc:creator>
      <description><![CDATA[How chunking, hierarchical tree summaries, re-ranking, query caching and vector-store chat memory fit together around a vector database in an LLM application.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/llm/rag-building-blocks</guid>
    </item>
  </channel>
</rss>