
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>Lawrence Dass Portfolio</title>
      <link>https://lawrence-dass.com//blog</link>
      <description>Full-stack developer and AI/ML engineer based in Vancouver, BC. I build production-grade systems with Next.js, TypeScript, and Node.js, working increasingly at the intersection of LLMs and RAG pipelines. Background includes financial dashboard engineering at Publicis Sapient (client: Wellington Management) and earlier experience in fraud detection and collections.</description>
      <language>en-us</language>
      <managingEditor>lawrence.Dass@outlook.in (Lawrence Dass)</managingEditor>
      <webMaster>lawrence.Dass@outlook.in (Lawrence Dass)</webMaster>
      <lastBuildDate>Tue, 24 Mar 2026 00:00:00 GMT</lastBuildDate>
      <atom:link href="https://lawrence-dass.com//tags/vector-search/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://lawrence-dass.com//blog/benchmarking_4_embedding_models</guid>
    <title>Benchmarking 4 Embedding Models on Real Documents for RAG</title>
    <link>https://lawrence-dass.com//blog/benchmarking_4_embedding_models</link>
    <description>I tested 4 encoders on 141 SEC filings. Voyage led retrieval at half the cost, BGE nearly matched it for free, and this is just the baseline.</description>
    <pubDate>Tue, 24 Mar 2026 00:00:00 GMT</pubDate>
    <author>lawrence.Dass@outlook.in (Lawrence Dass)</author>
    <category>rag</category><category>embeddings</category><category>benchmarking</category><category>vector-search</category>
  </item>

    </channel>
  </rss>
