<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<oembed>
  <author_name>rouliiiie</author_name>
  <author_url>https://blog.hatena.ne.jp/rouliiiie/</author_url>
  <blog_title>Ridge-institute R&amp;D Blog</blog_title>
  <blog_url>https://iblog.ridge-i.com/</blog_url>
  <categories>
  </categories>
  <description>Hello! This is Aurélie, an Artificial Intelligence Engineer at Ridge-i. In this blog post, I'll be sharing insights from a small trial where I experimented with LlamaIndex [1] and Qdrant [2] to build a multimodal Retrieval-Augmented Generation (multimodal RAG) system. Introduction Case study design …</description>
  <height>190</height>
  <html>&lt;iframe src=&quot;https://hatenablog-parts.com/embed?url=https%3A%2F%2Fiblog.ridge-i.com%2Fentry%2F2025%2F05%2F08%2F093645&quot; title=&quot;Multimodal RAG experiments with LlamaIndex and Qdrant - Ridge-institute R&amp;amp;D Blog&quot; class=&quot;embed-card embed-blogcard&quot; scrolling=&quot;no&quot; frameborder=&quot;0&quot; style=&quot;display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;&quot;&gt;&lt;/iframe&gt;</html>
  <image_url>https://cdn-ak.f.st-hatena.com/images/fotolife/r/rouliiiie/20250407/20250407150607.png</image_url>
  <provider_name>Hatena Blog</provider_name>
  <provider_url>https://hatena.blog</provider_url>
  <published>2025-05-08 09:36:45</published>
  <title>Multimodal RAG experiments with LlamaIndex and Qdrant</title>
  <type>rich</type>
  <url>https://iblog.ridge-i.com/entry/2025/05/08/093645</url>
  <version>1.0</version>
  <width>100%</width>
</oembed>
