index.html (2620B)
1 <!DOCTYPE html> 2 <html lang="en"> 3 <head> 4 <link rel="stylesheet" href="/style.css" type="text/css"> 5 <meta charset="utf-8"> 6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8"> 7 <meta name="viewport" content="width=device-width, initial-scale=1.0"> 8 <link rel="stylesheet" type="text/css" href="/style.css"> 9 <link rel="icon" href="data:image/svg+xml,<svg xmlns=%22http://www.w3.org/2000/svg%22 viewBox=%220 0 100 100%22><text y=%22.9em%22 font-size=%2290%22>🏕️</text></svg>"> 10 <title></title> 11 </head> 12 <body> 13 <div id="page-wrapper"> 14 <div id="header" role="banner"> 15 <header class="banner"> 16 <div id="banner-text"> 17 <span class="banner-title"><a href="/">beauhilton</a></span> 18 </div> 19 </header> 20 <nav> 21 <a href="/about">about</a> 22 <a href="/now">now</a> 23 <a href="/thanks">thanks</a> 24 <a class="nav-active" href="/posts">posts</a> 25 <a href="https://notes.beauhilton.com">notes</a> 26 <a href="https://talks.beauhilton.com">talks</a> 27 <a href="https://git.beauhilton.com">git</a> 28 <a href="/contact">contact</a> 29 <a href="/atom.xml">rss</a> 30 </nav> 31 </div> 32 <main> 33 <h1> 34 Playing with ColBERTV2 Embeddings and Retrieval 35 </h1> 36 <p> 37 <time id="post-date">2024-05-09</time> 38 </p> 39 <p id="post-excerpt"> 40 There are a lot of embedding models out there for LLMs. 41 ColbertV2 is a neat one. 42 Here are some thoughts and code examples. 43 </p> 44 <h2> 45 ColbertV2 46 </h2> 47 <p> 48 The way you shove data into any embedding model can make a 49 difference, and ColBERT is no different. I started off just giving it an 50 html file with the entirety of a website (<a href="https://www.vim-book.org/print_page/">vimbook’s print-site 51 one-pager</a>). This had a bunch of junk that wasn’t needed, which 52 occasionally affected the 53 </p> 54 <p> 55 <a href="https://sqlite-utils.datasette.io/en/stable/cli.html#id43">sqlite-utils 56 insert-files</a> https://github.com/bclavie/RAGatouille 57 </p> 58 <p> 59 Multiline script example: 60 </p> 61 <pre tabindex="0"><code class="language-sh"><span class="hl slc"># enable multilib - see link below</span> 62 paru <span class="hl slc"># make sure things are up to date generally</span> 63 paru <span class="hl kwb">-S</span> android<span class="hl kwb">-tools</span> android<span class="hl kwb">-sdk-build-tools</span> <span class="hl slc"># includes adb and other goodies</span> 64 reboot 65 </code></pre> 66 <p> 67 Image example: <img src="/images/ncmpcpp-mopidy-selector.png" alt="Source selection"> 68 </p> 69 </main> 70 <div id="footnotes"></div> 71 <footer></footer> 72 </div> 73 </body> 74 </html>