upstream-archive/fastembed
1
0
Fork 0
mirror of https://github.com/qdrant/fastembed.git synced 2026-08-02 08:00:58 -05:00
Code Issues Packages Projects Releases Wiki Activity
Files
gh-pages
fastembed/examples/SPLADE_with_FastEmbed/index.html

1535 lines
48 KiB
HTML
Raw Permalink Blame History

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<meta name="author" content="Nirant Kasliwal">
<link rel="canonical" href="https://qdrant.github.io/fastembed/examples/SPLADE_with_FastEmbed/">
<link rel="prev" href="../Image_Embedding/">
<link rel="next" href="../Supported_Models/">
<link rel="icon" href="../../assets/favicon.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.7.7">
<title>SPLADE with FastEmbed - FastEmbed</title>
<link rel="stylesheet" href="../../assets/stylesheets/main.ec1eaa64.min.css">
<link rel="stylesheet" href="../../assets/stylesheets/palette.ab4e12ef.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
<link rel="stylesheet" href="../../assets/_mkdocstrings.css">
<link rel="stylesheet" href="../../css/ansi-colours.css">
<link rel="stylesheet" href="../../css/jupyter-cells.css">
<link rel="stylesheet" href="../../css/pandas-dataframe.css">
<script>__md_scope=new URL("../..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
</head>
<body dir="ltr" data-md-color-scheme="default" data-md-color-primary="indigo" data-md-color-accent="indigo">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
<a href="#introduction-to-splade-with-fastembed" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
<aside class="md-banner">
<div class="md-banner__inner md-grid md-typeset">
<button class="md-banner__button md-icon" aria-label="Don't show this again">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
</button>
<div style="text-align: center">
If you're using FastEmbed from Qdrant, join the
<a rel="me" href="https://discord.gg/Qy6HCJK9Dc">
<span class="twemoji mastodon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M492.5 69.8c-.2-.3-.4-.6-.8-.7-38.1-17.5-78.4-30-119.7-37.1-.4-.1-.8 0-1.1.1s-.6.4-.8.8c-5.5 9.9-10.5 20.2-14.9 30.6-44.6-6.8-89.9-6.8-134.4 0-4.5-10.5-9.5-20.7-15.1-30.6-.2-.3-.5-.6-.8-.8s-.7-.2-1.1-.2C162.5 39 122.2 51.5 84.1 69c-.3.1-.6.4-.8.7C7.1 183.5-13.8 294.6-3.6 404.2c0 .3.1.5.2.8s.3.4.5.6c44.4 32.9 94 58 146.8 74.2.4.1.8.1 1.1 0s.7-.4.9-.7c11.3-15.4 21.4-31.8 30-48.8.1-.2.2-.5.2-.8s0-.5-.1-.8-.2-.5-.4-.6-.4-.3-.7-.4c-15.8-6.1-31.2-13.4-45.9-21.9-.3-.2-.5-.4-.7-.6s-.3-.6-.3-.9 0-.6.2-.9.3-.5.6-.7c3.1-2.3 6.2-4.7 9.1-7.1.3-.2.6-.4.9-.4s.7 0 1 .1c96.2 43.9 200.4 43.9 295.5 0 .3-.1.7-.2 1-.2s.7.2.9.4c2.9 2.4 6 4.9 9.1 7.2.2.2.4.4.6.7s.2.6.2.9-.1.6-.3.9-.4.5-.6.6c-14.7 8.6-30 15.9-45.9 21.8-.2.1-.5.2-.7.4s-.3.4-.4.7-.1.5-.1.8.1.5.2.8c8.8 17 18.8 33.3 30 48.8.2.3.6.6.9.7s.8.1 1.1 0c52.9-16.2 102.6-41.3 147.1-74.2.2-.2.4-.4.5-.6s.2-.5.2-.8c12.3-126.8-20.5-236.9-86.9-334.5zm-302 267.7c-29 0-52.8-26.6-52.8-59.2s23.4-59.2 52.8-59.2c29.7 0 53.3 26.8 52.8 59.2 0 32.7-23.4 59.2-52.8 59.2m195.4 0c-29 0-52.8-26.6-52.8-59.2s23.4-59.2 52.8-59.2c29.7 0 53.3 26.8 52.8 59.2 0 32.7-23.2 59.2-52.8 59.2"/></svg>
</span>
<strong>Qdrant Discord server</strong>
</a>
to get help and share your work! Or check out <a rel="me"
href="https://cloud.qdrant.io?utm_source=twitter&utm_medium=website&utm_campaign=fastembed">Qdrant Cloud</a> to
get started with vector search!
</div>
</div>
<script>var el=document.querySelector("[data-md-component=announce]");if(el){var content=el.querySelector(".md-typeset");__md_hash(content.innerHTML)===__md_get("__announce")&&(el.hidden=!0)}</script>
</aside>
</div>
<header class="md-header md-header--shadow" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href="../.." title="FastEmbed" class="md-header__button md-logo" aria-label="FastEmbed" data-md-component="logo">
<img src="../../assets/favicon.png" alt="logo">
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
</label>
<div class="md-header__title" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
FastEmbed
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
SPLADE with FastEmbed
</span>
</div>
</div>
</div>
<form class="md-header__option" data-md-component="palette">
<input class="md-option" data-md-color-media="" data-md-color-scheme="default" data-md-color-primary="indigo" data-md-color-accent="indigo" aria-label="Switch to dark mode" type="radio" name="__palette" id="__palette_0">
<label class="md-header__button md-icon" title="Switch to dark mode" for="__palette_1" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a4 4 0 0 0-4 4 4 4 0 0 0 4 4 4 4 0 0 0 4-4 4 4 0 0 0-4-4m0 10a6 6 0 0 1-6-6 6 6 0 0 1 6-6 6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12z"/></svg>
</label>
<input class="md-option" data-md-color-media="" data-md-color-scheme="slate" data-md-color-primary="indigo" data-md-color-accent="indigo" aria-label="Switch to light mode" type="radio" name="__palette" id="__palette_1">
<label class="md-header__button md-icon" title="Switch to light mode" for="__palette_0" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 18c-.89 0-1.74-.2-2.5-.55C11.56 16.5 13 14.42 13 12s-1.44-4.5-3.5-5.45C10.26 6.2 11.11 6 12 6a6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12z"/></svg>
</label>
</form>
<script>var palette=__md_get("__palette");if(palette&&palette.color){if("(prefers-color-scheme)"===palette.color.media){var media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent")}for(var[key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
<label class="md-header__button md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
</label>
<div class="md-search" data-md-component="search" role="dialog">
<label class="md-search__overlay" for="__search"></label>
<div class="md-search__inner" role="search">
<form class="md-search__form" name="search">
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
<label class="md-search__icon md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
</label>
<nav class="md-search__options" aria-label="Search">
<button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
</button>
</nav>
<div class="md-search__suggest" data-md-component="search-suggest"></div>
</form>
<div class="md-search__output">
<div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
<div class="md-search-result" data-md-component="search-result">
<div class="md-search-result__meta">
Initializing search
</div>
<ol class="md-search-result__list" role="presentation"></ol>
</div>
</div>
</div>
</div>
</div>
<div class="md-header__source">
<a href="https://github.com/qdrant/fastembed/" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M173.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6m-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3m44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9M252.8 8C114.1 8 8 113.3 8 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C436.2 457.8 504 362.9 504 252 504 113.3 391.5 8 252.8 8M105.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1m-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7m32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1m-11.4-14.7c-1.6 1-1.6 3.6 0 5.9s4.3 3.3 5.6 2.3c1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2"/></svg>
</div>
<div class="md-source__repository">
qdrant/fastembed
</div>
</a>
</div>
</nav>
</header>
<div class="md-container" data-md-component="container">
<main class="md-main" data-md-component="main">
<div class="md-main__inner md-grid">
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href="../.." title="FastEmbed" class="md-nav__button md-logo" aria-label="FastEmbed" data-md-component="logo">
<img src="../../assets/favicon.png" alt="logo">
</a>
FastEmbed
</label>
<div class="md-nav__source">
<a href="https://github.com/qdrant/fastembed/" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M173.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6m-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3m44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9M252.8 8C114.1 8 8 113.3 8 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C436.2 457.8 504 362.9 504 252 504 113.3 391.5 8 252.8 8M105.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1m-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7m32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1m-11.4-14.7c-1.6 1-1.6 3.6 0 5.9s4.3 3.3 5.6 2.3c1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2"/></svg>
</div>
<div class="md-source__repository">
qdrant/fastembed
</div>
</a>
</div>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../.." class="md-nav__link">
<span class="md-ellipsis">
⚡️ What is FastEmbed?
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../Getting%20Started/" class="md-nav__link">
<span class="md-ellipsis">
Getting Started
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--active md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3" checked>
<label class="md-nav__link" for="__nav_3" id="__nav_3_label" tabindex="">
<span class="md-ellipsis">
Examples
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_3_label" aria-expanded="true">
<label class="md-nav__title" for="__nav_3">
<span class="md-nav__icon md-icon"></span>
Examples
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../ColBERT_with_FastEmbed/" class="md-nav__link">
<span class="md-ellipsis">
ColBERT with FastEmbed
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../FastEmbed_GPU/" class="md-nav__link">
<span class="md-ellipsis">
FastEmbed GPU
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../FastEmbed_Multi_GPU/" class="md-nav__link">
<span class="md-ellipsis">
FastEmbed Multi GPU
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../FastEmbed_vs_HF_Comparison/" class="md-nav__link">
<span class="md-ellipsis">
FastEmbed vs HF Comparison
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../Hindi_Tamil_RAG_with_Navarasa7B/" class="md-nav__link">
<span class="md-ellipsis">
Hindi Tamil RAG with Navarasa7B
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../Hybrid_Search/" class="md-nav__link">
<span class="md-ellipsis">
Hybrid Search
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../Image_Embedding/" class="md-nav__link">
<span class="md-ellipsis">
Image Embedding
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--active">
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
<label class="md-nav__link md-nav__link--active" for="__toc">
<span class="md-ellipsis">
SPLADE with FastEmbed
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
SPLADE with FastEmbed
</span>
</a>
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#outline" class="md-nav__link">
<span class="md-ellipsis">
Outline:
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#what-is-splade" class="md-nav__link">
<span class="md-ellipsis">
What is SPLADE?
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#setting-up-the-environment" class="md-nav__link">
<span class="md-ellipsis">
Setting up the environment
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#understanding-splade-vectors" class="md-nav__link">
<span class="md-ellipsis">
Understanding SPLADE vectors
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#observations-and-model-design-choices" class="md-nav__link">
<span class="md-ellipsis">
Observations and Model Design Choices
</span>
</a>
<nav class="md-nav" aria-label="Observations and Model Design Choices">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#design-choices" class="md-nav__link">
<span class="md-ellipsis">
Design Choices
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../Supported_Models/" class="md-nav__link">
<span class="md-ellipsis">
Supported Models
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_4" >
<label class="md-nav__link" for="__nav_4" id="__nav_4_label" tabindex="">
<span class="md-ellipsis">
Experimental
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_4_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4">
<span class="md-nav__icon md-icon"></span>
Experimental
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../experimental/Binary%20Quantization%20from%20Scratch/" class="md-nav__link">
<span class="md-ellipsis">
Binary Quantization from Scratch
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_5" >
<label class="md-nav__link" for="__nav_5" id="__nav_5_label" tabindex="">
<span class="md-ellipsis">
Qdrant
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_5_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_5">
<span class="md-nav__icon md-icon"></span>
Qdrant
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../qdrant/Binary_Quantization_with_Qdrant/" class="md-nav__link">
<span class="md-ellipsis">
Binary Quantization with Qdrant
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../qdrant/Retrieval_with_FastEmbed/" class="md-nav__link">
<span class="md-ellipsis">
Retrieval with FastEmbed
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../qdrant/Usage_With_Qdrant/" class="md-nav__link">
<span class="md-ellipsis">
Usage With Qdrant
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#outline" class="md-nav__link">
<span class="md-ellipsis">
Outline:
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#what-is-splade" class="md-nav__link">
<span class="md-ellipsis">
What is SPLADE?
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#setting-up-the-environment" class="md-nav__link">
<span class="md-ellipsis">
Setting up the environment
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#understanding-splade-vectors" class="md-nav__link">
<span class="md-ellipsis">
Understanding SPLADE vectors
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#observations-and-model-design-choices" class="md-nav__link">
<span class="md-ellipsis">
Observations and Model Design Choices
</span>
</a>
<nav class="md-nav" aria-label="Observations and Model Design Choices">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#design-choices" class="md-nav__link">
<span class="md-ellipsis">
Design Choices
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.0.3/jquery.min.js"></script>
<script>
(function() {
function addWidgetsRenderer() {
var requireJsScript = document.createElement('script');
requireJsScript.src = 'https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js';
var mimeElement = document.querySelector('script[type="application/vnd.jupyter.widget-view+json"]');
var jupyterWidgetsScript = document.createElement('script');
var widgetRendererSrc = 'https://unpkg.com/@jupyter-widgets/html-manager@*/dist/embed-amd.js';
var widgetState;
// Fallback for older version:
try {
widgetState = mimeElement && JSON.parse(mimeElement.innerHTML);
if (widgetState && (widgetState.version_major < 2 || !widgetState.version_major)) {
widgetRendererSrc = 'jupyter-js-widgets@*/dist/embed.js';
}
} catch(e) {}
jupyterWidgetsScript.src = widgetRendererSrc;
document.body.appendChild(requireJsScript);
document.body.appendChild(jupyterWidgetsScript);
}
document.addEventListener('DOMContentLoaded', addWidgetsRenderer);
}());
</script>
<div class="cell border-box-sizing text_cell rendered">
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h1 id="introduction-to-splade-with-fastembed">Introduction to SPLADE with FastEmbed</h1>
<p>In this notebook, we will explore how to generate Sparse Vectors -- in particular a variant of the <a href="https://arxiv.org/abs/2107.05720">SPLADE</a>.</p>
<p>&gt; 💡 The original <a href="https://github.com/naver/splade">naver/SPLADE</a> models were licensed CC BY-NC-SA 4.0 -- Not for Commercial Use. This <a href="https://huggingface.co/prithivida/Splade_PP_en_v1">SPLADE++</a> model is Apache License and hence, licensed for commercial use. </p>
<h2 id="outline">Outline:</h2>
<ol>
<li><a href="#What-is-SPLADE?">What is SPLADE?</a></li>
<li><a href="#Setting-up-the-environment">Setting up the environment</a></li>
<li><a href="#Generating-SPLADE-vectors-with-FastEmbed">Generating SPLADE vectors with FastEmbed</a></li>
<li><a href="#Understanding-SPLADE-vectors">Understanding SPLADE vectors</a></li>
<li><a href="#Observations-and-Model-Design-Choices">Observations and Design Choices</a></li>
</ol>
<h2 id="what-is-splade">What is SPLADE?</h2>
<p>SPLADE was a novel method for <em>learning</em> sparse vectors for text representation. This model beats BM25 -- the underlying approach for the Elastic/Lucene family of implementations. Thus making it highly effective for tasks such as information retrieval, document classification, and more. </p>
<p>The key advantage of SPLADE is its ability to generate sparse vectors, which are more efficient and interpretable than dense vectors. This makes SPLADE a powerful tool for handling large-scale text data.</p>
<h2 id="setting-up-the-environment">Setting up the environment</h2>
<p>This notebook uses few dependencies, which are installed below: </p>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="c1"># !pip install -q fastembed</span>
</code></pre></div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered">
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<p>Let's get started! 🚀</p>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="kn">from</span><span class="w"> </span><span class="nn">fastembed</span><span class="w"> </span><span class="kn">import</span> <span class="n">SparseTextEmbedding</span><span class="p">,</span> <span class="n">SparseEmbedding</span>
</code></pre></div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered">
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<p>&gt; You can find the list of all supported Sparse Embedding models by calling this API: <code>SparseTextEmbedding.list_supported_models()</code></p>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="n">SparseTextEmbedding</span><span class="o">.</span><span class="n">list_supported_models</span><span class="p">()</span>
</code></pre></div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_text output_subarea output_execute_result">
<pre>
<code>[{'model': 'prithvida/Splade_PP_en_v1',
'vocab_size': 30522,
'description': 'Misspelled version of the model. Retained for backward compatibility. Independent Implementation of SPLADE++ Model for English',
'size_in_GB': 0.532,
'sources': {'hf': 'Qdrant/SPLADE_PP_en_v1'}},
{'model': 'prithivida/Splade_PP_en_v1',
'vocab_size': 30522,
'description': 'Independent Implementation of SPLADE++ Model for English',
'size_in_GB': 0.532,
'sources': {'hf': 'Qdrant/SPLADE_PP_en_v1'}}]</code>
</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="n">model_name</span> <span class="o">=</span> <span class="s2">&quot;prithvida/Splade_PP_en_v1&quot;</span>
<span class="c1"># This triggers the model download</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">SparseTextEmbedding</span><span class="p">(</span><span class="n">model_name</span><span class="o">=</span><span class="n">model_name</span><span class="p">)</span>
</code></pre></div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_text output_subarea">
<pre>
<code>Fetching 9 files: 0%| | 0/9 [00:00&lt;?, ?it/s]</code>
</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="n">documents</span><span class="p">:</span> <span class="nb">list</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="p">[</span>
<span class="s2">&quot;Chandrayaan-3 is India&#39;s third lunar mission&quot;</span><span class="p">,</span>
<span class="s2">&quot;It aimed to land a rover on the Moon&#39;s surface - joining the US, China and Russia&quot;</span><span class="p">,</span>
<span class="s2">&quot;The mission is a follow-up to Chandrayaan-2, which had partial success&quot;</span><span class="p">,</span>
<span class="s2">&quot;Chandrayaan-3 will be launched by the Indian Space Research Organisation (ISRO)&quot;</span><span class="p">,</span>
<span class="s2">&quot;The estimated cost of the mission is around $35 million&quot;</span><span class="p">,</span>
<span class="s2">&quot;It will carry instruments to study the lunar surface and atmosphere&quot;</span><span class="p">,</span>
<span class="s2">&quot;Chandrayaan-3 landed on the Moon&#39;s surface on 23rd August 2023&quot;</span><span class="p">,</span>
<span class="s2">&quot;It consists of a lander named Vikram and a rover named Pragyan similar to Chandrayaan-2. Its propulsion module would act like an orbiter.&quot;</span><span class="p">,</span>
<span class="s2">&quot;The propulsion module carries the lander and rover configuration until the spacecraft is in a 100-kilometre (62 mi) lunar orbit&quot;</span><span class="p">,</span>
<span class="s2">&quot;The mission used GSLV Mk III rocket for its launch&quot;</span><span class="p">,</span>
<span class="s2">&quot;Chandrayaan-3 was launched from the Satish Dhawan Space Centre in Sriharikota&quot;</span><span class="p">,</span>
<span class="s2">&quot;Chandrayaan-3 was launched earlier in the year 2023&quot;</span><span class="p">,</span>
<span class="p">]</span>
<span class="n">sparse_embeddings_list</span><span class="p">:</span> <span class="nb">list</span><span class="p">[</span><span class="n">SparseEmbedding</span><span class="p">]</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span>
<span class="n">model</span><span class="o">.</span><span class="n">embed</span><span class="p">(</span><span class="n">documents</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="mi">6</span><span class="p">)</span>
<span class="p">)</span> <span class="c1"># batch_size is optional, notice the generator</span>
</code></pre></div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="n">index</span> <span class="o">=</span> <span class="mi">0</span>
<span class="n">sparse_embeddings_list</span><span class="p">[</span><span class="n">index</span><span class="p">]</span>
</code></pre></div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_text output_subarea output_execute_result">
<pre>
<code>SparseEmbedding(values=array([0.05297208, 0.01963477, 0.36459631, 1.38508618, 0.71776593,
0.12667948, 0.46230844, 0.446771 , 0.26897505, 1.01519883,
1.5655334 , 0.29412213, 1.53102326, 0.59785569, 1.1001817 ,
0.02079751, 0.09955651, 0.44249091, 0.09747757, 1.53519952,
1.36765671, 0.15740395, 0.49882549, 0.38629025, 0.76612782,
1.25805044, 0.39058095, 0.27236196, 0.45152301, 0.48262018,
0.26085234, 1.35912788, 0.70710695, 1.71639752]), indices=array([ 1010, 1011, 1016, 1017, 2001, 2018, 2034, 2093, 2117,
2319, 2353, 2509, 2634, 2686, 2796, 2817, 2922, 2959,
3003, 3148, 3260, 3390, 3462, 3523, 3822, 4231, 4316,
4774, 5590, 5871, 6416, 11926, 12076, 16469]))</code>
</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered">
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<p>The previous output is a SparseEmbedding object for the first document in our list.</p>
<p>It contains two arrays: values and indices.
- The 'values' array represents the weights of the features (tokens) in the document.
- The 'indices' array represents the indices of these features in the model's vocabulary.</p>
<p>Each pair of corresponding values and indices represents a token and its weight in the document.</p>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="c1"># Let&#39;s print the first 5 features and their weights for better understanding.</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">5</span><span class="p">):</span>
<span class="nb">print</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;Token at index </span><span class="si">{</span><span class="n">sparse_embeddings_list</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">indices</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="si">}</span><span class="s2"> has weight </span><span class="si">{</span><span class="n">sparse_embeddings_list</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="si">}</span><span class="s2">&quot;</span>
<span class="p">)</span>
</code></pre></div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_subarea output_stream output_stdout output_text">
<pre>
<code>Token at index 1010 has weight 0.05297207832336426
Token at index 1011 has weight 0.01963476650416851
Token at index 1016 has weight 0.36459630727767944
Token at index 1017 has weight 1.385086178779602
Token at index 2001 has weight 0.7177659273147583
</code>
</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered">
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h2 id="understanding-splade-vectors">Understanding SPLADE vectors</h2>
<p>This is still a little abstract, so let's use the tokenizer vocab to make sense of these indices.</p>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="kn">import</span><span class="w"> </span><span class="nn">json</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">transformers</span><span class="w"> </span><span class="kn">import</span> <span class="n">AutoTokenizer</span>
<span class="n">tokenizer</span> <span class="o">=</span> <span class="n">AutoTokenizer</span><span class="o">.</span><span class="n">from_pretrained</span><span class="p">(</span>
<span class="n">SparseTextEmbedding</span><span class="o">.</span><span class="n">list_supported_models</span><span class="p">()[</span><span class="mi">0</span><span class="p">][</span><span class="s2">&quot;sources&quot;</span><span class="p">][</span><span class="s2">&quot;hf&quot;</span><span class="p">]</span>
<span class="p">)</span>
</code></pre></div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code><span class="k">def</span><span class="w"> </span><span class="nf">get_tokens_and_weights</span><span class="p">(</span><span class="n">sparse_embedding</span><span class="p">,</span> <span class="n">tokenizer</span><span class="p">):</span>
<span class="n">token_weight_dict</span> <span class="o">=</span> <span class="p">{}</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">sparse_embedding</span><span class="o">.</span><span class="n">indices</span><span class="p">)):</span>
<span class="n">token</span> <span class="o">=</span> <span class="n">tokenizer</span><span class="o">.</span><span class="n">decode</span><span class="p">([</span><span class="n">sparse_embedding</span><span class="o">.</span><span class="n">indices</span><span class="p">[</span><span class="n">i</span><span class="p">]])</span>
<span class="n">weight</span> <span class="o">=</span> <span class="n">sparse_embedding</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">i</span><span class="p">]</span>
<span class="n">token_weight_dict</span><span class="p">[</span><span class="n">token</span><span class="p">]</span> <span class="o">=</span> <span class="n">weight</span>
<span class="c1"># Sort the dictionary by weights</span>
<span class="n">token_weight_dict</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span>
<span class="nb">sorted</span><span class="p">(</span><span class="n">token_weight_dict</span><span class="o">.</span><span class="n">items</span><span class="p">(),</span> <span class="n">key</span><span class="o">=</span><span class="k">lambda</span> <span class="n">item</span><span class="p">:</span> <span class="n">item</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">reverse</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="p">)</span>
<span class="k">return</span> <span class="n">token_weight_dict</span>
<span class="c1"># Test the function with the first SparseEmbedding</span>
<span class="nb">print</span><span class="p">(</span><span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">get_tokens_and_weights</span><span class="p">(</span><span class="n">sparse_embeddings_list</span><span class="p">[</span><span class="n">index</span><span class="p">],</span> <span class="n">tokenizer</span><span class="p">),</span> <span class="n">indent</span><span class="o">=</span><span class="mi">4</span><span class="p">))</span>
</code></pre></div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_subarea output_stream output_stdout output_text">
<pre>
<code>{
"chandra": 1.7163975238800049,
"third": 1.5655333995819092,
"##ya": 1.535199522972107,
"india": 1.5310232639312744,
"3": 1.385086178779602,
"mission": 1.3676567077636719,
"lunar": 1.3591278791427612,
"moon": 1.2580504417419434,
"indian": 1.1001816987991333,
"##an": 1.015198826789856,
"3rd": 0.7661278247833252,
"was": 0.7177659273147583,
"spacecraft": 0.7071069478988647,
"space": 0.5978556871414185,
"flight": 0.4988254904747009,
"satellite": 0.4826201796531677,
"first": 0.46230843663215637,
"expedition": 0.4515230059623718,
"three": 0.4467709958553314,
"fourth": 0.44249090552330017,
"vehicle": 0.390580952167511,
"iii": 0.3862902522087097,
"2": 0.36459630727767944,
"##3": 0.2941221296787262,
"planet": 0.27236196398735046,
"second": 0.26897504925727844,
"missions": 0.2608523368835449,
"launched": 0.15740394592285156,
"had": 0.12667948007583618,
"largest": 0.09955651313066483,
"leader": 0.09747757017612457,
",": 0.05297207832336426,
"study": 0.02079751156270504,
"-": 0.01963476650416851
}
</code>
</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered">
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h2 id="observations-and-model-design-choices">Observations and Model Design Choices</h2>
<ol>
<li>The relative order of importance is quite useful. The most important tokens in the sentence have the highest weights.</li>
<li><strong>Term Expansion</strong>: The model can expand the terms in the document. This means that the model can generate weights for tokens that are not present in the document but are related to the tokens in the document. This is a powerful feature that allows the model to capture the context of the document. Here, you'll see that the model has added the tokens '3' from 'third' and 'moon' from 'lunar' to the sparse vector.</li>
</ol>
<h3 id="design-choices">Design Choices</h3>
<ol>
<li>The weights are not normalized. This means that the sum of the weights is not 1 or 100. This is a common practice in sparse embeddings, as it allows the model to capture the importance of each token in the document.</li>
<li>Tokens are included in the sparse vector only if they are present in the model's vocabulary. This means that the model will not generate a weight for tokens that it has not seen during training.</li>
<li>Tokens do not map to words directly -- allowing you to gracefully handle typo errors and out-of-vocabulary tokens.</li>
</ol>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="highlight"><pre><span></span><code>
</code></pre></div>
</div>
</div>
</article>
</div>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
</main>
<footer class="md-footer">
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
<div class="md-copyright__highlight">
Maintained by <a href="https://github.com/qdrant">Qdrant</a>. Originally created by <a href="https://nirantk.com/about">Nirant Kasliwal</a>.
</div>
Made with
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
Material for MkDocs
</a>
</div>
</div>
</div>
</footer>
</div>
<div class="md-dialog" data-md-component="dialog">
<div class="md-dialog__inner md-typeset"></div>
</div>
<script id="__config" type="application/json">{"annotate": null, "base": "../..", "features": ["search.suggest", "search.highlight", "navigation.instant", "navigation.tracking", "navigation.expand", "navigation.sections", "content.code.annotate", "toc.follow", "header.autohide", "announce.dismiss"], "search": "../../assets/javascripts/workers/search.2c215733.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
<script src="../../assets/javascripts/bundle.d7400e89.min.js"></script>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink