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/FastEmbed_GPU/index.html

1662 lines
50 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/FastEmbed_GPU/">
<link rel="prev" href="../ColBERT_with_FastEmbed/">
<link rel="next" href="../FastEmbed_Multi_GPU/">
<link rel="icon" href="../../assets/favicon.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.7.7">
<title>FastEmbed GPU - 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="#fastembed-on-gpu" 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">
FastEmbed GPU
</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 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">
FastEmbed GPU
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
FastEmbed GPU
</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="#installation" class="md-nav__link">
<span class="md-ellipsis">
Installation
</span>
</a>
<nav class="md-nav" aria-label="Installation">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#cuda-12x-support" class="md-nav__link">
<span class="md-ellipsis">
CUDA 12.x support
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#cuda-11x-support" class="md-nav__link">
<span class="md-ellipsis">
CUDA 11.x support
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#cuda-drivers" class="md-nav__link">
<span class="md-ellipsis">
CUDA drivers
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#setting-up-fastembed-gpu-on-gcp" class="md-nav__link">
<span class="md-ellipsis">
Setting up fastembed-gpu on GCP
</span>
</a>
<nav class="md-nav" aria-label="Setting up fastembed-gpu on GCP">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#cuda-drivers_1" class="md-nav__link">
<span class="md-ellipsis">
CUDA drivers
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#example-of-setting-up-cuda-12x-on-ubuntu-2204" class="md-nav__link">
<span class="md-ellipsis">
Example of setting up CUDA 12.x on Ubuntu 22.04
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#cudnn-9x" class="md-nav__link">
<span class="md-ellipsis">
CuDNN 9.x
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#example-of-setting-up-cudnn-9x-on-ubuntu-2204" class="md-nav__link">
<span class="md-ellipsis">
Example of setting up CuDNN 9.x on Ubuntu 22.04
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#common-issues" class="md-nav__link">
<span class="md-ellipsis">
Common issues
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#usage" class="md-nav__link">
<span class="md-ellipsis">
Usage
</span>
</a>
</li>
</ul>
</nav>
</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">
<a href="../SPLADE_with_FastEmbed/" class="md-nav__link">
<span class="md-ellipsis">
SPLADE with FastEmbed
</span>
</a>
</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="#installation" class="md-nav__link">
<span class="md-ellipsis">
Installation
</span>
</a>
<nav class="md-nav" aria-label="Installation">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#cuda-12x-support" class="md-nav__link">
<span class="md-ellipsis">
CUDA 12.x support
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#cuda-11x-support" class="md-nav__link">
<span class="md-ellipsis">
CUDA 11.x support
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#cuda-drivers" class="md-nav__link">
<span class="md-ellipsis">
CUDA drivers
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#setting-up-fastembed-gpu-on-gcp" class="md-nav__link">
<span class="md-ellipsis">
Setting up fastembed-gpu on GCP
</span>
</a>
<nav class="md-nav" aria-label="Setting up fastembed-gpu on GCP">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#cuda-drivers_1" class="md-nav__link">
<span class="md-ellipsis">
CUDA drivers
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#example-of-setting-up-cuda-12x-on-ubuntu-2204" class="md-nav__link">
<span class="md-ellipsis">
Example of setting up CUDA 12.x on Ubuntu 22.04
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#cudnn-9x" class="md-nav__link">
<span class="md-ellipsis">
CuDNN 9.x
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#example-of-setting-up-cudnn-9x-on-ubuntu-2204" class="md-nav__link">
<span class="md-ellipsis">
Example of setting up CuDNN 9.x on Ubuntu 22.04
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#common-issues" class="md-nav__link">
<span class="md-ellipsis">
Common issues
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#usage" class="md-nav__link">
<span class="md-ellipsis">
Usage
</span>
</a>
</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="fastembed-on-gpu">FastEmbed on GPU</h1>
<p>As of version 0.2.7 FastEmbed supports GPU acceleration.</p>
<p>This notebook covers the installation process and usage of fastembed on GPU.</p>
<h2 id="installation">Installation</h2>
<p>Fastembed depends on <code>onnxruntime</code> and inherits its scheme of GPU support.</p>
<p>In order to use GPU with onnx models, you would need to have <code>onnxruntime-gpu</code> package, which substitutes all the <code>onnxruntime</code> functionality.
Fastembed mimics this behavior and requires <code>fastembed-gpu</code> package to be installed.</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="err">!</span><span class="n">pip</span> <span class="n">install</span> <span class="n">fastembed</span><span class="o">-</span><span class="n">gpu</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><strong>NOTE</strong>: <code>onnxruntime-gpu</code> and <code>onnxruntime</code> can't be installed in the same environment. If you have <code>onnxruntime</code> installed, you would need to uninstall it before installing <code>onnxruntime-gpu</code>. Same is true for <code>fastembed</code> and <code>fastembed-gpu</code>.</p>
</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">
<h3 id="cuda-12x-support">CUDA 12.x support</h3>
<p>You can check your CUDA version using such commands as <code>nvidia-smi</code> or <code>nvcc --version</code></p>
<p>Starting from version 1.19.0, onnxruntime-gpu ships with support for CUDA 12.x by default.</p>
<p>Google Colab notebooks have by default CUDA 12.x and CuDNN 8.x.</p>
<p>Latest version of <code>onnxruntime-gpu</code> requires CuDNN 9.x, in order to install it you can run the following command: </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="err">!</span><span class="n">sudo</span> <span class="n">apt</span> <span class="n">install</span> <span class="n">cudnn9</span>
<span class="err">!</span><span class="n">pip</span> <span class="n">install</span> <span class="n">fastembed</span><span class="o">-</span><span class="n">gpu</span> <span class="o">-</span><span class="n">qqq</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>If it necessary to work with CuDNN 8, you can consider locking <code>onnxruntime-gpu</code> to 1.18.0 with CUDA 12.x by this command:</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="err">!</span><span class="n">pip</span> <span class="n">install</span> <span class="n">onnxruntime</span><span class="o">-</span><span class="n">gpu</span><span class="o">==</span><span class="mf">1.18.0</span> <span class="o">-</span><span class="n">i</span> <span class="n">https</span><span class="p">:</span><span class="o">//</span><span class="n">aiinfra</span><span class="o">.</span><span class="n">pkgs</span><span class="o">.</span><span class="n">visualstudio</span><span class="o">.</span><span class="n">com</span><span class="o">/</span><span class="n">PublicPackages</span><span class="o">/</span><span class="n">_packaging</span><span class="o">/</span><span class="n">onnxruntime</span><span class="o">-</span><span class="n">cuda</span><span class="o">-</span><span class="mi">12</span><span class="o">/</span><span class="n">pypi</span><span class="o">/</span><span class="n">simple</span><span class="o">/</span> <span class="o">-</span><span class="n">qq</span>
<span class="err">!</span><span class="n">pip</span> <span class="n">install</span> <span class="n">fastembed</span><span class="o">-</span><span class="n">gpu</span> <span class="o">-</span><span class="n">qqq</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">
<h3 id="cuda-11x-support">CUDA 11.x support</h3>
<p>To use latest version of <code>onnxruntime-gpu</code> with CUDA 11.x, you can run the following command:</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="err">!</span><span class="n">pip</span> <span class="n">install</span> <span class="n">onnxruntime</span><span class="o">-</span><span class="n">gpu</span> <span class="o">-</span><span class="n">i</span> <span class="n">https</span><span class="p">:</span><span class="o">//</span><span class="n">aiinfra</span><span class="o">.</span><span class="n">pkgs</span><span class="o">.</span><span class="n">visualstudio</span><span class="o">.</span><span class="n">com</span><span class="o">/</span><span class="n">PublicPackages</span><span class="o">/</span><span class="n">_packaging</span><span class="o">/</span><span class="n">onnxruntime</span><span class="o">-</span><span class="n">cuda</span><span class="o">-</span><span class="mi">11</span><span class="o">/</span><span class="n">pypi</span><span class="o">/</span><span class="n">simple</span><span class="o">/</span> <span class="o">-</span><span class="n">qq</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><strong>NOTE</strong>: Ensure that CuDNN 9.x is installed when working with the latest <code>onnxruntime-gpu</code>, whether using CUDA 11.x or 12.x.</p>
</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">
<h3 id="cuda-drivers">CUDA drivers</h3>
<p>FastEmbed does not include CUDA drivers and CuDNN libraries.
You would need to take care of the environment setup on your own.
The dependencies required for the chosen onnxruntime version are listed in the <a href="https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements">CUDA Execution Provider requirements</a>.</p>
</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">
<h3 id="setting-up-fastembed-gpu-on-gcp">Setting up fastembed-gpu on GCP</h3>
<h4 id="cuda-drivers_1">CUDA drivers</h4>
<p><a href="https://developer.nvidia.com/cuda-11-8-0-download-archive">CUDA 11.8 toolkit</a> or <a href="https://developer.nvidia.com/cuda-downloads">CUDA 12.x toolkit</a> has to be installed if they haven't yet been set up.</p>
<h4 id="example-of-setting-up-cuda-12x-on-ubuntu-2204">Example of setting up CUDA 12.x on Ubuntu 22.04</h4>
<p>Make sure to download an archive which has been created for your particular platform, CPU architecture and OS distribution.</p>
<p>For Ubuntu 22.04 with x86_64 CPU architecture the following <a href="https://developer.nvidia.com/cuda-downloads?target_os=Linux⌖_arch=x86_64&amp;Distribution=Ubuntu⌖_version=22.04⌖_type=deb_network">archive</a> has to be downloaded.</p>
<p><div class="highlight"><pre><span></span><code>wget<span class="w"> </span>https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb
sudo<span class="w"> </span>dpkg<span class="w"> </span>-i<span class="w"> </span>cuda-keyring_1.1-1_all.deb
sudo<span class="w"> </span>apt-get<span class="w"> </span>update
sudo<span class="w"> </span>apt-get<span class="w"> </span>-y<span class="w"> </span>install<span class="w"> </span>cuda
</code></pre></div>
<strong>NOTE</strong>: Specific CUDA libraries can be found in the <a href="https://docs.nvidia.com/cuda/cuda-installation-guide-linux/#meta-packages">meta packages section</a> in the CUDA installation guide.</p>
<p><strong>NOTE</strong>: When installing CUDA, the environment variable might not be set by default. Make sure to add the following line to your environment variables:
<div class="highlight"><pre><span></span><code><span class="nv">LD_LIBRARY_PATH</span><span class="o">=</span>/usr/local/cuda/lib64:<span class="nv">$LD_LIBRARY_PATH</span>
</code></pre></div>
This will ensure that the CUDA libraries are properly linked.</p>
<h4 id="cudnn-9x">CuDNN 9.x</h4>
<p>CuDNN 9.x library can be installed via the following <a href="https://developer.nvidia.com/rdp/cudnn-archive">archive</a>.</p>
<h4 id="example-of-setting-up-cudnn-9x-on-ubuntu-2204">Example of setting up CuDNN 9.x on Ubuntu 22.04</h4>
<p>CuDNN 9.x for Ubuntu 22.04 x86_64 <a href="https://developer.nvidia.com/cudnn-downloads?target_os=Linux⌖_arch=x86_64&amp;Distribution=Ubuntu⌖_version=22.04⌖_type=deb_network">archive</a> can be downloaded and installed in the following way:
<div class="highlight"><pre><span></span><code>wget<span class="w"> </span>https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb
sudo<span class="w"> </span>dpkg<span class="w"> </span>-i<span class="w"> </span>cuda-keyring_1.1-1_all.deb
sudo<span class="w"> </span>apt-get<span class="w"> </span>update
sudo<span class="w"> </span>apt-get<span class="w"> </span>-y<span class="w"> </span>install<span class="w"> </span>cudnn
</code></pre></div>
<strong>NOTE</strong>: When installing CuDNN, you can choose specific version, cudnn-cuda-11 or cudnn-cuda-12</p>
</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">
<h3 id="common-issues">Common issues</h3>
<p>The following are some common issues that may arise while using <code>fastembed-gpu</code> if not installed properly:</p>
<p>CUDA library is not installed:
<div class="highlight"><pre><span></span><code>FAIL<span class="w"> </span>:<span class="w"> </span>Failed<span class="w"> </span>to<span class="w"> </span>load<span class="w"> </span>library<span class="w"> </span>libonnxruntime_providers_cuda.so<span class="w"> </span>with<span class="w"> </span>error:<span class="w"> </span>libcublasLt.so.x:<span class="w"> </span>cannot<span class="w"> </span>open<span class="w"> </span>shared<span class="w"> </span>object<span class="w"> </span>file:<span class="w"> </span>No<span class="w"> </span>such<span class="w"> </span>file<span class="w"> </span>or<span class="w"> </span>directory
</code></pre></div></p>
<p>CuDNN library is not installed:
<div class="highlight"><pre><span></span><code>FAIL<span class="w"> </span>:<span class="w"> </span>Failed<span class="w"> </span>to<span class="w"> </span>load<span class="w"> </span>library<span class="w"> </span>libonnxruntime_providers_cuda.so<span class="w"> </span>with<span class="w"> </span>error:<span class="w"> </span>libcudnn.so.x:<span class="w"> </span>cannot<span class="w"> </span>open<span class="w"> </span>shared<span class="w"> </span>object<span class="w"> </span>file:<span class="w"> </span>No<span class="w"> </span>such<span class="w"> </span>file<span class="w"> </span>or<span class="w"> </span>directory
</code></pre></div></p>
<p>CUDA library path is not set:
<div class="highlight"><pre><span></span><code>FAIL<span class="w"> </span>:<span class="w"> </span>Failed<span class="w"> </span>to<span class="w"> </span>load<span class="w"> </span>library<span class="w"> </span>libonnxruntime_providers_cuda.so<span class="w"> </span>with<span class="w"> </span>error:<span class="w"> </span>libcufft.so.x:<span class="w"> </span>failed<span class="w"> </span>to<span class="w"> </span>map<span class="w"> </span>segment<span class="w"> </span>from<span class="w"> </span>shared<span class="w"> </span>object
</code></pre></div></p>
<p>Make sure to add the following line to your environment variables:
<div class="highlight"><pre><span></span><code><span class="nv">LD_LIBRARY_PATH</span><span class="o">=</span>/usr/local/cuda/lib64:<span class="nv">$LD_LIBRARY_PATH</span>
</code></pre></div></p>
</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="usage">Usage</h2>
</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">numpy</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">np</span>
<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">TextEmbedding</span>
<span class="n">embedding_model_gpu</span> <span class="o">=</span> <span class="n">TextEmbedding</span><span class="p">(</span>
<span class="n">model_name</span><span class="o">=</span><span class="s2">&quot;BAAI/bge-small-en-v1.5&quot;</span><span class="p">,</span> <span class="n">providers</span><span class="o">=</span><span class="p">[</span><span class="s2">&quot;CUDAExecutionProvider&quot;</span><span class="p">]</span>
<span class="p">)</span>
<span class="n">embedding_model_gpu</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">get_providers</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_stderr output_text">
<pre>
<code>/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:88: UserWarning:
The secret `HF_TOKEN` does not exist in your Colab secrets.
To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.
You will be able to reuse this secret in all of your notebooks.
Please note that authentication is recommended but still optional to access public models or datasets.
warnings.warn(
</code>
</pre>
</div>
</div>
<div class="output_area">
<div class="output_text output_subarea">
<pre>
<code>Fetching 5 files: 0%| | 0/5 [00:00&lt;?, ?it/s]</code>
</pre>
</div>
</div>
<div class="output_area">
<div class="output_text output_subarea">
<pre>
<code>tokenizer_config.json: 0%| | 0.00/1.24k [00:00&lt;?, ?B/s]</code>
</pre>
</div>
</div>
<div class="output_area">
<div class="output_text output_subarea">
<pre>
<code>config.json: 0%| | 0.00/706 [00:00&lt;?, ?B/s]</code>
</pre>
</div>
</div>
<div class="output_area">
<div class="output_text output_subarea">
<pre>
<code>special_tokens_map.json: 0%| | 0.00/695 [00:00&lt;?, ?B/s]</code>
</pre>
</div>
</div>
<div class="output_area">
<div class="output_text output_subarea">
<pre>
<code>tokenizer.json: 0%| | 0.00/711k [00:00&lt;?, ?B/s]</code>
</pre>
</div>
</div>
<div class="output_area">
<div class="output_text output_subarea">
<pre>
<code>model_optimized.onnx: 0%| | 0.00/66.5M [00:00&lt;?, ?B/s]</code>
</pre>
</div>
</div>
<div class="output_area">
<div class="output_text output_subarea output_execute_result">
<pre>
<code>['CUDAExecutionProvider', 'CPUExecutionProvider']</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="nb">list</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">repeat</span><span class="p">(</span><span class="s2">&quot;Demonstrating GPU acceleration in fastembed&quot;</span><span class="p">,</span> <span class="mi">500</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="o">%%</span><span class="n">timeit</span>
<span class="nb">list</span><span class="p">(</span><span class="n">embedding_model_gpu</span><span class="o">.</span><span class="n">embed</span><span class="p">(</span><span class="n">documents</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>43.4 ms ± 2.06 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
</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">embedding_model_cpu</span> <span class="o">=</span> <span class="n">TextEmbedding</span><span class="p">(</span><span class="n">model_name</span><span class="o">=</span><span class="s2">&quot;BAAI/bge-small-en-v1.5&quot;</span><span class="p">)</span>
<span class="n">embedding_model_cpu</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">get_providers</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 5 files: 0%| | 0/5 [00:00&lt;?, ?it/s]</code>
</pre>
</div>
</div>
<div class="output_area">
<div class="output_text output_subarea output_execute_result">
<pre>
<code>['CPUExecutionProvider']</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="o">%%</span><span class="n">timeit</span>
<span class="nb">list</span><span class="p">(</span><span class="n">embedding_model_cpu</span><span class="o">.</span><span class="n">embed</span><span class="p">(</span><span class="n">documents</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>4.33 s ± 591 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
</code>
</pre>
</div>
</div>
</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