andras/great-ai
1
0
Fork 0
Code Issues Pull requests 1 Projects Releases 4 Packages Wiki Activity Actions
great-ai/how-to-guides/large-file/index.html

1237 lines
No EOL
46 KiB
HTML
Raw 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="description" content="GreatAI helps you easily transform your prototype AI code into production-ready software.">
<meta name="author" content="András Schmelczer">
<link rel="icon" href="../../media/favicon.ico">
<meta name="generator" content="mkdocs-1.4.2, mkdocs-material-8.5.8">
<title>How to use LargeFiles - GreatAI documentation</title>
<link rel="stylesheet" href="../../assets/stylesheets/main.20d9efc8.min.css">
<link rel="stylesheet" href="../../assets/stylesheets/palette.815d1a91.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">
<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>
<meta property="og:title" content="">
<meta property="og:site_name" content="">
<meta property="og:url" content="">
<meta property="og:description" content="Transform your prototype AI code into production-ready software.">
<meta property="og:type" content="">
<meta property="og:image" content=https://great-ai.scoutinscience.com/media/og-image.png>
<style>
.jupyter-wrapper a {
color: var(--md-typeset-a-color) !important;
}
</style>
</head>
<body dir="ltr" data-md-color-scheme="default" data-md-color-primary="light-blue" data-md-color-accent="">
<script>var palette=__md_get("__palette");if(palette&&"object"==typeof palette.color)for(var key of Object.keys(palette.color))document.body.setAttribute("data-md-color-"+key,palette.color[key])</script>
<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="#how-to-use-largefiles" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<header class="md-header" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href="../.." title="GreatAI documentation" class="md-header__button md-logo" aria-label="GreatAI documentation" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54Z"/></svg>
</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 6h18v2H3V6m0 5h18v2H3v-2m0 5h18v2H3v-2Z"/></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">
GreatAI documentation
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
How to use LargeFiles
</span>
</div>
</div>
</div>
<form class="md-header__option" data-md-component="palette">
<input class="md-option" data-md-color-media="(prefers-color-scheme: light)" data-md-color-scheme="default" data-md-color-primary="light-blue" data-md-color-accent="" aria-label="Switch to dark mode" type="radio" name="__palette" id="__palette_1">
<label class="md-header__button md-icon" title="Switch to dark mode" for="__palette_2" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 2a7 7 0 0 0-7 7c0 2.38 1.19 4.47 3 5.74V17a1 1 0 0 0 1 1h6a1 1 0 0 0 1-1v-2.26c1.81-1.27 3-3.36 3-5.74a7 7 0 0 0-7-7M9 21a1 1 0 0 0 1 1h4a1 1 0 0 0 1-1v-1H9v1Z"/></svg>
</label>
<input class="md-option" data-md-color-media="(prefers-color-scheme: dark)" data-md-color-scheme="slate" data-md-color-primary="light-blue" data-md-color-accent="" aria-label="Switch to light mode" type="radio" name="__palette" id="__palette_2">
<label class="md-header__button md-icon" title="Switch to light mode" for="__palette_1" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 2a7 7 0 0 1 7 7c0 2.38-1.19 4.47-3 5.74V17a1 1 0 0 1-1 1H9a1 1 0 0 1-1-1v-2.26C6.19 13.47 5 11.38 5 9a7 7 0 0 1 7-7M9 21v-1h6v1a1 1 0 0 1-1 1h-4a1 1 0 0 1-1-1m3-17a5 5 0 0 0-5 5c0 2.05 1.23 3.81 3 4.58V16h4v-2.42c1.77-.77 3-2.53 3-4.58a5 5 0 0 0-5-5Z"/></svg>
</label>
</form>
<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-.27A6.516 6.516 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 5Z"/></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-.27A6.516 6.516 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 5Z"/></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 11h12Z"/></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 12 19 6.41Z"/></svg>
</button>
</nav>
</form>
<div class="md-search__output">
<div class="md-search__scrollwrap" 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"></ol>
</div>
</div>
</div>
</div>
</div>
<div class="md-header__source">
<a href="https://github.com/schmelczer/great-ai" 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 0 448 512"><!--! Font Awesome Free 6.2.0 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 2022 Fonticons, Inc.--><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81z"/></svg>
</div>
<div class="md-source__repository">
schmelczer/great-ai
</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="GreatAI documentation" class="md-nav__button md-logo" aria-label="GreatAI documentation" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54Z"/></svg>
</a>
GreatAI documentation
</label>
<div class="md-nav__source">
<a href="https://github.com/schmelczer/great-ai" 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 0 448 512"><!--! Font Awesome Free 6.2.0 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 2022 Fonticons, Inc.--><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81z"/></svg>
</div>
<div class="md-source__repository">
schmelczer/great-ai
</div>
</a>
</div>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../.." class="md-nav__link">
Overview
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle" data-md-toggle="__nav_2" type="checkbox" id="__nav_2" >
<label class="md-nav__link" for="__nav_2">
Tutorial
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" aria-label="Tutorial" data-md-level="1">
<label class="md-nav__title" for="__nav_2">
<span class="md-nav__icon md-icon"></span>
Tutorial
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../tutorial/" class="md-nav__link">
Tutorial overview
</a>
</li>
<li class="md-nav__item">
<a href="../../tutorial/train/" class="md-nav__link">
Train your model
</a>
</li>
<li class="md-nav__item">
<a href="../../tutorial/deploy/" class="md-nav__link">
Harden and deploy your app
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--active md-nav__item--nested">
<input class="md-nav__toggle md-toggle" data-md-toggle="__nav_3" type="checkbox" id="__nav_3" checked>
<label class="md-nav__link" for="__nav_3">
User Guides
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" aria-label="User Guides" data-md-level="1">
<label class="md-nav__title" for="__nav_3">
<span class="md-nav__icon md-icon"></span>
User Guides
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../install/" class="md-nav__link">
Installation guide
</a>
</li>
<li class="md-nav__item">
<a href="../create-service/" class="md-nav__link">
How to create a GreatAI service
</a>
</li>
<li class="md-nav__item">
<a href="../configure-service/" class="md-nav__link">
How to configure GreatAI
</a>
</li>
<li class="md-nav__item">
<a href="../use-service/" class="md-nav__link">
How to perform prediction with GreatAI
</a>
</li>
<li class="md-nav__item">
<a href="../handle-training-data/" class="md-nav__link">
How to manage training data
</a>
</li>
<li class="md-nav__item md-nav__item--active">
<input class="md-nav__toggle md-toggle" data-md-toggle="toc" type="checkbox" id="__toc">
<label class="md-nav__link md-nav__link--active" for="__toc">
How to use LargeFiles
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
How to use LargeFiles
</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="#motivation" class="md-nav__link">
Motivation
</a>
</li>
<li class="md-nav__item">
<a href="#simple-example" class="md-nav__link">
Simple example
</a>
<nav class="md-nav" aria-label="Simple example">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#more-details" class="md-nav__link">
More details
</a>
<nav class="md-nav" aria-label="More details">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#i-only-need-a-path" class="md-nav__link">
I only need a path
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#from-the-command-line" class="md-nav__link">
From the command-line
</a>
<nav class="md-nav" aria-label="From the command-line">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#setup" class="md-nav__link">
Setup
</a>
</li>
<li class="md-nav__item">
<a href="#upload-some-files" class="md-nav__link">
Upload some files
</a>
</li>
<li class="md-nav__item">
<a href="#download-some-files-to-the-local-cache" class="md-nav__link">
Download some files to the local cache
</a>
</li>
<li class="md-nav__item">
<a href="#delete-remote-files" class="md-nav__link">
Delete remote files
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../call-remote/" class="md-nav__link">
How to call remote GreatAI instances
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle" data-md-toggle="__nav_4" type="checkbox" id="__nav_4" >
<label class="md-nav__link" for="__nav_4">
Reference
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" aria-label="Reference" data-md-level="1">
<label class="md-nav__title" for="__nav_4">
<span class="md-nav__icon md-icon"></span>
Reference
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../reference/" class="md-nav__link">
GreatAI reference
</a>
</li>
<li class="md-nav__item">
<a href="../../reference/utilities/" class="md-nav__link">
Utilities
</a>
</li>
<li class="md-nav__item">
<a href="../../reference/large-file/" class="md-nav__link">
LargeFile
</a>
</li>
<li class="md-nav__item">
<a href="../../reference/views/" class="md-nav__link">
View models
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle" data-md-toggle="__nav_5" type="checkbox" id="__nav_5" >
<label class="md-nav__link" for="__nav_5">
Examples
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" aria-label="Examples" data-md-level="1">
<label class="md-nav__title" for="__nav_5">
<span class="md-nav__icon md-icon"></span>
Examples
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle" data-md-toggle="__nav_5_1" type="checkbox" id="__nav_5_1" >
<label class="md-nav__link" for="__nav_5_1">
Explainable Naive Bayes
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" aria-label="Explainable Naive Bayes" data-md-level="2">
<label class="md-nav__title" for="__nav_5_1">
<span class="md-nav__icon md-icon"></span>
Explainable Naive Bayes
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../examples/simple/data/" class="md-nav__link">
Simple example: data engineering
</a>
</li>
<li class="md-nav__item">
<a href="../../examples/simple/train/" class="md-nav__link">
Optimise and train a model
</a>
</li>
<li class="md-nav__item">
<a href="../../examples/simple/deploy/" class="md-nav__link">
Hardening and deployment
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle" data-md-toggle="__nav_5_2" type="checkbox" id="__nav_5_2" >
<label class="md-nav__link" for="__nav_5_2">
Explainable SciBERT
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" aria-label="Explainable SciBERT" data-md-level="2">
<label class="md-nav__title" for="__nav_5_2">
<span class="md-nav__icon md-icon"></span>
Explainable SciBERT
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../examples/scibert/" class="md-nav__link">
Summarising scientific publications from a tech-transfer perspective
</a>
</li>
<li class="md-nav__item">
<a href="../../examples/scibert/data/" class="md-nav__link">
Explore data and feasibility of approach
</a>
</li>
<li class="md-nav__item">
<a href="../../examples/scibert/train/" class="md-nav__link">
Fine-tune SciBERT
</a>
</li>
<li class="md-nav__item">
<a href="../../examples/scibert/deploy/" class="md-nav__link">
Create an inference function
</a>
</li>
<li class="md-nav__item">
<a href="../../examples/scibert/additional-files/" class="md-nav__link">
Additional files in the repository
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../../explanation/" class="md-nav__link">
Explanation
</a>
</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="#motivation" class="md-nav__link">
Motivation
</a>
</li>
<li class="md-nav__item">
<a href="#simple-example" class="md-nav__link">
Simple example
</a>
<nav class="md-nav" aria-label="Simple example">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#more-details" class="md-nav__link">
More details
</a>
<nav class="md-nav" aria-label="More details">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#i-only-need-a-path" class="md-nav__link">
I only need a path
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#from-the-command-line" class="md-nav__link">
From the command-line
</a>
<nav class="md-nav" aria-label="From the command-line">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#setup" class="md-nav__link">
Setup
</a>
</li>
<li class="md-nav__item">
<a href="#upload-some-files" class="md-nav__link">
Upload some files
</a>
</li>
<li class="md-nav__item">
<a href="#download-some-files-to-the-local-cache" class="md-nav__link">
Download some files to the local cache
</a>
</li>
<li class="md-nav__item">
<a href="#delete-remote-files" class="md-nav__link">
Delete remote files
</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">
<a href="https://github.com/schmelczer/great-ai/edit/main/docs/how-to-guides/large-file.md" title="Edit this page" class="md-content__button md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20.71 7.04c.39-.39.39-1.04 0-1.41l-2.34-2.34c-.37-.39-1.02-.39-1.41 0l-1.84 1.83 3.75 3.75M3 17.25V21h3.75L17.81 9.93l-3.75-3.75L3 17.25Z"/></svg>
</a>
<h1 id="how-to-use-largefiles">How to use LargeFiles<a class="headerlink" href="#how-to-use-largefiles" title="Permanent link">#</a></h1>
<p>The functions <a class="autorefs autorefs-internal" href="../../reference/#great_ai.use_model">save_model</a> and <a class="autorefs autorefs-internal" href="../../reference/#great_ai.use_model">@use_model</a> wrap LargeFile instances. Hence, besides configuring <a href="/reference/large-file">LargeFile</a>, users have few reasons to use LargeFiles directly.</p>
<h2 id="motivation">Motivation<a class="headerlink" href="#motivation" title="Permanent link">#</a></h2>
<p>Often, especially when working with data-heavy applications, large files can proliferate in a repository. Version controlling them is an obvious next step. However, GitHub's git LFS implementation <a href="https://docs.github.com/en/repositories/working-with-files/managing-large-files/removing-files-from-git-large-file-storage#git-lfs-objects-in-your-repository">doesn't support deleting</a> large files, making it easy for them to eat-up the LFS quota and explode the size of your repos.</p>
<p><a href="https://dvc.org/">DVC</a> is a viable alternative; however, it requires users to learn to use one more CLI tool.</p>
<details class="note">
<summary>Using LargeFile-s directly (usually not needed)</summary>
<p>LargeFile doesn't require users to learn too much new. It is a nearly exact copy of Python's built-in <code>open()</code> function, with which users are undoubtedly already familiar.</p>
<h2 id="simple-example">Simple example<a class="headerlink" href="#simple-example" title="Permanent link">#</a></h2>
<div class="highlight"><pre><span></span><code><a id="__codelineno-0-1" name="__codelineno-0-1" href="#__codelineno-0-1"></a><span class="kn">from</span> <span class="nn">great_ai.large_file</span> <span class="kn">import</span> <span class="n">LargeFileS3</span>
<a id="__codelineno-0-2" name="__codelineno-0-2" href="#__codelineno-0-2"></a>
<a id="__codelineno-0-3" name="__codelineno-0-3" href="#__codelineno-0-3"></a><span class="n">LargeFileS3</span><span class="o">.</span><span class="n">configure_credentials</span><span class="p">({</span>
<a id="__codelineno-0-4" name="__codelineno-0-4" href="#__codelineno-0-4"></a> <span class="s2">&quot;aws_region_name&quot;</span><span class="p">:</span> <span class="s2">&quot;your_region_like_eu-west-2&quot;</span><span class="p">,</span>
<a id="__codelineno-0-5" name="__codelineno-0-5" href="#__codelineno-0-5"></a> <span class="s2">&quot;aws_access_key_id&quot;</span><span class="p">:</span> <span class="s2">&quot;YOUR_ACCESS_KEY_ID&quot;</span><span class="p">,</span>
<a id="__codelineno-0-6" name="__codelineno-0-6" href="#__codelineno-0-6"></a> <span class="s2">&quot;aws_secret_access_key&quot;</span><span class="p">:</span> <span class="s2">&quot;YOUR_VERY_SECRET_ACCESS_KEY&quot;</span><span class="p">,</span>
<a id="__codelineno-0-7" name="__codelineno-0-7" href="#__codelineno-0-7"></a> <span class="s2">&quot;large_files_bucket_name&quot;</span><span class="p">:</span> <span class="s2">&quot;create_a_bucket_and_put_its_name_here&quot;</span><span class="p">,</span>
<a id="__codelineno-0-8" name="__codelineno-0-8" href="#__codelineno-0-8"></a><span class="p">})</span>
<a id="__codelineno-0-9" name="__codelineno-0-9" href="#__codelineno-0-9"></a>
<a id="__codelineno-0-10" name="__codelineno-0-10" href="#__codelineno-0-10"></a><span class="c1"># Creates a new version and deletes the older version </span>
<a id="__codelineno-0-11" name="__codelineno-0-11" href="#__codelineno-0-11"></a><span class="c1"># leaving the three most recently used intact</span>
<a id="__codelineno-0-12" name="__codelineno-0-12" href="#__codelineno-0-12"></a><span class="k">with</span> <span class="n">LargeFileS3</span><span class="p">(</span><span class="s2">&quot;test.txt&quot;</span><span class="p">,</span> <span class="s2">&quot;w&quot;</span><span class="p">,</span> <span class="n">keep_last_n</span><span class="o">=</span><span class="mi">3</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
<a id="__codelineno-0-13" name="__codelineno-0-13" href="#__codelineno-0-13"></a> <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">100000</span><span class="p">):</span>
<a id="__codelineno-0-14" name="__codelineno-0-14" href="#__codelineno-0-14"></a> <span class="n">f</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="s1">&#39;test</span><span class="se">\n</span><span class="s1">&#39;</span><span class="p">)</span>
<a id="__codelineno-0-15" name="__codelineno-0-15" href="#__codelineno-0-15"></a>
<a id="__codelineno-0-16" name="__codelineno-0-16" href="#__codelineno-0-16"></a><span class="c1"># The latest version is returned by default</span>
<a id="__codelineno-0-17" name="__codelineno-0-17" href="#__codelineno-0-17"></a><span class="c1"># but an optional `version` keyword argument can be provided as well</span>
<a id="__codelineno-0-18" name="__codelineno-0-18" href="#__codelineno-0-18"></a><span class="k">with</span> <span class="n">LargeFileS3</span><span class="p">(</span><span class="s2">&quot;test.txt&quot;</span><span class="p">,</span> <span class="s2">&quot;r&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span> <span class="c1">#(1)</span>
<a id="__codelineno-0-19" name="__codelineno-0-19" href="#__codelineno-0-19"></a> <span class="nb">print</span><span class="p">(</span><span class="n">f</span><span class="o">.</span><span class="n">readlines</span><span class="p">()[</span><span class="mi">0</span><span class="p">])</span>
</code></pre></div>
<ol>
<li>The latest version is already in the local cache; no download is required.</li>
</ol>
<h3 id="more-details">More details<a class="headerlink" href="#more-details" title="Permanent link">#</a></h3>
<p><code>LargeFile</code> behaves like an opened file (in the background, it is a temp file after all). Binary reads and writes are supported along with the <a href="https://docs.python.org/3/library/functions.html#open" target="_blank">different keywords <code>open()</code> accepts</a>.</p>
<p>The local cache can be configured with these properties:</p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-1-1" name="__codelineno-1-1" href="#__codelineno-1-1"></a><span class="n">LargeFileS3</span><span class="o">.</span><span class="n">cache_path</span> <span class="o">=</span> <span class="n">Path</span><span class="p">(</span><span class="s1">&#39;.cache&#39;</span><span class="p">)</span>
<a id="__codelineno-1-2" name="__codelineno-1-2" href="#__codelineno-1-2"></a><span class="n">LargeFileS3</span><span class="o">.</span><span class="n">max_cache_size</span> <span class="o">=</span> <span class="s2">&quot;30 GB&quot;</span>
</code></pre></div>
<h4 id="i-only-need-a-path">I only need a path<a class="headerlink" href="#i-only-need-a-path" title="Permanent link">#</a></h4>
<p>In case you only need a path to the (proxy of the) remote file, this pattern can be applied:</p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-2-1" name="__codelineno-2-1" href="#__codelineno-2-1"></a><span class="n">path_to_model</span> <span class="o">=</span> <span class="n">LargeFileS3</span><span class="p">(</span><span class="s2">&quot;folder-of-my-bert-model&quot;</span><span class="p">,</span> <span class="n">version</span><span class="o">=</span><span class="mi">31</span><span class="p">)</span><span class="o">.</span><span class="n">get</span><span class="p">()</span>
</code></pre></div>
<blockquote>
<p>This will first download the file/folder into your local cache folder. Then, it returns a <code>Path</code> object to the local version. Which can be turned into a string with <code>str(path_to_model)</code>.</p>
</blockquote>
<p>The same approach works for uploads:</p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-3-1" name="__codelineno-3-1" href="#__codelineno-3-1"></a><span class="n">LargeFileS3</span><span class="p">(</span><span class="s2">&quot;folder-of-my-bert-model&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">push</span><span class="p">(</span><span class="s1">&#39;path_to_local/folder_or_file&#39;</span><span class="p">)</span>
</code></pre></div>
<blockquote>
<p>This way, both regular files and folders can be handled. The uploaded file is called <strong>folder-of-my-bert-model</strong>, the local name is ignored.</p>
</blockquote>
<p>Lastly, all version of the remote object can be deleted by calling <code>LargeFileS3("my-file").delete()</code>. It will still reside in your local cache afterwards; its deletion will happen next time your local cache has to be pruned.</p>
</details>
<h2 id="from-the-command-line">From the command-line<a class="headerlink" href="#from-the-command-line" title="Permanent link">#</a></h2>
<p>The main reason for using the <code>large-file</code> or <code>python3 -m great_ai.large_file</code> commands is to upload or download models from the terminal. For example, when building a docker image, it is best practice to cache the referred models.</p>
<h3 id="setup">Setup<a class="headerlink" href="#setup" title="Permanent link">#</a></h3>
<p>Create an .ini file (or use <em>~/.aws/credentials</em>). It may look like this:</p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-4-1" name="__codelineno-4-1" href="#__codelineno-4-1"></a><span class="na">aws_region_name</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">your_region_like_eu-west-2</span><span class="w"></span>
<a id="__codelineno-4-2" name="__codelineno-4-2" href="#__codelineno-4-2"></a><span class="na">aws_access_key_id</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">YOUR_ACCESS_KEY_ID</span><span class="w"></span>
<a id="__codelineno-4-3" name="__codelineno-4-3" href="#__codelineno-4-3"></a><span class="na">aws_secret_access_key</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">YOUR_VERY_SECRET_ACCESS_KEY</span><span class="w"></span>
<a id="__codelineno-4-4" name="__codelineno-4-4" href="#__codelineno-4-4"></a><span class="na">large_files_bucket_name</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">my_large_files</span><span class="w"></span>
</code></pre></div>
<h3 id="upload-some-files">Upload some files<a class="headerlink" href="#upload-some-files" title="Permanent link">#</a></h3>
<div class="highlight"><pre><span></span><code><a id="__codelineno-5-1" name="__codelineno-5-1" href="#__codelineno-5-1"></a>large-file --backend s3 --secrets secrets.ini <span class="se">\</span>
<a id="__codelineno-5-2" name="__codelineno-5-2" href="#__codelineno-5-2"></a> --push my_first_file.json folder/my_second_file my_folder
</code></pre></div>
<blockquote>
<p>Only the filename is used as the S3 name; the rest of the path is ignored.</p>
</blockquote>
<div class="admonition important">
<p class="admonition-title">Using MongoDB</p>
<p>The possible values for <code>--backend</code> are <code>s3</code>, <code>mongo</code>, and <code>local</code>. The latter doesn't need credentials. It only versions and stores your files in a local folder. MongoDB, on the other hand, requires a <code>mongo_connection_string</code> and a <code>mongo_database</code> to be specified. For storing large files, it uses the <a href="https://www.mongodb.com/docs/manual/core/gridfs" target="_blank">GridFS</a> specification.</p>
</div>
<h3 id="download-some-files-to-the-local-cache">Download some files to the local cache<a class="headerlink" href="#download-some-files-to-the-local-cache" title="Permanent link">#</a></h3>
<p>This can be useful when building a Docker image, for example. This way, the files can already reside inside the container and need not be downloaded later.</p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-6-1" name="__codelineno-6-1" href="#__codelineno-6-1"></a>large-file --backend s3 --secrets ~/.aws/credentials <span class="se">\</span>
<a id="__codelineno-6-2" name="__codelineno-6-2" href="#__codelineno-6-2"></a> --cache my_first_file.json:3 my_second_file my_folder:0
</code></pre></div>
<blockquote>
<p>Versions may be specified by using <code>:</code>-s.</p>
</blockquote>
<h3 id="delete-remote-files">Delete remote files<a class="headerlink" href="#delete-remote-files" title="Permanent link">#</a></h3>
<div class="highlight"><pre><span></span><code><a id="__codelineno-7-1" name="__codelineno-7-1" href="#__codelineno-7-1"></a>large-file --backend s3 --secrets ~/.aws/credentials <span class="se">\</span>
<a id="__codelineno-7-2" name="__codelineno-7-2" href="#__codelineno-7-2"></a> --delete my_first_file.json
</code></pre></div>
<hr>
<div class="md-source-file">
<small>
Last update:
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-date">August 20, 2022</span>
</small>
</div>
</article>
</div>
</div>
</main>
<footer class="md-footer">
<nav class="md-footer__inner md-grid" aria-label="Footer" >
<a href="../handle-training-data/" class="md-footer__link md-footer__link--prev" aria-label="Previous: How to manage training data" rel="prev">
<div class="md-footer__button md-icon">
<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 11h12Z"/></svg>
</div>
<div class="md-footer__title">
<div class="md-ellipsis">
<span class="md-footer__direction">
Previous
</span>
How to manage training data
</div>
</div>
</a>
<a href="../call-remote/" class="md-footer__link md-footer__link--next" aria-label="Next: How to call remote GreatAI instances" rel="next">
<div class="md-footer__title">
<div class="md-ellipsis">
<span class="md-footer__direction">
Next
</span>
How to call remote GreatAI instances
</div>
</div>
<div class="md-footer__button md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M4 11v2h12l-5.5 5.5 1.42 1.42L19.84 12l-7.92-7.92L10.5 5.5 16 11H4Z"/></svg>
</div>
</a>
</nav>
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
<div class="md-copyright__highlight">
GNU General Public License v3
</div>
</div>
<div class="md-social">
<a href="https://schmelczer.dev" target="_blank" rel="noopener" title="about the author" class="md-social__link">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 512"><!--! Font Awesome Free 6.2.0 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 2022 Fonticons, Inc.--><path d="M392.8 1.2c-17-4.9-34.7 5-39.6 22l-128 448c-4.9 17 5 34.7 22 39.6s34.7-5 39.6-22l128-448c4.9-17-5-34.7-22-39.6zm80.6 120.1c-12.5 12.5-12.5 32.8 0 45.3l89.3 89.4-89.4 89.4c-12.5 12.5-12.5 32.8 0 45.3s32.8 12.5 45.3 0l112-112c12.5-12.5 12.5-32.8 0-45.3l-112-112c-12.5-12.5-32.8-12.5-45.3 0zm-306.7 0c-12.5-12.5-32.8-12.5-45.3 0l-112 112c-12.5 12.5-12.5 32.8 0 45.3l112 112c12.5 12.5 32.8 12.5 45.3 0s12.5-32.8 0-45.3L77.3 256l89.4-89.4c12.5-12.5 12.5-32.8 0-45.3z"/></svg>
</a>
<a href="https://github.com/schmelczer/great-ai" target="_blank" rel="noopener" title="great-ai on Github" class="md-social__link">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 496 512"><!--! Font Awesome Free 6.2.0 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 2022 Fonticons, Inc.--><path d="M165.9 397.4c0 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 3.6zm-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 2.3zm44.2-1.7c-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-.3-1.9-3-3.2-5.9-2.9zM244.8 8C106.1 8 0 113.3 0 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 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8zM97.2 352.9c-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-.7-5.2-1.6-1.6-3.9-2.3-5.2-1zm-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-.3-4.3.7zm32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1zm-11.4-14.7c-1.6 1-1.6 3.6 0 5.9 1.6 2.3 4.3 3.3 5.6 2.3 1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2z"/></svg>
</a>
<a href="https://hub.docker.com/repository/docker/schmelczera/great-ai" target="_blank" rel="noopener" title="great-ai on DockerHub" class="md-social__link">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 512"><!--! Font Awesome Free 6.2.0 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 2022 Fonticons, Inc.--><path d="M349.9 236.3h-66.1v-59.4h66.1v59.4zm0-204.3h-66.1v60.7h66.1V32zm78.2 144.8H362v59.4h66.1v-59.4zm-156.3-72.1h-66.1v60.1h66.1v-60.1zm78.1 0h-66.1v60.1h66.1v-60.1zm276.8 100c-14.4-9.7-47.6-13.2-73.1-8.4-3.3-24-16.7-44.9-41.1-63.7l-14-9.3-9.3 14c-18.4 27.8-23.4 73.6-3.7 103.8-8.7 4.7-25.8 11.1-48.4 10.7H2.4c-8.7 50.8 5.8 116.8 44 162.1 37.1 43.9 92.7 66.2 165.4 66.2 157.4 0 273.9-72.5 328.4-204.2 21.4.4 67.6.1 91.3-45.2 1.5-2.5 6.6-13.2 8.5-17.1l-13.3-8.9zm-511.1-27.9h-66v59.4h66.1v-59.4zm78.1 0h-66.1v59.4h66.1v-59.4zm78.1 0h-66.1v59.4h66.1v-59.4zm-78.1-72.1h-66.1v60.1h66.1v-60.1z"/></svg>
</a>
<a href="https://pypi.org/project/great-ai" target="_blank" rel="noopener" title="great-ai on PyPI" class="md-social__link">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.2.0 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 2022 Fonticons, Inc.--><path d="M439.8 200.5c-7.7-30.9-22.3-54.2-53.4-54.2h-40.1v47.4c0 36.8-31.2 67.8-66.8 67.8H172.7c-29.2 0-53.4 25-53.4 54.3v101.8c0 29 25.2 46 53.4 54.3 33.8 9.9 66.3 11.7 106.8 0 26.9-7.8 53.4-23.5 53.4-54.3v-40.7H226.2v-13.6h160.2c31.1 0 42.6-21.7 53.4-54.2 11.2-33.5 10.7-65.7 0-108.6zM286.2 404c11.1 0 20.1 9.1 20.1 20.3 0 11.3-9 20.4-20.1 20.4-11 0-20.1-9.2-20.1-20.4.1-11.3 9.1-20.3 20.1-20.3zM167.8 248.1h106.8c29.7 0 53.4-24.5 53.4-54.3V91.9c0-29-24.4-50.7-53.4-55.6-35.8-5.9-74.7-5.6-106.8.1-45.2 8-53.4 24.7-53.4 55.6v40.7h106.9v13.6h-147c-31.1 0-58.3 18.7-66.8 54.2-9.8 40.7-10.2 66.1 0 108.6 7.6 31.6 25.7 54.2 56.8 54.2H101v-48.8c0-35.3 30.5-66.4 66.8-66.4zm-6.7-142.6c-11.1 0-20.1-9.1-20.1-20.3.1-11.3 9-20.4 20.1-20.4 11 0 20.1 9.2 20.1 20.4s-9 20.3-20.1 20.3z"/></svg>
</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">{"base": "../..", "features": ["content.code.annotate", "content.tooltips"], "search": "../../assets/javascripts/workers/search.16e2a7d4.min.js", "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.config.lang": "en", "search.config.pipeline": "trimmer, stopWordFilter", "search.config.separator": "[\\s\\-]+", "search.placeholder": "Search", "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.title": "Select version"}}</script>
<script src="../../assets/javascripts/bundle.d6c3db9e.min.js"></script>
</body>
</html>
Reference in a new issue View git blame Copy permalink