595 lines
No EOL
28 KiB
HTML
595 lines
No EOL
28 KiB
HTML
|
|
<!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="../assets/images/favicon.png">
|
|
<meta name="generator" content="mkdocs-1.3.0, mkdocs-material-8.3.9">
|
|
|
|
|
|
|
|
<title>[open(S3)](https://pypi.org/project/open-large/) - GreatAI documentation</title>
|
|
|
|
|
|
|
|
<link rel="stylesheet" href="../assets/stylesheets/main.1d29e8d0.min.css">
|
|
|
|
|
|
<link rel="stylesheet" href="../assets/stylesheets/palette.cbb835fc.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_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="" 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="#opens3" 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">
|
|
|
|
[open(S3)](https://pypi.org/project/open-large/)
|
|
|
|
</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="" 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 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 12 20 8.69Z"/></svg>
|
|
</label>
|
|
|
|
|
|
|
|
|
|
<input class="md-option" data-md-color-media="" data-md-color-scheme="slate" data-md-color-primary="" 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 18c-.89 0-1.74-.2-2.5-.55C11.56 16.5 13 14.42 13 12c0-2.42-1.44-4.5-3.5-5.45C10.26 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 12 20 8.69Z"/></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" 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 6.1.1 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 6.1.1 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">
|
|
<a href="../tutorials/" class="md-nav__link">
|
|
Tutorials
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../how-to-guides/" class="md-nav__link">
|
|
How-To Guides
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../reference/" class="md-nav__link">
|
|
Reference
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../explanation/" class="md-nav__link">
|
|
Explanation
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../simple-mag/train/" class="md-nav__link">
|
|
Train a field of study (domain) classification of sentences on the MAG dataset
|
|
</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="#solution" class="md-nav__link">
|
|
Solution
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="Solution">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#simple-example" class="md-nav__link">
|
|
Simple example
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<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>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#command-line-example" class="md-nav__link">
|
|
Command-line example
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="Command-line example">
|
|
<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="#print-the-expected-options" class="md-nav__link">
|
|
Print the expected options
|
|
</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>
|
|
|
|
</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/open_s3.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="opens3"><a href="https://pypi.org/project/open-large/">open(S3)</a><a class="headerlink" href="#opens3" title="Permanent link">#</a></h1>
|
|
<p>Storing, versioning, and downloading files from S3 made as easy as using <code>open()</code> in Python. Caching included.</p>
|
|
<h2 id="motivation">Motivation<a class="headerlink" href="#motivation" title="Permanent link">#</a></h2>
|
|
<p>Oftentimes, 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 the deletion</a> of large files, making it easy for them to eat-up the LFS quota and explode the size of your repos.</p>
|
|
<h2 id="solution">Solution<a class="headerlink" href="#solution" 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>pip install open-large
|
|
</code></pre></div>
|
|
<h3 id="simple-example">Simple example<a class="headerlink" href="#simple-example" title="Permanent link">#</a></h3>
|
|
<div class="highlight"><pre><span></span><code><a id="__codelineno-1-1" name="__codelineno-1-1" href="#__codelineno-1-1"></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-1-2" name="__codelineno-1-2" href="#__codelineno-1-2"></a>
|
|
<a id="__codelineno-1-3" name="__codelineno-1-3" href="#__codelineno-1-3"></a><span class="n">LargeFileS3</span><span class="o">.</span><span class="n">configure_credentials</span><span class="p">({</span>
|
|
<a id="__codelineno-1-4" name="__codelineno-1-4" href="#__codelineno-1-4"></a> <span class="s2">"aws_region_name"</span><span class="p">:</span> <span class="s2">"your_region_like_eu-west-2"</span><span class="p">,</span>
|
|
<a id="__codelineno-1-5" name="__codelineno-1-5" href="#__codelineno-1-5"></a> <span class="s2">"aws_access_key_id"</span><span class="p">:</span> <span class="s2">"YOUR_ACCESS_KEY_ID"</span><span class="p">,</span>
|
|
<a id="__codelineno-1-6" name="__codelineno-1-6" href="#__codelineno-1-6"></a> <span class="s2">"aws_secret_access_key"</span><span class="p">:</span> <span class="s2">"YOUR_VERY_SECRET_ACCESS_KEY"</span><span class="p">,</span>
|
|
<a id="__codelineno-1-7" name="__codelineno-1-7" href="#__codelineno-1-7"></a> <span class="s2">"large_files_bucket_name"</span><span class="p">:</span> <span class="s2">"create_a_bucket_and_put_its_name_here"</span><span class="p">,</span>
|
|
<a id="__codelineno-1-8" name="__codelineno-1-8" href="#__codelineno-1-8"></a><span class="p">})</span>
|
|
<a id="__codelineno-1-9" name="__codelineno-1-9" href="#__codelineno-1-9"></a>
|
|
<a id="__codelineno-1-10" name="__codelineno-1-10" href="#__codelineno-1-10"></a><span class="c1"># Creates a new version and deletes the older version leaving the 3 most recently used intact</span>
|
|
<a id="__codelineno-1-11" name="__codelineno-1-11" href="#__codelineno-1-11"></a><span class="k">with</span> <span class="n">LargeFileS3</span><span class="p">(</span><span class="s2">"test.txt"</span><span class="p">,</span> <span class="s2">"w"</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-1-12" name="__codelineno-1-12" href="#__codelineno-1-12"></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-1-13" name="__codelineno-1-13" href="#__codelineno-1-13"></a> <span class="n">f</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="s1">'test</span><span class="se">\n</span><span class="s1">'</span><span class="p">)</span>
|
|
<a id="__codelineno-1-14" name="__codelineno-1-14" href="#__codelineno-1-14"></a>
|
|
<a id="__codelineno-1-15" name="__codelineno-1-15" href="#__codelineno-1-15"></a><span class="c1"># By default the latest version is returned</span>
|
|
<a id="__codelineno-1-16" name="__codelineno-1-16" href="#__codelineno-1-16"></a><span class="c1"># but an optional `version` keyword argument can be provided as well</span>
|
|
<a id="__codelineno-1-17" name="__codelineno-1-17" href="#__codelineno-1-17"></a><span class="k">with</span> <span class="n">LargeFileS3</span><span class="p">(</span><span class="s2">"test.txt"</span><span class="p">,</span> <span class="s2">"r"</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
|
|
<a id="__codelineno-1-18" name="__codelineno-1-18" href="#__codelineno-1-18"></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>
|
|
<blockquote>
|
|
<p>Automatically creates a file, writes to it, uploads it to S3, and then queries the most recent version of it.
|
|
In this case, the latest version is already in the local cache, no download is required.</p>
|
|
</blockquote>
|
|
<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 reading and writing is supported along with the <a href="https://docs.python.org/3/library/functions.html#open">different keywords</a> <code>open()</code> accepts.</p>
|
|
<p>The local cache can be configured with these properties:</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">LargeFile</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">'.cache'</span><span class="p">)</span>
|
|
<a id="__codelineno-2-2" name="__codelineno-2-2" href="#__codelineno-2-2"></a><span class="n">LargeFile</span><span class="o">.</span><span class="n">max_cache_size</span> <span class="o">=</span> <span class="s2">"30 GB"</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 "remote" file, this pattern can be applied:</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">path_to_model</span> <span class="o">=</span> <span class="n">LargeFile</span><span class="p">(</span><span class="s2">"folder-of-my-bert-model"</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-4-1" name="__codelineno-4-1" href="#__codelineno-4-1"></a><span class="n">LargeFile</span><span class="p">(</span><span class="s2">"folder-of-my-bert-model"</span><span class="p">)</span><span class="o">.</span><span class="n">push</span><span class="p">(</span><span class="s1">'path_to_local/folder_or_file'</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>LargeFile("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>
|
|
<h3 id="command-line-example">Command-line example<a class="headerlink" href="#command-line-example" title="Permanent link">#</a></h3>
|
|
<p>The package can be used as a module from the command-line to give you more flexibility.</p>
|
|
<h4 id="setup">Setup<a class="headerlink" href="#setup" title="Permanent link">#</a></h4>
|
|
<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-5-1" name="__codelineno-5-1" href="#__codelineno-5-1"></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-5-2" name="__codelineno-5-2" href="#__codelineno-5-2"></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-5-3" name="__codelineno-5-3" href="#__codelineno-5-3"></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-5-4" name="__codelineno-5-4" href="#__codelineno-5-4"></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>
|
|
<a id="__codelineno-5-5" name="__codelineno-5-5" href="#__codelineno-5-5"></a><span class="na">endpoint_url</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">this is optional, for backblaze, use this: https://s3.us-west-002.backblazeb2.com</span><span class="w"></span>
|
|
</code></pre></div>
|
|
<blockquote>
|
|
<p>Just like in <a href="../example_secrets.ini">example secrets</a>.</p>
|
|
</blockquote>
|
|
<h4 id="print-the-expected-options">Print the expected options<a class="headerlink" href="#print-the-expected-options" title="Permanent link">#</a></h4>
|
|
<div class="highlight"><pre><span></span><code><a id="__codelineno-6-1" name="__codelineno-6-1" href="#__codelineno-6-1"></a>python3 -m large_file --help
|
|
</code></pre></div>
|
|
<h4 id="upload-some-files">Upload some files<a class="headerlink" href="#upload-some-files" title="Permanent link">#</a></h4>
|
|
<div class="highlight"><pre><span></span><code><a id="__codelineno-7-1" name="__codelineno-7-1" href="#__codelineno-7-1"></a>python3 -m large_file --backend s3 --secrets secrets.ini --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>
|
|
<h4 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></h4>
|
|
<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-8-1" name="__codelineno-8-1" href="#__codelineno-8-1"></a>python3 -m large_file --backend s3 -secrets ~/.aws/credentials --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>
|
|
<h4 id="delete-remote-files">Delete remote files<a class="headerlink" href="#delete-remote-files" title="Permanent link">#</a></h4>
|
|
<div class="highlight"><pre><span></span><code><a id="__codelineno-9-1" name="__codelineno-9-1" href="#__codelineno-9-1"></a>python3 -m large_file --backend s3 --secrets ~/.aws/credentials --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">July 8, 2022</span>
|
|
|
|
|
|
</small>
|
|
</div>
|
|
|
|
|
|
|
|
</article>
|
|
|
|
</div>
|
|
</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">
|
|
|
|
|
|
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">{"base": "..", "features": ["content.code.annotate", "content.tooltips"], "search": "../assets/javascripts/workers/search.b97dbffb.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.6c7ad80a.min.js"></script>
|
|
|
|
|
|
</body>
|
|
</html> |