Files
kotaemon/reference/loaders/adobe_loader/index.html

5016 lines
166 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">
<link rel="prev" href="../">
<link rel="next" href="../azureai_document_intelligence_loader/">
<link rel="icon" href="../../../assets/images/favicon.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.5.40">
<title>Adobe Loader - kotaemon Docs</title>
<link rel="stylesheet" href="../../../assets/stylesheets/main.8c3ca2c6.min.css">
<link rel="stylesheet" href="../../../assets/stylesheets/palette.06af60db.min.css">
<script src="../../../assets/pymdownx-extras/material-extra-theme-TVq-kNRT.js" type="text/javascript"></script>
<script src="../../../assets/pymdownx-extras/material-extra-3rdparty-E-i8w1WA.js" type="text/javascript"></script>
<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="../../../css/timeago.css">
<link rel="stylesheet" href="../../../assets/_mkdocstrings.css">
<link rel="stylesheet" href="../../../extra/css/code_select.css">
<link rel="stylesheet" href="../../../assets/pymdownx-extras/extra-fb5a2a1c86.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="dracula" data-md-color-primary="deep-purple" data-md-color-accent="deep-purple">
<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="#loaders.adobe_loader" 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.title"
>
<a
href="../../.."
title="kotaemon Docs"
class="md-header__button md-logo"
aria-label="kotaemon Docs"
>
<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 3.54"/></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 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">
kotaemon Docs
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
Adobe Loader
</span>
</div>
</div>
</div>
<div class="md-header__options">
<div class="md-header-nav__scheme md-header-nav__button md-source__icon md-icon">
<a
href="javascript:toggleScheme();"
title="Light mode"
class="light-mode"
>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 7a5 5 0 0 1 5 5 5 5 0 0 1-5 5 5 5 0 0 1-5-5 5 5 0 0 1 5-5m0 2a3 3 0 0 0-3 3 3 3 0 0 0 3 3 3 3 0 0 0 3-3 3 3 0 0 0-3-3m0-7 2.39 3.42C13.65 5.15 12.84 5 12 5s-1.65.15-2.39.42zM3.34 7l4.16-.35A7.2 7.2 0 0 0 5.94 8.5c-.44.74-.69 1.5-.83 2.29zm.02 10 1.76-3.77a7.131 7.131 0 0 0 2.38 4.14zM20.65 7l-1.77 3.79a7.02 7.02 0 0 0-2.38-4.15zm-.01 10-4.14.36c.59-.51 1.12-1.14 1.54-1.86.42-.73.69-1.5.83-2.29zM12 22l-2.41-3.44c.74.27 1.55.44 2.41.44.82 0 1.63-.17 2.37-.44z"/></svg>
</a>
<a
href="javascript:toggleScheme();"
title="Dark mode"
class="dark-mode"
>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="m17.75 4.09-2.53 1.94.91 3.06-2.63-1.81-2.63 1.81.91-3.06-2.53-1.94L12.44 4l1.06-3 1.06 3zm3.5 6.91-1.64 1.25.59 1.98-1.7-1.17-1.7 1.17.59-1.98L15.75 11l2.06-.05L18.5 9l.69 1.95zm-2.28 4.95c.83-.08 1.72 1.1 1.19 1.85-.32.45-.66.87-1.08 1.27C15.17 23 8.84 23 4.94 19.07c-3.91-3.9-3.91-10.24 0-14.14.4-.4.82-.76 1.27-1.08.75-.53 1.93.36 1.85 1.19-.27 2.86.69 5.83 2.89 8.02a9.96 9.96 0 0 0 8.02 2.89m-1.64 2.02a12.08 12.08 0 0 1-7.8-3.47c-2.17-2.19-3.33-5-3.49-7.82-2.81 3.14-2.7 7.96.31 10.98 3.02 3.01 7.84 3.12 10.98.31"/></svg>
</a>
<a
href="javascript:toggleScheme();"
title="System preference"
class="system-mode"
>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M7.5 2c-1.79 1.15-3 3.18-3 5.5s1.21 4.35 3.03 5.5C4.46 13 2 10.54 2 7.5A5.5 5.5 0 0 1 7.5 2m11.57 1.5 1.43 1.43L4.93 20.5 3.5 19.07zm-6.18 2.43L11.41 5 9.97 6l.42-1.7L9 3.24l1.75-.12.58-1.65L12 3.1l1.73.03-1.35 1.13zm-3.3 3.61-1.16-.73-1.12.78.34-1.32-1.09-.83 1.36-.09.45-1.29.51 1.27 1.36.03-1.05.87zM19 13.5a5.5 5.5 0 0 1-5.5 5.5c-1.22 0-2.35-.4-3.26-1.07l7.69-7.69c.67.91 1.07 2.04 1.07 3.26m-4.4 6.58 2.77-1.15-.24 3.35zm4.33-2.7 1.15-2.77 2.2 2.54zm1.15-4.96-1.14-2.78 3.34.24zM9.63 18.93l2.77 1.15-2.53 2.19z"/></svg>
</a>
<!-- <a
href="javascript:toggleScheme();"
title="Unknown scheme"
class="unknown-mode"
>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="m15.07 11.25-.9.92C13.45 12.89 13 13.5 13 15h-2v-.5c0-1.11.45-2.11 1.17-2.83l1.24-1.26c.37-.36.59-.86.59-1.41a2 2 0 0 0-2-2 2 2 0 0 0-2 2H8a4 4 0 0 1 4-4 4 4 0 0 1 4 4 3.2 3.2 0 0 1-.93 2.25M13 19h-2v-2h2M12 2A10 10 0 0 0 2 12a10 10 0 0 0 10 10 10 10 0 0 0 10-10c0-5.53-4.5-10-10-10"/></svg>
</a> -->
</div>
</div>
<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">
<a href="javascript:void(0)" class="md-search__icon md-icon" title="Share" aria-label="Share" data-clipboard data-clipboard-text="" data-md-component="search-share" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M18 16.08c-.76 0-1.44.3-1.96.77L8.91 12.7c.05-.23.09-.46.09-.7s-.04-.47-.09-.7l7.05-4.11c.54.5 1.25.81 2.04.81a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3c0 .24.04.47.09.7L8.04 9.81C7.5 9.31 6.79 9 6 9a3 3 0 0 0-3 3 3 3 0 0 0 3 3c.79 0 1.5-.31 2.04-.81l7.12 4.15c-.05.21-.08.43-.08.66 0 1.61 1.31 2.91 2.92 2.91s2.92-1.3 2.92-2.91A2.92 2.92 0 0 0 18 16.08"/></svg>
</a>
<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/Cinnamon/kotaemon" 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 0 496 512"><!--! Font Awesome Free 6.6.0 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 2024 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 3.6m-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-.3-1.9-3-3.2-5.9-2.9M244.8 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 8M97.2 352.9c-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">
Cinnamon/kotaemon
</div>
</a>
</div>
</nav>
</header>
<div class="md-container" data-md-component="container">
<nav class="md-tabs" aria-label="Tabs" data-md-component="tabs">
<div class="md-grid">
<ul class="md-tabs__list">
<li class="md-tabs__item">
<a href="../../.." class="md-tabs__link">
Getting Started
</a>
</li>
<li class="md-tabs__item">
<a href="../../../development/" class="md-tabs__link">
Development
</a>
</li>
<li class="md-tabs__item md-tabs__item--active">
<a href="../../agents/" class="md-tabs__link">
API Reference
</a>
</li>
<li class="md-tabs__item">
<a href="https://github.com/Cinnamon/kotaemon/releases" class="md-tabs__link">
Changelogs
</a>
</li>
<li class="md-tabs__item">
<a href="https://github.com/Cinnamon/kotaemon/issues" class="md-tabs__link">
Issue Tracker
</a>
</li>
<li class="md-tabs__item">
<a href="https://huggingface.co/spaces/cin-model/kotaemon-demo" class="md-tabs__link">
Live Demo
</a>
</li>
</ul>
</div>
</nav>
<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 md-nav--lifted" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href="../../.." title="kotaemon Docs" class="md-nav__button md-logo" aria-label="kotaemon Docs" 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 3.54"/></svg>
</a>
kotaemon Docs
</label>
<div class="md-nav__source">
<a href="https://github.com/Cinnamon/kotaemon" 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 0 496 512"><!--! Font Awesome Free 6.6.0 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 2024 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 3.6m-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-.3-1.9-3-3.2-5.9-2.9M244.8 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 8M97.2 352.9c-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">
Cinnamon/kotaemon
</div>
</a>
</div>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_1" >
<div class="md-nav__link md-nav__container">
<a href="../../.." class="md-nav__link ">
<span class="md-ellipsis">
Getting Started
</span>
</a>
<label class="md-nav__link " for="__nav_1" id="__nav_1_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_1_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_1">
<span class="md-nav__icon md-icon"></span>
Getting Started
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../usage/" class="md-nav__link">
<span class="md-ellipsis">
Basic Usage
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_2" >
<div class="md-nav__link md-nav__container">
<a href="../../../development/" class="md-nav__link ">
<span class="md-ellipsis">
Development
</span>
</a>
<label class="md-nav__link " for="__nav_2" id="__nav_2_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_2">
<span class="md-nav__icon md-icon"></span>
Development
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../pages/app/customize-flows/" class="md-nav__link">
<span class="md-ellipsis">
Customize flow logic
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../development/create-a-component/" class="md-nav__link">
<span class="md-ellipsis">
Creating a Component
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_2_3" >
<label class="md-nav__link" for="__nav_2_3" id="__nav_2_3_label" tabindex="0">
<span class="md-ellipsis">
Components
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_2_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_2_3">
<span class="md-nav__icon md-icon"></span>
Components
</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 " type="checkbox" id="__nav_2_3_1" >
<label class="md-nav__link" for="__nav_2_3_1" id="__nav_2_3_1_label" tabindex="0">
<span class="md-ellipsis">
Index
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="3" aria-labelledby="__nav_2_3_1_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_2_3_1">
<span class="md-nav__icon md-icon"></span>
Index
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../pages/app/index/file/" class="md-nav__link">
<span class="md-ellipsis">
File index
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_2_3_2" >
<div class="md-nav__link md-nav__container">
<a href="../../../pages/app/settings/overview/" class="md-nav__link ">
<span class="md-ellipsis">
Settings
</span>
</a>
<label class="md-nav__link " for="__nav_2_3_2" id="__nav_2_3_2_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="3" aria-labelledby="__nav_2_3_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_2_3_2">
<span class="md-nav__icon md-icon"></span>
Settings
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../pages/app/settings/user-settings/" class="md-nav__link">
<span class="md-ellipsis">
User settings
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_2_3_3" >
<label class="md-nav__link" for="__nav_2_3_3" id="__nav_2_3_3_label" tabindex="0">
<span class="md-ellipsis">
Extension
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="3" aria-labelledby="__nav_2_3_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_2_3_3">
<span class="md-nav__icon md-icon"></span>
Extension
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../pages/app/ext/user-management/" class="md-nav__link">
<span class="md-ellipsis">
User management
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../../../development/contributing/" class="md-nav__link">
<span class="md-ellipsis">
Contributing
</span>
</a>
</li>
</ul>
</nav>
</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>
<div class="md-nav__link md-nav__container">
<a href="../../agents/" class="md-nav__link ">
<span class="md-ellipsis">
API Reference
</span>
</a>
<label class="md-nav__link " for="__nav_3" id="__nav_3_label" tabindex="">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<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>
API Reference
</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 " type="checkbox" id="__nav_3_2" >
<div class="md-nav__link md-nav__container">
<a href="../../base/" class="md-nav__link ">
<span class="md-ellipsis">
Base
</span>
</a>
<label class="md-nav__link " for="__nav_3_2" id="__nav_3_2_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_3_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_2">
<span class="md-nav__icon md-icon"></span>
Base
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../base/component/" class="md-nav__link">
<span class="md-ellipsis">
Component
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../base/schema/" class="md-nav__link">
<span class="md-ellipsis">
Schema
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3_3" >
<div class="md-nav__link md-nav__container">
<a href="../../chatbot/" class="md-nav__link ">
<span class="md-ellipsis">
Chatbot
</span>
</a>
<label class="md-nav__link " for="__nav_3_3" id="__nav_3_3_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_3_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_3">
<span class="md-nav__icon md-icon"></span>
Chatbot
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../chatbot/base/" class="md-nav__link">
<span class="md-ellipsis">
Base
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../chatbot/simple_respondent/" class="md-nav__link">
<span class="md-ellipsis">
Simple Respondent
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../../cli/" class="md-nav__link">
<span class="md-ellipsis">
CLI
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3_5" >
<div class="md-nav__link md-nav__container">
<a href="../../embeddings/" class="md-nav__link ">
<span class="md-ellipsis">
Embeddings
</span>
</a>
<label class="md-nav__link " for="__nav_3_5" id="__nav_3_5_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_3_5_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_5">
<span class="md-nav__icon md-icon"></span>
Embeddings
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../embeddings/base/" class="md-nav__link">
<span class="md-ellipsis">
Base
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../embeddings/endpoint_based/" class="md-nav__link">
<span class="md-ellipsis">
Endpoint Based
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../embeddings/fastembed/" class="md-nav__link">
<span class="md-ellipsis">
Fastembed
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../embeddings/langchain_based/" class="md-nav__link">
<span class="md-ellipsis">
Langchain Based
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../embeddings/openai/" class="md-nav__link">
<span class="md-ellipsis">
Openai
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../embeddings/tei_endpoint_embed/" class="md-nav__link">
<span class="md-ellipsis">
Tei Endpoint Embed
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3_6" >
<div class="md-nav__link md-nav__container">
<a href="../../indices/" class="md-nav__link ">
<span class="md-ellipsis">
Indices
</span>
</a>
<label class="md-nav__link " for="__nav_3_6" id="__nav_3_6_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_3_6_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_6">
<span class="md-nav__icon md-icon"></span>
Indices
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../indices/base/" class="md-nav__link">
<span class="md-ellipsis">
Base
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3_6_2" >
<div class="md-nav__link md-nav__container">
<a href="../../indices/extractors/" class="md-nav__link ">
<span class="md-ellipsis">
Extractors
</span>
</a>
<label class="md-nav__link " for="__nav_3_6_2" id="__nav_3_6_2_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="3" aria-labelledby="__nav_3_6_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_6_2">
<span class="md-nav__icon md-icon"></span>
Extractors
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../indices/extractors/doc_parsers/" class="md-nav__link">
<span class="md-ellipsis">
Doc Parsers
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3_6_3" >
<div class="md-nav__link md-nav__container">
<a href="../../indices/ingests/" class="md-nav__link ">
<span class="md-ellipsis">
Ingests
</span>
</a>
<label class="md-nav__link " for="__nav_3_6_3" id="__nav_3_6_3_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="3" aria-labelledby="__nav_3_6_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_6_3">
<span class="md-nav__icon md-icon"></span>
Ingests
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../indices/ingests/files/" class="md-nav__link">
<span class="md-ellipsis">
Files
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3_6_4" >
<div class="md-nav__link md-nav__container">
<a href="../../indices/qa/" class="md-nav__link ">
<span class="md-ellipsis">
Qa
</span>
</a>
<label class="md-nav__link " for="__nav_3_6_4" id="__nav_3_6_4_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="3" aria-labelledby="__nav_3_6_4_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_6_4">
<span class="md-nav__icon md-icon"></span>
Qa
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../indices/qa/citation/" class="md-nav__link">
<span class="md-ellipsis">
Citation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../indices/qa/citation_qa/" class="md-nav__link">
<span class="md-ellipsis">
Citation Qa
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../indices/qa/citation_qa_inline/" class="md-nav__link">
<span class="md-ellipsis">
Citation Qa Inline
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../indices/qa/format_context/" class="md-nav__link">
<span class="md-ellipsis">
Format Context
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../indices/qa/utils/" class="md-nav__link">
<span class="md-ellipsis">
Utils
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3_6_5" >
<div class="md-nav__link md-nav__container">
<a href="../../indices/rankings/" class="md-nav__link ">
<span class="md-ellipsis">
Rankings
</span>
</a>
<label class="md-nav__link " for="__nav_3_6_5" id="__nav_3_6_5_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="3" aria-labelledby="__nav_3_6_5_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_6_5">
<span class="md-nav__icon md-icon"></span>
Rankings
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../indices/rankings/base/" class="md-nav__link">
<span class="md-ellipsis">
Base
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../indices/rankings/cohere/" class="md-nav__link">
<span class="md-ellipsis">
Cohere
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../indices/rankings/llm/" class="md-nav__link">
<span class="md-ellipsis">
Llm
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../indices/rankings/llm_scoring/" class="md-nav__link">
<span class="md-ellipsis">
Llm Scoring
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../indices/rankings/llm_trulens/" class="md-nav__link">
<span class="md-ellipsis">
Llm Trulens
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3_6_6" >
<div class="md-nav__link md-nav__container">
<a href="../../indices/retrievers/" class="md-nav__link ">
<span class="md-ellipsis">
Retrievers
</span>
</a>
<label class="md-nav__link " for="__nav_3_6_6" id="__nav_3_6_6_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="3" aria-labelledby="__nav_3_6_6_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_6_6">
<span class="md-nav__icon md-icon"></span>
Retrievers
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../indices/retrievers/jina_web_search/" class="md-nav__link">
<span class="md-ellipsis">
Jina Web Search
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../indices/retrievers/tavily_web_search/" class="md-nav__link">
<span class="md-ellipsis">
Tavily Web Search
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../../indices/splitters/" class="md-nav__link">
<span class="md-ellipsis">
Splitters
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../indices/vectorindex/" class="md-nav__link">
<span class="md-ellipsis">
Vectorindex
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3_7" >
<div class="md-nav__link md-nav__container">
<a href="../../llms/" class="md-nav__link ">
<span class="md-ellipsis">
LLMs
</span>
</a>
<label class="md-nav__link " for="__nav_3_7" id="__nav_3_7_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_3_7_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_7">
<span class="md-nav__icon md-icon"></span>
LLMs
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../llms/base/" class="md-nav__link">
<span class="md-ellipsis">
Base
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../llms/branching/" class="md-nav__link">
<span class="md-ellipsis">
Branching
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3_7_3" >
<div class="md-nav__link md-nav__container">
<a href="../../llms/chats/" class="md-nav__link ">
<span class="md-ellipsis">
Chats
</span>
</a>
<label class="md-nav__link " for="__nav_3_7_3" id="__nav_3_7_3_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="3" aria-labelledby="__nav_3_7_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_7_3">
<span class="md-nav__icon md-icon"></span>
Chats
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../llms/chats/base/" class="md-nav__link">
<span class="md-ellipsis">
Base
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../llms/chats/endpoint_based/" class="md-nav__link">
<span class="md-ellipsis">
Endpoint Based
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../llms/chats/langchain_based/" class="md-nav__link">
<span class="md-ellipsis">
Langchain Based
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../llms/chats/llamacpp/" class="md-nav__link">
<span class="md-ellipsis">
Llamacpp
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../llms/chats/openai/" class="md-nav__link">
<span class="md-ellipsis">
Openai
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3_7_4" >
<div class="md-nav__link md-nav__container">
<a href="../../llms/completions/" class="md-nav__link ">
<span class="md-ellipsis">
Completions
</span>
</a>
<label class="md-nav__link " for="__nav_3_7_4" id="__nav_3_7_4_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="3" aria-labelledby="__nav_3_7_4_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_7_4">
<span class="md-nav__icon md-icon"></span>
Completions
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../llms/completions/base/" class="md-nav__link">
<span class="md-ellipsis">
Base
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../llms/completions/langchain_based/" class="md-nav__link">
<span class="md-ellipsis">
Langchain Based
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../../llms/cot/" class="md-nav__link">
<span class="md-ellipsis">
Cot
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../llms/linear/" class="md-nav__link">
<span class="md-ellipsis">
Linear
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3_7_7" >
<div class="md-nav__link md-nav__container">
<a href="../../llms/prompts/" class="md-nav__link ">
<span class="md-ellipsis">
Prompts
</span>
</a>
<label class="md-nav__link " for="__nav_3_7_7" id="__nav_3_7_7_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="3" aria-labelledby="__nav_3_7_7_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_7_7">
<span class="md-nav__icon md-icon"></span>
Prompts
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../llms/prompts/base/" class="md-nav__link">
<span class="md-ellipsis">
Base
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../llms/prompts/template/" class="md-nav__link">
<span class="md-ellipsis">
Template
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--active md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3_8" checked>
<div class="md-nav__link md-nav__container">
<a href="../" class="md-nav__link ">
<span class="md-ellipsis">
Loaders
</span>
</a>
<label class="md-nav__link " for="__nav_3_8" id="__nav_3_8_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_3_8_label" aria-expanded="true">
<label class="md-nav__title" for="__nav_3_8">
<span class="md-nav__icon md-icon"></span>
Loaders
</label>
<ul class="md-nav__list" data-md-scrollfix>
<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">
Adobe Loader
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
Adobe Loader
</span>
</a>
<nav class="md-nav md-nav--secondary" aria-label="Page contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Page contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#loaders.adobe_loader" class="md-nav__link">
<span class="md-ellipsis">
adobe_loader
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#loaders.adobe_loader.AdobeReader" class="md-nav__link">
<span class="md-ellipsis">
AdobeReader
</span>
</a>
<nav class="md-nav" aria-label="AdobeReader">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#loaders.adobe_loader.AdobeReader.load_data" class="md-nav__link">
<span class="md-ellipsis">
load_data
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../azureai_document_intelligence_loader/" class="md-nav__link">
<span class="md-ellipsis">
Azureai Document Intelligence Loader
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../base/" class="md-nav__link">
<span class="md-ellipsis">
Base
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../composite_loader/" class="md-nav__link">
<span class="md-ellipsis">
Composite Loader
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../docling_loader/" class="md-nav__link">
<span class="md-ellipsis">
Docling Loader
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../docx_loader/" class="md-nav__link">
<span class="md-ellipsis">
Docx Loader
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../excel_loader/" class="md-nav__link">
<span class="md-ellipsis">
Excel Loader
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../html_loader/" class="md-nav__link">
<span class="md-ellipsis">
Html Loader
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../mathpix_loader/" class="md-nav__link">
<span class="md-ellipsis">
Mathpix Loader
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../ocr_loader/" class="md-nav__link">
<span class="md-ellipsis">
Ocr Loader
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../pdf_loader/" class="md-nav__link">
<span class="md-ellipsis">
Pdf Loader
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../txt_loader/" class="md-nav__link">
<span class="md-ellipsis">
Txt Loader
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../unstructured_loader/" class="md-nav__link">
<span class="md-ellipsis">
Unstructured Loader
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3_8_14" >
<div class="md-nav__link md-nav__container">
<a href="../utils/" class="md-nav__link ">
<span class="md-ellipsis">
Utils
</span>
</a>
<label class="md-nav__link " for="__nav_3_8_14" id="__nav_3_8_14_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="3" aria-labelledby="__nav_3_8_14_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_8_14">
<span class="md-nav__icon md-icon"></span>
Utils
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../utils/adobe/" class="md-nav__link">
<span class="md-ellipsis">
Adobe
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../utils/box/" class="md-nav__link">
<span class="md-ellipsis">
Box
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../utils/gpt4v/" class="md-nav__link">
<span class="md-ellipsis">
Gpt4V
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../utils/pdf_ocr/" class="md-nav__link">
<span class="md-ellipsis">
Pdf Ocr
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../utils/table/" class="md-nav__link">
<span class="md-ellipsis">
Table
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../web_loader/" class="md-nav__link">
<span class="md-ellipsis">
Web Loader
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3_9" >
<div class="md-nav__link md-nav__container">
<a href="../../parsers/" class="md-nav__link ">
<span class="md-ellipsis">
Parsers
</span>
</a>
<label class="md-nav__link " for="__nav_3_9" id="__nav_3_9_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_3_9_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_9">
<span class="md-nav__icon md-icon"></span>
Parsers
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../parsers/regex_extractor/" class="md-nav__link">
<span class="md-ellipsis">
Regex Extractor
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3_10" >
<div class="md-nav__link md-nav__container">
<a href="../../rerankings/" class="md-nav__link ">
<span class="md-ellipsis">
Rerankings
</span>
</a>
<label class="md-nav__link " for="__nav_3_10" id="__nav_3_10_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_3_10_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_10">
<span class="md-nav__icon md-icon"></span>
Rerankings
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../rerankings/base/" class="md-nav__link">
<span class="md-ellipsis">
Base
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../rerankings/cohere/" class="md-nav__link">
<span class="md-ellipsis">
Cohere
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../rerankings/tei_fast_rerank/" class="md-nav__link">
<span class="md-ellipsis">
Tei Fast Rerank
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3_11" >
<div class="md-nav__link md-nav__container">
<a href="../../storages/" class="md-nav__link ">
<span class="md-ellipsis">
Storages
</span>
</a>
<label class="md-nav__link " for="__nav_3_11" id="__nav_3_11_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_3_11_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_11">
<span class="md-nav__icon md-icon"></span>
Storages
</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 " type="checkbox" id="__nav_3_11_1" >
<div class="md-nav__link md-nav__container">
<a href="../../storages/docstores/" class="md-nav__link ">
<span class="md-ellipsis">
Docstores
</span>
</a>
<label class="md-nav__link " for="__nav_3_11_1" id="__nav_3_11_1_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="3" aria-labelledby="__nav_3_11_1_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_11_1">
<span class="md-nav__icon md-icon"></span>
Docstores
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../storages/docstores/base/" class="md-nav__link">
<span class="md-ellipsis">
Base
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../storages/docstores/elasticsearch/" class="md-nav__link">
<span class="md-ellipsis">
Elasticsearch
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../storages/docstores/in_memory/" class="md-nav__link">
<span class="md-ellipsis">
In Memory
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../storages/docstores/lancedb/" class="md-nav__link">
<span class="md-ellipsis">
Lancedb
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../storages/docstores/simple_file/" class="md-nav__link">
<span class="md-ellipsis">
Simple File
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3_11_2" >
<div class="md-nav__link md-nav__container">
<a href="../../storages/vectorstores/" class="md-nav__link ">
<span class="md-ellipsis">
Vectorstores
</span>
</a>
<label class="md-nav__link " for="__nav_3_11_2" id="__nav_3_11_2_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="3" aria-labelledby="__nav_3_11_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_11_2">
<span class="md-nav__icon md-icon"></span>
Vectorstores
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../storages/vectorstores/base/" class="md-nav__link">
<span class="md-ellipsis">
Base
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../storages/vectorstores/chroma/" class="md-nav__link">
<span class="md-ellipsis">
Chroma
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../storages/vectorstores/in_memory/" class="md-nav__link">
<span class="md-ellipsis">
In Memory
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../storages/vectorstores/lancedb/" class="md-nav__link">
<span class="md-ellipsis">
Lancedb
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../storages/vectorstores/milvus/" class="md-nav__link">
<span class="md-ellipsis">
Milvus
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../storages/vectorstores/qdrant/" class="md-nav__link">
<span class="md-ellipsis">
Qdrant
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../storages/vectorstores/simple_file/" class="md-nav__link">
<span class="md-ellipsis">
Simple File
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="https://github.com/Cinnamon/kotaemon/releases" class="md-nav__link">
<span class="md-ellipsis">
Changelogs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="https://github.com/Cinnamon/kotaemon/issues" class="md-nav__link">
<span class="md-ellipsis">
Issue Tracker
</span>
</a>
</li>
<li class="md-nav__item">
<a href="https://huggingface.co/spaces/cin-model/kotaemon-demo" class="md-nav__link">
<span class="md-ellipsis">
Live Demo
</span>
</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="Page contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Page contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#loaders.adobe_loader" class="md-nav__link">
<span class="md-ellipsis">
adobe_loader
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#loaders.adobe_loader.AdobeReader" class="md-nav__link">
<span class="md-ellipsis">
AdobeReader
</span>
</a>
<nav class="md-nav" aria-label="AdobeReader">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#loaders.adobe_loader.AdobeReader.load_data" class="md-nav__link">
<span class="md-ellipsis">
load_data
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<a href="https://github.com/Cinnamon/kotaemon/edit/main/kotaemon/loaders/adobe_loader.py" 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-3.75-3.75z"/></svg>
</a>
<h1>Adobe Loader</h1>
<div class="doc doc-object doc-module">
<a id="loaders.adobe_loader"></a>
<div class="doc doc-contents first">
<div class="doc doc-children">
<div class="doc doc-object doc-class">
<h2 id="loaders.adobe_loader.AdobeReader" class="doc doc-heading">
<span class="doc doc-object-name doc-class-name">AdobeReader</span>
<a href="#loaders.adobe_loader.AdobeReader" class="headerlink" title="Permanent link"></a></h2>
<div class="doc doc-contents ">
<p class="doc doc-class-bases">
Bases: <code>BaseReader</code></p>
<p>Read PDF using the Adobe's PDF Services.
Be able to extract text, table, and figure with high accuracy</p>
<details class="example" open>
<summary>Example</summary>
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span>
<span class="normal"><a href="#__codelineno-0-2">2</a></span>
<span class="normal"><a href="#__codelineno-0-3">3</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="o">&gt;&gt;</span> <span class="kn">from</span> <span class="nn">kotaemon.loaders</span> <span class="kn">import</span> <span class="n">AdobeReader</span>
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a><span class="o">&gt;&gt;</span> <span class="n">reader</span> <span class="o">=</span> <span class="n">AdobeReader</span><span class="p">()</span>
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a><span class="o">&gt;&gt;</span> <span class="n">documents</span> <span class="o">=</span> <span class="n">reader</span><span class="o">.</span><span class="n">load_data</span><span class="p">(</span><span class="s2">"path/to/pdf"</span><span class="p">)</span>
</span></code></pre></div></td></tr></table></div>
</details> <p>Args:
endpoint: URL to the Vision Language Model endpoint. If not provided,
will use the default <code>kotaemon.loaders.adobe_loader.DEFAULT_VLM_ENDPOINT</code></p>
<div class="language-text highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">1</span>
<span class="normal">2</span></pre></div></td><td class="code"><div><pre><span></span><code>max_figures_to_caption: an int decides how many figured will be captioned.
The rest will be ignored (are indexed without captions).
</code></pre></div></td></tr></table></div>
<details class="quote">
<summary>Source code in <code>libs/kotaemon/kotaemon/loaders/adobe_loader.py</code></summary>
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-24"> 24</a></span>
<span class="normal"><a href="#__codelineno-0-25"> 25</a></span>
<span class="normal"><a href="#__codelineno-0-26"> 26</a></span>
<span class="normal"><a href="#__codelineno-0-27"> 27</a></span>
<span class="normal"><a href="#__codelineno-0-28"> 28</a></span>
<span class="normal"><a href="#__codelineno-0-29"> 29</a></span>
<span class="normal"><a href="#__codelineno-0-30"> 30</a></span>
<span class="normal"><a href="#__codelineno-0-31"> 31</a></span>
<span class="normal"><a href="#__codelineno-0-32"> 32</a></span>
<span class="normal"><a href="#__codelineno-0-33"> 33</a></span>
<span class="normal"><a href="#__codelineno-0-34"> 34</a></span>
<span class="normal"><a href="#__codelineno-0-35"> 35</a></span>
<span class="normal"><a href="#__codelineno-0-36"> 36</a></span>
<span class="normal"><a href="#__codelineno-0-37"> 37</a></span>
<span class="normal"><a href="#__codelineno-0-38"> 38</a></span>
<span class="normal"><a href="#__codelineno-0-39"> 39</a></span>
<span class="normal"><a href="#__codelineno-0-40"> 40</a></span>
<span class="normal"><a href="#__codelineno-0-41"> 41</a></span>
<span class="normal"><a href="#__codelineno-0-42"> 42</a></span>
<span class="normal"><a href="#__codelineno-0-43"> 43</a></span>
<span class="normal"><a href="#__codelineno-0-44"> 44</a></span>
<span class="normal"><a href="#__codelineno-0-45"> 45</a></span>
<span class="normal"><a href="#__codelineno-0-46"> 46</a></span>
<span class="normal"><a href="#__codelineno-0-47"> 47</a></span>
<span class="normal"><a href="#__codelineno-0-48"> 48</a></span>
<span class="normal"><a href="#__codelineno-0-49"> 49</a></span>
<span class="normal"><a href="#__codelineno-0-50"> 50</a></span>
<span class="normal"><a href="#__codelineno-0-51"> 51</a></span>
<span class="normal"><a href="#__codelineno-0-52"> 52</a></span>
<span class="normal"><a href="#__codelineno-0-53"> 53</a></span>
<span class="normal"><a href="#__codelineno-0-54"> 54</a></span>
<span class="normal"><a href="#__codelineno-0-55"> 55</a></span>
<span class="normal"><a href="#__codelineno-0-56"> 56</a></span>
<span class="normal"><a href="#__codelineno-0-57"> 57</a></span>
<span class="normal"><a href="#__codelineno-0-58"> 58</a></span>
<span class="normal"><a href="#__codelineno-0-59"> 59</a></span>
<span class="normal"><a href="#__codelineno-0-60"> 60</a></span>
<span class="normal"><a href="#__codelineno-0-61"> 61</a></span>
<span class="normal"><a href="#__codelineno-0-62"> 62</a></span>
<span class="normal"><a href="#__codelineno-0-63"> 63</a></span>
<span class="normal"><a href="#__codelineno-0-64"> 64</a></span>
<span class="normal"><a href="#__codelineno-0-65"> 65</a></span>
<span class="normal"><a href="#__codelineno-0-66"> 66</a></span>
<span class="normal"><a href="#__codelineno-0-67"> 67</a></span>
<span class="normal"><a href="#__codelineno-0-68"> 68</a></span>
<span class="normal"><a href="#__codelineno-0-69"> 69</a></span>
<span class="normal"><a href="#__codelineno-0-70"> 70</a></span>
<span class="normal"><a href="#__codelineno-0-71"> 71</a></span>
<span class="normal"><a href="#__codelineno-0-72"> 72</a></span>
<span class="normal"><a href="#__codelineno-0-73"> 73</a></span>
<span class="normal"><a href="#__codelineno-0-74"> 74</a></span>
<span class="normal"><a href="#__codelineno-0-75"> 75</a></span>
<span class="normal"><a href="#__codelineno-0-76"> 76</a></span>
<span class="normal"><a href="#__codelineno-0-77"> 77</a></span>
<span class="normal"><a href="#__codelineno-0-78"> 78</a></span>
<span class="normal"><a href="#__codelineno-0-79"> 79</a></span>
<span class="normal"><a href="#__codelineno-0-80"> 80</a></span>
<span class="normal"><a href="#__codelineno-0-81"> 81</a></span>
<span class="normal"><a href="#__codelineno-0-82"> 82</a></span>
<span class="normal"><a href="#__codelineno-0-83"> 83</a></span>
<span class="normal"><a href="#__codelineno-0-84"> 84</a></span>
<span class="normal"><a href="#__codelineno-0-85"> 85</a></span>
<span class="normal"><a href="#__codelineno-0-86"> 86</a></span>
<span class="normal"><a href="#__codelineno-0-87"> 87</a></span>
<span class="normal"><a href="#__codelineno-0-88"> 88</a></span>
<span class="normal"><a href="#__codelineno-0-89"> 89</a></span>
<span class="normal"><a href="#__codelineno-0-90"> 90</a></span>
<span class="normal"><a href="#__codelineno-0-91"> 91</a></span>
<span class="normal"><a href="#__codelineno-0-92"> 92</a></span>
<span class="normal"><a href="#__codelineno-0-93"> 93</a></span>
<span class="normal"><a href="#__codelineno-0-94"> 94</a></span>
<span class="normal"><a href="#__codelineno-0-95"> 95</a></span>
<span class="normal"><a href="#__codelineno-0-96"> 96</a></span>
<span class="normal"><a href="#__codelineno-0-97"> 97</a></span>
<span class="normal"><a href="#__codelineno-0-98"> 98</a></span>
<span class="normal"><a href="#__codelineno-0-99"> 99</a></span>
<span class="normal"><a href="#__codelineno-0-100">100</a></span>
<span class="normal"><a href="#__codelineno-0-101">101</a></span>
<span class="normal"><a href="#__codelineno-0-102">102</a></span>
<span class="normal"><a href="#__codelineno-0-103">103</a></span>
<span class="normal"><a href="#__codelineno-0-104">104</a></span>
<span class="normal"><a href="#__codelineno-0-105">105</a></span>
<span class="normal"><a href="#__codelineno-0-106">106</a></span>
<span class="normal"><a href="#__codelineno-0-107">107</a></span>
<span class="normal"><a href="#__codelineno-0-108">108</a></span>
<span class="normal"><a href="#__codelineno-0-109">109</a></span>
<span class="normal"><a href="#__codelineno-0-110">110</a></span>
<span class="normal"><a href="#__codelineno-0-111">111</a></span>
<span class="normal"><a href="#__codelineno-0-112">112</a></span>
<span class="normal"><a href="#__codelineno-0-113">113</a></span>
<span class="normal"><a href="#__codelineno-0-114">114</a></span>
<span class="normal"><a href="#__codelineno-0-115">115</a></span>
<span class="normal"><a href="#__codelineno-0-116">116</a></span>
<span class="normal"><a href="#__codelineno-0-117">117</a></span>
<span class="normal"><a href="#__codelineno-0-118">118</a></span>
<span class="normal"><a href="#__codelineno-0-119">119</a></span>
<span class="normal"><a href="#__codelineno-0-120">120</a></span>
<span class="normal"><a href="#__codelineno-0-121">121</a></span>
<span class="normal"><a href="#__codelineno-0-122">122</a></span>
<span class="normal"><a href="#__codelineno-0-123">123</a></span>
<span class="normal"><a href="#__codelineno-0-124">124</a></span>
<span class="normal"><a href="#__codelineno-0-125">125</a></span>
<span class="normal"><a href="#__codelineno-0-126">126</a></span>
<span class="normal"><a href="#__codelineno-0-127">127</a></span>
<span class="normal"><a href="#__codelineno-0-128">128</a></span>
<span class="normal"><a href="#__codelineno-0-129">129</a></span>
<span class="normal"><a href="#__codelineno-0-130">130</a></span>
<span class="normal"><a href="#__codelineno-0-131">131</a></span>
<span class="normal"><a href="#__codelineno-0-132">132</a></span>
<span class="normal"><a href="#__codelineno-0-133">133</a></span>
<span class="normal"><a href="#__codelineno-0-134">134</a></span>
<span class="normal"><a href="#__codelineno-0-135">135</a></span>
<span class="normal"><a href="#__codelineno-0-136">136</a></span>
<span class="normal"><a href="#__codelineno-0-137">137</a></span>
<span class="normal"><a href="#__codelineno-0-138">138</a></span>
<span class="normal"><a href="#__codelineno-0-139">139</a></span>
<span class="normal"><a href="#__codelineno-0-140">140</a></span>
<span class="normal"><a href="#__codelineno-0-141">141</a></span>
<span class="normal"><a href="#__codelineno-0-142">142</a></span>
<span class="normal"><a href="#__codelineno-0-143">143</a></span>
<span class="normal"><a href="#__codelineno-0-144">144</a></span>
<span class="normal"><a href="#__codelineno-0-145">145</a></span>
<span class="normal"><a href="#__codelineno-0-146">146</a></span>
<span class="normal"><a href="#__codelineno-0-147">147</a></span>
<span class="normal"><a href="#__codelineno-0-148">148</a></span>
<span class="normal"><a href="#__codelineno-0-149">149</a></span>
<span class="normal"><a href="#__codelineno-0-150">150</a></span>
<span class="normal"><a href="#__codelineno-0-151">151</a></span>
<span class="normal"><a href="#__codelineno-0-152">152</a></span>
<span class="normal"><a href="#__codelineno-0-153">153</a></span>
<span class="normal"><a href="#__codelineno-0-154">154</a></span>
<span class="normal"><a href="#__codelineno-0-155">155</a></span>
<span class="normal"><a href="#__codelineno-0-156">156</a></span>
<span class="normal"><a href="#__codelineno-0-157">157</a></span>
<span class="normal"><a href="#__codelineno-0-158">158</a></span>
<span class="normal"><a href="#__codelineno-0-159">159</a></span>
<span class="normal"><a href="#__codelineno-0-160">160</a></span>
<span class="normal"><a href="#__codelineno-0-161">161</a></span>
<span class="normal"><a href="#__codelineno-0-162">162</a></span>
<span class="normal"><a href="#__codelineno-0-163">163</a></span>
<span class="normal"><a href="#__codelineno-0-164">164</a></span>
<span class="normal"><a href="#__codelineno-0-165">165</a></span>
<span class="normal"><a href="#__codelineno-0-166">166</a></span>
<span class="normal"><a href="#__codelineno-0-167">167</a></span>
<span class="normal"><a href="#__codelineno-0-168">168</a></span>
<span class="normal"><a href="#__codelineno-0-169">169</a></span>
<span class="normal"><a href="#__codelineno-0-170">170</a></span>
<span class="normal"><a href="#__codelineno-0-171">171</a></span>
<span class="normal"><a href="#__codelineno-0-172">172</a></span>
<span class="normal"><a href="#__codelineno-0-173">173</a></span>
<span class="normal"><a href="#__codelineno-0-174">174</a></span>
<span class="normal"><a href="#__codelineno-0-175">175</a></span>
<span class="normal"><a href="#__codelineno-0-176">176</a></span>
<span class="normal"><a href="#__codelineno-0-177">177</a></span>
<span class="normal"><a href="#__codelineno-0-178">178</a></span>
<span class="normal"><a href="#__codelineno-0-179">179</a></span>
<span class="normal"><a href="#__codelineno-0-180">180</a></span>
<span class="normal"><a href="#__codelineno-0-181">181</a></span>
<span class="normal"><a href="#__codelineno-0-182">182</a></span>
<span class="normal"><a href="#__codelineno-0-183">183</a></span>
<span class="normal"><a href="#__codelineno-0-184">184</a></span>
<span class="normal"><a href="#__codelineno-0-185">185</a></span>
<span class="normal"><a href="#__codelineno-0-186">186</a></span>
<span class="normal"><a href="#__codelineno-0-187">187</a></span>
<span class="normal"><a href="#__codelineno-0-188">188</a></span>
<span class="normal"><a href="#__codelineno-0-189">189</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-24"><a id="__codelineno-0-24" name="__codelineno-0-24"></a><span class="k">class</span> <span class="nc">AdobeReader</span><span class="p">(</span><span class="n">BaseReader</span><span class="p">):</span>
</span><span id="__span-0-25"><a id="__codelineno-0-25" name="__codelineno-0-25"></a><span class="w"> </span><span class="sd">"""Read PDF using the Adobe's PDF Services.</span>
</span><span id="__span-0-26"><a id="__codelineno-0-26" name="__codelineno-0-26"></a><span class="sd"> Be able to extract text, table, and figure with high accuracy</span>
</span><span id="__span-0-27"><a id="__codelineno-0-27" name="__codelineno-0-27"></a>
</span><span id="__span-0-28"><a id="__codelineno-0-28" name="__codelineno-0-28"></a><span class="sd"> Example:</span>
</span><span id="__span-0-29"><a id="__codelineno-0-29" name="__codelineno-0-29"></a><span class="sd"> ```python</span>
</span><span id="__span-0-30"><a id="__codelineno-0-30" name="__codelineno-0-30"></a><span class="sd"> &gt;&gt; from kotaemon.loaders import AdobeReader</span>
</span><span id="__span-0-31"><a id="__codelineno-0-31" name="__codelineno-0-31"></a><span class="sd"> &gt;&gt; reader = AdobeReader()</span>
</span><span id="__span-0-32"><a id="__codelineno-0-32" name="__codelineno-0-32"></a><span class="sd"> &gt;&gt; documents = reader.load_data("path/to/pdf")</span>
</span><span id="__span-0-33"><a id="__codelineno-0-33" name="__codelineno-0-33"></a><span class="sd"> ```</span>
</span><span id="__span-0-34"><a id="__codelineno-0-34" name="__codelineno-0-34"></a><span class="sd"> Args:</span>
</span><span id="__span-0-35"><a id="__codelineno-0-35" name="__codelineno-0-35"></a><span class="sd"> endpoint: URL to the Vision Language Model endpoint. If not provided,</span>
</span><span id="__span-0-36"><a id="__codelineno-0-36" name="__codelineno-0-36"></a><span class="sd"> will use the default `kotaemon.loaders.adobe_loader.DEFAULT_VLM_ENDPOINT`</span>
</span><span id="__span-0-37"><a id="__codelineno-0-37" name="__codelineno-0-37"></a>
</span><span id="__span-0-38"><a id="__codelineno-0-38" name="__codelineno-0-38"></a><span class="sd"> max_figures_to_caption: an int decides how many figured will be captioned.</span>
</span><span id="__span-0-39"><a id="__codelineno-0-39" name="__codelineno-0-39"></a><span class="sd"> The rest will be ignored (are indexed without captions).</span>
</span><span id="__span-0-40"><a id="__codelineno-0-40" name="__codelineno-0-40"></a><span class="sd"> """</span>
</span><span id="__span-0-41"><a id="__codelineno-0-41" name="__codelineno-0-41"></a>
</span><span id="__span-0-42"><a id="__codelineno-0-42" name="__codelineno-0-42"></a> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
</span><span id="__span-0-43"><a id="__codelineno-0-43" name="__codelineno-0-43"></a> <span class="bp">self</span><span class="p">,</span>
</span><span id="__span-0-44"><a id="__codelineno-0-44" name="__codelineno-0-44"></a> <span class="n">vlm_endpoint</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
</span><span id="__span-0-45"><a id="__codelineno-0-45" name="__codelineno-0-45"></a> <span class="n">max_figures_to_caption</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">100</span><span class="p">,</span>
</span><span id="__span-0-46"><a id="__codelineno-0-46" name="__codelineno-0-46"></a> <span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">Any</span><span class="p">,</span>
</span><span id="__span-0-47"><a id="__codelineno-0-47" name="__codelineno-0-47"></a> <span class="o">**</span><span class="n">kwargs</span><span class="p">:</span> <span class="n">Any</span><span class="p">,</span>
</span><span id="__span-0-48"><a id="__codelineno-0-48" name="__codelineno-0-48"></a> <span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span>
</span><span id="__span-0-49"><a id="__codelineno-0-49" name="__codelineno-0-49"></a><span class="w"> </span><span class="sd">"""Init params"""</span>
</span><span id="__span-0-50"><a id="__codelineno-0-50" name="__codelineno-0-50"></a> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">)</span>
</span><span id="__span-0-51"><a id="__codelineno-0-51" name="__codelineno-0-51"></a> <span class="bp">self</span><span class="o">.</span><span class="n">table_regex</span> <span class="o">=</span> <span class="sa">r</span><span class="s2">"/Table(\[\d+\])?$"</span>
</span><span id="__span-0-52"><a id="__codelineno-0-52" name="__codelineno-0-52"></a> <span class="bp">self</span><span class="o">.</span><span class="n">figure_regex</span> <span class="o">=</span> <span class="sa">r</span><span class="s2">"/Figure(\[\d+\])?$"</span>
</span><span id="__span-0-53"><a id="__codelineno-0-53" name="__codelineno-0-53"></a> <span class="bp">self</span><span class="o">.</span><span class="n">vlm_endpoint</span> <span class="o">=</span> <span class="n">vlm_endpoint</span> <span class="ow">or</span> <span class="n">DEFAULT_VLM_ENDPOINT</span>
</span><span id="__span-0-54"><a id="__codelineno-0-54" name="__codelineno-0-54"></a> <span class="bp">self</span><span class="o">.</span><span class="n">max_figures_to_caption</span> <span class="o">=</span> <span class="n">max_figures_to_caption</span>
</span><span id="__span-0-55"><a id="__codelineno-0-55" name="__codelineno-0-55"></a>
</span><span id="__span-0-56"><a id="__codelineno-0-56" name="__codelineno-0-56"></a> <span class="k">def</span> <span class="nf">load_data</span><span class="p">(</span>
</span><span id="__span-0-57"><a id="__codelineno-0-57" name="__codelineno-0-57"></a> <span class="bp">self</span><span class="p">,</span> <span class="n">file</span><span class="p">:</span> <span class="n">Path</span><span class="p">,</span> <span class="n">extra_info</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Dict</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span>
</span><span id="__span-0-58"><a id="__codelineno-0-58" name="__codelineno-0-58"></a> <span class="p">)</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="n">Document</span><span class="p">]:</span>
</span><span id="__span-0-59"><a id="__codelineno-0-59" name="__codelineno-0-59"></a><span class="w"> </span><span class="sd">"""Load data by calling to the Adobe's API</span>
</span><span id="__span-0-60"><a id="__codelineno-0-60" name="__codelineno-0-60"></a>
</span><span id="__span-0-61"><a id="__codelineno-0-61" name="__codelineno-0-61"></a><span class="sd"> Args:</span>
</span><span id="__span-0-62"><a id="__codelineno-0-62" name="__codelineno-0-62"></a><span class="sd"> file (Path): Path to the PDF file</span>
</span><span id="__span-0-63"><a id="__codelineno-0-63" name="__codelineno-0-63"></a>
</span><span id="__span-0-64"><a id="__codelineno-0-64" name="__codelineno-0-64"></a><span class="sd"> Returns:</span>
</span><span id="__span-0-65"><a id="__codelineno-0-65" name="__codelineno-0-65"></a><span class="sd"> List[Document]: list of documents extracted from the PDF file,</span>
</span><span id="__span-0-66"><a id="__codelineno-0-66" name="__codelineno-0-66"></a><span class="sd"> includes 3 types: text, table, and image</span>
</span><span id="__span-0-67"><a id="__codelineno-0-67" name="__codelineno-0-67"></a>
</span><span id="__span-0-68"><a id="__codelineno-0-68" name="__codelineno-0-68"></a><span class="sd"> """</span>
</span><span id="__span-0-69"><a id="__codelineno-0-69" name="__codelineno-0-69"></a> <span class="kn">from</span> <span class="nn">.utils.adobe</span> <span class="kn">import</span> <span class="p">(</span>
</span><span id="__span-0-70"><a id="__codelineno-0-70" name="__codelineno-0-70"></a> <span class="n">generate_figure_captions</span><span class="p">,</span>
</span><span id="__span-0-71"><a id="__codelineno-0-71" name="__codelineno-0-71"></a> <span class="n">load_json</span><span class="p">,</span>
</span><span id="__span-0-72"><a id="__codelineno-0-72" name="__codelineno-0-72"></a> <span class="n">parse_figure_paths</span><span class="p">,</span>
</span><span id="__span-0-73"><a id="__codelineno-0-73" name="__codelineno-0-73"></a> <span class="n">parse_table_paths</span><span class="p">,</span>
</span><span id="__span-0-74"><a id="__codelineno-0-74" name="__codelineno-0-74"></a> <span class="n">request_adobe_service</span><span class="p">,</span>
</span><span id="__span-0-75"><a id="__codelineno-0-75" name="__codelineno-0-75"></a> <span class="p">)</span>
</span><span id="__span-0-76"><a id="__codelineno-0-76" name="__codelineno-0-76"></a>
</span><span id="__span-0-77"><a id="__codelineno-0-77" name="__codelineno-0-77"></a> <span class="n">filename</span> <span class="o">=</span> <span class="n">file</span><span class="o">.</span><span class="n">name</span>
</span><span id="__span-0-78"><a id="__codelineno-0-78" name="__codelineno-0-78"></a> <span class="n">filepath</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">Path</span><span class="p">(</span><span class="n">file</span><span class="p">)</span><span class="o">.</span><span class="n">resolve</span><span class="p">())</span>
</span><span id="__span-0-79"><a id="__codelineno-0-79" name="__codelineno-0-79"></a> <span class="n">output_path</span> <span class="o">=</span> <span class="n">request_adobe_service</span><span class="p">(</span><span class="n">file_path</span><span class="o">=</span><span class="nb">str</span><span class="p">(</span><span class="n">file</span><span class="p">),</span> <span class="n">output_path</span><span class="o">=</span><span class="s2">""</span><span class="p">)</span>
</span><span id="__span-0-80"><a id="__codelineno-0-80" name="__codelineno-0-80"></a> <span class="n">results_path</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">output_path</span><span class="p">,</span> <span class="s2">"structuredData.json"</span><span class="p">)</span>
</span><span id="__span-0-81"><a id="__codelineno-0-81" name="__codelineno-0-81"></a>
</span><span id="__span-0-82"><a id="__codelineno-0-82" name="__codelineno-0-82"></a> <span class="k">if</span> <span class="ow">not</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">results_path</span><span class="p">):</span>
</span><span id="__span-0-83"><a id="__codelineno-0-83" name="__codelineno-0-83"></a> <span class="n">logger</span><span class="o">.</span><span class="n">exception</span><span class="p">(</span><span class="s2">"Fail to parse the document."</span><span class="p">)</span>
</span><span id="__span-0-84"><a id="__codelineno-0-84" name="__codelineno-0-84"></a> <span class="k">return</span> <span class="p">[]</span>
</span><span id="__span-0-85"><a id="__codelineno-0-85" name="__codelineno-0-85"></a>
</span><span id="__span-0-86"><a id="__codelineno-0-86" name="__codelineno-0-86"></a> <span class="n">data</span> <span class="o">=</span> <span class="n">load_json</span><span class="p">(</span><span class="n">results_path</span><span class="p">)</span>
</span><span id="__span-0-87"><a id="__codelineno-0-87" name="__codelineno-0-87"></a>
</span><span id="__span-0-88"><a id="__codelineno-0-88" name="__codelineno-0-88"></a> <span class="n">texts</span> <span class="o">=</span> <span class="n">defaultdict</span><span class="p">(</span><span class="nb">list</span><span class="p">)</span>
</span><span id="__span-0-89"><a id="__codelineno-0-89" name="__codelineno-0-89"></a> <span class="n">tables</span> <span class="o">=</span> <span class="p">[]</span>
</span><span id="__span-0-90"><a id="__codelineno-0-90" name="__codelineno-0-90"></a> <span class="n">figures</span> <span class="o">=</span> <span class="p">[]</span>
</span><span id="__span-0-91"><a id="__codelineno-0-91" name="__codelineno-0-91"></a>
</span><span id="__span-0-92"><a id="__codelineno-0-92" name="__codelineno-0-92"></a> <span class="n">elements</span> <span class="o">=</span> <span class="n">data</span><span class="p">[</span><span class="s2">"elements"</span><span class="p">]</span>
</span><span id="__span-0-93"><a id="__codelineno-0-93" name="__codelineno-0-93"></a> <span class="k">for</span> <span class="n">item_id</span><span class="p">,</span> <span class="n">item</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">elements</span><span class="p">):</span>
</span><span id="__span-0-94"><a id="__codelineno-0-94" name="__codelineno-0-94"></a> <span class="n">page_number</span> <span class="o">=</span> <span class="n">item</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"Page"</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">)</span> <span class="o">+</span> <span class="mi">1</span>
</span><span id="__span-0-95"><a id="__codelineno-0-95" name="__codelineno-0-95"></a> <span class="n">item_path</span> <span class="o">=</span> <span class="n">item</span><span class="p">[</span><span class="s2">"Path"</span><span class="p">]</span>
</span><span id="__span-0-96"><a id="__codelineno-0-96" name="__codelineno-0-96"></a> <span class="n">item_text</span> <span class="o">=</span> <span class="n">item</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"Text"</span><span class="p">,</span> <span class="s2">""</span><span class="p">)</span>
</span><span id="__span-0-97"><a id="__codelineno-0-97" name="__codelineno-0-97"></a>
</span><span id="__span-0-98"><a id="__codelineno-0-98" name="__codelineno-0-98"></a> <span class="n">file_paths</span> <span class="o">=</span> <span class="p">[</span>
</span><span id="__span-0-99"><a id="__codelineno-0-99" name="__codelineno-0-99"></a> <span class="n">Path</span><span class="p">(</span><span class="n">output_path</span><span class="p">)</span> <span class="o">/</span> <span class="n">path</span> <span class="k">for</span> <span class="n">path</span> <span class="ow">in</span> <span class="n">item</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"filePaths"</span><span class="p">,</span> <span class="p">[])</span>
</span><span id="__span-0-100"><a id="__codelineno-0-100" name="__codelineno-0-100"></a> <span class="p">]</span>
</span><span id="__span-0-101"><a id="__codelineno-0-101" name="__codelineno-0-101"></a> <span class="n">prev_item</span> <span class="o">=</span> <span class="n">elements</span><span class="p">[</span><span class="n">item_id</span> <span class="o">-</span> <span class="mi">1</span><span class="p">]</span>
</span><span id="__span-0-102"><a id="__codelineno-0-102" name="__codelineno-0-102"></a> <span class="n">title</span> <span class="o">=</span> <span class="n">prev_item</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"Text"</span><span class="p">,</span> <span class="s2">""</span><span class="p">)</span>
</span><span id="__span-0-103"><a id="__codelineno-0-103" name="__codelineno-0-103"></a>
</span><span id="__span-0-104"><a id="__codelineno-0-104" name="__codelineno-0-104"></a> <span class="k">if</span> <span class="n">re</span><span class="o">.</span><span class="n">search</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">table_regex</span><span class="p">,</span> <span class="n">item_path</span><span class="p">):</span>
</span><span id="__span-0-105"><a id="__codelineno-0-105" name="__codelineno-0-105"></a> <span class="n">table_content</span> <span class="o">=</span> <span class="n">parse_table_paths</span><span class="p">(</span><span class="n">file_paths</span><span class="p">)</span>
</span><span id="__span-0-106"><a id="__codelineno-0-106" name="__codelineno-0-106"></a> <span class="k">if</span> <span class="ow">not</span> <span class="n">table_content</span><span class="p">:</span>
</span><span id="__span-0-107"><a id="__codelineno-0-107" name="__codelineno-0-107"></a> <span class="k">continue</span>
</span><span id="__span-0-108"><a id="__codelineno-0-108" name="__codelineno-0-108"></a> <span class="n">table_caption</span> <span class="o">=</span> <span class="p">(</span>
</span><span id="__span-0-109"><a id="__codelineno-0-109" name="__codelineno-0-109"></a> <span class="n">table_content</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"|"</span><span class="p">,</span> <span class="s2">""</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"---"</span><span class="p">,</span> <span class="s2">""</span><span class="p">)</span>
</span><span id="__span-0-110"><a id="__codelineno-0-110" name="__codelineno-0-110"></a> <span class="o">+</span> <span class="sa">f</span><span class="s2">"</span><span class="se">\n</span><span class="s2">(Table in Page </span><span class="si">{</span><span class="n">page_number</span><span class="si">}</span><span class="s2">. </span><span class="si">{</span><span class="n">title</span><span class="si">}</span><span class="s2">)"</span>
</span><span id="__span-0-111"><a id="__codelineno-0-111" name="__codelineno-0-111"></a> <span class="p">)</span>
</span><span id="__span-0-112"><a id="__codelineno-0-112" name="__codelineno-0-112"></a> <span class="n">tables</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">page_number</span><span class="p">,</span> <span class="n">table_content</span><span class="p">,</span> <span class="n">table_caption</span><span class="p">))</span>
</span><span id="__span-0-113"><a id="__codelineno-0-113" name="__codelineno-0-113"></a>
</span><span id="__span-0-114"><a id="__codelineno-0-114" name="__codelineno-0-114"></a> <span class="k">elif</span> <span class="n">re</span><span class="o">.</span><span class="n">search</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">figure_regex</span><span class="p">,</span> <span class="n">item_path</span><span class="p">):</span>
</span><span id="__span-0-115"><a id="__codelineno-0-115" name="__codelineno-0-115"></a> <span class="n">figure_caption</span> <span class="o">=</span> <span class="p">(</span>
</span><span id="__span-0-116"><a id="__codelineno-0-116" name="__codelineno-0-116"></a> <span class="n">item_text</span> <span class="o">+</span> <span class="sa">f</span><span class="s2">"</span><span class="se">\n</span><span class="s2">(Figure in Page </span><span class="si">{</span><span class="n">page_number</span><span class="si">}</span><span class="s2">. </span><span class="si">{</span><span class="n">title</span><span class="si">}</span><span class="s2">)"</span>
</span><span id="__span-0-117"><a id="__codelineno-0-117" name="__codelineno-0-117"></a> <span class="p">)</span>
</span><span id="__span-0-118"><a id="__codelineno-0-118" name="__codelineno-0-118"></a> <span class="n">figure_content</span> <span class="o">=</span> <span class="n">parse_figure_paths</span><span class="p">(</span><span class="n">file_paths</span><span class="p">)</span>
</span><span id="__span-0-119"><a id="__codelineno-0-119" name="__codelineno-0-119"></a> <span class="k">if</span> <span class="ow">not</span> <span class="n">figure_content</span><span class="p">:</span>
</span><span id="__span-0-120"><a id="__codelineno-0-120" name="__codelineno-0-120"></a> <span class="k">continue</span>
</span><span id="__span-0-121"><a id="__codelineno-0-121" name="__codelineno-0-121"></a> <span class="n">figures</span><span class="o">.</span><span class="n">append</span><span class="p">([</span><span class="n">page_number</span><span class="p">,</span> <span class="n">figure_content</span><span class="p">,</span> <span class="n">figure_caption</span><span class="p">])</span>
</span><span id="__span-0-122"><a id="__codelineno-0-122" name="__codelineno-0-122"></a>
</span><span id="__span-0-123"><a id="__codelineno-0-123" name="__codelineno-0-123"></a> <span class="k">else</span><span class="p">:</span>
</span><span id="__span-0-124"><a id="__codelineno-0-124" name="__codelineno-0-124"></a> <span class="k">if</span> <span class="n">item_text</span> <span class="ow">and</span> <span class="s2">"Table"</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">item_path</span> <span class="ow">and</span> <span class="s2">"Figure"</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">item_path</span><span class="p">:</span>
</span><span id="__span-0-125"><a id="__codelineno-0-125" name="__codelineno-0-125"></a> <span class="n">texts</span><span class="p">[</span><span class="n">page_number</span><span class="p">]</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">item_text</span><span class="p">)</span>
</span><span id="__span-0-126"><a id="__codelineno-0-126" name="__codelineno-0-126"></a>
</span><span id="__span-0-127"><a id="__codelineno-0-127" name="__codelineno-0-127"></a> <span class="c1"># get figure caption using GPT-4V</span>
</span><span id="__span-0-128"><a id="__codelineno-0-128" name="__codelineno-0-128"></a> <span class="n">figure_captions</span> <span class="o">=</span> <span class="n">generate_figure_captions</span><span class="p">(</span>
</span><span id="__span-0-129"><a id="__codelineno-0-129" name="__codelineno-0-129"></a> <span class="bp">self</span><span class="o">.</span><span class="n">vlm_endpoint</span><span class="p">,</span>
</span><span id="__span-0-130"><a id="__codelineno-0-130" name="__codelineno-0-130"></a> <span class="p">[</span><span class="n">item</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">item</span> <span class="ow">in</span> <span class="n">figures</span><span class="p">],</span>
</span><span id="__span-0-131"><a id="__codelineno-0-131" name="__codelineno-0-131"></a> <span class="bp">self</span><span class="o">.</span><span class="n">max_figures_to_caption</span><span class="p">,</span>
</span><span id="__span-0-132"><a id="__codelineno-0-132" name="__codelineno-0-132"></a> <span class="p">)</span>
</span><span id="__span-0-133"><a id="__codelineno-0-133" name="__codelineno-0-133"></a> <span class="k">for</span> <span class="n">item</span><span class="p">,</span> <span class="n">caption</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">figures</span><span class="p">,</span> <span class="n">figure_captions</span><span class="p">):</span>
</span><span id="__span-0-134"><a id="__codelineno-0-134" name="__codelineno-0-134"></a> <span class="c1"># update figure caption</span>
</span><span id="__span-0-135"><a id="__codelineno-0-135" name="__codelineno-0-135"></a> <span class="n">item</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span> <span class="o">+=</span> <span class="s2">" "</span> <span class="o">+</span> <span class="n">caption</span>
</span><span id="__span-0-136"><a id="__codelineno-0-136" name="__codelineno-0-136"></a>
</span><span id="__span-0-137"><a id="__codelineno-0-137" name="__codelineno-0-137"></a> <span class="c1"># Wrap elements with Document</span>
</span><span id="__span-0-138"><a id="__codelineno-0-138" name="__codelineno-0-138"></a> <span class="n">documents</span> <span class="o">=</span> <span class="p">[]</span>
</span><span id="__span-0-139"><a id="__codelineno-0-139" name="__codelineno-0-139"></a>
</span><span id="__span-0-140"><a id="__codelineno-0-140" name="__codelineno-0-140"></a> <span class="c1"># join plain text elements</span>
</span><span id="__span-0-141"><a id="__codelineno-0-141" name="__codelineno-0-141"></a> <span class="k">for</span> <span class="n">page_number</span><span class="p">,</span> <span class="n">txts</span> <span class="ow">in</span> <span class="n">texts</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
</span><span id="__span-0-142"><a id="__codelineno-0-142" name="__codelineno-0-142"></a> <span class="n">documents</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
</span><span id="__span-0-143"><a id="__codelineno-0-143" name="__codelineno-0-143"></a> <span class="n">Document</span><span class="p">(</span>
</span><span id="__span-0-144"><a id="__codelineno-0-144" name="__codelineno-0-144"></a> <span class="n">text</span><span class="o">=</span><span class="s2">"</span><span class="se">\n</span><span class="s2">"</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">txts</span><span class="p">),</span>
</span><span id="__span-0-145"><a id="__codelineno-0-145" name="__codelineno-0-145"></a> <span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
</span><span id="__span-0-146"><a id="__codelineno-0-146" name="__codelineno-0-146"></a> <span class="s2">"page_label"</span><span class="p">:</span> <span class="n">page_number</span><span class="p">,</span>
</span><span id="__span-0-147"><a id="__codelineno-0-147" name="__codelineno-0-147"></a> <span class="s2">"file_name"</span><span class="p">:</span> <span class="n">filename</span><span class="p">,</span>
</span><span id="__span-0-148"><a id="__codelineno-0-148" name="__codelineno-0-148"></a> <span class="s2">"file_path"</span><span class="p">:</span> <span class="n">filepath</span><span class="p">,</span>
</span><span id="__span-0-149"><a id="__codelineno-0-149" name="__codelineno-0-149"></a> <span class="o">**</span><span class="p">(</span><span class="n">extra_info</span> <span class="k">if</span> <span class="n">extra_info</span> <span class="k">else</span> <span class="p">{}),</span>
</span><span id="__span-0-150"><a id="__codelineno-0-150" name="__codelineno-0-150"></a> <span class="p">},</span>
</span><span id="__span-0-151"><a id="__codelineno-0-151" name="__codelineno-0-151"></a> <span class="p">)</span>
</span><span id="__span-0-152"><a id="__codelineno-0-152" name="__codelineno-0-152"></a> <span class="p">)</span>
</span><span id="__span-0-153"><a id="__codelineno-0-153" name="__codelineno-0-153"></a>
</span><span id="__span-0-154"><a id="__codelineno-0-154" name="__codelineno-0-154"></a> <span class="c1"># table elements</span>
</span><span id="__span-0-155"><a id="__codelineno-0-155" name="__codelineno-0-155"></a> <span class="k">for</span> <span class="n">page_number</span><span class="p">,</span> <span class="n">table_content</span><span class="p">,</span> <span class="n">table_caption</span> <span class="ow">in</span> <span class="n">tables</span><span class="p">:</span>
</span><span id="__span-0-156"><a id="__codelineno-0-156" name="__codelineno-0-156"></a> <span class="n">documents</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
</span><span id="__span-0-157"><a id="__codelineno-0-157" name="__codelineno-0-157"></a> <span class="n">Document</span><span class="p">(</span>
</span><span id="__span-0-158"><a id="__codelineno-0-158" name="__codelineno-0-158"></a> <span class="n">text</span><span class="o">=</span><span class="n">table_content</span><span class="p">,</span>
</span><span id="__span-0-159"><a id="__codelineno-0-159" name="__codelineno-0-159"></a> <span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
</span><span id="__span-0-160"><a id="__codelineno-0-160" name="__codelineno-0-160"></a> <span class="s2">"table_origin"</span><span class="p">:</span> <span class="n">table_content</span><span class="p">,</span>
</span><span id="__span-0-161"><a id="__codelineno-0-161" name="__codelineno-0-161"></a> <span class="s2">"type"</span><span class="p">:</span> <span class="s2">"table"</span><span class="p">,</span>
</span><span id="__span-0-162"><a id="__codelineno-0-162" name="__codelineno-0-162"></a> <span class="s2">"page_label"</span><span class="p">:</span> <span class="n">page_number</span><span class="p">,</span>
</span><span id="__span-0-163"><a id="__codelineno-0-163" name="__codelineno-0-163"></a> <span class="s2">"file_name"</span><span class="p">:</span> <span class="n">filename</span><span class="p">,</span>
</span><span id="__span-0-164"><a id="__codelineno-0-164" name="__codelineno-0-164"></a> <span class="s2">"file_path"</span><span class="p">:</span> <span class="n">filepath</span><span class="p">,</span>
</span><span id="__span-0-165"><a id="__codelineno-0-165" name="__codelineno-0-165"></a> <span class="o">**</span><span class="p">(</span><span class="n">extra_info</span> <span class="k">if</span> <span class="n">extra_info</span> <span class="k">else</span> <span class="p">{}),</span>
</span><span id="__span-0-166"><a id="__codelineno-0-166" name="__codelineno-0-166"></a> <span class="p">},</span>
</span><span id="__span-0-167"><a id="__codelineno-0-167" name="__codelineno-0-167"></a> <span class="n">metadata_template</span><span class="o">=</span><span class="s2">""</span><span class="p">,</span>
</span><span id="__span-0-168"><a id="__codelineno-0-168" name="__codelineno-0-168"></a> <span class="n">metadata_seperator</span><span class="o">=</span><span class="s2">""</span><span class="p">,</span>
</span><span id="__span-0-169"><a id="__codelineno-0-169" name="__codelineno-0-169"></a> <span class="p">)</span>
</span><span id="__span-0-170"><a id="__codelineno-0-170" name="__codelineno-0-170"></a> <span class="p">)</span>
</span><span id="__span-0-171"><a id="__codelineno-0-171" name="__codelineno-0-171"></a>
</span><span id="__span-0-172"><a id="__codelineno-0-172" name="__codelineno-0-172"></a> <span class="c1"># figure elements</span>
</span><span id="__span-0-173"><a id="__codelineno-0-173" name="__codelineno-0-173"></a> <span class="k">for</span> <span class="n">page_number</span><span class="p">,</span> <span class="n">figure_content</span><span class="p">,</span> <span class="n">figure_caption</span> <span class="ow">in</span> <span class="n">figures</span><span class="p">:</span>
</span><span id="__span-0-174"><a id="__codelineno-0-174" name="__codelineno-0-174"></a> <span class="n">documents</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
</span><span id="__span-0-175"><a id="__codelineno-0-175" name="__codelineno-0-175"></a> <span class="n">Document</span><span class="p">(</span>
</span><span id="__span-0-176"><a id="__codelineno-0-176" name="__codelineno-0-176"></a> <span class="n">text</span><span class="o">=</span><span class="n">figure_caption</span><span class="p">,</span>
</span><span id="__span-0-177"><a id="__codelineno-0-177" name="__codelineno-0-177"></a> <span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
</span><span id="__span-0-178"><a id="__codelineno-0-178" name="__codelineno-0-178"></a> <span class="s2">"image_origin"</span><span class="p">:</span> <span class="n">figure_content</span><span class="p">,</span>
</span><span id="__span-0-179"><a id="__codelineno-0-179" name="__codelineno-0-179"></a> <span class="s2">"type"</span><span class="p">:</span> <span class="s2">"image"</span><span class="p">,</span>
</span><span id="__span-0-180"><a id="__codelineno-0-180" name="__codelineno-0-180"></a> <span class="s2">"page_label"</span><span class="p">:</span> <span class="n">page_number</span><span class="p">,</span>
</span><span id="__span-0-181"><a id="__codelineno-0-181" name="__codelineno-0-181"></a> <span class="s2">"file_name"</span><span class="p">:</span> <span class="n">filename</span><span class="p">,</span>
</span><span id="__span-0-182"><a id="__codelineno-0-182" name="__codelineno-0-182"></a> <span class="s2">"file_path"</span><span class="p">:</span> <span class="n">filepath</span><span class="p">,</span>
</span><span id="__span-0-183"><a id="__codelineno-0-183" name="__codelineno-0-183"></a> <span class="o">**</span><span class="p">(</span><span class="n">extra_info</span> <span class="k">if</span> <span class="n">extra_info</span> <span class="k">else</span> <span class="p">{}),</span>
</span><span id="__span-0-184"><a id="__codelineno-0-184" name="__codelineno-0-184"></a> <span class="p">},</span>
</span><span id="__span-0-185"><a id="__codelineno-0-185" name="__codelineno-0-185"></a> <span class="n">metadata_template</span><span class="o">=</span><span class="s2">""</span><span class="p">,</span>
</span><span id="__span-0-186"><a id="__codelineno-0-186" name="__codelineno-0-186"></a> <span class="n">metadata_seperator</span><span class="o">=</span><span class="s2">""</span><span class="p">,</span>
</span><span id="__span-0-187"><a id="__codelineno-0-187" name="__codelineno-0-187"></a> <span class="p">)</span>
</span><span id="__span-0-188"><a id="__codelineno-0-188" name="__codelineno-0-188"></a> <span class="p">)</span>
</span><span id="__span-0-189"><a id="__codelineno-0-189" name="__codelineno-0-189"></a> <span class="k">return</span> <span class="n">documents</span>
</span></code></pre></div></td></tr></table></div>
</details>
<div class="doc doc-children">
<div class="doc doc-object doc-function">
<h3 id="loaders.adobe_loader.AdobeReader.load_data" class="doc doc-heading">
<span class="doc doc-object-name doc-function-name">load_data</span>
<a href="#loaders.adobe_loader.AdobeReader.load_data" class="headerlink" title="Permanent link"></a></h3>
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">load_data</span><span class="p">(</span><span class="n">file</span><span class="p">,</span> <span class="n">extra_info</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Load data by calling to the Adobe's API</p>
<p><span class="doc-section-title">Parameters:</span></p>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td>
<code>file</code>
</td>
<td>
<code>Path</code>
</td>
<td>
<div class="doc-md-description">
<p>Path to the PDF file</p>
</div>
</td>
<td>
<em>required</em>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Returns:</span></p>
<table>
<thead>
<tr>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td>
<code>List[Document]</code>
</td>
<td>
<div class="doc-md-description">
<p>List[Document]: list of documents extracted from the PDF file,
includes 3 types: text, table, and image</p>
</div>
</td>
</tr>
</tbody>
</table>
<details class="quote">
<summary>Source code in <code>libs/kotaemon/kotaemon/loaders/adobe_loader.py</code></summary>
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-56"> 56</a></span>
<span class="normal"><a href="#__codelineno-0-57"> 57</a></span>
<span class="normal"><a href="#__codelineno-0-58"> 58</a></span>
<span class="normal"><a href="#__codelineno-0-59"> 59</a></span>
<span class="normal"><a href="#__codelineno-0-60"> 60</a></span>
<span class="normal"><a href="#__codelineno-0-61"> 61</a></span>
<span class="normal"><a href="#__codelineno-0-62"> 62</a></span>
<span class="normal"><a href="#__codelineno-0-63"> 63</a></span>
<span class="normal"><a href="#__codelineno-0-64"> 64</a></span>
<span class="normal"><a href="#__codelineno-0-65"> 65</a></span>
<span class="normal"><a href="#__codelineno-0-66"> 66</a></span>
<span class="normal"><a href="#__codelineno-0-67"> 67</a></span>
<span class="normal"><a href="#__codelineno-0-68"> 68</a></span>
<span class="normal"><a href="#__codelineno-0-69"> 69</a></span>
<span class="normal"><a href="#__codelineno-0-70"> 70</a></span>
<span class="normal"><a href="#__codelineno-0-71"> 71</a></span>
<span class="normal"><a href="#__codelineno-0-72"> 72</a></span>
<span class="normal"><a href="#__codelineno-0-73"> 73</a></span>
<span class="normal"><a href="#__codelineno-0-74"> 74</a></span>
<span class="normal"><a href="#__codelineno-0-75"> 75</a></span>
<span class="normal"><a href="#__codelineno-0-76"> 76</a></span>
<span class="normal"><a href="#__codelineno-0-77"> 77</a></span>
<span class="normal"><a href="#__codelineno-0-78"> 78</a></span>
<span class="normal"><a href="#__codelineno-0-79"> 79</a></span>
<span class="normal"><a href="#__codelineno-0-80"> 80</a></span>
<span class="normal"><a href="#__codelineno-0-81"> 81</a></span>
<span class="normal"><a href="#__codelineno-0-82"> 82</a></span>
<span class="normal"><a href="#__codelineno-0-83"> 83</a></span>
<span class="normal"><a href="#__codelineno-0-84"> 84</a></span>
<span class="normal"><a href="#__codelineno-0-85"> 85</a></span>
<span class="normal"><a href="#__codelineno-0-86"> 86</a></span>
<span class="normal"><a href="#__codelineno-0-87"> 87</a></span>
<span class="normal"><a href="#__codelineno-0-88"> 88</a></span>
<span class="normal"><a href="#__codelineno-0-89"> 89</a></span>
<span class="normal"><a href="#__codelineno-0-90"> 90</a></span>
<span class="normal"><a href="#__codelineno-0-91"> 91</a></span>
<span class="normal"><a href="#__codelineno-0-92"> 92</a></span>
<span class="normal"><a href="#__codelineno-0-93"> 93</a></span>
<span class="normal"><a href="#__codelineno-0-94"> 94</a></span>
<span class="normal"><a href="#__codelineno-0-95"> 95</a></span>
<span class="normal"><a href="#__codelineno-0-96"> 96</a></span>
<span class="normal"><a href="#__codelineno-0-97"> 97</a></span>
<span class="normal"><a href="#__codelineno-0-98"> 98</a></span>
<span class="normal"><a href="#__codelineno-0-99"> 99</a></span>
<span class="normal"><a href="#__codelineno-0-100">100</a></span>
<span class="normal"><a href="#__codelineno-0-101">101</a></span>
<span class="normal"><a href="#__codelineno-0-102">102</a></span>
<span class="normal"><a href="#__codelineno-0-103">103</a></span>
<span class="normal"><a href="#__codelineno-0-104">104</a></span>
<span class="normal"><a href="#__codelineno-0-105">105</a></span>
<span class="normal"><a href="#__codelineno-0-106">106</a></span>
<span class="normal"><a href="#__codelineno-0-107">107</a></span>
<span class="normal"><a href="#__codelineno-0-108">108</a></span>
<span class="normal"><a href="#__codelineno-0-109">109</a></span>
<span class="normal"><a href="#__codelineno-0-110">110</a></span>
<span class="normal"><a href="#__codelineno-0-111">111</a></span>
<span class="normal"><a href="#__codelineno-0-112">112</a></span>
<span class="normal"><a href="#__codelineno-0-113">113</a></span>
<span class="normal"><a href="#__codelineno-0-114">114</a></span>
<span class="normal"><a href="#__codelineno-0-115">115</a></span>
<span class="normal"><a href="#__codelineno-0-116">116</a></span>
<span class="normal"><a href="#__codelineno-0-117">117</a></span>
<span class="normal"><a href="#__codelineno-0-118">118</a></span>
<span class="normal"><a href="#__codelineno-0-119">119</a></span>
<span class="normal"><a href="#__codelineno-0-120">120</a></span>
<span class="normal"><a href="#__codelineno-0-121">121</a></span>
<span class="normal"><a href="#__codelineno-0-122">122</a></span>
<span class="normal"><a href="#__codelineno-0-123">123</a></span>
<span class="normal"><a href="#__codelineno-0-124">124</a></span>
<span class="normal"><a href="#__codelineno-0-125">125</a></span>
<span class="normal"><a href="#__codelineno-0-126">126</a></span>
<span class="normal"><a href="#__codelineno-0-127">127</a></span>
<span class="normal"><a href="#__codelineno-0-128">128</a></span>
<span class="normal"><a href="#__codelineno-0-129">129</a></span>
<span class="normal"><a href="#__codelineno-0-130">130</a></span>
<span class="normal"><a href="#__codelineno-0-131">131</a></span>
<span class="normal"><a href="#__codelineno-0-132">132</a></span>
<span class="normal"><a href="#__codelineno-0-133">133</a></span>
<span class="normal"><a href="#__codelineno-0-134">134</a></span>
<span class="normal"><a href="#__codelineno-0-135">135</a></span>
<span class="normal"><a href="#__codelineno-0-136">136</a></span>
<span class="normal"><a href="#__codelineno-0-137">137</a></span>
<span class="normal"><a href="#__codelineno-0-138">138</a></span>
<span class="normal"><a href="#__codelineno-0-139">139</a></span>
<span class="normal"><a href="#__codelineno-0-140">140</a></span>
<span class="normal"><a href="#__codelineno-0-141">141</a></span>
<span class="normal"><a href="#__codelineno-0-142">142</a></span>
<span class="normal"><a href="#__codelineno-0-143">143</a></span>
<span class="normal"><a href="#__codelineno-0-144">144</a></span>
<span class="normal"><a href="#__codelineno-0-145">145</a></span>
<span class="normal"><a href="#__codelineno-0-146">146</a></span>
<span class="normal"><a href="#__codelineno-0-147">147</a></span>
<span class="normal"><a href="#__codelineno-0-148">148</a></span>
<span class="normal"><a href="#__codelineno-0-149">149</a></span>
<span class="normal"><a href="#__codelineno-0-150">150</a></span>
<span class="normal"><a href="#__codelineno-0-151">151</a></span>
<span class="normal"><a href="#__codelineno-0-152">152</a></span>
<span class="normal"><a href="#__codelineno-0-153">153</a></span>
<span class="normal"><a href="#__codelineno-0-154">154</a></span>
<span class="normal"><a href="#__codelineno-0-155">155</a></span>
<span class="normal"><a href="#__codelineno-0-156">156</a></span>
<span class="normal"><a href="#__codelineno-0-157">157</a></span>
<span class="normal"><a href="#__codelineno-0-158">158</a></span>
<span class="normal"><a href="#__codelineno-0-159">159</a></span>
<span class="normal"><a href="#__codelineno-0-160">160</a></span>
<span class="normal"><a href="#__codelineno-0-161">161</a></span>
<span class="normal"><a href="#__codelineno-0-162">162</a></span>
<span class="normal"><a href="#__codelineno-0-163">163</a></span>
<span class="normal"><a href="#__codelineno-0-164">164</a></span>
<span class="normal"><a href="#__codelineno-0-165">165</a></span>
<span class="normal"><a href="#__codelineno-0-166">166</a></span>
<span class="normal"><a href="#__codelineno-0-167">167</a></span>
<span class="normal"><a href="#__codelineno-0-168">168</a></span>
<span class="normal"><a href="#__codelineno-0-169">169</a></span>
<span class="normal"><a href="#__codelineno-0-170">170</a></span>
<span class="normal"><a href="#__codelineno-0-171">171</a></span>
<span class="normal"><a href="#__codelineno-0-172">172</a></span>
<span class="normal"><a href="#__codelineno-0-173">173</a></span>
<span class="normal"><a href="#__codelineno-0-174">174</a></span>
<span class="normal"><a href="#__codelineno-0-175">175</a></span>
<span class="normal"><a href="#__codelineno-0-176">176</a></span>
<span class="normal"><a href="#__codelineno-0-177">177</a></span>
<span class="normal"><a href="#__codelineno-0-178">178</a></span>
<span class="normal"><a href="#__codelineno-0-179">179</a></span>
<span class="normal"><a href="#__codelineno-0-180">180</a></span>
<span class="normal"><a href="#__codelineno-0-181">181</a></span>
<span class="normal"><a href="#__codelineno-0-182">182</a></span>
<span class="normal"><a href="#__codelineno-0-183">183</a></span>
<span class="normal"><a href="#__codelineno-0-184">184</a></span>
<span class="normal"><a href="#__codelineno-0-185">185</a></span>
<span class="normal"><a href="#__codelineno-0-186">186</a></span>
<span class="normal"><a href="#__codelineno-0-187">187</a></span>
<span class="normal"><a href="#__codelineno-0-188">188</a></span>
<span class="normal"><a href="#__codelineno-0-189">189</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-56"><a id="__codelineno-0-56" name="__codelineno-0-56"></a><span class="k">def</span> <span class="nf">load_data</span><span class="p">(</span>
</span><span id="__span-0-57"><a id="__codelineno-0-57" name="__codelineno-0-57"></a> <span class="bp">self</span><span class="p">,</span> <span class="n">file</span><span class="p">:</span> <span class="n">Path</span><span class="p">,</span> <span class="n">extra_info</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Dict</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span>
</span><span id="__span-0-58"><a id="__codelineno-0-58" name="__codelineno-0-58"></a><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="n">Document</span><span class="p">]:</span>
</span><span id="__span-0-59"><a id="__codelineno-0-59" name="__codelineno-0-59"></a><span class="w"> </span><span class="sd">"""Load data by calling to the Adobe's API</span>
</span><span id="__span-0-60"><a id="__codelineno-0-60" name="__codelineno-0-60"></a>
</span><span id="__span-0-61"><a id="__codelineno-0-61" name="__codelineno-0-61"></a><span class="sd"> Args:</span>
</span><span id="__span-0-62"><a id="__codelineno-0-62" name="__codelineno-0-62"></a><span class="sd"> file (Path): Path to the PDF file</span>
</span><span id="__span-0-63"><a id="__codelineno-0-63" name="__codelineno-0-63"></a>
</span><span id="__span-0-64"><a id="__codelineno-0-64" name="__codelineno-0-64"></a><span class="sd"> Returns:</span>
</span><span id="__span-0-65"><a id="__codelineno-0-65" name="__codelineno-0-65"></a><span class="sd"> List[Document]: list of documents extracted from the PDF file,</span>
</span><span id="__span-0-66"><a id="__codelineno-0-66" name="__codelineno-0-66"></a><span class="sd"> includes 3 types: text, table, and image</span>
</span><span id="__span-0-67"><a id="__codelineno-0-67" name="__codelineno-0-67"></a>
</span><span id="__span-0-68"><a id="__codelineno-0-68" name="__codelineno-0-68"></a><span class="sd"> """</span>
</span><span id="__span-0-69"><a id="__codelineno-0-69" name="__codelineno-0-69"></a> <span class="kn">from</span> <span class="nn">.utils.adobe</span> <span class="kn">import</span> <span class="p">(</span>
</span><span id="__span-0-70"><a id="__codelineno-0-70" name="__codelineno-0-70"></a> <span class="n">generate_figure_captions</span><span class="p">,</span>
</span><span id="__span-0-71"><a id="__codelineno-0-71" name="__codelineno-0-71"></a> <span class="n">load_json</span><span class="p">,</span>
</span><span id="__span-0-72"><a id="__codelineno-0-72" name="__codelineno-0-72"></a> <span class="n">parse_figure_paths</span><span class="p">,</span>
</span><span id="__span-0-73"><a id="__codelineno-0-73" name="__codelineno-0-73"></a> <span class="n">parse_table_paths</span><span class="p">,</span>
</span><span id="__span-0-74"><a id="__codelineno-0-74" name="__codelineno-0-74"></a> <span class="n">request_adobe_service</span><span class="p">,</span>
</span><span id="__span-0-75"><a id="__codelineno-0-75" name="__codelineno-0-75"></a> <span class="p">)</span>
</span><span id="__span-0-76"><a id="__codelineno-0-76" name="__codelineno-0-76"></a>
</span><span id="__span-0-77"><a id="__codelineno-0-77" name="__codelineno-0-77"></a> <span class="n">filename</span> <span class="o">=</span> <span class="n">file</span><span class="o">.</span><span class="n">name</span>
</span><span id="__span-0-78"><a id="__codelineno-0-78" name="__codelineno-0-78"></a> <span class="n">filepath</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">Path</span><span class="p">(</span><span class="n">file</span><span class="p">)</span><span class="o">.</span><span class="n">resolve</span><span class="p">())</span>
</span><span id="__span-0-79"><a id="__codelineno-0-79" name="__codelineno-0-79"></a> <span class="n">output_path</span> <span class="o">=</span> <span class="n">request_adobe_service</span><span class="p">(</span><span class="n">file_path</span><span class="o">=</span><span class="nb">str</span><span class="p">(</span><span class="n">file</span><span class="p">),</span> <span class="n">output_path</span><span class="o">=</span><span class="s2">""</span><span class="p">)</span>
</span><span id="__span-0-80"><a id="__codelineno-0-80" name="__codelineno-0-80"></a> <span class="n">results_path</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">output_path</span><span class="p">,</span> <span class="s2">"structuredData.json"</span><span class="p">)</span>
</span><span id="__span-0-81"><a id="__codelineno-0-81" name="__codelineno-0-81"></a>
</span><span id="__span-0-82"><a id="__codelineno-0-82" name="__codelineno-0-82"></a> <span class="k">if</span> <span class="ow">not</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">results_path</span><span class="p">):</span>
</span><span id="__span-0-83"><a id="__codelineno-0-83" name="__codelineno-0-83"></a> <span class="n">logger</span><span class="o">.</span><span class="n">exception</span><span class="p">(</span><span class="s2">"Fail to parse the document."</span><span class="p">)</span>
</span><span id="__span-0-84"><a id="__codelineno-0-84" name="__codelineno-0-84"></a> <span class="k">return</span> <span class="p">[]</span>
</span><span id="__span-0-85"><a id="__codelineno-0-85" name="__codelineno-0-85"></a>
</span><span id="__span-0-86"><a id="__codelineno-0-86" name="__codelineno-0-86"></a> <span class="n">data</span> <span class="o">=</span> <span class="n">load_json</span><span class="p">(</span><span class="n">results_path</span><span class="p">)</span>
</span><span id="__span-0-87"><a id="__codelineno-0-87" name="__codelineno-0-87"></a>
</span><span id="__span-0-88"><a id="__codelineno-0-88" name="__codelineno-0-88"></a> <span class="n">texts</span> <span class="o">=</span> <span class="n">defaultdict</span><span class="p">(</span><span class="nb">list</span><span class="p">)</span>
</span><span id="__span-0-89"><a id="__codelineno-0-89" name="__codelineno-0-89"></a> <span class="n">tables</span> <span class="o">=</span> <span class="p">[]</span>
</span><span id="__span-0-90"><a id="__codelineno-0-90" name="__codelineno-0-90"></a> <span class="n">figures</span> <span class="o">=</span> <span class="p">[]</span>
</span><span id="__span-0-91"><a id="__codelineno-0-91" name="__codelineno-0-91"></a>
</span><span id="__span-0-92"><a id="__codelineno-0-92" name="__codelineno-0-92"></a> <span class="n">elements</span> <span class="o">=</span> <span class="n">data</span><span class="p">[</span><span class="s2">"elements"</span><span class="p">]</span>
</span><span id="__span-0-93"><a id="__codelineno-0-93" name="__codelineno-0-93"></a> <span class="k">for</span> <span class="n">item_id</span><span class="p">,</span> <span class="n">item</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">elements</span><span class="p">):</span>
</span><span id="__span-0-94"><a id="__codelineno-0-94" name="__codelineno-0-94"></a> <span class="n">page_number</span> <span class="o">=</span> <span class="n">item</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"Page"</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">)</span> <span class="o">+</span> <span class="mi">1</span>
</span><span id="__span-0-95"><a id="__codelineno-0-95" name="__codelineno-0-95"></a> <span class="n">item_path</span> <span class="o">=</span> <span class="n">item</span><span class="p">[</span><span class="s2">"Path"</span><span class="p">]</span>
</span><span id="__span-0-96"><a id="__codelineno-0-96" name="__codelineno-0-96"></a> <span class="n">item_text</span> <span class="o">=</span> <span class="n">item</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"Text"</span><span class="p">,</span> <span class="s2">""</span><span class="p">)</span>
</span><span id="__span-0-97"><a id="__codelineno-0-97" name="__codelineno-0-97"></a>
</span><span id="__span-0-98"><a id="__codelineno-0-98" name="__codelineno-0-98"></a> <span class="n">file_paths</span> <span class="o">=</span> <span class="p">[</span>
</span><span id="__span-0-99"><a id="__codelineno-0-99" name="__codelineno-0-99"></a> <span class="n">Path</span><span class="p">(</span><span class="n">output_path</span><span class="p">)</span> <span class="o">/</span> <span class="n">path</span> <span class="k">for</span> <span class="n">path</span> <span class="ow">in</span> <span class="n">item</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"filePaths"</span><span class="p">,</span> <span class="p">[])</span>
</span><span id="__span-0-100"><a id="__codelineno-0-100" name="__codelineno-0-100"></a> <span class="p">]</span>
</span><span id="__span-0-101"><a id="__codelineno-0-101" name="__codelineno-0-101"></a> <span class="n">prev_item</span> <span class="o">=</span> <span class="n">elements</span><span class="p">[</span><span class="n">item_id</span> <span class="o">-</span> <span class="mi">1</span><span class="p">]</span>
</span><span id="__span-0-102"><a id="__codelineno-0-102" name="__codelineno-0-102"></a> <span class="n">title</span> <span class="o">=</span> <span class="n">prev_item</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"Text"</span><span class="p">,</span> <span class="s2">""</span><span class="p">)</span>
</span><span id="__span-0-103"><a id="__codelineno-0-103" name="__codelineno-0-103"></a>
</span><span id="__span-0-104"><a id="__codelineno-0-104" name="__codelineno-0-104"></a> <span class="k">if</span> <span class="n">re</span><span class="o">.</span><span class="n">search</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">table_regex</span><span class="p">,</span> <span class="n">item_path</span><span class="p">):</span>
</span><span id="__span-0-105"><a id="__codelineno-0-105" name="__codelineno-0-105"></a> <span class="n">table_content</span> <span class="o">=</span> <span class="n">parse_table_paths</span><span class="p">(</span><span class="n">file_paths</span><span class="p">)</span>
</span><span id="__span-0-106"><a id="__codelineno-0-106" name="__codelineno-0-106"></a> <span class="k">if</span> <span class="ow">not</span> <span class="n">table_content</span><span class="p">:</span>
</span><span id="__span-0-107"><a id="__codelineno-0-107" name="__codelineno-0-107"></a> <span class="k">continue</span>
</span><span id="__span-0-108"><a id="__codelineno-0-108" name="__codelineno-0-108"></a> <span class="n">table_caption</span> <span class="o">=</span> <span class="p">(</span>
</span><span id="__span-0-109"><a id="__codelineno-0-109" name="__codelineno-0-109"></a> <span class="n">table_content</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"|"</span><span class="p">,</span> <span class="s2">""</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"---"</span><span class="p">,</span> <span class="s2">""</span><span class="p">)</span>
</span><span id="__span-0-110"><a id="__codelineno-0-110" name="__codelineno-0-110"></a> <span class="o">+</span> <span class="sa">f</span><span class="s2">"</span><span class="se">\n</span><span class="s2">(Table in Page </span><span class="si">{</span><span class="n">page_number</span><span class="si">}</span><span class="s2">. </span><span class="si">{</span><span class="n">title</span><span class="si">}</span><span class="s2">)"</span>
</span><span id="__span-0-111"><a id="__codelineno-0-111" name="__codelineno-0-111"></a> <span class="p">)</span>
</span><span id="__span-0-112"><a id="__codelineno-0-112" name="__codelineno-0-112"></a> <span class="n">tables</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">page_number</span><span class="p">,</span> <span class="n">table_content</span><span class="p">,</span> <span class="n">table_caption</span><span class="p">))</span>
</span><span id="__span-0-113"><a id="__codelineno-0-113" name="__codelineno-0-113"></a>
</span><span id="__span-0-114"><a id="__codelineno-0-114" name="__codelineno-0-114"></a> <span class="k">elif</span> <span class="n">re</span><span class="o">.</span><span class="n">search</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">figure_regex</span><span class="p">,</span> <span class="n">item_path</span><span class="p">):</span>
</span><span id="__span-0-115"><a id="__codelineno-0-115" name="__codelineno-0-115"></a> <span class="n">figure_caption</span> <span class="o">=</span> <span class="p">(</span>
</span><span id="__span-0-116"><a id="__codelineno-0-116" name="__codelineno-0-116"></a> <span class="n">item_text</span> <span class="o">+</span> <span class="sa">f</span><span class="s2">"</span><span class="se">\n</span><span class="s2">(Figure in Page </span><span class="si">{</span><span class="n">page_number</span><span class="si">}</span><span class="s2">. </span><span class="si">{</span><span class="n">title</span><span class="si">}</span><span class="s2">)"</span>
</span><span id="__span-0-117"><a id="__codelineno-0-117" name="__codelineno-0-117"></a> <span class="p">)</span>
</span><span id="__span-0-118"><a id="__codelineno-0-118" name="__codelineno-0-118"></a> <span class="n">figure_content</span> <span class="o">=</span> <span class="n">parse_figure_paths</span><span class="p">(</span><span class="n">file_paths</span><span class="p">)</span>
</span><span id="__span-0-119"><a id="__codelineno-0-119" name="__codelineno-0-119"></a> <span class="k">if</span> <span class="ow">not</span> <span class="n">figure_content</span><span class="p">:</span>
</span><span id="__span-0-120"><a id="__codelineno-0-120" name="__codelineno-0-120"></a> <span class="k">continue</span>
</span><span id="__span-0-121"><a id="__codelineno-0-121" name="__codelineno-0-121"></a> <span class="n">figures</span><span class="o">.</span><span class="n">append</span><span class="p">([</span><span class="n">page_number</span><span class="p">,</span> <span class="n">figure_content</span><span class="p">,</span> <span class="n">figure_caption</span><span class="p">])</span>
</span><span id="__span-0-122"><a id="__codelineno-0-122" name="__codelineno-0-122"></a>
</span><span id="__span-0-123"><a id="__codelineno-0-123" name="__codelineno-0-123"></a> <span class="k">else</span><span class="p">:</span>
</span><span id="__span-0-124"><a id="__codelineno-0-124" name="__codelineno-0-124"></a> <span class="k">if</span> <span class="n">item_text</span> <span class="ow">and</span> <span class="s2">"Table"</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">item_path</span> <span class="ow">and</span> <span class="s2">"Figure"</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">item_path</span><span class="p">:</span>
</span><span id="__span-0-125"><a id="__codelineno-0-125" name="__codelineno-0-125"></a> <span class="n">texts</span><span class="p">[</span><span class="n">page_number</span><span class="p">]</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">item_text</span><span class="p">)</span>
</span><span id="__span-0-126"><a id="__codelineno-0-126" name="__codelineno-0-126"></a>
</span><span id="__span-0-127"><a id="__codelineno-0-127" name="__codelineno-0-127"></a> <span class="c1"># get figure caption using GPT-4V</span>
</span><span id="__span-0-128"><a id="__codelineno-0-128" name="__codelineno-0-128"></a> <span class="n">figure_captions</span> <span class="o">=</span> <span class="n">generate_figure_captions</span><span class="p">(</span>
</span><span id="__span-0-129"><a id="__codelineno-0-129" name="__codelineno-0-129"></a> <span class="bp">self</span><span class="o">.</span><span class="n">vlm_endpoint</span><span class="p">,</span>
</span><span id="__span-0-130"><a id="__codelineno-0-130" name="__codelineno-0-130"></a> <span class="p">[</span><span class="n">item</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">item</span> <span class="ow">in</span> <span class="n">figures</span><span class="p">],</span>
</span><span id="__span-0-131"><a id="__codelineno-0-131" name="__codelineno-0-131"></a> <span class="bp">self</span><span class="o">.</span><span class="n">max_figures_to_caption</span><span class="p">,</span>
</span><span id="__span-0-132"><a id="__codelineno-0-132" name="__codelineno-0-132"></a> <span class="p">)</span>
</span><span id="__span-0-133"><a id="__codelineno-0-133" name="__codelineno-0-133"></a> <span class="k">for</span> <span class="n">item</span><span class="p">,</span> <span class="n">caption</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">figures</span><span class="p">,</span> <span class="n">figure_captions</span><span class="p">):</span>
</span><span id="__span-0-134"><a id="__codelineno-0-134" name="__codelineno-0-134"></a> <span class="c1"># update figure caption</span>
</span><span id="__span-0-135"><a id="__codelineno-0-135" name="__codelineno-0-135"></a> <span class="n">item</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span> <span class="o">+=</span> <span class="s2">" "</span> <span class="o">+</span> <span class="n">caption</span>
</span><span id="__span-0-136"><a id="__codelineno-0-136" name="__codelineno-0-136"></a>
</span><span id="__span-0-137"><a id="__codelineno-0-137" name="__codelineno-0-137"></a> <span class="c1"># Wrap elements with Document</span>
</span><span id="__span-0-138"><a id="__codelineno-0-138" name="__codelineno-0-138"></a> <span class="n">documents</span> <span class="o">=</span> <span class="p">[]</span>
</span><span id="__span-0-139"><a id="__codelineno-0-139" name="__codelineno-0-139"></a>
</span><span id="__span-0-140"><a id="__codelineno-0-140" name="__codelineno-0-140"></a> <span class="c1"># join plain text elements</span>
</span><span id="__span-0-141"><a id="__codelineno-0-141" name="__codelineno-0-141"></a> <span class="k">for</span> <span class="n">page_number</span><span class="p">,</span> <span class="n">txts</span> <span class="ow">in</span> <span class="n">texts</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
</span><span id="__span-0-142"><a id="__codelineno-0-142" name="__codelineno-0-142"></a> <span class="n">documents</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
</span><span id="__span-0-143"><a id="__codelineno-0-143" name="__codelineno-0-143"></a> <span class="n">Document</span><span class="p">(</span>
</span><span id="__span-0-144"><a id="__codelineno-0-144" name="__codelineno-0-144"></a> <span class="n">text</span><span class="o">=</span><span class="s2">"</span><span class="se">\n</span><span class="s2">"</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">txts</span><span class="p">),</span>
</span><span id="__span-0-145"><a id="__codelineno-0-145" name="__codelineno-0-145"></a> <span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
</span><span id="__span-0-146"><a id="__codelineno-0-146" name="__codelineno-0-146"></a> <span class="s2">"page_label"</span><span class="p">:</span> <span class="n">page_number</span><span class="p">,</span>
</span><span id="__span-0-147"><a id="__codelineno-0-147" name="__codelineno-0-147"></a> <span class="s2">"file_name"</span><span class="p">:</span> <span class="n">filename</span><span class="p">,</span>
</span><span id="__span-0-148"><a id="__codelineno-0-148" name="__codelineno-0-148"></a> <span class="s2">"file_path"</span><span class="p">:</span> <span class="n">filepath</span><span class="p">,</span>
</span><span id="__span-0-149"><a id="__codelineno-0-149" name="__codelineno-0-149"></a> <span class="o">**</span><span class="p">(</span><span class="n">extra_info</span> <span class="k">if</span> <span class="n">extra_info</span> <span class="k">else</span> <span class="p">{}),</span>
</span><span id="__span-0-150"><a id="__codelineno-0-150" name="__codelineno-0-150"></a> <span class="p">},</span>
</span><span id="__span-0-151"><a id="__codelineno-0-151" name="__codelineno-0-151"></a> <span class="p">)</span>
</span><span id="__span-0-152"><a id="__codelineno-0-152" name="__codelineno-0-152"></a> <span class="p">)</span>
</span><span id="__span-0-153"><a id="__codelineno-0-153" name="__codelineno-0-153"></a>
</span><span id="__span-0-154"><a id="__codelineno-0-154" name="__codelineno-0-154"></a> <span class="c1"># table elements</span>
</span><span id="__span-0-155"><a id="__codelineno-0-155" name="__codelineno-0-155"></a> <span class="k">for</span> <span class="n">page_number</span><span class="p">,</span> <span class="n">table_content</span><span class="p">,</span> <span class="n">table_caption</span> <span class="ow">in</span> <span class="n">tables</span><span class="p">:</span>
</span><span id="__span-0-156"><a id="__codelineno-0-156" name="__codelineno-0-156"></a> <span class="n">documents</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
</span><span id="__span-0-157"><a id="__codelineno-0-157" name="__codelineno-0-157"></a> <span class="n">Document</span><span class="p">(</span>
</span><span id="__span-0-158"><a id="__codelineno-0-158" name="__codelineno-0-158"></a> <span class="n">text</span><span class="o">=</span><span class="n">table_content</span><span class="p">,</span>
</span><span id="__span-0-159"><a id="__codelineno-0-159" name="__codelineno-0-159"></a> <span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
</span><span id="__span-0-160"><a id="__codelineno-0-160" name="__codelineno-0-160"></a> <span class="s2">"table_origin"</span><span class="p">:</span> <span class="n">table_content</span><span class="p">,</span>
</span><span id="__span-0-161"><a id="__codelineno-0-161" name="__codelineno-0-161"></a> <span class="s2">"type"</span><span class="p">:</span> <span class="s2">"table"</span><span class="p">,</span>
</span><span id="__span-0-162"><a id="__codelineno-0-162" name="__codelineno-0-162"></a> <span class="s2">"page_label"</span><span class="p">:</span> <span class="n">page_number</span><span class="p">,</span>
</span><span id="__span-0-163"><a id="__codelineno-0-163" name="__codelineno-0-163"></a> <span class="s2">"file_name"</span><span class="p">:</span> <span class="n">filename</span><span class="p">,</span>
</span><span id="__span-0-164"><a id="__codelineno-0-164" name="__codelineno-0-164"></a> <span class="s2">"file_path"</span><span class="p">:</span> <span class="n">filepath</span><span class="p">,</span>
</span><span id="__span-0-165"><a id="__codelineno-0-165" name="__codelineno-0-165"></a> <span class="o">**</span><span class="p">(</span><span class="n">extra_info</span> <span class="k">if</span> <span class="n">extra_info</span> <span class="k">else</span> <span class="p">{}),</span>
</span><span id="__span-0-166"><a id="__codelineno-0-166" name="__codelineno-0-166"></a> <span class="p">},</span>
</span><span id="__span-0-167"><a id="__codelineno-0-167" name="__codelineno-0-167"></a> <span class="n">metadata_template</span><span class="o">=</span><span class="s2">""</span><span class="p">,</span>
</span><span id="__span-0-168"><a id="__codelineno-0-168" name="__codelineno-0-168"></a> <span class="n">metadata_seperator</span><span class="o">=</span><span class="s2">""</span><span class="p">,</span>
</span><span id="__span-0-169"><a id="__codelineno-0-169" name="__codelineno-0-169"></a> <span class="p">)</span>
</span><span id="__span-0-170"><a id="__codelineno-0-170" name="__codelineno-0-170"></a> <span class="p">)</span>
</span><span id="__span-0-171"><a id="__codelineno-0-171" name="__codelineno-0-171"></a>
</span><span id="__span-0-172"><a id="__codelineno-0-172" name="__codelineno-0-172"></a> <span class="c1"># figure elements</span>
</span><span id="__span-0-173"><a id="__codelineno-0-173" name="__codelineno-0-173"></a> <span class="k">for</span> <span class="n">page_number</span><span class="p">,</span> <span class="n">figure_content</span><span class="p">,</span> <span class="n">figure_caption</span> <span class="ow">in</span> <span class="n">figures</span><span class="p">:</span>
</span><span id="__span-0-174"><a id="__codelineno-0-174" name="__codelineno-0-174"></a> <span class="n">documents</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
</span><span id="__span-0-175"><a id="__codelineno-0-175" name="__codelineno-0-175"></a> <span class="n">Document</span><span class="p">(</span>
</span><span id="__span-0-176"><a id="__codelineno-0-176" name="__codelineno-0-176"></a> <span class="n">text</span><span class="o">=</span><span class="n">figure_caption</span><span class="p">,</span>
</span><span id="__span-0-177"><a id="__codelineno-0-177" name="__codelineno-0-177"></a> <span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
</span><span id="__span-0-178"><a id="__codelineno-0-178" name="__codelineno-0-178"></a> <span class="s2">"image_origin"</span><span class="p">:</span> <span class="n">figure_content</span><span class="p">,</span>
</span><span id="__span-0-179"><a id="__codelineno-0-179" name="__codelineno-0-179"></a> <span class="s2">"type"</span><span class="p">:</span> <span class="s2">"image"</span><span class="p">,</span>
</span><span id="__span-0-180"><a id="__codelineno-0-180" name="__codelineno-0-180"></a> <span class="s2">"page_label"</span><span class="p">:</span> <span class="n">page_number</span><span class="p">,</span>
</span><span id="__span-0-181"><a id="__codelineno-0-181" name="__codelineno-0-181"></a> <span class="s2">"file_name"</span><span class="p">:</span> <span class="n">filename</span><span class="p">,</span>
</span><span id="__span-0-182"><a id="__codelineno-0-182" name="__codelineno-0-182"></a> <span class="s2">"file_path"</span><span class="p">:</span> <span class="n">filepath</span><span class="p">,</span>
</span><span id="__span-0-183"><a id="__codelineno-0-183" name="__codelineno-0-183"></a> <span class="o">**</span><span class="p">(</span><span class="n">extra_info</span> <span class="k">if</span> <span class="n">extra_info</span> <span class="k">else</span> <span class="p">{}),</span>
</span><span id="__span-0-184"><a id="__codelineno-0-184" name="__codelineno-0-184"></a> <span class="p">},</span>
</span><span id="__span-0-185"><a id="__codelineno-0-185" name="__codelineno-0-185"></a> <span class="n">metadata_template</span><span class="o">=</span><span class="s2">""</span><span class="p">,</span>
</span><span id="__span-0-186"><a id="__codelineno-0-186" name="__codelineno-0-186"></a> <span class="n">metadata_seperator</span><span class="o">=</span><span class="s2">""</span><span class="p">,</span>
</span><span id="__span-0-187"><a id="__codelineno-0-187" name="__codelineno-0-187"></a> <span class="p">)</span>
</span><span id="__span-0-188"><a id="__codelineno-0-188" name="__codelineno-0-188"></a> <span class="p">)</span>
</span><span id="__span-0-189"><a id="__codelineno-0-189" name="__codelineno-0-189"></a> <span class="k">return</span> <span class="n">documents</span>
</span></code></pre></div></td></tr></table></div>
</details>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
<aside class="md-source-file">
<span class="md-source-file__fact">
<span class="md-icon" title="Last update">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M21 13.1c-.1 0-.3.1-.4.2l-1 1 2.1 2.1 1-1c.2-.2.2-.6 0-.8l-1.3-1.3c-.1-.1-.2-.2-.4-.2m-1.9 1.8-6.1 6V23h2.1l6.1-6.1zM12.5 7v5.2l4 2.4-1 1L11 13V7zM11 21.9c-5.1-.5-9-4.8-9-9.9C2 6.5 6.5 2 12 2c5.3 0 9.6 4.1 10 9.3-.3-.1-.6-.2-1-.2s-.7.1-1 .2C19.6 7.2 16.2 4 12 4c-4.4 0-8 3.6-8 8 0 4.1 3.1 7.5 7.1 7.9l-.1.2z"/></svg>
</span>
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-timeago"><span class="timeago" datetime="2025-02-02T08:38:35+00:00" locale="en"></span></span><span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-iso_date">2025-02-02</span>
</span>
<span class="md-source-file__fact">
<span class="md-icon" title="Created">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M14.47 15.08 11 13V7h1.5v5.25l3.08 1.83c-.41.28-.79.62-1.11 1m-1.39 4.84c-.36.05-.71.08-1.08.08-4.42 0-8-3.58-8-8s3.58-8 8-8 8 3.58 8 8c0 .37-.03.72-.08 1.08.69.1 1.33.32 1.92.64.1-.56.16-1.13.16-1.72 0-5.5-4.5-10-10-10S2 6.5 2 12s4.47 10 10 10c.59 0 1.16-.06 1.72-.16-.32-.59-.54-1.23-.64-1.92M18 15v3h-3v2h3v3h2v-3h3v-2h-3v-3z"/></svg>
</span>
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-timeago"><span class="timeago" datetime="2025-02-02T08:38:35+00:00" locale="en"></span></span><span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-iso_date">2025-02-02</span>
</span>
</aside>
</article>
</div>
<script>var tabs=__md_get("__tabs");if(Array.isArray(tabs))e:for(var set of document.querySelectorAll(".tabbed-set")){var labels=set.querySelector(".tabbed-labels");for(var tab of tabs)for(var label of labels.getElementsByTagName("label"))if(label.innerText.trim()===tab){var input=document.getElementById(label.htmlFor);input.checked=!0;continue e}}</script>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
<button type="button" class="md-top md-icon" data-md-component="top" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13 20h-2V8l-5.5 5.5-1.42-1.42L12 4.16l7.92 7.92-1.42 1.42L13 8z"/></svg>
Back to top
</button>
</main>
<footer class="md-footer">
<nav
class="md-footer__inner md-grid"
aria-label="footer.title"
>
<a
href="../"
class="md-footer__link md-footer__link--prev"
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 11z"/></svg>
</div>
<div class="md-footer__title">
<div class="md-ellipsis">
<span class="md-footer__direction">
Previous
</span>
Loaders
</div>
</div>
</a>
<a
href="../azureai_document_intelligence_loader/"
class="md-footer__link md-footer__link--next"
rel="next"
>
<div class="md-footer__title">
<div class="md-ellipsis">
<span class="md-footer__direction">
Next
</span>
Azureai Document Intelligence Loader
</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 11z"/></svg>
</div>
</a>
</nav>
</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.action.edit", "content.tabs.link", "content.code.annotate", "content.code.annotations", "content.code.copy", "navigation.tabs", "navigation.top", "navigation.instant", "navigation.indexes", "toc.follow", "search.share", "search.highlight", "search.suggest"], "search": "../../../assets/javascripts/workers/search.6ce7567c.min.js", "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"}}</script>
<script src="../../../assets/javascripts/bundle.525ec568.min.js"></script>
<script src="../../../js/timeago.min.js"></script>
<script src="../../../js/timeago_mkdocs_material.js"></script>
<script src="../../../assets/pymdownx-extras/extra-loader-MCFnu0Wd.js"></script>
</body>
</html>