792 lines
54 KiB
HTML
792 lines
54 KiB
HTML
|
||
<!DOCTYPE html>
|
||
|
||
|
||
<html lang="en" data-content_root="./" >
|
||
|
||
<head>
|
||
<meta charset="utf-8" />
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||
|
||
<title>API Reference — TexTeller documentation</title>
|
||
|
||
|
||
|
||
<script data-cfasync="false">
|
||
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
|
||
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
|
||
</script>
|
||
|
||
<!-- Loaded before other Sphinx assets -->
|
||
<link href="_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
|
||
<link href="_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
|
||
<link href="_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
|
||
|
||
|
||
<link href="_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
|
||
<link rel="preload" as="font" type="font/woff2" crossorigin href="_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" />
|
||
<link rel="preload" as="font" type="font/woff2" crossorigin href="_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" />
|
||
<link rel="preload" as="font" type="font/woff2" crossorigin href="_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" />
|
||
|
||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=8f2a1f02" />
|
||
<link rel="stylesheet" type="text/css" href="_static/styles/sphinx-book-theme.css?v=eba8b062" />
|
||
<link rel="stylesheet" type="text/css" href="_static/copybutton.css?v=76b2166b" />
|
||
<link rel="stylesheet" type="text/css" href="_static/sphinx-design.min.css?v=95c83b7e" />
|
||
|
||
<!-- Pre-loaded scripts that we'll load fully later -->
|
||
<link rel="preload" as="script" href="_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" />
|
||
<link rel="preload" as="script" href="_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" />
|
||
<script src="_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
|
||
|
||
<script src="_static/documentation_options.js?v=9eb32ce0"></script>
|
||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||
<script src="_static/clipboard.min.js?v=a7894cd8"></script>
|
||
<script src="_static/copybutton.js?v=f281be69"></script>
|
||
<script src="_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
|
||
<script src="_static/design-tabs.js?v=f930bc37"></script>
|
||
<script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
|
||
<script>DOCUMENTATION_OPTIONS.pagename = 'api';</script>
|
||
<link rel="index" title="Index" href="genindex.html" />
|
||
<link rel="search" title="Search" href="search.html" />
|
||
<link rel="prev" title="TexTeller Documentation" href="index.html" />
|
||
<meta name="viewport" content="width=device-width, initial-scale=1"/>
|
||
<meta name="docsearch:language" content="en"/>
|
||
</head>
|
||
|
||
|
||
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
|
||
|
||
|
||
|
||
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
|
||
|
||
<div id="pst-scroll-pixel-helper"></div>
|
||
|
||
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
|
||
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
|
||
|
||
|
||
<input type="checkbox"
|
||
class="sidebar-toggle"
|
||
id="pst-primary-sidebar-checkbox"/>
|
||
<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
|
||
|
||
<input type="checkbox"
|
||
class="sidebar-toggle"
|
||
id="pst-secondary-sidebar-checkbox"/>
|
||
<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
|
||
|
||
<div class="search-button__wrapper">
|
||
<div class="search-button__overlay"></div>
|
||
<div class="search-button__search-container">
|
||
<form class="bd-search d-flex align-items-center"
|
||
action="search.html"
|
||
method="get">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<input type="search"
|
||
class="form-control"
|
||
name="q"
|
||
id="search-input"
|
||
placeholder="Search..."
|
||
aria-label="Search..."
|
||
autocomplete="off"
|
||
autocorrect="off"
|
||
autocapitalize="off"
|
||
spellcheck="false"/>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
|
||
</form></div>
|
||
</div>
|
||
|
||
<div class="pst-async-banner-revealer d-none">
|
||
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
|
||
</div>
|
||
|
||
|
||
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
|
||
</header>
|
||
|
||
|
||
<div class="bd-container">
|
||
<div class="bd-container__inner bd-page-width">
|
||
|
||
|
||
|
||
<div class="bd-sidebar-primary bd-sidebar">
|
||
|
||
|
||
|
||
<div class="sidebar-header-items sidebar-primary__section">
|
||
|
||
|
||
|
||
|
||
</div>
|
||
|
||
<div class="sidebar-primary-items__start sidebar-primary__section">
|
||
<div class="sidebar-primary-item">
|
||
|
||
|
||
|
||
|
||
|
||
<a class="navbar-brand logo" href="index.html">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<img src="_static/logo.svg" class="logo__image only-light" alt="TexTeller documentation - Home"/>
|
||
<script>document.write(`<img src="_static/logo.svg" class="logo__image only-dark" alt="TexTeller documentation - Home"/>`);</script>
|
||
|
||
|
||
</a></div>
|
||
<div class="sidebar-primary-item">
|
||
|
||
<script>
|
||
document.write(`
|
||
<button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<span class="search-button__default-text">Search</span>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
|
||
</button>
|
||
`);
|
||
</script></div>
|
||
<div class="sidebar-primary-item"><nav class="bd-links bd-docs-nav" aria-label="Main">
|
||
<div class="bd-toc-item navbar-nav active">
|
||
<ul class="current nav bd-sidenav">
|
||
<li class="toctree-l1 current active"><a class="current reference internal" href="#">API Reference</a></li>
|
||
</ul>
|
||
|
||
</div>
|
||
</nav></div>
|
||
</div>
|
||
|
||
|
||
<div class="sidebar-primary-items__end sidebar-primary__section">
|
||
</div>
|
||
|
||
<div id="rtd-footer-container"></div>
|
||
|
||
|
||
</div>
|
||
|
||
<main id="main-content" class="bd-main" role="main">
|
||
|
||
|
||
|
||
<div class="sbt-scroll-pixel-helper"></div>
|
||
|
||
<div class="bd-content">
|
||
<div class="bd-article-container">
|
||
|
||
<div class="bd-header-article d-print-none">
|
||
<div class="header-article-items header-article__inner">
|
||
|
||
<div class="header-article-items__start">
|
||
|
||
<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" title="Toggle primary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<span class="fa-solid fa-bars"></span>
|
||
</button></div>
|
||
|
||
</div>
|
||
|
||
|
||
<div class="header-article-items__end">
|
||
|
||
<div class="header-article-item">
|
||
|
||
<div class="article-header-buttons">
|
||
|
||
|
||
|
||
|
||
|
||
<div class="dropdown dropdown-source-buttons">
|
||
<button class="btn dropdown-toggle" type="button" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Source repositories">
|
||
<i class="fab fa-github"></i>
|
||
</button>
|
||
<ul class="dropdown-menu">
|
||
|
||
|
||
|
||
<li><a href="https://github.com/OleehyO/TexTeller" target="_blank"
|
||
class="btn btn-sm btn-source-repository-button dropdown-item"
|
||
title="Source repository"
|
||
data-bs-placement="left" data-bs-toggle="tooltip"
|
||
>
|
||
|
||
|
||
<span class="btn__icon-container">
|
||
<i class="fab fa-github"></i>
|
||
</span>
|
||
<span class="btn__text-container">Repository</span>
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
<li><a href="https://github.com/OleehyO/TexTeller/edit/main/api.rst" target="_blank"
|
||
class="btn btn-sm btn-source-edit-button dropdown-item"
|
||
title="Suggest edit"
|
||
data-bs-placement="left" data-bs-toggle="tooltip"
|
||
>
|
||
|
||
|
||
<span class="btn__icon-container">
|
||
<i class="fas fa-pencil-alt"></i>
|
||
</span>
|
||
<span class="btn__text-container">Suggest edit</span>
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
<li><a href="https://github.com/OleehyO/TexTeller/issues/new?title=Issue%20on%20page%20%2Fapi.html&body=Your%20issue%20content%20here." target="_blank"
|
||
class="btn btn-sm btn-source-issues-button dropdown-item"
|
||
title="Open an issue"
|
||
data-bs-placement="left" data-bs-toggle="tooltip"
|
||
>
|
||
|
||
|
||
<span class="btn__icon-container">
|
||
<i class="fas fa-lightbulb"></i>
|
||
</span>
|
||
<span class="btn__text-container">Open issue</span>
|
||
</a>
|
||
</li>
|
||
|
||
</ul>
|
||
</div>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<div class="dropdown dropdown-download-buttons">
|
||
<button class="btn dropdown-toggle" type="button" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download this page">
|
||
<i class="fas fa-download"></i>
|
||
</button>
|
||
<ul class="dropdown-menu">
|
||
|
||
|
||
|
||
<li><a href="_sources/api.rst" target="_blank"
|
||
class="btn btn-sm btn-download-source-button dropdown-item"
|
||
title="Download source file"
|
||
data-bs-placement="left" data-bs-toggle="tooltip"
|
||
>
|
||
|
||
|
||
<span class="btn__icon-container">
|
||
<i class="fas fa-file"></i>
|
||
</span>
|
||
<span class="btn__text-container">.rst</span>
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
<li>
|
||
<button onclick="window.print()"
|
||
class="btn btn-sm btn-download-pdf-button dropdown-item"
|
||
title="Print to PDF"
|
||
data-bs-placement="left" data-bs-toggle="tooltip"
|
||
>
|
||
|
||
|
||
<span class="btn__icon-container">
|
||
<i class="fas fa-file-pdf"></i>
|
||
</span>
|
||
<span class="btn__text-container">.pdf</span>
|
||
</button>
|
||
</li>
|
||
|
||
</ul>
|
||
</div>
|
||
|
||
|
||
|
||
|
||
<button onclick="toggleFullScreen()"
|
||
class="btn btn-sm btn-fullscreen-button"
|
||
title="Fullscreen mode"
|
||
data-bs-placement="bottom" data-bs-toggle="tooltip"
|
||
>
|
||
|
||
|
||
<span class="btn__icon-container">
|
||
<i class="fas fa-expand"></i>
|
||
</span>
|
||
|
||
</button>
|
||
|
||
|
||
|
||
<script>
|
||
document.write(`
|
||
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
|
||
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
|
||
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
|
||
</button>
|
||
`);
|
||
</script>
|
||
|
||
|
||
<script>
|
||
document.write(`
|
||
<button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="fa-solid fa-magnifying-glass fa-lg"></i>
|
||
</button>
|
||
`);
|
||
</script>
|
||
<button class="sidebar-toggle secondary-toggle btn btn-sm" title="Toggle secondary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<span class="fa-solid fa-list"></span>
|
||
</button>
|
||
</div></div>
|
||
|
||
</div>
|
||
|
||
</div>
|
||
</div>
|
||
|
||
|
||
|
||
<div id="jb-print-docs-body" class="onlyprint">
|
||
<h1>API Reference</h1>
|
||
<!-- Table of contents -->
|
||
<div id="print-main-content">
|
||
<div id="jb-print-toc">
|
||
|
||
<div>
|
||
<h2> Contents </h2>
|
||
</div>
|
||
<nav aria-label="Page">
|
||
<ul class="visible nav section-nav flex-column">
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#image-to-latex-conversion">Image to LaTeX Conversion</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#texteller.api.img2latex"><code class="docutils literal notranslate"><span class="pre">img2latex()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#paragraph-to-markdown-conversion">Paragraph to Markdown Conversion</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#texteller.api.paragraph2md"><code class="docutils literal notranslate"><span class="pre">paragraph2md()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#latex-detection">LaTeX Detection</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#texteller.api.detection.latex_detect"><code class="docutils literal notranslate"><span class="pre">latex_detect()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#model-loading">Model Loading</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#texteller.api.load_model"><code class="docutils literal notranslate"><span class="pre">load_model()</span></code></a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#texteller.api.load_tokenizer"><code class="docutils literal notranslate"><span class="pre">load_tokenizer()</span></code></a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#texteller.api.load_latexdet_model"><code class="docutils literal notranslate"><span class="pre">load_latexdet_model()</span></code></a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#texteller.api.load_textdet_model"><code class="docutils literal notranslate"><span class="pre">load_textdet_model()</span></code></a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#texteller.api.load_textrec_model"><code class="docutils literal notranslate"><span class="pre">load_textrec_model()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#katex-conversion">KaTeX Conversion</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#texteller.api.to_katex"><code class="docutils literal notranslate"><span class="pre">to_katex()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</nav>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
|
||
|
||
<div id="searchbox"></div>
|
||
<article class="bd-article">
|
||
|
||
<section id="api-reference">
|
||
<h1>API Reference<a class="headerlink" href="#api-reference" title="Link to this heading">#</a></h1>
|
||
<p>This section provides detailed API documentation for the TexTeller package. TexTeller is a tool for detecting and recognizing LaTeX formulas in images and converting mixed text and formula images to markdown.</p>
|
||
<nav class="contents local" id="table-of-contents">
|
||
<p class="topic-title">Table of Contents</p>
|
||
<ul class="simple">
|
||
<li><p><a class="reference internal" href="#image-to-latex-conversion" id="id1">Image to LaTeX Conversion</a></p></li>
|
||
<li><p><a class="reference internal" href="#paragraph-to-markdown-conversion" id="id2">Paragraph to Markdown Conversion</a></p></li>
|
||
<li><p><a class="reference internal" href="#latex-detection" id="id3">LaTeX Detection</a></p></li>
|
||
<li><p><a class="reference internal" href="#model-loading" id="id4">Model Loading</a></p></li>
|
||
<li><p><a class="reference internal" href="#katex-conversion" id="id5">KaTeX Conversion</a></p></li>
|
||
</ul>
|
||
</nav>
|
||
<section id="image-to-latex-conversion">
|
||
<h2><a class="toc-backref" href="#id1" role="doc-backlink">Image to LaTeX Conversion</a><a class="headerlink" href="#image-to-latex-conversion" title="Link to this heading">#</a></h2>
|
||
<dl class="py function">
|
||
<dt class="sig sig-object py" id="texteller.api.img2latex">
|
||
<span class="sig-name descname"><span class="pre">img2latex</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">VisionEncoderDecoderModel</span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><span class="pre">ORTModelForVision2Seq</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tokenizer</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">RobertaTokenizerFast</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">images</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.13)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.13)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://numpy.org/doc/stable/reference/generated/numpy.ndarray.html#numpy.ndarray" title="(in NumPy v2.2)"><span class="pre">ndarray</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://pytorch.org/docs/stable/tensor_attributes.html#torch.device" title="(in PyTorch v2.6)"><span class="pre">device</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_format</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Literal" title="(in Python v3.13)"><span class="pre">Literal</span></a><span class="p"><span class="pre">[</span></span><span class="s"><span class="pre">'latex'</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="s"><span class="pre">'katex'</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'latex'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_style</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.13)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_tokens</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">1024</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_beams</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">no_repeat_ngram_size</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.13)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></span><a class="reference internal" href="_modules/texteller/api/inference.html#img2latex"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#texteller.api.img2latex" title="Link to this definition">#</a></dt>
|
||
<dd><p>Convert images to LaTeX or KaTeX formatted strings.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><ul class="simple">
|
||
<li><p><strong>model</strong> – The TexTeller or ORTModelForVision2Seq model instance</p></li>
|
||
<li><p><strong>tokenizer</strong> – The tokenizer for the model</p></li>
|
||
<li><p><strong>images</strong> – List of image paths or numpy arrays (RGB format)</p></li>
|
||
<li><p><strong>device</strong> – The torch device to use (defaults to available GPU or CPU)</p></li>
|
||
<li><p><strong>out_format</strong> – Output format, either “latex” or “katex”</p></li>
|
||
<li><p><strong>keep_style</strong> – Whether to keep the style of the LaTeX</p></li>
|
||
<li><p><strong>max_tokens</strong> – Maximum number of tokens to generate</p></li>
|
||
<li><p><strong>num_beams</strong> – Number of beams for beam search</p></li>
|
||
<li><p><strong>no_repeat_ngram_size</strong> – Size of n-grams to prevent repetition</p></li>
|
||
</ul>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>List of LaTeX or KaTeX strings corresponding to each input image</p>
|
||
</dd>
|
||
</dl>
|
||
<p class="rubric">Example</p>
|
||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">import</span><span class="w"> </span><span class="nn">torch</span>
|
||
<span class="gp">>>> </span><span class="kn">from</span><span class="w"> </span><span class="nn">texteller</span><span class="w"> </span><span class="kn">import</span> <span class="n">load_model</span><span class="p">,</span> <span class="n">load_tokenizer</span><span class="p">,</span> <span class="n">img2latex</span>
|
||
<span class="gp">>>></span>
|
||
<span class="gp">>>> </span><span class="n">model</span> <span class="o">=</span> <span class="n">load_model</span><span class="p">(</span><span class="n">model_path</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">use_onnx</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
|
||
<span class="gp">>>> </span><span class="n">tokenizer</span> <span class="o">=</span> <span class="n">load_tokenizer</span><span class="p">(</span><span class="n">tokenizer_path</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span>
|
||
<span class="gp">>>> </span><span class="n">device</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="s2">"cuda"</span> <span class="k">if</span> <span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">is_available</span><span class="p">()</span> <span class="k">else</span> <span class="s2">"cpu"</span><span class="p">)</span>
|
||
<span class="gp">>>></span>
|
||
<span class="gp">>>> </span><span class="n">res</span> <span class="o">=</span> <span class="n">img2latex</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">tokenizer</span><span class="p">,</span> <span class="p">[</span><span class="s2">"path/to/image.png"</span><span class="p">],</span> <span class="n">device</span><span class="o">=</span><span class="n">device</span><span class="p">,</span> <span class="n">out_format</span><span class="o">=</span><span class="s2">"katex"</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="paragraph-to-markdown-conversion">
|
||
<h2><a class="toc-backref" href="#id2" role="doc-backlink">Paragraph to Markdown Conversion</a><a class="headerlink" href="#paragraph-to-markdown-conversion" title="Link to this heading">#</a></h2>
|
||
<dl class="py function">
|
||
<dt class="sig sig-object py" id="texteller.api.paragraph2md">
|
||
<span class="sig-name descname"><span class="pre">paragraph2md</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">img_path</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">latexdet_model</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">InferenceSession</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">textdet_model</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">TextDetector</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">textrec_model</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">TextRecognizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">latexrec_model</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">VisionEncoderDecoderModel</span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><span class="pre">ORTModelForVision2Seq</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tokenizer</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">RobertaTokenizerFast</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://pytorch.org/docs/stable/tensor_attributes.html#torch.device" title="(in PyTorch v2.6)"><span class="pre">device</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_beams</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></span><a class="reference internal" href="_modules/texteller/api/inference.html#paragraph2md"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#texteller.api.paragraph2md" title="Link to this definition">#</a></dt>
|
||
<dd><p>Convert an image containing both text and mathematical formulas to markdown format.</p>
|
||
<p>This function processes a mixed-content image by:
|
||
1. Detecting mathematical formulas using a latex detection model
|
||
2. Masking detected formula areas and detecting text regions using OCR
|
||
3. Recognizing text in the detected regions
|
||
4. Converting formula regions to LaTeX using the latex recognition model
|
||
5. Combining all detected elements into a properly formatted markdown string</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><ul class="simple">
|
||
<li><p><strong>img_path</strong> – Path to the input image containing text and formulas</p></li>
|
||
<li><p><strong>latexdet_model</strong> – ONNX InferenceSession for LaTeX formula detection</p></li>
|
||
<li><p><strong>textdet_model</strong> – OCR text detector model</p></li>
|
||
<li><p><strong>textrec_model</strong> – OCR text recognition model</p></li>
|
||
<li><p><strong>latexrec_model</strong> – TexTeller model for LaTeX formula recognition</p></li>
|
||
<li><p><strong>tokenizer</strong> – Tokenizer for the LaTeX recognition model</p></li>
|
||
<li><p><strong>device</strong> – The torch device to use (defaults to available GPU or CPU)</p></li>
|
||
<li><p><strong>num_beams</strong> – Number of beams for beam search during LaTeX generation</p></li>
|
||
</ul>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>Markdown formatted string containing the recognized text and formulas</p>
|
||
</dd>
|
||
</dl>
|
||
<p class="rubric">Example</p>
|
||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">from</span><span class="w"> </span><span class="nn">texteller</span><span class="w"> </span><span class="kn">import</span> <span class="n">load_latexdet_model</span><span class="p">,</span> <span class="n">load_textdet_model</span><span class="p">,</span> <span class="n">load_textrec_model</span><span class="p">,</span> <span class="n">load_tokenizer</span><span class="p">,</span> <span class="n">paragraph2md</span>
|
||
<span class="gp">>>></span>
|
||
<span class="gp">>>> </span><span class="c1"># Load all required models</span>
|
||
<span class="gp">>>> </span><span class="n">latexdet_model</span> <span class="o">=</span> <span class="n">load_latexdet_model</span><span class="p">()</span>
|
||
<span class="gp">>>> </span><span class="n">textdet_model</span> <span class="o">=</span> <span class="n">load_textdet_model</span><span class="p">()</span>
|
||
<span class="gp">>>> </span><span class="n">textrec_model</span> <span class="o">=</span> <span class="n">load_textrec_model</span><span class="p">()</span>
|
||
<span class="gp">>>> </span><span class="n">latexrec_model</span> <span class="o">=</span> <span class="n">load_model</span><span class="p">()</span>
|
||
<span class="gp">>>> </span><span class="n">tokenizer</span> <span class="o">=</span> <span class="n">load_tokenizer</span><span class="p">()</span>
|
||
<span class="gp">>>></span>
|
||
<span class="gp">>>> </span><span class="c1"># Convert image to markdown</span>
|
||
<span class="gp">>>> </span><span class="n">markdown_text</span> <span class="o">=</span> <span class="n">paragraph2md</span><span class="p">(</span>
|
||
<span class="gp">... </span> <span class="n">img_path</span><span class="o">=</span><span class="s2">"path/to/mixed_content_image.jpg"</span><span class="p">,</span>
|
||
<span class="gp">... </span> <span class="n">latexdet_model</span><span class="o">=</span><span class="n">latexdet_model</span><span class="p">,</span>
|
||
<span class="gp">... </span> <span class="n">textdet_model</span><span class="o">=</span><span class="n">textdet_model</span><span class="p">,</span>
|
||
<span class="gp">... </span> <span class="n">textrec_model</span><span class="o">=</span><span class="n">textrec_model</span><span class="p">,</span>
|
||
<span class="gp">... </span> <span class="n">latexrec_model</span><span class="o">=</span><span class="n">latexrec_model</span><span class="p">,</span>
|
||
<span class="gp">... </span> <span class="n">tokenizer</span><span class="o">=</span><span class="n">tokenizer</span><span class="p">,</span>
|
||
<span class="gp">... </span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="latex-detection">
|
||
<h2><a class="toc-backref" href="#id3" role="doc-backlink">LaTeX Detection</a><a class="headerlink" href="#latex-detection" title="Link to this heading">#</a></h2>
|
||
<dl class="py function">
|
||
<dt class="sig sig-object py" id="texteller.api.detection.latex_detect">
|
||
<span class="sig-name descname"><span class="pre">latex_detect</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">img_path</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">predictor</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">InferenceSession</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.List" title="(in Python v3.13)"><span class="pre">List</span></a><span class="p"><span class="pre">[</span></span><span class="pre">Bbox</span><span class="p"><span class="pre">]</span></span></span></span><a class="reference internal" href="_modules/texteller/api/detection/detect.html#latex_detect"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#texteller.api.detection.latex_detect" title="Link to this definition">#</a></dt>
|
||
<dd><p>Detect LaTeX formulas in an image and classify them as isolated or embedded.</p>
|
||
<p>This function uses an ONNX model to detect LaTeX formulas in images. The model
|
||
identifies two types of LaTeX formulas:
|
||
- ‘isolated’: Standalone LaTeX formulas (typically displayed equations)
|
||
- ‘embedding’: Inline LaTeX formulas embedded within text</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><ul class="simple">
|
||
<li><p><strong>img_path</strong> – Path to the input image file</p></li>
|
||
<li><p><strong>predictor</strong> – ONNX InferenceSession model for LaTeX detection</p></li>
|
||
</ul>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>List of Bbox objects representing the detected LaTeX formulas with their
|
||
positions, classifications, and confidence scores</p>
|
||
</dd>
|
||
</dl>
|
||
<p class="rubric">Example</p>
|
||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">from</span><span class="w"> </span><span class="nn">texteller.api</span><span class="w"> </span><span class="kn">import</span> <span class="n">load_latexdet_model</span><span class="p">,</span> <span class="n">latex_detect</span>
|
||
<span class="gp">>>> </span><span class="n">model</span> <span class="o">=</span> <span class="n">load_latexdet_model</span><span class="p">()</span>
|
||
<span class="gp">>>> </span><span class="n">bboxes</span> <span class="o">=</span> <span class="n">latex_detect</span><span class="p">(</span><span class="s2">"path/to/image.png"</span><span class="p">,</span> <span class="n">model</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="model-loading">
|
||
<h2><a class="toc-backref" href="#id4" role="doc-backlink">Model Loading</a><a class="headerlink" href="#model-loading" title="Link to this heading">#</a></h2>
|
||
<dl class="py function">
|
||
<dt class="sig sig-object py" id="texteller.api.load_model">
|
||
<span class="sig-name descname"><span class="pre">load_model</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model_dir</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_onnx</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.13)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><span class="pre">VisionEncoderDecoderModel</span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><span class="pre">ORTModelForVision2Seq</span></span></span><a class="reference internal" href="_modules/texteller/api/load.html#load_model"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#texteller.api.load_model" title="Link to this definition">#</a></dt>
|
||
<dd><p>Load the TexTeller model for LaTeX recognition.</p>
|
||
<p>This function loads the main TexTeller model, which is responsible for
|
||
converting images to LaTeX. It can load either the standard PyTorch model
|
||
or the optimized ONNX version.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><ul class="simple">
|
||
<li><p><strong>model_dir</strong> – Directory containing the model files. If None, uses the default model.</p></li>
|
||
<li><p><strong>use_onnx</strong> – Whether to load the ONNX version of the model for faster inference.
|
||
Requires the ‘optimum’ package and ONNX Runtime.</p></li>
|
||
</ul>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>Loaded TexTeller model instance</p>
|
||
</dd>
|
||
</dl>
|
||
<p class="rubric">Example</p>
|
||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">from</span><span class="w"> </span><span class="nn">texteller</span><span class="w"> </span><span class="kn">import</span> <span class="n">load_model</span>
|
||
<span class="gp">>>></span>
|
||
<span class="gp">>>> </span><span class="n">model</span> <span class="o">=</span> <span class="n">load_model</span><span class="p">(</span><span class="n">use_onnx</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="py function">
|
||
<dt class="sig sig-object py" id="texteller.api.load_tokenizer">
|
||
<span class="sig-name descname"><span class="pre">load_tokenizer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tokenizer_dir</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><span class="pre">RobertaTokenizerFast</span></span></span><a class="reference internal" href="_modules/texteller/api/load.html#load_tokenizer"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#texteller.api.load_tokenizer" title="Link to this definition">#</a></dt>
|
||
<dd><p>Load the tokenizer for the TexTeller model.</p>
|
||
<p>This function loads the tokenizer used by the TexTeller model for
|
||
encoding and decoding LaTeX sequences.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p><strong>tokenizer_dir</strong> – Directory containing the tokenizer files. If None, uses the default tokenizer.</p>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>RobertaTokenizerFast instance</p>
|
||
</dd>
|
||
</dl>
|
||
<p class="rubric">Example</p>
|
||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">from</span><span class="w"> </span><span class="nn">texteller</span><span class="w"> </span><span class="kn">import</span> <span class="n">load_tokenizer</span>
|
||
<span class="gp">>>></span>
|
||
<span class="gp">>>> </span><span class="n">tokenizer</span> <span class="o">=</span> <span class="n">load_tokenizer</span><span class="p">()</span>
|
||
</pre></div>
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="py function">
|
||
<dt class="sig sig-object py" id="texteller.api.load_latexdet_model">
|
||
<span class="sig-name descname"><span class="pre">load_latexdet_model</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><span class="pre">InferenceSession</span></span></span><a class="reference internal" href="_modules/texteller/api/load.html#load_latexdet_model"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#texteller.api.load_latexdet_model" title="Link to this definition">#</a></dt>
|
||
<dd><p>Load the LaTeX detection model.</p>
|
||
<p>This function loads the model responsible for detecting LaTeX formulas in images.
|
||
The model is implemented as an ONNX InferenceSession for optimal performance.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>ONNX InferenceSession for LaTeX detection</p>
|
||
</dd>
|
||
</dl>
|
||
<p class="rubric">Example</p>
|
||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">from</span><span class="w"> </span><span class="nn">texteller</span><span class="w"> </span><span class="kn">import</span> <span class="n">load_latexdet_model</span>
|
||
<span class="gp">>>></span>
|
||
<span class="gp">>>> </span><span class="n">detector</span> <span class="o">=</span> <span class="n">load_latexdet_model</span><span class="p">()</span>
|
||
</pre></div>
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="py function">
|
||
<dt class="sig sig-object py" id="texteller.api.load_textdet_model">
|
||
<span class="sig-name descname"><span class="pre">load_textdet_model</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><span class="pre">TextDetector</span></span></span><a class="reference internal" href="_modules/texteller/api/load.html#load_textdet_model"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#texteller.api.load_textdet_model" title="Link to this definition">#</a></dt>
|
||
<dd><p>Load the text detection model.</p>
|
||
<p>This function loads the model responsible for detecting text regions in images.
|
||
It’s based on PaddleOCR’s text detection model.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>PaddleOCR TextDetector instance</p>
|
||
</dd>
|
||
</dl>
|
||
<p class="rubric">Example</p>
|
||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">from</span><span class="w"> </span><span class="nn">texteller</span><span class="w"> </span><span class="kn">import</span> <span class="n">load_textdet_model</span>
|
||
<span class="gp">>>></span>
|
||
<span class="gp">>>> </span><span class="n">text_detector</span> <span class="o">=</span> <span class="n">load_textdet_model</span><span class="p">()</span>
|
||
</pre></div>
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="py function">
|
||
<dt class="sig sig-object py" id="texteller.api.load_textrec_model">
|
||
<span class="sig-name descname"><span class="pre">load_textrec_model</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><span class="pre">TextRecognizer</span></span></span><a class="reference internal" href="_modules/texteller/api/load.html#load_textrec_model"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#texteller.api.load_textrec_model" title="Link to this definition">#</a></dt>
|
||
<dd><p>Load the text recognition model.</p>
|
||
<p>This function loads the model responsible for recognizing regular text in images.
|
||
It’s based on PaddleOCR’s text recognition model.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>PaddleOCR TextRecognizer instance</p>
|
||
</dd>
|
||
</dl>
|
||
<p class="rubric">Example</p>
|
||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">from</span><span class="w"> </span><span class="nn">texteller</span><span class="w"> </span><span class="kn">import</span> <span class="n">load_textrec_model</span>
|
||
<span class="gp">>>></span>
|
||
<span class="gp">>>> </span><span class="n">text_recognizer</span> <span class="o">=</span> <span class="n">load_textrec_model</span><span class="p">()</span>
|
||
</pre></div>
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="katex-conversion">
|
||
<h2><a class="toc-backref" href="#id5" role="doc-backlink">KaTeX Conversion</a><a class="headerlink" href="#katex-conversion" title="Link to this heading">#</a></h2>
|
||
<dl class="py function">
|
||
<dt class="sig sig-object py" id="texteller.api.to_katex">
|
||
<span class="sig-name descname"><span class="pre">to_katex</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">formula</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></span><a class="reference internal" href="_modules/texteller/api/katex.html#to_katex"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#texteller.api.to_katex" title="Link to this definition">#</a></dt>
|
||
<dd><p>Convert LaTeX formula to KaTeX-compatible format.</p>
|
||
<p>This function processes a LaTeX formula string and converts it to a format
|
||
that is compatible with KaTeX rendering. It removes unsupported commands
|
||
and structures, simplifies LaTeX environments, and optimizes the formula
|
||
for web display.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p><strong>formula</strong> – LaTeX formula string to convert</p>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>KaTeX-compatible formula string</p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
</section>
|
||
</section>
|
||
|
||
|
||
</article>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<footer class="prev-next-footer d-print-none">
|
||
|
||
<div class="prev-next-area">
|
||
<a class="left-prev"
|
||
href="index.html"
|
||
title="previous page">
|
||
<i class="fa-solid fa-angle-left"></i>
|
||
<div class="prev-next-info">
|
||
<p class="prev-next-subtitle">previous</p>
|
||
<p class="prev-next-title">TexTeller Documentation</p>
|
||
</div>
|
||
</a>
|
||
</div>
|
||
</footer>
|
||
|
||
</div>
|
||
|
||
|
||
|
||
<div class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
|
||
|
||
|
||
<div class="sidebar-secondary-item">
|
||
<div class="page-toc tocsection onthispage">
|
||
<i class="fa-solid fa-list"></i> Contents
|
||
</div>
|
||
<nav class="bd-toc-nav page-toc">
|
||
<ul class="visible nav section-nav flex-column">
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#image-to-latex-conversion">Image to LaTeX Conversion</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#texteller.api.img2latex"><code class="docutils literal notranslate"><span class="pre">img2latex()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#paragraph-to-markdown-conversion">Paragraph to Markdown Conversion</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#texteller.api.paragraph2md"><code class="docutils literal notranslate"><span class="pre">paragraph2md()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#latex-detection">LaTeX Detection</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#texteller.api.detection.latex_detect"><code class="docutils literal notranslate"><span class="pre">latex_detect()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#model-loading">Model Loading</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#texteller.api.load_model"><code class="docutils literal notranslate"><span class="pre">load_model()</span></code></a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#texteller.api.load_tokenizer"><code class="docutils literal notranslate"><span class="pre">load_tokenizer()</span></code></a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#texteller.api.load_latexdet_model"><code class="docutils literal notranslate"><span class="pre">load_latexdet_model()</span></code></a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#texteller.api.load_textdet_model"><code class="docutils literal notranslate"><span class="pre">load_textdet_model()</span></code></a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#texteller.api.load_textrec_model"><code class="docutils literal notranslate"><span class="pre">load_textrec_model()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#katex-conversion">KaTeX Conversion</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#texteller.api.to_katex"><code class="docutils literal notranslate"><span class="pre">to_katex()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</nav></div>
|
||
|
||
</div></div>
|
||
|
||
|
||
</div>
|
||
<footer class="bd-footer-content">
|
||
|
||
<div class="bd-footer-content__inner container">
|
||
|
||
<div class="footer-item">
|
||
|
||
<p class="component-author">
|
||
By TexTeller Team
|
||
</p>
|
||
|
||
</div>
|
||
|
||
<div class="footer-item">
|
||
|
||
|
||
<p class="copyright">
|
||
|
||
© Copyright 2025, TexTeller Team.
|
||
<br/>
|
||
|
||
</p>
|
||
|
||
</div>
|
||
|
||
<div class="footer-item">
|
||
|
||
</div>
|
||
|
||
<div class="footer-item">
|
||
|
||
</div>
|
||
|
||
</div>
|
||
</footer>
|
||
|
||
|
||
</main>
|
||
</div>
|
||
</div>
|
||
|
||
<!-- Scripts loaded after <body> so the DOM is not blocked -->
|
||
<script src="_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
|
||
<script src="_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
|
||
|
||
<footer class="bd-footer">
|
||
</footer>
|
||
</body>
|
||
</html> |