mirror of
https://github.com/langflow-ai/langflow.git
synced 2026-07-24 11:47:11 +08:00
85 lines
32 KiB
HTML
85 lines
32 KiB
HTML
<!doctype html>
|
||
<html lang="en" dir="ltr" class="docs-wrapper plugin-docs plugin-id-default docs-version-current docs-doc-page docs-doc-id-Integrations/Docling/integrations-docling" data-has-hydrated="false">
|
||
<head>
|
||
<meta charset="UTF-8">
|
||
<meta name="generator" content="Docusaurus v3.8.1">
|
||
<title data-rh="true">Integrate Docling with Langflow | Langflow Documentation</title><meta data-rh="true" name="viewport" content="width=device-width,initial-scale=1"><meta data-rh="true" name="twitter:card" content="summary_large_image"><meta data-rh="true" property="og:url" content="https://docs.langflow.org/integrations-docling"><meta data-rh="true" property="og:locale" content="en"><meta data-rh="true" name="docusaurus_locale" content="en"><meta data-rh="true" name="docsearch:language" content="en"><meta data-rh="true" name="docusaurus_version" content="current"><meta data-rh="true" name="docusaurus_tag" content="docs-default-current"><meta data-rh="true" name="docsearch:version" content="current"><meta data-rh="true" name="docsearch:docusaurus_tag" content="docs-default-current"><meta data-rh="true" property="og:title" content="Integrate Docling with Langflow | Langflow Documentation"><meta data-rh="true" name="description" content="Langflow integrates with Docling through a suite of components for parsing documents."><meta data-rh="true" property="og:description" content="Langflow integrates with Docling through a suite of components for parsing documents."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.langflow.org/integrations-docling"><link data-rh="true" rel="alternate" href="https://docs.langflow.org/integrations-docling" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.langflow.org/integrations-docling" hreflang="x-default"><link data-rh="true" rel="preconnect" href="https://UZK6BDPCVY-dsn.algolia.net" crossorigin="anonymous"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Docling","item":"https://docs.langflow.org/integrations-docling"}]}</script><link rel="preconnect" href="https://www.google-analytics.com">
|
||
<link rel="preconnect" href="https://www.googletagmanager.com">
|
||
<script async src="https://www.googletagmanager.com/gtag/js?id=G-SLQFLQ3KPT"></script>
|
||
<script>function gtag(){dataLayer.push(arguments)}window.dataLayer=window.dataLayer||[],gtag("js",new Date),gtag("config","G-SLQFLQ3KPT",{})</script>
|
||
|
||
|
||
|
||
|
||
|
||
<link rel="search" type="application/opensearchdescription+xml" title="Langflow Documentation" href="/opensearch.xml">
|
||
|
||
|
||
|
||
|
||
|
||
<link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=Sora:wght@550;600&display=swap">
|
||
<script>!function(){window.semaphore=window.semaphore||[],window.ketch=function(){window.semaphore.push(arguments)};var e=document.createElement("script");e.type="text/javascript",e.src="https://global.ketchcdn.com/web/v3/config/datastax/langflow_org_web/boot.js",e.defer=e.async=!0,document.getElementsByTagName("head")[0].appendChild(e)}()</script>
|
||
<script defer="true">!function(){const e=e=>{if(window.gtag&&e.purposes&&"analytics"in e.purposes&&"targeted_advertising"in e.purposes){const n=!0===e.purposes.analytics?"granted":"denied",t=!0===e.purposes.targeted_advertising?"granted":"denied",a={analytics_storage:n,ad_personalization:t,ad_storage:t,ad_user_data:t};window.gtag("consent","update",a)}};window.ketch&&window.ketch("on","consent",e)}()</script><link rel="stylesheet" href="/assets/css/styles.530387df.css">
|
||
<script src="/assets/js/runtime~main.9b7f373f.js" defer="defer"></script>
|
||
<script src="/assets/js/main.9ab00253.js" defer="defer"></script>
|
||
</head>
|
||
<body class="navigation-with-keyboard">
|
||
<svg xmlns="http://www.w3.org/2000/svg" style="display: none;"><defs>
|
||
<symbol id="theme-svg-external-link" viewBox="0 0 24 24"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"/></symbol>
|
||
</defs></svg>
|
||
<script>!function(){var t=function(){try{return new URLSearchParams(window.location.search).get("docusaurus-theme")}catch(t){}}()||function(){try{return window.localStorage.getItem("theme")}catch(t){}}();document.documentElement.setAttribute("data-theme",t||(window.matchMedia("(prefers-color-scheme: dark)").matches?"dark":"light")),document.documentElement.setAttribute("data-theme-choice",t||"system")}(),function(){try{const c=new URLSearchParams(window.location.search).entries();for(var[t,e]of c)if(t.startsWith("docusaurus-data-")){var a=t.replace("docusaurus-data-","data-");document.documentElement.setAttribute(a,e)}}catch(t){}}()</script><div id="__docusaurus"><div role="region" aria-label="Skip to main content"><a class="skipToContent_fXgn" href="#__docusaurus_skipToContent_fallback">Skip to main content</a></div><nav aria-label="Main" class="theme-layout-navbar navbar navbar--fixed-top navbarHideable_m1mJ"><div class="navbar__inner"><div class="theme-layout-navbar-left navbar__items"><button aria-label="Toggle navigation bar" aria-expanded="false" class="navbar__toggle clean-btn" type="button"><svg width="30" height="30" viewBox="0 0 30 30" aria-hidden="true"><path stroke="currentColor" stroke-linecap="round" stroke-miterlimit="10" stroke-width="2" d="M4 7h22M4 15h22M4 23h22"></path></svg></button><a class="navbar__brand" href="/"><div class="navbar__logo"><img src="/img/lf-docs-light.svg" alt="Langflow" class="themedComponent_mlkZ themedComponent--light_NVdE"><img src="/img/lf-docs-dark.svg" alt="Langflow" class="themedComponent_mlkZ themedComponent--dark_xIcU"></div></a></div><div class="theme-layout-navbar-right navbar__items navbar__items--right"><a href="https://github.com/langflow-ai/langflow" target="_blank" class="navbar__item navbar__link header-github-link"></a><a href="https://twitter.com/langflow_ai" target="_blank" class="navbar__item navbar__link header-twitter-link"></a><a href="https://discord.gg/EqksyE2EX9" target="_blank" class="navbar__item navbar__link header-discord-link"></a><div class="toggle_vylO colorModeToggle_DEke"><button class="clean-btn toggleButton_gllP toggleButtonDisabled_aARS" type="button" disabled="" title="system mode" aria-label="Switch between dark and light mode (currently system mode)"><svg viewBox="0 0 24 24" width="24" height="24" aria-hidden="true" class="toggleIcon_g3eP lightToggleIcon_pyhR"><path fill="currentColor" d="M12,9c1.65,0,3,1.35,3,3s-1.35,3-3,3s-3-1.35-3-3S10.35,9,12,9 M12,7c-2.76,0-5,2.24-5,5s2.24,5,5,5s5-2.24,5-5 S14.76,7,12,7L12,7z M2,13l2,0c0.55,0,1-0.45,1-1s-0.45-1-1-1l-2,0c-0.55,0-1,0.45-1,1S1.45,13,2,13z M20,13l2,0c0.55,0,1-0.45,1-1 s-0.45-1-1-1l-2,0c-0.55,0-1,0.45-1,1S19.45,13,20,13z M11,2v2c0,0.55,0.45,1,1,1s1-0.45,1-1V2c0-0.55-0.45-1-1-1S11,1.45,11,2z M11,20v2c0,0.55,0.45,1,1,1s1-0.45,1-1v-2c0-0.55-0.45-1-1-1C11.45,19,11,19.45,11,20z M5.99,4.58c-0.39-0.39-1.03-0.39-1.41,0 c-0.39,0.39-0.39,1.03,0,1.41l1.06,1.06c0.39,0.39,1.03,0.39,1.41,0s0.39-1.03,0-1.41L5.99,4.58z M18.36,16.95 c-0.39-0.39-1.03-0.39-1.41,0c-0.39,0.39-0.39,1.03,0,1.41l1.06,1.06c0.39,0.39,1.03,0.39,1.41,0c0.39-0.39,0.39-1.03,0-1.41 L18.36,16.95z M19.42,5.99c0.39-0.39,0.39-1.03,0-1.41c-0.39-0.39-1.03-0.39-1.41,0l-1.06,1.06c-0.39,0.39-0.39,1.03,0,1.41 s1.03,0.39,1.41,0L19.42,5.99z M7.05,18.36c0.39-0.39,0.39-1.03,0-1.41c-0.39-0.39-1.03-0.39-1.41,0l-1.06,1.06 c-0.39,0.39-0.39,1.03,0,1.41s1.03,0.39,1.41,0L7.05,18.36z"></path></svg><svg viewBox="0 0 24 24" width="24" height="24" aria-hidden="true" class="toggleIcon_g3eP darkToggleIcon_wfgR"><path fill="currentColor" d="M9.37,5.51C9.19,6.15,9.1,6.82,9.1,7.5c0,4.08,3.32,7.4,7.4,7.4c0.68,0,1.35-0.09,1.99-0.27C17.45,17.19,14.93,19,12,19 c-3.86,0-7-3.14-7-7C5,9.07,6.81,6.55,9.37,5.51z M12,3c-4.97,0-9,4.03-9,9s4.03,9,9,9s9-4.03,9-9c0-0.46-0.04-0.92-0.1-1.36 c-0.98,1.37-2.58,2.26-4.4,2.26c-2.98,0-5.4-2.42-5.4-5.4c0-1.81,0.89-3.42,2.26-4.4C12.92,3.04,12.46,3,12,3L12,3z"></path></svg><svg viewBox="0 0 24 24" width="24" height="24" aria-hidden="true" class="toggleIcon_g3eP systemToggleIcon_QzmC"><path fill="currentColor" d="m12 21c4.971 0 9-4.029 9-9s-4.029-9-9-9-9 4.029-9 9 4.029 9 9 9zm4.95-13.95c1.313 1.313 2.05 3.093 2.05 4.95s-0.738 3.637-2.05 4.95c-1.313 1.313-3.093 2.05-4.95 2.05v-14c1.857 0 3.637 0.737 4.95 2.05z"></path></svg></button></div><div class="navbarSearchContainer_Bca1"><button type="button" class="DocSearch DocSearch-Button" aria-label="Search (Command+K)"><span class="DocSearch-Button-Container"><svg width="20" height="20" class="DocSearch-Search-Icon" viewBox="0 0 20 20" aria-hidden="true"><path d="M14.386 14.386l4.0877 4.0877-4.0877-4.0877c-2.9418 2.9419-7.7115 2.9419-10.6533 0-2.9419-2.9418-2.9419-7.7115 0-10.6533 2.9418-2.9419 7.7115-2.9419 10.6533 0 2.9419 2.9418 2.9419 7.7115 0 10.6533z" stroke="currentColor" fill="none" fill-rule="evenodd" stroke-linecap="round" stroke-linejoin="round"></path></svg><span class="DocSearch-Button-Placeholder">Search</span></span><span class="DocSearch-Button-Keys"></span></button></div></div></div><div role="presentation" class="navbar-sidebar__backdrop"></div></nav><div id="__docusaurus_skipToContent_fallback" class="theme-layout-main main-wrapper mainWrapper_z2l0"><div class="docsWrapper_hBAB"><button aria-label="Scroll back to top" class="clean-btn theme-back-to-top-button backToTopButton_sjWU" type="button"></button><div class="docRoot_UBD9"><aside class="theme-doc-sidebar-container docSidebarContainer_YfHR"><div class="sidebarViewport_aRkj"><div class="sidebar_njMd sidebarWithHideableNavbar_wUlq"><a tabindex="-1" class="sidebarLogo_isFc" href="/"><img src="/img/lf-docs-light.svg" alt="Langflow" class="themedComponent_mlkZ themedComponent--light_NVdE"><img src="/img/lf-docs-dark.svg" alt="Langflow" class="themedComponent_mlkZ themedComponent--dark_xIcU"></a><nav aria-label="Docs sidebar" class="menu thin-scrollbar menu_SIkG"><ul class="theme-doc-sidebar-menu menu__list"><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/">Welcome to Langflow</a></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" role="button" aria-expanded="false" href="/about-langflow">Get started</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" role="button" aria-expanded="false" href="/basic-prompting">Templates</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" role="button" aria-expanded="false" href="/concepts-overview">Flows</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" role="button" aria-expanded="false" href="/concepts-components">Components</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" role="button" aria-expanded="false" href="/agents">Agents</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" role="button" aria-expanded="false" href="/mcp-server">Model Context Protocol (MCP)</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" role="button" aria-expanded="false" href="/configuration-api-keys">Configuration</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" role="button" aria-expanded="false" href="/develop-overview">Develop</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" role="button" aria-expanded="false" href="/deployment-overview">Deployment</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" role="button" aria-expanded="false" href="/api-reference-api-examples">API reference</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret menu__link--active" role="button" aria-expanded="true" href="/integrations-apify">Integrations</a></div><ul class="menu__list"><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/integrations-apify">Apify</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/integrations-arize">Arize</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/integrations-assemblyai">AssemblyAI</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/mcp-component-astra">Astra DB MCP server</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/integrations-cleanlab">Cleanlab</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/integrations-composio">Composio</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link menu__link--active" aria-current="page" tabindex="0" href="/integrations-docling">Docling</a></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-2 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" role="button" aria-expanded="false" tabindex="0" href="/integrations-setup-google-oauth-langflow">Google</a></div></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/integrations-langfuse">Langfuse</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/integrations-langsmith">LangSmith</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/integrations-langwatch">LangWatch</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/integrations-opik">Opik</a></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-2 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" role="button" aria-expanded="false" tabindex="0" href="/integrations/notion/setup">Notion</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-2 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" role="button" aria-expanded="false" tabindex="0" href="/integrations-nvidia-ingest">NVIDIA</a></div></li></ul></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" role="button" aria-expanded="false" href="/contributing-community">Contribute</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" role="button" aria-expanded="false" href="/release-notes">Release notes</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" role="button" aria-expanded="false" href="/troubleshoot">Support</a></div></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 sidebar-ad">
|
||
<a href="https://astra.datastax.com/signup?type=langflow" target="_blank" class="menu__link">
|
||
<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="1" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-cloud"><path d="M17.5 19H9a7 7 0 1 1 6.71-9h1.79a4.5 4.5 0 1 1 0 9Z"/></svg>
|
||
<div class="sidebar-ad-text-container">
|
||
<span class="sidebar-ad-text">Use Langflow in the cloud</span>
|
||
<span class="sidebar-ad-text sidebar-ad-text-gradient">Sign up for DataStax Langflow</span>
|
||
</div>
|
||
</a>
|
||
</li></ul></nav></div></div></aside><main class="docMainContainer_TBSr"><div class="container padding-top--md padding-bottom--lg"><div class="row"><div class="col docItemCol_VOVn"><div class="docItemContainer_Djhp"><article><nav class="theme-doc-breadcrumbs breadcrumbsContainer_Z_bl" aria-label="Breadcrumbs"><ul class="breadcrumbs"><li class="breadcrumbs__item"><a aria-label="Home page" class="breadcrumbs__link" href="/"><svg viewBox="0 0 24 24" class="breadcrumbHomeIcon_YNFT"><path d="M10 19v-5h4v5c0 .55.45 1 1 1h3c.55 0 1-.45 1-1v-7h1.7c.46 0 .68-.57.33-.87L12.67 3.6c-.38-.34-.96-.34-1.34 0l-8.36 7.53c-.34.3-.13.87.33.87H5v7c0 .55.45 1 1 1h3c.55 0 1-.45 1-1z" fill="currentColor"></path></svg></a></li><li class="breadcrumbs__item"><span class="breadcrumbs__link">Integrations</span></li><li class="breadcrumbs__item breadcrumbs__item--active"><span class="breadcrumbs__link">Docling</span></li></ul></nav><div class="tocCollapsible_ETCw theme-doc-toc-mobile tocMobile_ITEo"><button type="button" class="clean-btn tocCollapsibleButton_TO0P">On this page</button></div><div class="theme-doc-markdown markdown"><header><h1>Integrate Docling with Langflow</h1></header><p>Langflow integrates with <a href="https://docling-project.github.io/docling/" target="_blank" rel="noopener noreferrer">Docling</a> through a suite of components for parsing documents.</p>
|
||
<h2 class="anchor anchorWithHideOnScrollNavbar_WYt5" id="install-docling-dependency">Install Docling dependency<a href="#install-docling-dependency" class="hash-link" aria-label="Direct link to Install Docling dependency" title="Direct link to Install Docling dependency"></a></h2>
|
||
<ul>
|
||
<li>
|
||
<p>Install the Docling extra in Langflow OSS with <code>uv pip install langflow[docling]</code> or <code>uv pip install docling</code>.</p>
|
||
<p>To add a dependency to Langflow Desktop, add an entry for Docling to the application's <code>requirements.txt</code> file.
|
||
For more information, see <a href="/install-custom-dependencies#langflow-desktop">Install custom dependencies in Langflow Desktop</a>.</p>
|
||
</li>
|
||
</ul>
|
||
<h2 class="anchor anchorWithHideOnScrollNavbar_WYt5" id="use-docling-components-in-a-flow">Use Docling components in a flow<a href="#use-docling-components-in-a-flow" class="hash-link" aria-label="Direct link to Use Docling components in a flow" title="Direct link to Use Docling components in a flow"></a></h2>
|
||
<p>This example demonstrates how to use Docling components to split a PDF in a flow:</p>
|
||
<ol>
|
||
<li>Connect a <strong>Docling</strong> and an <strong>ExportDoclingDocument</strong> component to a <a href="/components-processing#split-text"><strong>Split Text</strong></a> component.
|
||
The <strong>Docling</strong> component loads the document, and the <strong>ExportDoclingDocument</strong> component converts the DoclingDocument into the format you select. This example converts the document to Markdown, with images represented as placeholders.
|
||
The <strong>Split Text</strong> component will split the Markdown into chunks for the vector database to store in the next part of the flow.</li>
|
||
<li>Connect a <a href="/components-vector-stores#chroma-db"><strong>Chroma DB</strong></a> component to the <strong>Split text</strong> component's <strong>Chunks</strong> output.</li>
|
||
<li>Connect an <a href="/components-embedding-models"><strong>Embedding Model</strong></a> to Chroma's <strong>Embedding</strong> port, and a <strong>Chat Output</strong> component to view the extracted <a href="/concepts-objects#dataframe-object">DataFrame</a>.</li>
|
||
<li>Add your OpenAI API key to the Embedding Model.</li>
|
||
</ol>
|
||
<p>The flow looks like this:</p>
|
||
<p><img decoding="async" loading="lazy" alt="Docling and ExportDoclingDocument extracting and splitting text to vector database" src="/assets/images/integrations-docling-split-text-7dfa4c618be68f4559ce6247630dbdf1.png" width="4000" height="2060" class="img_ev3q"></p>
|
||
<ol start="5">
|
||
<li>Add a file to the <strong>Docling</strong> component.</li>
|
||
<li>To run the flow, click <svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-play" aria-hidden="true"><polygon points="6 3 20 12 6 21 6 3"></polygon></svg> <strong>Playground</strong>.
|
||
The chunked document is loaded as vectors into your vector database.</li>
|
||
</ol>
|
||
<h2 class="anchor anchorWithHideOnScrollNavbar_WYt5" id="docling-components">Docling components<a href="#docling-components" class="hash-link" aria-label="Direct link to Docling components" title="Direct link to Docling components"></a></h2>
|
||
<p>The following sections describe the purpose and configuration options for each component in the Docling bundle.</p>
|
||
<h3 class="anchor anchorWithHideOnScrollNavbar_WYt5" id="docling">Docling<a href="#docling" class="hash-link" aria-label="Direct link to Docling" title="Direct link to Docling"></a></h3>
|
||
<p>This component uses Docling to process input documents running the Docling models locally.</p>
|
||
<details class="details_lb9f alert alert--info details_b_Ee" data-collapsed="true"><summary>Parameters</summary><div><div class="collapsibleContent_i85q"><p><strong>Inputs</strong></p><table><thead><tr><th>Name</th><th>Type</th><th>Description</th></tr></thead><tbody><tr><td>files</td><td>File</td><td>The files to process.</td></tr><tr><td>pipeline</td><td>String</td><td>Docling pipeline to use (standard, vlm).</td></tr><tr><td>ocr_engine</td><td>String</td><td>OCR engine to use (easyocr, tesserocr, rapidocr, ocrmac).</td></tr></tbody></table><p><strong>Outputs</strong></p><table><thead><tr><th>Name</th><th>Type</th><th>Description</th></tr></thead><tbody><tr><td>files</td><td>File</td><td>The processed files with DoclingDocument data.</td></tr></tbody></table></div></div></details>
|
||
<h3 class="anchor anchorWithHideOnScrollNavbar_WYt5" id="docling-serve">Docling Serve<a href="#docling-serve" class="hash-link" aria-label="Direct link to Docling Serve" title="Direct link to Docling Serve"></a></h3>
|
||
<p>This component uses Docling to process input documents connecting to your instance of Docling Serve.</p>
|
||
<details class="details_lb9f alert alert--info details_b_Ee" data-collapsed="true"><summary>Parameters</summary><div><div class="collapsibleContent_i85q"><p><strong>Inputs</strong></p><table><thead><tr><th>Name</th><th>Type</th><th>Description</th></tr></thead><tbody><tr><td>files</td><td>File</td><td>The files to process.</td></tr><tr><td>api_url</td><td>String</td><td>URL of the Docling Serve instance.</td></tr><tr><td>max_concurrency</td><td>Integer</td><td>Maximum number of concurrent requests for the server.</td></tr><tr><td>max_poll_timeout</td><td>Float</td><td>Maximum waiting time for the document conversion to complete.</td></tr><tr><td>api_headers</td><td>Dict</td><td>Optional dictionary of additional headers required for connecting to Docling Serve.</td></tr><tr><td>docling_serve_opts</td><td>Dict</td><td>Optional dictionary of additional options for Docling Serve.</td></tr></tbody></table><p><strong>Outputs</strong></p><table><thead><tr><th>Name</th><th>Type</th><th>Description</th></tr></thead><tbody><tr><td>files</td><td>File</td><td>The processed files with DoclingDocument data.</td></tr></tbody></table></div></div></details>
|
||
<h3 class="anchor anchorWithHideOnScrollNavbar_WYt5" id="chunk-doclingdocument">Chunk DoclingDocument<a href="#chunk-doclingdocument" class="hash-link" aria-label="Direct link to Chunk DoclingDocument" title="Direct link to Chunk DoclingDocument"></a></h3>
|
||
<p>This component uses the DoclingDocument chunkers to split a document into chunks.</p>
|
||
<details class="details_lb9f alert alert--info details_b_Ee" data-collapsed="true"><summary>Parameters</summary><div><div class="collapsibleContent_i85q"><p><strong>Inputs</strong></p><table><thead><tr><th>Name</th><th>Type</th><th>Description</th></tr></thead><tbody><tr><td>data_inputs</td><td>Data/DataFrame</td><td>The data with documents to split in chunks.</td></tr><tr><td>chunker</td><td>String</td><td>Which chunker to use (HybridChunker, HierarchicalChunker).</td></tr><tr><td>provider</td><td>String</td><td>Which tokenizer provider (Hugging Face, OpenAI).</td></tr><tr><td>hf_model_name</td><td>String</td><td>Model name of the tokenizer to use with the HybridChunker when Hugging Face is chosen.</td></tr><tr><td>openai_model_name</td><td>String</td><td>Model name of the tokenizer to use with the HybridChunker when OpenAI is chosen.</td></tr><tr><td>max_tokens</td><td>Integer</td><td>Maximum number of tokens for the HybridChunker.</td></tr><tr><td>doc_key</td><td>String</td><td>The key to use for the DoclingDocument column.</td></tr></tbody></table><p><strong>Outputs</strong></p><table><thead><tr><th>Name</th><th>Type</th><th>Description</th></tr></thead><tbody><tr><td>dataframe</td><td>DataFrame</td><td>The chunked documents as a DataFrame.</td></tr></tbody></table></div></div></details>
|
||
<h3 class="anchor anchorWithHideOnScrollNavbar_WYt5" id="export-doclingdocument">Export DoclingDocument<a href="#export-doclingdocument" class="hash-link" aria-label="Direct link to Export DoclingDocument" title="Direct link to Export DoclingDocument"></a></h3>
|
||
<p>This component exports DoclingDocument to Markdown, HTML, and other formats.</p>
|
||
<details class="details_lb9f alert alert--info details_b_Ee" data-collapsed="true"><summary>Parameters</summary><div><div class="collapsibleContent_i85q"><p><strong>Inputs</strong></p><table><thead><tr><th>Name</th><th>Type</th><th>Description</th></tr></thead><tbody><tr><td>data_inputs</td><td>Data/DataFrame</td><td>The data with documents to export.</td></tr><tr><td>export_format</td><td>String</td><td>Select the export format to convert the input (Markdown, HTML, Plaintext, DocTags).</td></tr><tr><td>image_mode</td><td>String</td><td>Specify how images are exported in the output (placeholder, embedded).</td></tr><tr><td>md_image_placeholder</td><td>String</td><td>Specify the image placeholder for markdown exports.</td></tr><tr><td>md_page_break_placeholder</td><td>String</td><td>Add this placeholder between pages in the markdown output.</td></tr><tr><td>doc_key</td><td>String</td><td>The key to use for the DoclingDocument column.</td></tr></tbody></table><p><strong>Outputs</strong></p><table><thead><tr><th>Name</th><th>Type</th><th>Description</th></tr></thead><tbody><tr><td>data</td><td>Data</td><td>The exported data.</td></tr><tr><td>dataframe</td><td>DataFrame</td><td>The exported data as a DataFrame.</td></tr></tbody></table></div></div></details>
|
||
<h2 class="anchor anchorWithHideOnScrollNavbar_WYt5" id="docling-video-tutorial">Docling video tutorial<a href="#docling-video-tutorial" class="hash-link" aria-label="Direct link to Docling video tutorial" title="Direct link to Docling video tutorial"></a></h2>
|
||
<p>To learn more about content extraction with Docling, see the video tutorial <a href="https://www.youtube.com/watch?v=5DuS6uRI5OM" target="_blank" rel="noopener noreferrer">Docling + Langflow: Document Processing for AI Workflows</a>.</p></div></article><nav class="docusaurus-mt-lg pagination-nav" aria-label="Docs pages"><a class="pagination-nav__link pagination-nav__link--prev" href="/integrations-composio"><div class="pagination-nav__sublabel">Previous</div><div class="pagination-nav__label">Composio</div></a><a class="pagination-nav__link pagination-nav__link--next" href="/integrations-setup-google-oauth-langflow"><div class="pagination-nav__sublabel">Next</div><div class="pagination-nav__label">Integrate Google OAuth with Langflow</div></a></nav></div></div><div class="col col--3"><div class="tableOfContents_bqdL thin-scrollbar theme-doc-toc-desktop"><ul class="table-of-contents table-of-contents__left-border"><li><a href="#install-docling-dependency" class="table-of-contents__link toc-highlight">Install Docling dependency</a></li><li><a href="#use-docling-components-in-a-flow" class="table-of-contents__link toc-highlight">Use Docling components in a flow</a></li><li><a href="#docling-components" class="table-of-contents__link toc-highlight">Docling components</a><ul><li><a href="#docling" class="table-of-contents__link toc-highlight">Docling</a></li><li><a href="#docling-serve" class="table-of-contents__link toc-highlight">Docling Serve</a></li><li><a href="#chunk-doclingdocument" class="table-of-contents__link toc-highlight">Chunk DoclingDocument</a></li><li><a href="#export-doclingdocument" class="table-of-contents__link toc-highlight">Export DoclingDocument</a></li></ul></li><li><a href="#docling-video-tutorial" class="table-of-contents__link toc-highlight">Docling video tutorial</a></li></ul></div></div></div></div></main></div></div></div><footer class="theme-layout-footer footer"><div class="container container-fluid"><div class="row footer__links"><div class="theme-layout-footer-column col footer__col"><div class="footer__title"></div><ul class="footer__items clean-list"><li class="footer__item"><div class="footer-links">
|
||
<span>© 2025 Langflow</span>
|
||
<span id="preferenceCenterContainer"> · <a href="https://langflow.org/preferences">Manage Privacy Choices</a></span>
|
||
</div></li></ul></div></div><div class="footer__bottom text--center"><div class="margin-bottom--sm"><img src="/img/lf-docs-light.svg" alt="Langflow" class="footer__logo themedComponent_mlkZ themedComponent--light_NVdE" width="160" height="40"><img src="/img/lf-docs-dark.svg" alt="Langflow" class="footer__logo themedComponent_mlkZ themedComponent--dark_xIcU" width="160" height="40"></div></div></div></footer><div style="position:fixed;right:20px;bottom:20px;z-index:100;display:flex;align-items:center;gap:10px;cursor:pointer"><div style="background-color:#f6f6f6;border-radius:50%;width:48px;height:48px;display:flex;align-items:center;justify-content:center;box-shadow:0 2px 4px rgba(0,0,0,0.1)"><img src="/img/langflow-icon-black-transparent.svg" style="width:40px" alt="Search"></div></div></div>
|
||
</body>
|
||
</html> |