mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-27 20:44:16 +00:00
Code Issues Packages Projects Releases Wiki Activity
109e0a6311
docling/faq/index.html

3614 lines
75 KiB
HTML
Raw Blame History

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<link rel="canonical" href="https://docling-project.github.io/docling/faq/">
<link rel="prev" href="../usage/vision_models/">
<link rel="next" href="../concepts/">
<link rel="icon" href="../assets/logo.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.15">
<title>FAQ - Docling</title>
<link rel="stylesheet" href="../assets/stylesheets/main.342714a4.min.css">
<link rel="stylesheet" href="../assets/stylesheets/palette.06af60db.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
<link rel="stylesheet" href="../assets/_mkdocstrings.css">
<link rel="stylesheet" href="../stylesheets/extra.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="default" data-md-color-primary="black" data-md-color-accent="indigo">
<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="#faq" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<header class="md-header" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href=".." title="Docling" class="md-header__button md-logo" aria-label="Docling" data-md-component="logo">
<img src="../assets/logo.png" alt="logo">
</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">
Docling
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
FAQ
</span>
</div>
</div>
</div>
<form class="md-header__option" data-md-component="palette">
<input class="md-option" data-md-color-media="(prefers-color-scheme)" data-md-color-scheme="default" data-md-color-primary="black" data-md-color-accent="indigo" aria-label="Switch to light mode" type="radio" name="__palette" id="__palette_0">
<label class="md-header__button md-icon" title="Switch to light mode" for="__palette_1" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="m14.3 16-.7-2h-3.2l-.7 2H7.8L11 7h2l3.2 9zM20 8.69V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12zm-9.15 3.96h2.3L12 9z"/></svg>
</label>
<input class="md-option" data-md-color-media="(prefers-color-scheme: light)" data-md-color-scheme="default" data-md-color-primary="black" data-md-color-accent="indigo" aria-label="Switch to dark mode" type="radio" name="__palette" id="__palette_1">
<label class="md-header__button md-icon" title="Switch to dark mode" for="__palette_2" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a4 4 0 0 0-4 4 4 4 0 0 0 4 4 4 4 0 0 0 4-4 4 4 0 0 0-4-4m0 10a6 6 0 0 1-6-6 6 6 0 0 1 6-6 6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12z"/></svg>
</label>
<input class="md-option" data-md-color-media="(prefers-color-scheme: dark)" data-md-color-scheme="slate" data-md-color-primary="black" data-md-color-accent="indigo" aria-label="Switch to system preference" type="radio" name="__palette" id="__palette_2">
<label class="md-header__button md-icon" title="Switch to system preference" for="__palette_0" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 18c-.89 0-1.74-.2-2.5-.55C11.56 16.5 13 14.42 13 12s-1.44-4.5-3.5-5.45C10.26 6.2 11.11 6 12 6a6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12z"/></svg>
</label>
</form>
<script>var palette=__md_get("__palette");if(palette&&palette.color){if("(prefers-color-scheme)"===palette.color.media){var media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent")}for(var[key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
<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">
<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/docling-project/docling" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.7.2 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="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81"/></svg>
</div>
<div class="md-source__repository">
docling-project/docling
</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 md-tabs__item--active">
<a href=".." class="md-tabs__link">
Home
</a>
</li>
<li class="md-tabs__item">
<a href="../concepts/" class="md-tabs__link">
Concepts
</a>
</li>
<li class="md-tabs__item">
<a href="../examples/" class="md-tabs__link">
Examples
</a>
</li>
<li class="md-tabs__item">
<a href="../integrations/" class="md-tabs__link">
Integrations
</a>
</li>
<li class="md-tabs__item">
<a href="../reference/document_converter/" class="md-tabs__link">
Reference
</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="Docling" class="md-nav__button md-logo" aria-label="Docling" data-md-component="logo">
<img src="../assets/logo.png" alt="logo">
</a>
Docling
</label>
<div class="md-nav__source">
<a href="https://github.com/docling-project/docling" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.7.2 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="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81"/></svg>
</div>
<div class="md-source__repository">
docling-project/docling
</div>
</a>
</div>
<ul class="md-nav__list" data-md-scrollfix>
<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_1" checked>
<div class="md-nav__link md-nav__container">
<a href=".." class="md-nav__link ">
<span class="md-ellipsis">
Home
</span>
</a>
<label class="md-nav__link " for="__nav_1" id="__nav_1_label" tabindex="">
<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="true">
<label class="md-nav__title" for="__nav_1">
<span class="md-nav__icon md-icon"></span>
Home
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_1_2" >
<div class="md-nav__link md-nav__container">
<a href="../installation/" class="md-nav__link ">
<span class="md-ellipsis">
Installation
</span>
</a>
</div>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_1_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_1_2">
<span class="md-nav__icon md-icon"></span>
Installation
</label>
<ul class="md-nav__list" data-md-scrollfix>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_1_3" >
<div class="md-nav__link md-nav__container">
<a href="../usage/" class="md-nav__link ">
<span class="md-ellipsis">
Usage
</span>
</a>
<label class="md-nav__link " for="__nav_1_3" id="__nav_1_3_label" tabindex="">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_1_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_1_3">
<span class="md-nav__icon md-icon"></span>
Usage
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../usage/supported_formats/" class="md-nav__link">
<span class="md-ellipsis">
Supported formats
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../usage/enrichments/" class="md-nav__link">
<span class="md-ellipsis">
Enrichment features
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../usage/vision_models/" class="md-nav__link">
<span class="md-ellipsis">
Vision models
</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_1_4" checked>
<div class="md-nav__link md-nav__container">
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
FAQ
</span>
</a>
</div>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_1_4_label" aria-expanded="true">
<label class="md-nav__title" for="__nav_1_4">
<span class="md-nav__icon md-icon"></span>
FAQ
</label>
<ul class="md-nav__list" data-md-scrollfix>
</ul>
</nav>
</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="../concepts/" class="md-nav__link ">
<span class="md-ellipsis">
Concepts
</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>
Concepts
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../concepts/architecture/" class="md-nav__link">
<span class="md-ellipsis">
Architecture
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../concepts/docling_document/" class="md-nav__link">
<span class="md-ellipsis">
Docling Document
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../concepts/serialization/" class="md-nav__link">
<span class="md-ellipsis">
Serialization
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../concepts/confidence_scores/" class="md-nav__link">
<span class="md-ellipsis">
Confidence Scores
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../concepts/chunking/" class="md-nav__link">
<span class="md-ellipsis">
Chunking
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../concepts/plugins/" class="md-nav__link">
<span class="md-ellipsis">
Plugins
</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" >
<div class="md-nav__link md-nav__container">
<a href="../examples/" class="md-nav__link ">
<span class="md-ellipsis">
Examples
</span>
</a>
<label class="md-nav__link " for="__nav_3" id="__nav_3_label" tabindex="0">
<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="false">
<label class="md-nav__title" for="__nav_3">
<span class="md-nav__icon md-icon"></span>
Examples
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3_2" >
<label class="md-nav__link" for="__nav_3_2" id="__nav_3_2_label" tabindex="0">
<span class="md-ellipsis">
🔀 Conversion
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<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>
🔀 Conversion
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../examples/minimal/" class="md-nav__link">
<span class="md-ellipsis">
Simple conversion
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/custom_convert/" class="md-nav__link">
<span class="md-ellipsis">
Custom conversion
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/batch_convert/" class="md-nav__link">
<span class="md-ellipsis">
Batch conversion
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/run_with_formats/" class="md-nav__link">
<span class="md-ellipsis">
Multi-format conversion
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/minimal_vlm_pipeline/" class="md-nav__link">
<span class="md-ellipsis">
VLM pipeline with SmolDocling
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/vlm_pipeline_api_model/" class="md-nav__link">
<span class="md-ellipsis">
VLM pipeline with remote model
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/compare_vlm_models/" class="md-nav__link">
<span class="md-ellipsis">
Compare VLM models
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/minimal_asr_pipeline/" class="md-nav__link">
<span class="md-ellipsis">
ASR pipeline with Whisper
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/export_figures/" class="md-nav__link">
<span class="md-ellipsis">
Figure export
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/export_tables/" class="md-nav__link">
<span class="md-ellipsis">
Table export
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/export_multimodal/" class="md-nav__link">
<span class="md-ellipsis">
Multimodal export
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/full_page_ocr/" class="md-nav__link">
<span class="md-ellipsis">
Force full page OCR
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/tesseract_lang_detection/" class="md-nav__link">
<span class="md-ellipsis">
Automatic OCR language detection with tesseract
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/rapidocr_with_custom_models/" class="md-nav__link">
<span class="md-ellipsis">
RapidOCR with custom OCR models
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/run_with_accelerator/" class="md-nav__link">
<span class="md-ellipsis">
Accelerator options
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/translate/" class="md-nav__link">
<span class="md-ellipsis">
Simple translation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/backend_csv/" class="md-nav__link">
<span class="md-ellipsis">
Conversion of CSV files
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/backend_xml_rag/" class="md-nav__link">
<span class="md-ellipsis">
Conversion of custom XML
</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" >
<label class="md-nav__link" for="__nav_3_3" id="__nav_3_3_label" tabindex="0">
<span class="md-ellipsis">
✂️ Serialization & chunking
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<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>
✂️ Serialization & chunking
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../examples/serialization/" class="md-nav__link">
<span class="md-ellipsis">
Serialization
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/hybrid_chunking/" class="md-nav__link">
<span class="md-ellipsis">
Hybrid chunking
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/advanced_chunking_and_serialization/" class="md-nav__link">
<span class="md-ellipsis">
Advanced chunking &amp; serialization
</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_4" >
<label class="md-nav__link" for="__nav_3_4" id="__nav_3_4_label" tabindex="0">
<span class="md-ellipsis">
🤖 RAG with AI dev frameworks
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_3_4_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3_4">
<span class="md-nav__icon md-icon"></span>
🤖 RAG with AI dev frameworks
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../examples/rag_haystack/" class="md-nav__link">
<span class="md-ellipsis">
RAG with Haystack
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/rag_langchain/" class="md-nav__link">
<span class="md-ellipsis">
RAG with LangChain
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/rag_llamaindex/" class="md-nav__link">
<span class="md-ellipsis">
RAG with LlamaIndex
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/visual_grounding/" class="md-nav__link">
<span class="md-ellipsis">
Visual grounding
</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_5" >
<label class="md-nav__link" for="__nav_3_5" id="__nav_3_5_label" tabindex="0">
<span class="md-ellipsis">
🖼️ Picture annotation
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<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>
🖼️ Picture annotation
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../examples/pictures_description/" class="md-nav__link">
<span class="md-ellipsis">
Annotate picture with local VLM
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/pictures_description_api/" class="md-nav__link">
<span class="md-ellipsis">
Annotate picture with remote VLM
</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" >
<label class="md-nav__link" for="__nav_3_6" id="__nav_3_6_label" tabindex="0">
<span class="md-ellipsis">
✨ Enrichment development
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<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>
✨ Enrichment development
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../examples/develop_picture_enrichment/" class="md-nav__link">
<span class="md-ellipsis">
Figure enrichment
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/develop_formula_understanding/" class="md-nav__link">
<span class="md-ellipsis">
Formula enrichment
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/enrich_doclingdocument/" class="md-nav__link">
<span class="md-ellipsis">
Enrich DoclingDocument
</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" >
<label class="md-nav__link" for="__nav_3_7" id="__nav_3_7_label" tabindex="0">
<span class="md-ellipsis">
🗂️ More examples
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<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>
🗂️ More examples
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../examples/rag_milvus/" class="md-nav__link">
<span class="md-ellipsis">
RAG with Milvus
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/rag_weaviate/" class="md-nav__link">
<span class="md-ellipsis">
RAG with Weaviate
</span>
</a>
</li>
<li class="md-nav__item">
<a href="https://github.com/ibm-granite-community/granite-snack-cookbook/blob/main/recipes/RAG/Granite_Docling_RAG.ipynb" class="md-nav__link">
<span class="md-ellipsis">
RAG with Granite [↗]
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/rag_azuresearch/" class="md-nav__link">
<span class="md-ellipsis">
RAG with Azure AI Search
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../examples/retrieval_qdrant/" class="md-nav__link">
<span class="md-ellipsis">
Retrieval with Qdrant
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4" >
<div class="md-nav__link md-nav__container">
<a href="../integrations/" class="md-nav__link ">
<span class="md-ellipsis">
Integrations
</span>
</a>
<label class="md-nav__link " for="__nav_4" id="__nav_4_label" tabindex="0">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_4_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4">
<span class="md-nav__icon md-icon"></span>
Integrations
</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_4_2" >
<label class="md-nav__link" for="__nav_4_2" id="__nav_4_2_label" tabindex="0">
<span class="md-ellipsis">
🤖 Agentic / AI dev frameworks
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_4_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4_2">
<span class="md-nav__icon md-icon"></span>
🤖 Agentic / AI dev frameworks
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../integrations/bee/" class="md-nav__link">
<span class="md-ellipsis">
Bee Agent Framework
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../integrations/crewai/" class="md-nav__link">
<span class="md-ellipsis">
Crew AI
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../integrations/haystack/" class="md-nav__link">
<span class="md-ellipsis">
Haystack
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../integrations/langchain/" class="md-nav__link">
<span class="md-ellipsis">
LangChain
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../integrations/llamaindex/" class="md-nav__link">
<span class="md-ellipsis">
LlamaIndex
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../integrations/txtai/" class="md-nav__link">
<span class="md-ellipsis">
txtai
</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_4_3" >
<label class="md-nav__link" for="__nav_4_3" id="__nav_4_3_label" tabindex="0">
<span class="md-ellipsis">
⭐️ Featured
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_4_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4_3">
<span class="md-nav__icon md-icon"></span>
⭐️ Featured
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../integrations/apify/" class="md-nav__link">
<span class="md-ellipsis">
Apify
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../integrations/data_prep_kit/" class="md-nav__link">
<span class="md-ellipsis">
Data Prep Kit
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../integrations/instructlab/" class="md-nav__link">
<span class="md-ellipsis">
InstructLab
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../integrations/nvidia/" class="md-nav__link">
<span class="md-ellipsis">
NVIDIA
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../integrations/prodigy/" class="md-nav__link">
<span class="md-ellipsis">
Prodigy
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../integrations/rhel_ai/" class="md-nav__link">
<span class="md-ellipsis">
RHEL AI
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../integrations/spacy/" class="md-nav__link">
<span class="md-ellipsis">
spaCy
</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_4_4" >
<label class="md-nav__link" for="__nav_4_4" id="__nav_4_4_label" tabindex="0">
<span class="md-ellipsis">
🗂️ More integrations
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_4_4_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4_4">
<span class="md-nav__icon md-icon"></span>
🗂️ More integrations
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../integrations/cloudera/" class="md-nav__link">
<span class="md-ellipsis">
Cloudera
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../integrations/docetl/" class="md-nav__link">
<span class="md-ellipsis">
DocETL
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../integrations/kotaemon/" class="md-nav__link">
<span class="md-ellipsis">
Kotaemon
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../integrations/opencontracts/" class="md-nav__link">
<span class="md-ellipsis">
OpenContracts
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../integrations/openwebui/" class="md-nav__link">
<span class="md-ellipsis">
Open WebUI
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../integrations/vectara/" class="md-nav__link">
<span class="md-ellipsis">
Vectara
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_5" >
<label class="md-nav__link" for="__nav_5" id="__nav_5_label" tabindex="0">
<span class="md-ellipsis">
Reference
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_5_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_5">
<span class="md-nav__icon md-icon"></span>
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_5_1" >
<label class="md-nav__link" for="__nav_5_1" id="__nav_5_1_label" tabindex="0">
<span class="md-ellipsis">
Python API
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_5_1_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_5_1">
<span class="md-nav__icon md-icon"></span>
Python API
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../reference/document_converter/" class="md-nav__link">
<span class="md-ellipsis">
Document Converter
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../reference/pipeline_options/" class="md-nav__link">
<span class="md-ellipsis">
Pipeline options
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../reference/docling_document/" class="md-nav__link">
<span class="md-ellipsis">
Docling Document
</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_5_2" >
<label class="md-nav__link" for="__nav_5_2" id="__nav_5_2_label" tabindex="0">
<span class="md-ellipsis">
CLI
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_5_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_5_2">
<span class="md-nav__icon md-icon"></span>
CLI
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../reference/cli/" class="md-nav__link">
<span class="md-ellipsis">
CLI reference
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#is-python-313-supported" class="md-nav__link">
<span class="md-ellipsis">
Is Python 3.13 supported?
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#install-conflicts-with-numpy-python-313" class="md-nav__link">
<span class="md-ellipsis">
Install conflicts with numpy (python 3.13)
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#is-macos-x86_64-supported" class="md-nav__link">
<span class="md-ellipsis">
Is macOS x86_64 supported?
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#are-text-styles-bold-underline-etc-supported" class="md-nav__link">
<span class="md-ellipsis">
Are text styles (bold, underline, etc) supported?
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#how-do-i-run-completely-offline" class="md-nav__link">
<span class="md-ellipsis">
How do I run completely offline?
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#which-model-weights-are-needed-to-run-docling" class="md-nav__link">
<span class="md-ellipsis">
Which model weights are needed to run Docling?
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#ssl-error-downloading-model-weights" class="md-nav__link">
<span class="md-ellipsis">
SSL error downloading model weights
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#which-ocr-languages-are-supported" class="md-nav__link">
<span class="md-ellipsis">
Which OCR languages are supported?
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#some-images-are-missing-from-ms-word-and-powerpoint" class="md-nav__link">
<span class="md-ellipsis">
Some images are missing from MS Word and Powerpoint
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#hybridchunker-triggers-warning-token-indices-sequence-length-is-longer-than-the-specified-maximum-sequence-length-for-this-model" class="md-nav__link">
<span class="md-ellipsis">
HybridChunker triggers warning: 'Token indices sequence length is longer than the specified maximum sequence length for this model'
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#how-to-use-flash-attention" class="md-nav__link">
<span class="md-ellipsis">
How to use flash attention?
</span>
</a>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1 id="faq">FAQ</h1>
<p>This is a collection of FAQ collected from the user questions on <a href="https://github.com/docling-project/docling/discussions">https://github.com/docling-project/docling/discussions</a>.</p>
<details class="question">
<summary>Is Python 3.13 supported?</summary>
<h3 id="is-python-313-supported">Is Python 3.13 supported?</h3>
<p>Python 3.13 is supported from Docling 2.18.0.</p>
</details>
<details class="question">
<summary>Install conflicts with numpy (python 3.13)</summary>
<h3 id="install-conflicts-with-numpy-python-313">Install conflicts with numpy (python 3.13)</h3>
<p>When using <code>docling-ibm-models&gt;=2.0.7</code> and <code>deepsearch-glm&gt;=0.26.2</code> these issues should not show up anymore.
Docling supports numpy versions <code>&gt;=1.24.4,&lt;3.0.0</code> which should match all usages.</p>
<p><strong>For older versions</strong></p>
<p>This has been observed installing docling and langchain via poetry.</p>
<div class="highlight"><pre><span></span><code>...
Thus, docling (&gt;=2.7.0,&lt;3.0.0) requires numpy (&gt;=1.26.4,&lt;2.0.0).
So, because ... depends on both numpy (&gt;=2.0.2,&lt;3.0.0) and docling (^2.7.0), version solving failed.
</code></pre></div>
<p>Numpy is only adding Python 3.13 support starting in some 2.x.y version. In order to prepare for 3.13, Docling depends on a 2.x.y for 3.13, otherwise depending an 1.x.y version. If you are allowing 3.13 in your pyproject.toml, Poetry will try to find some way to reconcile Docling's numpy version for 3.13 (some 2.x.y) with LangChain's version for that (some 1.x.y) — leading to the error above.</p>
<p>Check if Python 3.13 is among the Python versions allowed by your pyproject.toml and if so, remove it and try again.
E.g., if you have python = "^3.10", use python = "&gt;=3.10,&lt;3.13" instead.</p>
<p>If you want to retain compatibility with python 3.9-3.13, you can also use a selector in pyproject.toml similar to the following</p>
<div class="highlight"><pre><span></span><code><span class="n">numpy</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">[</span>
<span class="w"> </span><span class="p">{</span><span class="w"> </span><span class="n">version</span><span class="w"> </span><span class="p">=</span><span class="w"> </span><span class="s2">&quot;^2.1.0&quot;</span><span class="p">,</span><span class="w"> </span><span class="n">markers</span><span class="w"> </span><span class="p">=</span><span class="w"> </span><span class="s1">&#39;python_version &gt;= &quot;3.13&quot;&#39;</span><span class="w"> </span><span class="p">},</span>
<span class="w"> </span><span class="p">{</span><span class="w"> </span><span class="n">version</span><span class="w"> </span><span class="p">=</span><span class="w"> </span><span class="s2">&quot;^1.24.4&quot;</span><span class="p">,</span><span class="w"> </span><span class="n">markers</span><span class="w"> </span><span class="p">=</span><span class="w"> </span><span class="s1">&#39;python_version &lt; &quot;3.13&quot;&#39;</span><span class="w"> </span><span class="p">},</span>
<span class="p">]</span>
</code></pre></div>
<p>Source: Issue <a href="https://github.com/docling-project/docling/issues/283#issuecomment-2465035868">#283</a></p>
</details>
<details class="question">
<summary>Is macOS x86_64 supported?</summary>
<h3 id="is-macos-x86_64-supported">Is macOS x86_64 supported?</h3>
<p>Yes, Docling (still) supports running the standard pipeline on macOS x86_64.</p>
<p>However, users might get into a combination of incompatible dependencies on a fresh install.
Because Docling depends on PyTorch which dropped support for macOS x86_64 after the 2.2.2 release,
and this old version of PyTorch works only with NumPy 1.x, users <strong>must</strong> ensure the correct NumPy version is running.</p>
<div class="highlight"><pre><span></span><code>pip<span class="w"> </span>install<span class="w"> </span>docling<span class="w"> </span><span class="s2">&quot;numpy&lt;2.0.0&quot;</span>
</code></pre></div>
<p>Source: Issue <a href="https://github.com/docling-project/docling/issues/1694">#1694</a>.</p>
</details>
<details class="question">
<summary>Are text styles (bold, underline, etc) supported?</summary>
<h3 id="are-text-styles-bold-underline-etc-supported">Are text styles (bold, underline, etc) supported?</h3>
<p>Currently text styles are not supported in the <code>DoclingDocument</code> format.
If you are interest in contributing this feature, please open a discussion topic to brainstorm on the design.</p>
<p><em>Note: this is not a simple topic</em></p>
</details>
<details class="question">
<summary>How do I run completely offline?</summary>
<h3 id="how-do-i-run-completely-offline">How do I run completely offline?</h3>
<p>Docling is not using any remote service, hence it can run in completely isolated air-gapped environments.</p>
<p>The only requirement is pointing the Docling runtime to the location where the model artifacts have been stored.</p>
<p>For example</p>
<div class="highlight"><pre><span></span><code><span class="n">pipeline_options</span> <span class="o">=</span> <span class="n">PdfPipelineOptions</span><span class="p">(</span><span class="n">artifacts_path</span><span class="o">=</span><span class="s2">&quot;your location&quot;</span><span class="p">)</span>
<span class="n">converter</span> <span class="o">=</span> <span class="n">DocumentConverter</span><span class="p">(</span>
<span class="n">format_options</span><span class="o">=</span><span class="p">{</span>
<span class="n">InputFormat</span><span class="o">.</span><span class="n">PDF</span><span class="p">:</span> <span class="n">PdfFormatOption</span><span class="p">(</span><span class="n">pipeline_options</span><span class="o">=</span><span class="n">pipeline_options</span><span class="p">)</span>
<span class="p">}</span>
<span class="p">)</span>
</code></pre></div>
<p>Source: Issue <a href="https://github.com/docling-project/docling/issues/326">#326</a></p>
</details>
<details class="question">
<summary> Which model weights are needed to run Docling?</summary>
<h3 id="which-model-weights-are-needed-to-run-docling">Which model weights are needed to run Docling?</h3>
<p>Model weights are needed for the AI models used in the PDF pipeline. Other document types (docx, pptx, etc) do not have any such requirement.</p>
<p>For processing PDF documents, Docling requires the model weights from <a href="https://huggingface.co/ds4sd/docling-models">https://huggingface.co/ds4sd/docling-models</a>.</p>
<p>When OCR is enabled, some engines also require model artifacts. For example EasyOCR, for which Docling has <a href="https://github.com/docling-project/docling/blob/main/docling/datamodel/pipeline_options.py#L68">special pipeline options</a> to control the runtime behavior.</p>
</details>
<details class="question">
<summary>SSL error downloading model weights</summary>
<h3 id="ssl-error-downloading-model-weights">SSL error downloading model weights</h3>
<div class="highlight"><pre><span></span><code>URLError: &lt;urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1000)&gt;
</code></pre></div>
<p>Similar SSL download errors have been observed by some users. This happens when model weights are fetched from Hugging Face.
The error could happen when the python environment doesn't have an up-to-date list of trusted certificates.</p>
<p>Possible solutions were</p>
<ul>
<li>Update to the latest version of <a href="https://pypi.org/project/certifi/">certifi</a>, i.e. <code>pip install --upgrade certifi</code></li>
<li>Use <a href="https://pypi.org/project/pip-system-certs/">pip-system-certs</a> to use the latest trusted certificates on your system.</li>
<li>Set environment variables <code>SSL_CERT_FILE</code> and <code>REQUESTS_CA_BUNDLE</code> to the value of <code>python -m certifi</code>:
<div class="highlight"><pre><span></span><code>CERT_PATH=$(python -m certifi)
export SSL_CERT_FILE=${CERT_PATH}
export REQUESTS_CA_BUNDLE=${CERT_PATH}
</code></pre></div></li>
</ul>
</details>
<details class="question">
<summary>Which OCR languages are supported?</summary>
<h3 id="which-ocr-languages-are-supported">Which OCR languages are supported?</h3>
<p>Docling supports multiple OCR engine, each one has its own list of supported languages.
Here is a collection of links to the original OCR engine's documentation listing the OCR languages.</p>
<ul>
<li><a href="https://www.jaided.ai/easyocr/">EasyOCR</a></li>
<li><a href="https://tesseract-ocr.github.io/tessdoc/Data-Files-in-different-versions.html">Tesseract</a></li>
<li><a href="https://rapidai.github.io/RapidOCRDocs/blog/2022/09/28/%E6%94%AF%E6%8C%81%E8%AF%86%E5%88%AB%E8%AF%AD%E8%A8%80/">RapidOCR</a></li>
<li><a href="https://github.com/straussmaximilian/ocrmac/tree/main?tab=readme-ov-file#example-select-language-preference">Mac OCR</a></li>
</ul>
<p>Setting the OCR language in Docling is done via the OCR pipeline options:</p>
<div class="highlight"><pre><span></span><code><span class="kn">from</span><span class="w"> </span><span class="nn">docling.datamodel.pipeline_options</span><span class="w"> </span><span class="kn">import</span> <span class="n">PdfPipelineOptions</span>
<span class="n">pipeline_options</span> <span class="o">=</span> <span class="n">PdfPipelineOptions</span><span class="p">()</span>
<span class="n">pipeline_options</span><span class="o">.</span><span class="n">ocr_options</span><span class="o">.</span><span class="n">lang</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;fr&quot;</span><span class="p">,</span> <span class="s2">&quot;de&quot;</span><span class="p">,</span> <span class="s2">&quot;es&quot;</span><span class="p">,</span> <span class="s2">&quot;en&quot;</span><span class="p">]</span> <span class="c1"># example of languages for EasyOCR</span>
</code></pre></div>
</details>
<details class="question">
<summary>Some images are missing from MS Word and Powerpoint</summary>
<h3 id="some-images-are-missing-from-ms-word-and-powerpoint">Some images are missing from MS Word and Powerpoint</h3>
<p>The image processing library used by Docling is able to handle embedded WMF images only on Windows platform.
If you are on other operating systems, these images will be ignored.</p>
</details>
<details class="question">
<summary><code>HybridChunker</code> triggers warning: 'Token indices sequence length is longer than the specified maximum sequence length for this model'</summary>
<h3 id="hybridchunker-triggers-warning-token-indices-sequence-length-is-longer-than-the-specified-maximum-sequence-length-for-this-model"><code>HybridChunker</code> triggers warning: 'Token indices sequence length is longer than the specified maximum sequence length for this model'</h3>
<p><strong>TLDR</strong>:
In the context of the <code>HybridChunker</code>, this is a known &amp; ancitipated "false alarm".</p>
<p><strong>Details</strong>:</p>
<p>Using the <a href="../concepts/chunking/#hybrid-chunker"><code>HybridChunker</code></a> often triggers a warning like this:</p>
<blockquote>
<p>Token indices sequence length is longer than the specified maximum sequence length for this model (531 &gt; 512). Running this sequence through the model will result in indexing errors</p>
</blockquote>
<p>This is a warning that is emitted by transformers, saying that actually <em>running this sequence through the model</em> will result in indexing errors, i.e. the problematic case is only if one indeed passes the particular sequence through the (embedding) model.</p>
<p>In our case though, this occurs as a "false alarm", since what happens is the following:</p>
<ul>
<li>the chunker invokes the tokenizer on a potentially long sequence (e.g. 530 tokens as mentioned in the warning) in order to count its tokens, i.e. to assess if it is short enough. At this point transformers already emits the warning above!</li>
<li>whenever the sequence at hand is oversized, the chunker proceeds to split it (but the transformers warning has already been shown nonetheless)</li>
</ul>
<p>What is important is the actual token length of the produced chunks.
The snippet below can be used for getting the actual maximum chunk size (for users wanting to confirm that this does not exceed the model limit):</p>
<div class="highlight"><pre><span></span><code><span class="n">chunk_max_len</span> <span class="o">=</span> <span class="mi">0</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">chunk</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">chunks</span><span class="p">):</span>
<span class="n">ser_txt</span> <span class="o">=</span> <span class="n">chunker</span><span class="o">.</span><span class="n">serialize</span><span class="p">(</span><span class="n">chunk</span><span class="o">=</span><span class="n">chunk</span><span class="p">)</span>
<span class="n">ser_tokens</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">tokenizer</span><span class="o">.</span><span class="n">tokenize</span><span class="p">(</span><span class="n">ser_txt</span><span class="p">))</span>
<span class="k">if</span> <span class="n">ser_tokens</span> <span class="o">&gt;</span> <span class="n">chunk_max_len</span><span class="p">:</span>
<span class="n">chunk_max_len</span> <span class="o">=</span> <span class="n">ser_tokens</span>
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="n">i</span><span class="si">}</span><span class="se">\t</span><span class="si">{</span><span class="n">ser_tokens</span><span class="si">}</span><span class="se">\t</span><span class="si">{</span><span class="nb">repr</span><span class="p">(</span><span class="n">ser_txt</span><span class="p">[:</span><span class="mi">100</span><span class="p">])</span><span class="si">}</span><span class="s2">...&quot;</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Longest chunk yielded: </span><span class="si">{</span><span class="n">chunk_max_len</span><span class="si">}</span><span class="s2"> tokens&quot;</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Model max length: </span><span class="si">{</span><span class="n">tokenizer</span><span class="o">.</span><span class="n">model_max_length</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
</code></pre></div>
<p>Also see <a href="https://github.com/docling-project/docling/issues/725">docling#725</a>.</p>
<p>Source: Issue <a href="https://github.com/docling-project/docling-core/issues/119">docling-core#119</a></p>
</details>
<details class="question">
<summary>How to use flash attention?</summary>
<h3 id="how-to-use-flash-attention">How to use flash attention?</h3>
<p>When running models in Docling on CUDA devices, you can enable the usage of the Flash Attention2 library.</p>
<p>Using environment variables:</p>
<div class="highlight"><pre><span></span><code>DOCLING_CUDA_USE_FLASH_ATTENTION2=1
</code></pre></div>
<p>Using code:</p>
<div class="highlight"><pre><span></span><code><span class="kn">from</span><span class="w"> </span><span class="nn">docling.datamodel.accelerator_options</span><span class="w"> </span><span class="kn">import</span> <span class="p">(</span>
<span class="n">AcceleratorOptions</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">pipeline_options</span> <span class="o">=</span> <span class="n">VlmPipelineOptions</span><span class="p">(</span>
<span class="n">accelerator_options</span><span class="o">=</span><span class="n">AcceleratorOptions</span><span class="p">(</span><span class="n">cuda_use_flash_attention2</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="p">)</span>
</code></pre></div>
<p>This requires having the <a href="https://pypi.org/project/flash-attn/">flash-attn</a> package installed. Below are two alternative ways for installing it:</p>
<div class="highlight"><pre><span></span><code><span class="c1"># Building from sources (required the CUDA dev environment)</span>
pip<span class="w"> </span>install<span class="w"> </span>flash-attn
<span class="c1"># Using pre-built wheels (not available in all possible setups)</span>
<span class="nv">FLASH_ATTENTION_SKIP_CUDA_BUILD</span><span class="o">=</span>TRUE<span class="w"> </span>pip<span class="w"> </span>install<span class="w"> </span>flash-attn
</code></pre></div>
</details>
</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" >
<a href="../usage/vision_models/" class="md-footer__link md-footer__link--prev" aria-label="Previous: Vision models">
<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">
<span class="md-footer__direction">
Previous
</span>
<div class="md-ellipsis">
Vision models
</div>
</div>
</a>
<a href="../concepts/" class="md-footer__link md-footer__link--next" aria-label="Next: Concepts">
<div class="md-footer__title">
<span class="md-footer__direction">
Next
</span>
<div class="md-ellipsis">
Concepts
</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>
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
Made with
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
Material for MkDocs
</a>
</div>
</div>
</div>
</footer>
</div>
<div class="md-dialog" data-md-component="dialog">
<div class="md-dialog__inner md-typeset"></div>
</div>
<div class="md-progress" data-md-component="progress" role="progressbar"></div>
<script id="__config" type="application/json">{"base": "..", "features": ["content.tabs.link", "content.code.annotate", "content.code.copy", "announce.dismiss", "navigation.footer", "navigation.tabs", "navigation.indexes", "navigation.instant", "navigation.instant.prefetch", "navigation.instant.progress", "navigation.path", "navigation.sections", "navigation.top", "navigation.tracking", "search.suggest", "toc.follow"], "search": "../assets/javascripts/workers/search.d50fe291.min.js", "tags": null, "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"}, "version": null}</script>
<script src="../assets/javascripts/bundle.56ea9cef.min.js"></script>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink