docling-project /docling
Get your documents ready for gen AI
★ 70,615⑂ 5,357👁 221⑃ 2,433● 2,400▤ 240
TA的项目
+36
日增长
+300
周增长
+1,854
月增长
70,615
stars
5,357
forks
221
watchers
2,433
prs
2,400
issues
240
releases
README
Docling What is Docling ? Docling simplifies document processing by parsing diverse formats — including advanced PDF understanding — and providing seamless integrations with the generative AI ecosystem. Features - 🗂️ Parsing of [multiple document formats][supported_formats] including PDF, DOCX, PPTX, XLSX, HTML, EPUB, Apple Pages, Numbers & Keynote, WAV, MP3, WebVTT, Box Notes, email formats (EML, MSG), iCalendar (ICS), images (PNG, TIFF, JPEG, ...), LaTeX, DocLang, plain text, and more - 📑 Advanced PDF understanding incl. page layout, reading order, table structure, code, formulas, image classification, and more - 🧬 A unified, expressive [DoclingDocument][docling_document] representation format - ↪️ Various [export formats][supported_formats] and options, including Markdown, HTML, WebVTT, DocLang, DocTags and lossless JSON - 📜 Support for several application-specific XML schemas including DocLang, USPTO patents, JATS articles, and XBRL financial reports. - 🔒 Local execution capabilities for sensitive data and air-gapped environments - 🤖 Plug-and-play [integrations][integrations] incl. LangChain, LlamaIndex, Crew AI & Haystack for agentic AI - 🔍 Extensive OCR support for scanned PDFs and images - 👓 Support for several Visual Language Models, such as (GraniteDocling) - 🎙️ Audio support with Automatic Speech Recognition (ASR) models - 🔌 Connect to any agent using the MCP server - 🌐 Run Docling as a service with the API server (docling-serve) - 💻 Simple and convenient CLI What's new - 🎬 Parsing of video files (MP4, AVI, MOV, MKV, and WebM) with an ASR transcript and representative keyframes - 📄 Parsing of ODF (OpenDocument Format) files for text documents (.odt), spreadsheets (.ods), and presentations (.odp) - 💼 Parsing of XBRL (eXtensible Business Reporting Language) and iXBRL (Inline eXtensible Business Reporting Language) documents for financial reports - 📧 Parsing of email files (.eml, .msg), including meeting invitations - 📅 Parsing of calendar files (.ics, .ical, .icalendar, .ifb) with events, tasks, journal entries and free/busy times, with attendees, reminders and attachment names - 📚 Parsing of EPUB (Electronic Publication) files for e-books - 🍎 Parsing of Apple Pages (.pages) documents, Numbers (.numbers) spreadsheets and Keynote (.key) presentations - 📝 Parsing of plain-text files (.txt, .text) and Markdown supersets (.qmd, .Rmd) - 📊 Chart understanding (Barchart, Piechart, LinePlot): convert them into tables or code and add detailed descriptions Coming soon - 📝 Metadata extraction, including title, authors, references & language - 📝 Complex chemistry understanding (Molecular structures) Quickstart 1. Install bash pip install docling Note: Python 3.9 support was dropped in docling version 2.70.0. Please use Python 3.10 or higher. Works on macOS, Linux and Windows environments for both x86_64 and arm64 architectures. More detailed installation instructions are available in the docs. 2. Convert
Top issues
#3910Docling and llm granite-docling 258m (RockMan256) with LM Studio-0.4.2053 comments · 2026-07-29#287Identify table of contents for better chunking Hierarchy Identification44 comments · 2024-11-09#1023Export to markdown only contains H2 headers26 comments · 2025-02-19#2102Please add more descriptions on how to use VLM.23 comments · 2025-08-19#2779Docling consumes all available memory and gets killed19 comments · 2025-12-13#1111Convert PDF file error [RuntimeError: Invalid code point]18 comments · 2025-03-04#3201SIGABRT crash on Python 3.12 — all docling versions fail on Databricks Serverless17 comments · 2026-03-27#2186Using vision model for document conversion, clarity about picture and table enrichment16 comments · 2025-09-04
Discussions
#5336Visualizing Docling HybridChunker + contextualize() vs. Naive Splitters for pgvector Hybrid RRF0 comments · 2026-11-13#5334Chopper: a small open model that cuts only the needed sentences out of retrieved text0 comments · 2026-11-13#5251Attachments and embedded documents in Docling1 comments · 2026-11-09#5239Would Docling be a named pilot for an open tool that records why AI-generated code changed?0 comments · 2026-11-08#5093Proposal: alignment of independently converted document revisions0 comments · 2026-10-29#5074docmutant: real-document evidence for parser bugs, without sharing the document0 comments · 2026-10-28#5066Page numbers and bounding boxes for DOCX: filling `prov` in Docling's own output from a Word-compatible layout engine0 comments · 2026-10-28#4997Any suggestions for the best approach to read and extract from pdfs and in a great accuracy and low cost? A solution was about deploying gemma model on a rented gpu on amazon with jevv as router.. any recommendations ?4 comments · 2026-10-23
Latest release
v2.150.1 v2.150.1 2026-11-14Fix cli: Omit from_formats in convert-remote unless --from is set (5346) (ebc50e3) docx: Detect headings from paragraph-level w:outlineLvl (3312) (4129) (31d14a7) docx: Keep hyperlink targets in footnotes and endnotes (5322) (0c9a1cd) docx: Keep a single-cell table nested in a table cell inside the cell (5258) (b9bf356) docx: Close an open list before a table that follows it (5309) (fec4dc3) docx: Use default properties when an OMML element has none (5325) (8e210fb) Scale 16-bit images to 8 bits before converting them to RGB (5248) (293f620) ods: Compute sheet page size as bounding-bo
相关报道 (9)
bilibiliOffice 文档怎么喂给 AI?Docling 实测2026-04-23blog.csdn从文档到AI:docling一站式数据预处理流水线详解2026-01-05note【Githubの宝石シリーズ】Docling: 生成AI向けドキュメント処理を革新するオープンソースライブラリ2025-10-05blog.csdn【GitHub项目推荐--Docling:面向生成式AI的智能文档处理框架】2025-09-13IBMIBM Granite-Docling:通过一个微型模型实现端到端文档理解2025-10-0851CTORAG系列:MinerU、Docling还是Unstructured?用OmniDocBench评测开源文档解析工具2025-07-16智源社区SmolVLM2: 让视频理解能力触手可及2025-03-22智源社区6大RAG知识库PDF文档处理工具对比!2025-03-04凤凰网微软开源Markdown工具爆了:支持Office文档,可接多模态LLM直出报告2025-01-20
News & coverage (9)
Hacker NewsDocling-serve: Running Docling as an API service▲ 3 · 0 comments · 2025-09-01Hacker NewsDocling simplifies document processing, parsing diverse formats▲ 2 · 0 comments · 2025-09-08Hacker NewsDocling: Document Processing, Diverse Format Parsing, Advanced PDF Understanding▲ 2 · 0 comments · 2025-05-15Hacker NewsDocling - Composite file format▲ 1 · 0 comments · 2026-07-17Hacker NewsDocling - Get your documents ready for gen AI▲ 1 · 0 comments · 2025-12-14it-daily.netIBM macht Dokumente schlau: Granite-Docling verwandelt PDFs in KI-Futter2025-09-28dbta.comIBM Releases New Granite-Docling Model to Deliver End-to-End Document Understanding2025-09-21InfoWorldDocling: An open-source tool kit for advanced document processing2025-05-29MarkTechPostDatalab Lift vs the Field: How a 9B Schema-First Extractor Compares with NuExtract3, LlamaExtract, Marker, and Docling2026-07-09