docling
SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications.
Decision gist · record as of 2026-08-14
Yes. Docling is actively maintained, production-stable, permissively licensed (MIT), and solves a real problem—unified parsing of many document formats with strong PDF understanding. Low install friction, no known vulnerabilities, and broad Python version support make it a solid choice for document-heavy AI and data extraction projects. Install if you need to parse or convert diverse document types at scale.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or higher (3.9 support was dropped in version 2.70.0).
- Active maintenance with a recent release (0 days since last update) and high repository engagement (64769 stars).
- Single runtime dependency (docling-slim) keeps install friction low.
License · maintenance · safety
MIT (permissive) — MIT license is permissive; you can use, modify, and distribute Docling freely in commercial and private projects with minimal restrictions.
last release 2026-08-14 (0 days) · last repo commit 2026-08-14 · 64,769 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 17,994,695 downloads/mo, #1,092 on PyPI
Alternatives
Verify before relying
pip install docling
from docling.document_converter import DocumentConverter
converter = DocumentConverter()
result = converter.convert("https://arxiv.org/pdf/2408.09869")
print(result.document.export_to_markdown())- Performance characteristics and memory footprint for large documents or batch processing.
- Whether all advertised export formats (DocTags, DocLang, JATS, XBRL) are production-ready or still experimental.
- Accuracy and reliability of OCR and Visual Language Model integrations in real-world deployments.
What it is and what it does
Docling is a document processing SDK that converts PDFs, Word documents, spreadsheets, presentations, email, images, video, audio, and other formats into a unified, structured representation. It specializes in advanced PDF understanding—extracting page layout, reading order, table structure, code blocks, formulas, and charts—and can export to Markdown, HTML, JSON, and domain-specific schemas (DocLang, USPTO patents, JATS articles, XBRL financial reports). The library runs locally, supports OCR for scanned documents, integrates with Visual Language Models and ASR systems, and plugs into AI frameworks like LangChain, LlamaIndex, and Haystack.
It is designed for developers building document-aware AI applications, knowledge extraction pipelines, and content processing workflows. The package offers both a Python API and a command-line interface, with options to run as a service via an API server or as an MCP server for agent integration.
Use it for
- Convert research papers or technical PDFs to structured Markdown for ingestion into RAG or LLM pipelines.
- Extract tables, charts, and text from financial reports (XBRL) or patent documents (USPTO) for automated analysis.
- Process scanned or image-based documents using OCR and Visual Language Models to recover structured content.
- Build document-aware chatbots or Q&A systems by parsing diverse input formats into a unified representation.
- Batch-convert email archives (EML, MSG) and office documents (DOCX, XLSX, PPTX) to Markdown or JSON for downstream workflows.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
Docling is actively maintained, production-stable, permissively licensed (MIT), and solves a real problem—unified parsing of many document formats with strong PDF understanding. Low install friction, no known vulnerabilities, and broad Python version support make it a solid choice for document-heavy AI and data extraction projects. Install if you need to parse or convert diverse document types at scale.
Install
docling on PyPI
Before you install
Active maintenance with a recent release (0 days since last update) and high repository engagement (64769 stars). Single runtime dependency (docling-slim) keeps install friction low. Supports current Python versions (3.10–3.14).
Requires Python 3.10 or higher (3.9 support was dropped in version 2.70.0).
License in practice
MIT license is permissive; you can use, modify, and distribute Docling freely in commercial and private projects with minimal restrictions.
Quickstart
pip install docling
from docling.document_converter import DocumentConverter
converter = DocumentConverter()
result = converter.convert("https://arxiv.org/pdf/2408.09869")
print(result.document.export_to_markdown())Verify before relying
- Performance characteristics and memory footprint for large documents or batch processing.
- Whether all advertised export formats (DocTags, DocLang, JATS, XBRL) are production-ready or still experimental.
- Accuracy and reliability of OCR and Visual Language Model integrations in real-world deployments.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release <4.0,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 1 packagedocling-slim |
| Maintenance | Actively maintained 0 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 17,994,695 / month, #1,092 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: DevelopersIntended Audience :: Science/ResearchOperating System :: MacOS :: MacOS XOperating System :: Microsoft :: WindowsOperating System :: POSIX :: LinuxProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: Scientific/Engineering :: Artificial Intelligence |
Evidence: docling-2.120.1-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “pdf parsing and conversion”
- doclingDocling parses diverse document formats—PDF, DOCX, PPTX, XLSX, HTML,…
- pdf-oxideExtracts text, images, and metadata from PDFs and converts them to…
- docling-parseExtracts text, coordinates, and bitmap images from programmatic PDFs…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also doclang · docling-core · docling-ibm-models · docling-parse · docling-slim · marker-pdf · mineru · langchain-docling · pdf2docx · pypandoc