Package profile
docling
- Summary: SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications.
- Author: Christoph Auer <cau@zurich.ibm.com>, Michele Dolfi <dol@zurich.ibm.com>, Maxim Lysak <mly@zurich.ibm.com>, Nikos Livathinos <nli@zurich.ibm.com>, Ahmed Nassar <ahn@zurich.ibm.com>, Panos Vagenas <pva@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>
- License: MIT
- Homepage: https://github.com/docling-project/docling
- Source: https://github.com/docling-project/docling
- Number of releases: 223
- First release: 0.1.0 on 2024-07-15
- Latest release: 2.135.0 on 2026-10-07
- Latest release size: 5.1 KB (pure Python wheel)
11 known vulnerabilitiesLatest: GHSA-3cr3-8m4c-fpxw — Docling: METS-GBS archive member limit enforced after full member enumeration (memory exhaustion during format detection) View all →
Dependencies
Docling has one dependency (non-optional).View all 1 dependencies →Dependent packages
| Package | Optional | Group |
|---|---|---|
| agno | true | docling |
| autogen | true | rag |
| crewai | true | docling |
| feast | true | docling |
Similar packages
- faceA command-line application framework (and CLI parser). Friendly for users, full-featured for developers.
- unstructuredA library that prepares raw documents for downstream ML tasks.
- docling-ibm-modelsThis package contains the AI models used by the Docling PDF conversion package
- mkdocstringsAutomatic documentation from sources, for MkDocs.
- semantic-kernelSemantic Kernel Python SDK
- spdx-toolsSPDX parser and tools.
- ibm-cos-sdk-coreLow-level, data-driven core of IBM SDK for Python