Back: Catalog

docling

Docling is a Python library developed to process documents of different formats, such as PDF, DOCX, audio, and video files. It offers advanced PDF comprehension features such as page layout, table structure, and formula analysis. It can work locally and be integrated with various tools in the productive AI ecosystem.

DO

docling

100

docling-project · PDF & Document Processing

STARS69.9K
FORKS5.2K
COMMITS1.4K
CONTRIBUTORS300
VERSIONv2.126.0
UPDATEDtoday
PythonBelge İşlemePDF AyrıştırmaAIMIT

Common commercial products in this category: Adobe Acrobat, ABBYY FineReader, Foxit PDF Editor

What can it do?
  • You parse various document formats such as PDF, DOCX and visual.
  • You convert documents to Markdown, HTML or JSON formats.
  • You integrate with AI tools like LangChain and LlamaIndex.
Heads up
  • • High number of open issues (926)
User reviews
  • ↓ NegativeGitHub Issue

    Docling and llm granite-docling 258m (RockMan256) with LM Studio-0.4.20

    “### Bug Malheureusement, je ne suis pas en mesure de créer des issues GitHub directement. Mais voici une description de ticket prête à copier-coller pour ouvrir une issue sur le repo [docling]( : *** **Titre :** `AttributeError: 'NoneType' object has no attribute 'info'` during…”

  • • NeutralGitHub Issue

    Identify table of contents for better chunking Hierarchy Identification

    “Question I am working on a custom chunking method where I need to identify headings, subheadings, and child headings separately. Here's the detailed explanation: Current Issue: I am using Docling to tag headings in a PDF. Currently, all nested headings (subheadings and child…”

Website GitHub

Verified against README · Oct 26, 2026 · source

My note

Alternative pages

Adobe Acrobat alternativesABBYY FineReader alternativesFoxit PDF Editor alternatives

More in: PDF & Document Processing