Docling
Document parsing library by IBM for converting PDFs and documents to structured data.
About
Docling by IBM Research converts PDFs, DOCX, PPTX, and other formats into structured JSON or Markdown for LLM and RAG pipelines. It parses complex layouts, tables, figures, and equations, preserving reading order, and exposes a Python API built with Pydantic models. It runs on CPU and is part of the LF AI and Data Foundation. Released under the MIT license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- OCR & Document Processing
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- License
- MIT
- Added
- Apr 3, 2026
Related Tools
OCR tool specialized in recognizing mathematical equations and LaTeX.
One-stop tool for high-quality PDF extraction to Markdown or JSON.
Python bindings for MuPDF library for fast PDF text and image extraction.
Python library for extracting text, tables, and metadata from PDFs.
Multilingual document OCR toolkit with line detection and layout analysis.
Deep learning based OCR library in Python and TensorFlow/PyTorch.