What it is
An open-source fork of Docling, a foundation created by IBM, focused on enhancing functionality and adding document-processing capabilities.
Open-source project
Convert documents into ready-to-use formats.
Docowling is a fork of Docling, an IBM project, developed to enhance functionality and add document-processing capabilities. Its SDK and CLI convert popular formats into a unified representation for downstream workflows, including generative AI applications.
Input formats
CSV, PDF, DOCX, PPTX, XLSX, images, HTML, AsciiDoc and Markdown, as listed in the official repository.
Outputs and representation
Exports to HTML, Markdown and JSON with embedded or referenced images, using the unified DoclingDocument format.
Integrations
The README lists ready-to-use integrations with LangChain, LlamaIndex, Crew AI and Haystack.
SDK and CLI
Use it through the Python SDK with DocumentConverter or through its CLI for batch processing and customizable export parameters.
Environments and license
Installable with pip or uv, it works on macOS, Linux and Windows across x86_64 and arm64, under the MIT license.
Verified from the source
This description follows the README and package configuration in the official repository. The project itself credits IBM for Docling, its foundation.
Let's talk
What software does your company need to build?
Bring a need, a process or a hypothesis. We help turn the context into a viable technical solution.