opendataloader-project/opendataloader-pdf

OpenDataLoader PDF is a multi-language toolkit for extracting and converting PDF documents into structured formats like JSON, Markdown, and HTML. It provides a Java core library featuring hybrid processing that routes complex pages to external AI backends for enhanced parsing, alongside standard extraction pipelines. The system is distributed via Python, Node.js, and MCP server wrappers, enabling programmatic and CLI-based document processing with robust error handling and testing.

The project underwent a major architectural shift, migrating to a multi-module Java build and introducing a comprehensive public API for PDF processing and auto-tagging. This period saw the introduction of new output formats (HTML, Markdown), a hybrid processing mode with AI backend support, and the release of standalone packages for Python and Node.js alongside the existing Java core.

29 changes

This period focused on integrating external AI backends for PDF processing, introducing a hybrid mode that routes pages to services like Docling and Hancom. The team also expanded the project's tooling ecosystem by adding an MCP server, agent skills, and a CLI API, while significantly increasing test coverage for these new features and existing components.

16 changes

opendataloader-project/opendataloader-pdf was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point the surveyor at a repository you know and see whether you agree with it.