I am working on Bulkparse at Bulkgrid. It’s an MIT-licensed Rust library that converts PDFs, Word documents, Excel spreadsheets, PowerPoint presentations and other popular formats into Markdown and structured JSON.

The focus is fast conversion, memory efficiency and preserving document structure. We did a 200 PDF benchmark, where Bulkparse processed the whole corpus in 0.440 seconds, 40% less conversion time than the next-fastest tested configuration. It achieved the highest reading-order, table and heading scores among the tested configurations, using only 169 MiB peak memory.

These measurements exclude startup and OCR. Although optional local OCR is available for scanned documents.

The conversion core runs locally without an API key or external parsing service. You can use it from Rust, Python, Node.js or WebAssembly, or try the CLI:

npx @bulkgrid/bulkparse parse document.docx 

I’d welcome feedback on the Rust API, integration experience, and documents that don’t convert well.

Bulkparse repository

1 post - 1 participant

Read full topic