MinerUHeavyweight document-to-markdown/JSON parser — PDFs plus Office (docx/pptx/xlsx) through layout analysis and OCR into LLM-ready output for RAG and agentic pipelines. 73k stars, self-hostable.
Why switchSame heavyweight PDF-to-structured-data slot: MinerU throws ML layout analysis and OCR at everything; OpenDataLoader is deterministic-first with an optional hybrid AI mode — and beats it on extraction accuracy in its published bench at a fraction of the compute.
Full comparison → markerDatalab's 39k-star PDF-to-Markdown/JSON converter: a layout pipeline plus an optional LLM pass for tables, forms and equations, with chunk output and form-value extraction built in.
Why switchPick opendataloader-pdf when the corpus is born-digital and you want deterministic, model-free extraction with bounding boxes; marker when you accept model calls to recover tables, forms and math.
Full comparison → pdf-inspectorFirecrawl's Rust PDF triage: classifies text-based vs scanned in ~10-50ms, extracts positioned text and clean Markdown without OCR — routing the ~54% of PDFs that never needed a model.
Why switchKindred no-ML philosophy, different depth — pdf-inspector triages and extracts in 200ms; OpenDataLoader does full layout analysis with bounding boxes. Notably, pdf-inspector benchmarks itself on opendataloader-bench: same yardstick, acknowledged rivalry.
Full comparison → liteparseLlamaIndex's local document parser in Rust: PDFium text with bounding boxes at ~2-5 ms/page, selective Tesseract or HTTP OCR, Markdown/JSON output, screenshots; Python, Node, WASM.
Why switchBoth are deterministic local PDF parsers with bounding boxes on every element and no LLM; opendataloader-pdf leads its own accuracy bench and auto-tags for accessibility, LiteParse adds OCR routing and bindings for Python, Node and WASM.
Full comparison →