MiSource available
MinerU
Turn complex papers and reports into structured content, including text, tables, and formulas.
Format Conversion & Document Databases
Docling
Convert PDF and Office files into a consistent document model for retrieval and data workflows.
DOCUMENTATION-BASED SELECTION
Why it is a Featured Tool
Its consistent document model is a useful entry point for teams converting mixed document formats before indexing or extraction.
Before you choose: Inspect structured JSON for provenance; validate OCR configuration and export fidelity on difficult pages.
See the shortlist and criteria →At a glance
- Input
- PDF, DOCX, PPTX, images
- Output
- Markdown, JSON, HTML
- Provenance
- Page and region provenance in the document model
- Scanned pages
- Requires an OCR backend
- Deployment
- Self-hosted
- Availability
- Open source
- Costs to plan for
- Compute and model costs
Limitations to check
The structured document model carries richer provenance than a plain Markdown export. Test your exact export path.
Build a meaningful sample
Include your hardest pages: low-quality scans, missing fields, dense tables, and evidence split across pages. Validate output correctness separately from citation accuracy.