Docling
Top pickIBM's document converter. Layout-aware PDF to clean Markdown, MIT.
94
sovereigntyDocling parses PDFs, Office documents, images and HTML into a structured representation that preserves reading order, tables, figures and headings, then exports to Markdown or JSON. It uses purpose-trained layout and table models rather than heuristics, which is why it holds up on multi-column academic papers and financial statements where simpler extractors interleave columns into nonsense. It integrates directly with LlamaIndex and Haystack, is MIT licensed, and runs entirely locally including on CPU.
OPEN SOURCEMITSELF-HOSTLOCAL-FIRST
LicenseMIT
PricingFree, MIT. Runs on your own hardware, CPU or GPU.
Open sourceYes
Self-hostableYes
Local-first dataYes
What it does well
- +Layout-aware — preserves reading order, tables and structure
- +Outputs clean Markdown/JSON that drops into a RAG pipeline
- +Direct integrations with LlamaIndex and Haystack
- +MIT, fully local, no per-page cost
Where it falls short
- −Slower per page than cloud OCR on very large batches
- −Handwriting support is weak compared with Textract
- −No specialised invoice or receipt models
Docling as an alternative to
Where Docling shows up in our comparisons, and how it ranked.
Docling head-to-head
Straight comparisons against the tools people weigh it against.