chandraDatalab's SOTA open OCR model: images/PDFs to structured HTML/Markdown/JSON with layout, tables, forms, checkboxes, handwriting and math, in 90+ languages. Local HF or vLLM inference.
Why switchSame shop, two tiers: marker is the pipeline you run at volume with selective LLM assist, chandra is the vision-language model you reach for when accuracy on scans, handwriting and dense tables matters more than throughput.
Full comparison → 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 switchBoth convert PDF and Office files to LLM-ready Markdown/JSON. MinerU casts the wider format and pipeline net; marker is leaner to install, faster per page, and pushes hard blocks to an LLM of your choosing.
Full comparison → olmocrOpen toolkit that linearizes messy PDFs — scans, tables, equations, handwriting — into clean ordered Markdown with a self-hosted vision-language model. Built for LLM training data and RAG ingestion.
Why switcholmOCR runs one vision-language model over every page; marker runs layout analysis first and calls a model only where needed — cheaper at corpus scale, weaker on truly messy scans.
Full comparison → opendataloader-pdfDeterministic PDF parser for AI pipelines: #1 extraction accuracy (0.907) on its public bench, bounding boxes on every element, 0.015s/page — plus the first open PDF auto-tagging for accessibility.
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 →