StackMap
Subscribe

MinerU vs Unlimited-OCR

Heavyweight 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. — versus — Baidu's open OCR VLM that parses entire multi-page documents in one shot — 'unlimited' long-horizon parsing pushing DeepSeek-OCR further. MIT weights on HF; serve via transformers, vLLM or SGLang.

The curated verdict

Both turn documents into LLM-ready text: Unlimited-OCR is a one-shot long-horizon VLM; MinerU is a staged layout-analysis + OCR pipeline that also ingests Office formats.

MinerUUnlimited-OCR
Stars75k14k
Forks6.3k1.2k
LanguagePythonPython
LicenseNOASSERTIONMIT
Last activity2 days ago14 days ago
Topicsocr, ragocr, rag
Curated connections65

MinerU — the curator's take

The incumbent when document variety is the problem: beyond PDFs it handles Office formats, with mature layout analysis (reading order, tables, formulas) and a huge user base shaking out edge cases. NOT the lightest option — it's a full pipeline with model downloads and real hardware appetite; for a handful of clean PDFs a smaller tool is faster to stand up. Check the license (NOASSERTION on GitHub — AGPL-family, matters for commercial use).

Unlimited-OCR — the curator's take

The current bar if you batch-parse long PDFs: one-shot multi-page parsing keeps cross-page structure (tables spanning pages, running sections) that page-by-page OCR pipelines lose, and first-party vLLM/SGLang recipes plus official Docker images make serving unusually painless for a fresh research model. NOT a lightweight dependency — it's a GPU-hungry VLM; for occasional single pages classic OCR or a hosted API is cheaper. Inference-only repo: no training code, and evaluation beyond the paper's claims is on you.