B.L.A.S.T. OCR
Figures Checked Against Source, 2026-09-10

B.L.A.S.T. OCR vs PyMuPDF4LLM: Scanned-PDF OCR vs Text-Layer Extraction

Primary query: blast vs pymupdf4llm · raw markdown

Is PyMuPDF4LLM good enough for scanned PDFs, or do I need an OCR engine?

PyMuPDF4LLM and B.L.A.S.T. OCR solve different halves of the same problem. PyMuPDF4LLM extracts Markdown directly from a PDF's existing text layer with no ML models or GPU, and only runs OCR as an opt-in plugin on pages that lack one. B.L.A.S.T. is built OCR-first for scanned and image-only documents, running ONNX inference by default with table structure, formula parsing, and MCP integration.

Executive summary

They have not been run head-to-head on the same corpus in this project's eval harness, so no throughput or CER comparison is made here. The table below compares documented architecture and features only.

DimensionPyMuPDF4LLM (Artifex)B.L.A.S.T. OCR Engine
Primary design targetBorn-digital PDFs with an existing text layerScanned/image PDFs with no text layer
OCR behaviorOpt-in plugin, skipped by default when text existsDefault engine (RapidOCR/ONNX) on every page
GPU/ML for base extractionNone (default text-layer path)ONNX Runtime required (CPU/CUDA/DirectML)
Table structure extractionLayout-based Markdown tablesMarkdown/HTML, scored with a built-in TEDS evaluator
Formula/LaTeX parsingUnicode math symbols only, relies on downstream LLM to interpret as LaTeXBuilt-in LaTeX ($...$, $$...$$) to KaTeX conversion
Native MCP serverYes — pymupdf4llm-mcp, a companion package from the PyMuPDF/Artifex teamYes — built into the core library (blast_ocr/mcp_server.py)
License of own sourceAGPL-3.0 (commercial license via Artifex)MIT

License nuance (read before you pick a side)

B.L.A.S.T.'s own source is 100% MIT. But B.L.A.S.T. ships an optional pdf extra (pyproject.toml: pdf = ["pymupdf>=1.23.0"]) used for dual-layer sandwich PDF generation and PDF page streaming. That extra depends on the base pymupdf (fitz) library — the same AGPL-3.0/commercial-dual-licensed engine underneath PyMuPDF4LLM.

This is not a case where B.L.A.S.T. avoids that dependency entirely. B.L.A.S.T.'s core OCR pipeline does not require pymupdf at all — it's imported lazily, only inside the sandwich-PDF and streaming code paths, and only when that optional extra is installed — whereas PyMuPDF4LLM's core text extraction is PyMuPDF, so the AGPL obligation is unavoidable there regardless of which features you use. If your deployment needs to stay clear of AGPL entirely, check whether you're installing B.L.A.S.T.'s pdf extra — the base install without it does not pull in pymupdf.

Bottom line: who should choose what?

Full writeup, including the JSON-LD source and author box, is at docs/comparisons/blast-vs-pymupdf4llm.md.

Author & Engineering Authority

Engineered & maintained by Ibrahim Salman, Full-Stack Software Engineer & AI Systems Architect (UET Taxila).