Opendataloader pdf

Skill matematicsolutions/awesome-matematic-skills-pl/dokumenty/skills/opendataloader-pdf

Polish hub of legal-AI skills - 41 skills in 8 Claude Code / Cowork bundles (LLM output verification, PL/EU case law, DOCX redline, AI Act audit bundle). GDPR-safe, vendor-neutral, MIT.

Install

npx -y skills add matematicsolutions/awesome-matematic-skills-pl --skill opendataloader-pdf

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Wysokiej jakości konwerter PDF→JSON/Markdown dla AI - zachowuje reading order, strukturę tabel, headings. Użyj gdy użytkownik mówi "wysoka jakość PDF", "papers naukowe PDF", "tabele z PDF", "opendataloader", "PDF z skomplikowaną strukturą", albo gdy MarkItDown daje słaby output. Główny konwerter PDF→MD w pipeline Konwerter/ w Obsidian Vault.

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.4 KB, 941 tokens by cl100k_base, as published. Nobody here has run it

OpenDataLoader PDF - PDF→JSON/MD (PL)

Java-based (Python wrapper) parser PDF najwyższej jakości dla AI. Benchmarki: NID (reading order), TEDS (tabele), MHS (headings). Używany w pipeline Konwerter/ w vault.

Instalacja (zrobione 2026-04-21)

python -m pip install --user opendataloader-pdf

Python 3.14, opendataloader-pdf 2.2.1. Wymaga Java 17+ (mamy Eclipse Adoptium JDK 17). CLI: python -m opendataloader_pdf albo opendataloader-pdf.exe ze Scripts/.

Wspierane outputy

JSON (pełna struktura - reading order, bounding boxes, tabele jako 2D arrays) - default
Markdown (flattened output, gotowy pod LLM)
HTML (opcjonalnie)

Użycie

CLI - pojedynczy PDF

python -m opendataloader_pdf --input plik.pdf --output output/ --format md

Batch (Obsidian Vault, pipeline Konwerter)

python -m opendataloader_pdf \
  --input "%USERPROFILE%/Documents/Obsidian Vault/wszystko co wpada szybko/" \
  --output "%USERPROFILE%/Documents/Obsidian Vault/Konwerter/" \
  --format md \
  --recursive

Zaawansowane flagi

--enrich-formula - wyciąga formuły LaTeX
--enrich-picture-description - opis obrazów (wymaga --hybrid-mode full)
--filter-hidden-text - wykrywa ukryty tekst (off by default, per-page rendering)

Python API

import opendataloader_pdf
result = opendataloader_pdf.load("plik.pdf", output_format="markdown")
print(result.markdown)

Kiedy użyć vs MarkItDown

PDF	Narzędzie
Prosty, tekst liniowy (blog, artykuł prasowy)	MarkItDown (szybsze)
Papers naukowe, raporty z tabelami	OpenDataLoader (jakość)
Dokumenty z 2-kolumnowym layoutem	OpenDataLoader (reading order)
Multi-page tabele	OpenDataLoader (TEDS)
Batch Konwerter/ (domyślnie)	OpenDataLoader

Integracja z vault

Pipeline Konwerter (istnieje Python script w _vault-management/scripts/):

PDF wrzucone do wszystko co wpada szybko/ lub dropowane bezpośrednio
opendataloader-pdf --input <path> --format md --output Konwerter/
Frontmatter: type: source-pdf, tags: [pdf, zrodlo] - zgodnie z vault-rules.json → clippings.classification_rules.pdf_source
Powiązane oryginały PDF w folderze Konwerter/ lub Attachments

Gotcha

Java 17 wymagana - Adoptium JDK zainstalowana (/c/Program Files/Eclipse Adoptium/jdk-17.0.10.7-hotspot/)
Wolniejsze niż MarkItDown - nie używaj dla prostych PDFów
ForkJoinPool parallelism - per-page przetwarzanie równoległe, --filter-hidden-text wyłącza parallel
Przy zmianach CLI opcji w Java: npm run sync (dla kontrybutorów - nas nie dotyczy)

Zasady

Zawsze output do Konwerter/, nie nadpisuj oryginalnych PDF
Batch > 10 PDF → zapytaj Wiesława przed startem
Idempotencja: jeśli .md już istnieje w output i checksumma PDF nie zmieniona → skip

Gives 0 of the 12 instructions most pdf office docs skills give in 941 tokens

Counted across 635 of the 690 authors here whose files we hold, read 2026-08-06

extract text using pdfplumberin 92 of 635, across 25 files
create PDFs using reportlabin 83 of 635, across 16 files
read FORMS.md to fill out PDF formsin 80 of 635, across 13 files
OCR scanned PDFs using pytesseractin 77 of 635, across 10 files
merge or split PDFs using qpdfin 70 of 635, across 3 files
use Excel formulas instead of hardcoded calculated valuesin 68 of 635, across 12 files
unpack edit xml and repack existing documentsin 63 of 635, across 8 files
document sources for hardcoded valuesin 61 of 635, across 9 files
write minimal python code without unnecessary commentsin 59 of 635, across 7 files
run the recalculation script after adding or modifying formulasin 58 of 635, across 6 files
fix all identified formula errors and recalculatein 58 of 635, across 6 files
format years as text stringsin 57 of 635, across 5 files

Said here and by no other author read

use opendataloader for multi-page tables
use opendataloader for two-column layouts
use opendataloader for the batch conversion pipeline
use markitdown for simple linear PDFs
ask before processing batches over ten PDFs
skip if markdown exists and checksum matches

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.