opendataloader-project /opendataloader-pdf
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
★ 30,304⑂ 2,903👁 99⑃ 665● 248▤ 84
+5
日增长
30,304
stars
2,903
forks
99
watchers
665
prs
248
issues
84
releases
README
OpenDataLoader PDF
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
🔍 PDF parser for AI data extraction — Extract Markdown, JSON (with bounding boxes), and HTML from any PDF. 1 in benchmarks (0.907 overall). Deterministic local mode + AI hybrid mode for complex pages.
- How accurate is it? — 1 in benchmarks: 0.907 overall, 0.928 table accuracy across 200 real-world PDFs including multi-column and scientific papers. Deterministic local mode + AI hybrid mode for complex pages (benchmarks)
- Scanned PDFs and OCR? — Yes. Built-in OCR (80+ languages) in hybrid mode. Works with poor-quality scans at 300 DPI+ (hybrid mode)
- Tables, formulas, images, charts? — Yes. Complex/borderless tables, LaTeX formulas, and AI-generated picture/chart descriptions all via hybrid mode (hybrid mode)
- How do I use this for RAG? — pip install opendataloader-pdf, convert in 3 lines. Outputs structured Markdown for chunking, JSON with bounding boxes for source citations, and HTML. LangChain integration available. Python, Node.js, Java SDKs (quick start | LangChain)
♿ PDF accessibility automation — Auto-tag untagged PDFs into screen-reader-ready Tagged PDFs at scale. First open-source tool to generate Tagged PDFs end-to-end.
- What's the problem? — Accessibility regulations are now enforced worldwide. Manual PDF remediation costs $50–200 per document and doesn't scale (regulations)
- What's free? — Layout analysis + auto-tagging (Apache 2.0). Untagged PDF in → Tagged PDF out. No proprietary SDK dependency (auto-tagging)
- What about PDF/UA compliance? — Converting Tagged PDF to PDF/UA-1 or PDF/UA-2 is an enterprise add-on. Auto-tagging generates the Tagged PDF; PDF/UA export is the final step (pipeline)
- Why trust this? — Built in collaboration with Dual Lab (veraPDF developers) based on PDF Association specifications, best practice guides and expertise of the PDF Community. Auto-tagging follows the Well-Tagged PDF specification, validated with veraPDF (collaboration)
Get Started in 30 Seconds
Requires: Java 11+ and Python 3.11+ (Node.js | Java also available)
Before you start: run java -version. If not found, install JDK 11+ from Adoptium.
bash
pip install -U opendataloader-pdf
python
import opendataloader_pdf
Batch all files in one call — each convert() spawns a JVM process, so repeated calls are slow
opendataloader_pdf.convert(
input_path=["file1.pdf", "file2.pdf", "folder/"],
output_dir="output/",
format="markdown,json"
)
!OpenDataLoader PDF layout analysis — headings, tables, images detected with bounding boxes
Annotated PDF output — each element (heading, paragraph, table, image) detected with bounding boxes and semantic type.
What Problems Does This Solve?
| Problem | Solution | Status |
|---------|----------|--------|
| PDF structure lost during parsing — wrong reading order, broken tables, no element coordinates | Deterministic local PDF to Markdown/JSON with bounding boxes, XY-Cut++ reading order | STop issues
#652After upgrading to latest version 2.50 seeing issues in image extraction,extra grey scale image seen10 comments · 2026-07-24#767JSON output keeps U+0000 from a `<0000>` ToUnicode entry; every writer loses the glyph (Skia line-end hyphen)9 comments · 2026-10-06#463Inconsistent structural parsing (list vs paragraph) for similar financial tables8 comments · 2026-04-29#627Urgent - [Bug] Hybrid full mode collapses logical table rows and misaligns values4 comments · 2026-07-09#531Poor image extraction4 comments · 2026-05-21#451Error handling in opendataloader.convert3 comments · 2026-04-23#803Hybrid mode: text nested in Docling `groups` (key_value_area) is silently dropped from JSON/Markdown output2 comments · 2026-10-16#711Python/Node wrappers silently drop empty-string hybrid_chunk_size2 comments · 2026-08-29
Discussions
#931Chopper: a small open model that cuts only the needed sentences out of retrieved text0 comments · 2026-11-15#845docmutant: shareable reproducers and exact-ground-truth test files from unshareable PDFs0 comments · 2026-10-28#743Idea: an openly licensed, professionally tagged PDF/UA ground-truth corpus — would it be useful to `odl-bench` and the auto-tagger?0 comments · 2026-09-21#661PDF Accessibility Checker and veraPDF says document corrupted4 comments · 2026-07-29#602Can it OCR handwritten numbers1 comments · 2026-06-20#575Is there a way to handle cases where a table spans multiple pages?1 comments · 2026-06-16#538Hancom-AI Set up1 comments · 2026-05-29#494Image parsing1 comments · 2026-05-11
Latest release
Release v2.5.22 v2.5.22 2026-11-12What's Changed chore: begin 2.5.22-SNAPSHOT by @github-actions[bot] in https://github.com/opendataloader-project/opendataloader-pdf/pull/917 fix(cli): refuse --to-stdout with a format that stdout cannot carry by @bundolee in https://github.com/opendataloader-project/opendataloader-pdf/pull/918 fix(core): read the columns first when a gap starts a section in one column only by @bundolee in https://github.com/opendataloader-project/opendataloader-pdf/pull/921 fix(core): do not read an underline below a text as a leader by @bundolee in https://github.com/opendataloader-project/opendataloader-