OpenDataLoader PDF
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source. observed · 2026-10-19
Health v2 · maintenance only
83/100
- Activity 100
- Release rhythm 87
- Longevity 37
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.
- gap_med: 2
- age_days: 525
- days_rel: 8
- days_push: 2
- n_releases_24m: 62
Adoption not part of the score
29741 stars · 2825 forks observed · 2026-10-19
What it is AI-extracted, prompt v1, taxonomy v1, 2026-10-05, confidence 0.97
OpenDataLoader PDF is an open‑source PDF parsing library that converts PDFs into AI‑ready formats such as Markdown, JSON with bounding boxes, HTML and Tagged PDFs. It supports deterministic local processing and an optional hybrid AI mode for OCR and complex layouts.
Use cases
- extract structured tables and headings from PDFs for RAG pipelines
- convert academic papers to markdown with correct reading order for LLM ingestion
- generate accessible Tagged PDFs automatically for compliance (PDF/UA)
- obtain JSON with element coordinates to cite source locations in AI responses
- run fast, local PDF-to‑text conversion without sending data to the cloud
- process scanned PDFs with built‑in OCR and multi‑language support
When to choose
- You need deterministic, locally‑run PDF extraction with bounding‑box metadata.
- Your RAG or LLM workflow requires accurate reading order and table fidelity.
- Compliance with PDF accessibility standards (PDF/UA) is a requirement.
- You want a single tool that works across Java, Python, and Node.js ecosystems.
When to avoid
- You require a pure Python solution without a Java runtime dependency.
- Real‑time, high‑throughput streaming of millions of pages is needed.
- Your use case relies solely on GPU‑accelerated OCR without hybrid mode.
Facets
library · maturity active
parser rag llm-inference accessibility artificial-intelligence data-science jvm python cli pdf markdown json html bounding-boxes hybrid-mode xy-cut ai-safety auto-tagging table-extraction retrieval-augmented-generation natural-language-processing nodejs
10 sources
- readme: https://github.com/opendataloader-project/opendataloader-pdf · fetched 2026-10-19 · 2304f60bba1a
- homepage: https://opendataloader.org · fetched 2026-09-21 · 23c88043f31e
- site_page: https://opendataloader.org/docs/reading-order · fetched 2026-09-21 · 0e579ae96cb6
- site_page: https://opendataloader.org/docs/hybrid-mode · fetched 2026-09-21 · d23722d5ec13
- site_page: https://opendataloader.org/docs/reference/json-schema · fetched 2026-09-21 · de2eece53ed9
- site_page: https://opendataloader.org/docs/ai-safety · fetched 2026-09-21 · 4016a8b17e2a
- site_page: https://opendataloader.org/docs · fetched 2026-09-21 · 3a1541cedc18
- site_page: https://opendataloader.org/docs/quick-start-python · fetched 2026-09-21 · 668c8421d2aa
- site_page: https://opendataloader.org/docs/benchmark · fetched 2026-09-21 · d8bd0ae2cf6c
- site_page: https://opendataloader.org/docs/rag-integration · fetched 2026-09-21 · 56ac896c5221
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| opendataloader-project/opendataloader-pdf | main | 83 |
| opendataloader-project/langchain-opendataloader-pdf | sdk | 60 |
For agents
markdown · JSON · MCP: product_card(name="opendataloader-project/opendataloader-pdf")
Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem