Brothers, yet another mind-blowing open-source tool has appeared. Someone built a PDF parser that converts 100 pages per second to Markdown — and the best part is it’s 100% free, runs on CPU only, no GPU, no cloud, not even an API key needed. It’s called OpenDataLoader, and it tops every benchmark leaderboard. Here’s a quick comparison:

• docling scores well but is 15x slower
• marker needs a GPU and is 1000x slower
• Pymupdf4llm is fast, but its table score is only 0.40

https://github.com/opendataloader-project/opendataloader-pdf…

What’s even more impressive? It’s built by the PDF Association and the veraPDF team — the very people who define the standards. 8.6k stars, Apache 2.0, zero commercial dependencies. Who can resist?

opendataloader-project/opendataloader-pdf

Source: https://github.com/opendataloader-project/opendataloader-pdf

OpenDataLoader PDF

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

License (https://github.com/opendataloader-project/opendataloader-pdf/blob/main/LICENSE) PyPI version (https://pypi.org/project/opendataloader-pdf/) npm version (https://www.npmjs.com/package/@opendataloader/pdf) Maven Central (https://search.maven.org/artifact/org.opendataloader/opendataloader-pdf-core) Java (https://github.com/opendataloader-project/opendataloader-pdf#java)

🔍 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 (https://duallab.com) (veraPDF (https://verapdf.org) developers) based on PDF Association (https://pdfa.org) specifications, best practice guides and expertise of the PDF Community (https://pdfa.org/community/). Auto-tagging follows the Well-Tagged PDF specification (https://pdfa.org/wtpdf/), validated with veraPDF (collaboration (https://opendataloader.org/docs/tagged-pdf-collaboration))

Get Started in 30 Seconds

Requires: Java 11+ and Python 3.10+ (Node.js (https://opendataloader.org/docs/quick-start-nodejs) | Java (https://opendataloader.org/docs/quick-start-java) also available)

Before you start: run java -version. If not found, install JDK 11+ from Adoptium (https://adoptium.net/).

pip install -U opendataloader-pdf

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?

Capability Matrix

Extraction Benchmarks

opendataloader-pdf [hybrid] ranks #1 overall (0.907) across reading order, table, and heading extraction accuracy.

Scores normalized to [0, 1]. Higher is better for accuracy; lower is better for speed. Bold = best. Full benchmark details (https://github.com/opendataloader-project/opendataloader-bench)

Benchmark (https://github.com/opendataloader-project/opendataloader-bench) | Quality Breakdown (https://github.com/opendataloader-project/opendataloader-bench)

Which Mode Should I Use?

Quick Start

Python

pip install -U opendataloader-pdf

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"
)

Node.js

npm install @opendataloader/pdf

import { convert } from '@opendataloader/pdf';

await convert(['file1.pdf', 'file2.pdf', 'folder/'], {
  outputDir: 'output/',
  format: 'markdown,json'
});

Java

<dependency>
    <groupId>org.opendataloader</groupId>
    <artifactId>opendataloader-pdf-core</artifactId>
    <version>1.0.0</version>
</dependency>

Python Quick Start (https://opendataloader.org/docs/quick-start-python) | Node.js Quick Start (https://opendataloader.org/docs/quick-start-nodejs) | Java Quick Start (https://opendataloader.org/docs/quick-start-java)

Hybrid Mode: #1 Accuracy for Complex PDFs

Hybrid mode combines fast local Java processing with AI backends. Simple pages stay local (0.02s); complex pages route to AI for +90% table accuracy.

pip install -U "opendataloader-pdf[hybrid]"

Terminal 1 — Start the backend server:

opendataloader-pdf-hybrid --port 5002

Terminal 2 — Process PDFs:

# Batch all files in one call — each invocation spawns a JVM process, so repeated calls are slow
opendataloader-pdf --hybrid docling-fast file1.pdf file2.pdf folder/

Python:

# 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/",
    hybrid="docling-fast"
)

OCR for Scanned PDFs

Start the backend with --force-ocr for image-based PDFs with no selectable text:

opendataloader-pdf-hybrid --port 5002 --force-ocr

For non-English documents, specify the language:

opendataloader-pdf-hybrid --port 5002 --force-ocr --ocr-lang "ko,en"

Supported languages: en, ko, ja, ch_sim, ch_tra, de, fr, ar, and more.

Formula Extraction (LaTeX)

Extract mathematical formulas as LaTeX from scientific PDFs:

# Server: enable formula enrichment
opendataloader-pdf-hybrid --enrich-formula

# Batch all files in one call — each invocation spawns a JVM process, so repeated calls are slow
opendataloader-pdf --hybrid docling-fast --hybrid-mode full file1.pdf file2.pdf folder/

Output in JSON:

{
  "type": "formula",
  "page number": 1,
  "bounding box": [226.2, 144.7, 377.1, 168.7],
  "content": "\\frac{f(x+h) - f(x)}{h}"
}

Note: Formula and picture description enrichments require --hybrid-mode full on the client side.

Chart & Image Description

Generate AI descriptions for charts and images — useful for RAG search and accessibility alt text:

# Server
opendataloader-pdf-hybrid --enrich-picture-description

# Batch all files in one call — each invocation spawns a JVM process, so repeated calls are slow
opendataloader-pdf --hybrid docling-fast --hybrid-mode full file1.pdf file2.pdf folder/

Output in JSON:

{
  "type": "picture",
  "page number": 1,
  "bounding box": [72.0, 400.0, 540.0, 650.0],
  "description": "A bar chart showing waste generation by region from 2016 to 2030..."
}

Uses SmolVLM (256M), a lightweight vision model. Custom prompts supported via --picture-description-prompt.

Hancom Data Loader Integration — Coming Soon

Enterprise-grade AI document analysis via Hancom Data Loader (https://sdk.hancom.com/en/services/1?utm_source=github&utm_medium=readme&utm_campaign=opendataloader-pdf) — customer-customized models trained on your domain-specific documents. 30+ element types (tables, charts, formulas, captions, footnotes, etc.), VLM-based image/chart understanding, complex table extraction (merged cells, nested tables), SLA-backed OCR for scanned documents, and native HWP/HWPX support. Supports PDF, DOCX, XLSX, PPTX, HWP, PNG, JPG. Live demo (https://livedemo.sdk.hancom.com/en/dataloader?utm_source=github&utm_medium=readme&utm_campaign=opendataloader-pdf)

Hybrid Mode Guide (https://opendataloader.org/docs/hybrid-mode)

Output Formats

Combine formats: format="json,markdown"

JSON Output Example

{
  "type": "heading",
  "id": 42,
  "level": "Title",
  "page number": 1,
  "bounding box": [72.0, 700.0, 540.0, 730.0],
  "heading level": 1,
  "font": "Helvetica-Bold",
  "font size": 24.0,
  "text color": "[0.0]",
  "content": "Introduction"
}

Full JSON Schema (https://opendataloader.org/docs/reference/json-schema)

Advanced Features

Tagged PDF Support

When a PDF has structure tags, OpenDataLoader extracts the exact layout the author intended — no guessing, no heuristics. Headings, lists, tables, and reading order are preserved from the source.

Output quality depends on tag quality. Not all tagged PDFs are well-tagged. For PDFs with sparse or incorrect tags, the default heuristic mode or --hybrid docling-fast often produces better results.

# 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/",
    use_struct_tree=True  # Use native PDF structure tags
)

Most PDF parsers ignore structure tags entirely. Learn more (https://opendataloader.org/docs/tagged-pdf)

AI Safety: Prompt Injection Protection

PDFs can contain hidden prompt injection attacks. OpenDataLoader automatically filters:

• Hidden text (transparent, zero-size fonts)
• Off-page content
• Suspicious invisible layers

To sanitize sensitive data (emails, URLs, phone numbers → placeholders), enable it explicitly:

# Batch all files in one call — each invocation spawns a JVM process, so repeated calls are slow
opendataloader-pdf file1.pdf file2.pdf folder/ --sanitize

AI Safety Guide (https://opendataloader.org/docs/ai-safety)

LangChain Integration

pip install -U langchain-opendataloader-pdf

from langchain_opendataloader_pdf import OpenDataLoaderPDFLoader

loader = OpenDataLoaderPDFLoader(
    file_path=["file1.pdf", "file2.pdf", "folder/"],
    output_dir="output/",
    mode="hybrid",
    model="docling-fast"
)

LangChain Quick Start (https://opendataloader.org/docs/langchain)

Memory & Performance

OpenDataLoader is designed for efficient resource usage.

Roadmap

• Python, Node.js, Java SDKs
• Hybrid mode with AI backends
• OCR for scanned PDFs
• Formula extraction (LaTeX)
• Chart/image description
• Auto-tagging → Tagged PDF
• PDF/UA-1, PDF/UA-2 export (Enterprise)
• Hancom Data Loader integration
• Cloud API (Enterprise)

FAQ

Q: Why is the first call slow?
A: The first call starts a JVM process. Subsequent calls reuse it. For batch processing, always pass multiple files in a single call.

Q: Can I use GPU?
A: Not needed. Fast mode is CPU-only. Hybrid mode uses a lightweight AI backend that runs on CPU (though GPU speeds up the backend if available).

Q: Is it really free?
A: Yes. Apache 2.0 license. No hidden costs. The hybrid mode uses open-source AI models.

Q: How does it compare to commercial tools?
A: Outperforms most commercial tools in accuracy, and is free. Commercial tools may offer better speed or additional enterprise features.

Contributing

We welcome contributions! See the contribution guide (https://github.com/opendataloader-project/opendataloader-pdf/blob/main/CONTRIBUTING.md)

License

Apache 2.0 (https://github.com/opendataloader-project/opendataloader-pdf/blob/main/LICENSE)

Acknowledgments

Built with ❤️ by the PDF community. Special thanks to:

• PDF Association (https://pdfa.org) for specifications and guidance
• Dual Lab (https://duallab.com) for veraPDF development
• Hancom (https://sdk.hancom.com) for AI collaboration
• All contributors and early adopters

Star History