This skill is based on OpenDataLoader PDF, licensed under Apache License 2.0.

OpenDataLoader PDF#

PDF parser for AI-ready data extraction. Open-source. #1 in benchmarks (0.90 overall accuracy).

Prerequisites#

• Java 11+ required (run java -version to verify)
• Python 3.10+ or Node.js 18+

Installation#

bash

# Python
pip install -U opendataloader-pdf

# Python with hybrid AI mode (for complex documents)
pip install -U "opendataloader-pdf[hybrid]"

# Node.js
npm install @opendataloader/pdf

Quick Start#

Python#

python

import opendataloader_pdf

opendataloader_pdf.convert(
    input_path=["file1.pdf", "file2.pdf", "folder/"],
    output_dir="output/",
    format="markdown,json"  # Output formats: markdown, json, html
)

Node.js#

typescript

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

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

CLI#

bash

# Fast local mode (0.05s/page)
opendataloader-pdf file1.pdf file2.pdf -o output/

# With hybrid AI mode (higher accuracy for complex docs)
opendataloader-pdf --hybrid docling-fast file1.pdf

Mode Selection#

Document TypeModeCommandStandard digital PDFFast (default)pip install opendataloader-pdfComplex tablesHybridpip install "opendataloader-pdf[hybrid]" + start serverScanned PDFsHybrid + OCRopendataloader-pdf-hybrid --force-ocrMulti-language scannedHybrid + OCR--ocr-lang "zh,en"Mathematical formulasHybrid + formula--enrich-formulaCharts needing descriptionHybrid + picture--enrich-picture-description

Benchmark Comparison#

EngineOverallTableSpeed (s/page)opendataloader [hybrid]0.900.930.43opendataloader (local)0.720.490.05docling0.860.890.73marker0.830.8153.93pymupdf4llm0.570.400.09

Key Features#

• Bounding boxes for every element (for source citations in RAG)
• XY-Cut++ reading order for multi-column layouts
• 100% local - no data sent to cloud
• AI safety filters - prompt injection protection
• Table extraction - borderless tables via hybrid mode
• OCR - 80+ languages via hybrid mode
• Formula extraction - LaTeX output

LangChain Integration#

bash

pip install langchain-opendataloader-pdf

python

from langchain_opendataloader_pdf import OpenDataLoaderPDF

loader = OpenDataLoaderPDF(file_path="document.pdf")
docs = loader.load()

Output Formats#

• markdown: Structured text with heading hierarchy
• json: Element-level with bounding boxes, page numbers, types
• html: Rich formatted output

JSON output includes:

• type: paragraph, heading, table, image, etc.
• content: text content
• bbox: [left, bottom, right, top] in PDF points
• page: page number
• heading_level: for headings

Common Issues#

IssueSolution"java not found"Install JDK 11+ from adoptium.netSlow repeated callsBatch files in single call; each spawns JVMPoor table accuracyUse hybrid mode ( --hybrid docling-fast)Scanned PDF not extractedUse hybrid mode with --force-ocrNon-English OCR not workSpecify --ocr-lang "zh,en"

Resources#

• Quick Start
• Hybrid Mode Guide
• JSON Schema
• LangChain Integration