Agent Paddleocr Vision

Multi-language document understanding with PaddleOCR

Allen Niu

@nhzallen

What This Skill Does

Extracts text from documents using PaddleOCR cloud API, automatically classifies them into 11 types (invoice, receipt, contract, etc.), and suggests structured actions like creating expenses or adding contacts. Supports batch processing and searchable PDF generation.

Replaces manual document sorting and data entry by combining OCR extraction with automatic classification and action prompts.

When to Use It

  • Extract text and classify an invoice for expense tracking
  • Process a batch of receipts and generate expense reports
  • Convert a scanned contract into a searchable PDF with text layer
  • Extract contact details from a business card and save as vCard
  • Analyze a table from a scanned document and export as CSV
  • Verify passport or ID card information from a scanned image

Install

$ openclaw skills install @nhzallen/agent-paddleocr-vision

Agent PaddleOCR Vision

OCR with Agent Actions — powered by PaddleOCR only. Automatically classifies documents and provides actionable prompts.

What It Does

  • OCR extraction via PaddleOCR cloud API (requires credentials)
  • 11 document types: invoice, business card, receipt, table, contract, ID card, passport, bank statement, driver's license, tax form, general
  • Action suggestion with structured parameters
  • Batch processing
  • Searchable PDF generation (with bbox alignment)

Quick Start

# Install dependencies
pip3 install -r scripts/requirements.txt

# Configure PaddleOCR API
export PADDLEOCR_DOC_PARSING_API_URL=https://your-api.paddleocr.com/layout-parsing
export PADDLEOCR_ACCESS_TOKEN=your_token

# Process a file
python3 scripts/doc_vision.py --file-path ./invoice.jpg --pretty --make-searchable-pdf

Batch

python3 scripts/doc_vision.py --batch-dir ./inbox --output-dir ./out

Output

See docs/README.zh.md for full JSON schema and integration guide.

Supported Types

TypeActions
Invoicecreate_expense, archive, tax_report
Business Cardadd_contact, save_vcard
Receiptcreate_expense, split_bill
Tableexport_csv, analyze_data
Contractsummarize, extract_dates, flag_obligations
ID Cardextract_id_info, verify_age
Passportstore_passport_info, check_validity
Bank Statementcategorize_transactions, generate_report
Driver Licensestore_license_info, check_expiry
Tax Formsummarize_tax, suggest_deductions
Generalsummarize, translate, search_keywords

Configuration

Required environment variables:

  • PADDLEOCR_DOC_PARSING_API_URL — API endpoint ending in /layout-parsing
  • PADDLEOCR_ACCESS_TOKEN — Access token

Optional:

  • PADDLEOCR_DOC_PARSING_TIMEOUT — Default 600 seconds

Searchable PDF

With --make-searchable-pdf, embeds OCR text layer aligned to original layout using bounding boxes. Requires pdf2image + poppler (system) and reportlab, pypdf, pillow (Python).

Full Documentation

Detailed usage, troubleshooting, and development guide available in multiple languages under docs/:

  • 中文: docs/README.zh.md
  • English: docs/README.en.md
  • Español: docs/README.es.md
  • العربية: docs/README.ar.md

License

MIT-0


Made for OpenClaw. Let your agent see and act.

Top skills in this category