Wisediag Medocr

WiseDiag MedOcr Skill

Convert PDF files into Markdown format. The script handles API authentication, file upload, OCR processing, and saves the result automatically.

⚠️ IMPORTANT: How to Use This Skill

You MUST use the provided script to process files. Do NOT call any API or HTTP endpoint directly.

The script scripts/medocr.py handles everything:

• API authentication (reads WISEDIAG_API_KEY from environment)
• PDF upload and OCR processing
• Saves the Markdown result to WiseDiag-MedOcr-1.0.0/{filename}.md

🔑 API Key Setup (Required)

Get your API key: 👉 https://chat.wisediag.com/apiKeyManage

export WISEDIAG_API_KEY=your_api_key

Installation

pip install -r requirements.txt

Usage

To process a PDF file, run:

cd scripts
python medocr.py -i /path/to/input.pdf

The script will automatically save the result to WiseDiag-MedOcr-1.0.0/{filename}.md.

Example:

python medocr.py -i /path/to/体检报告.pdf
# Output saved to: WiseDiag-MedOcr-1.0.0/体检报告.md

With custom output directory:

python medocr.py -i /path/to/input.pdf -o /custom/output/dir

Arguments

Output

After the script runs, the Markdown file is saved automatically:

• Default: WiseDiag-MedOcr-1.0.0/{filename}.md
• The file is named after the input PDF (e.g. 报告.pdf → 报告.md)
• No additional saving is needed — the file is already on disk

License

MIT