⚠️ Privacy Warning
IMPORTANT - READ BEFORE INSTALLING:
This skill uploads your file to WiseDiag's cloud servers for OCR processing.
Do NOT use with sensitive or confidential documents unless:
- - You trust WiseDiag's data handling policies
- You accept that file contents will be transmitted and processed remotely
🚫 Personal Sensitive Information Warning
Do NOT upload documents containing any of the following:
| Category | Examples |
|---|
| Identity | ID card numbers, passport numbers, driver's license numbers |
| Financial |
Bank account numbers, credit card numbers, tax IDs |
| Biometric | Fingerprints, facial recognition data, voiceprints |
| Credentials | Passwords, PINs, security question answers |
| Personal contact | Home address, personal phone number, personal email |
| Minor's info | Any information belonging to children under 18 |
If the document contains sensitive personal information, it is recommended to use a local/offline OCR solution.
WiseOCR Skill (powered by WiseDiag)
A high-accuracy OCR tool that converts a single PDF or image file into Markdown format. After processing, the Markdown result is automatically saved to disk — no additional saving is needed.
Supported formats: PDF, jpg, jpeg, png, webp, gif, bmp, tiff.
Installation
CODEBLOCK0
🔑 API Key Setup (Required)
Get your API key: 👉 https://console.wisediag.com/apiKeyManage
The API key MUST be set as an environment variable. The script reads it automatically.
CODEBLOCK1
How to Process a File (Step-by-Step)
NEVER call any API or HTTP endpoint directly. ONLY use the script below.
Step 1: Set the API key (if not already set):
CODEBLOCK2
Step 2: Run the script with the input file:
CODEBLOCK3
IMPORTANT: If the input file has been copied or renamed (e.g. to a temp path), always pass -n with the original filename (without extension) so the output file is named correctly:
CODEBLOCK4
The Markdown result is saved to ~/.openclaw/workspace/WiseOCR/{name}.md automatically. No additional saving is needed.
Arguments
| Flag | Description |
|---|
| INLINECODE2 | Input file: PDF or image — single file path (required) |
| INLINECODE3 |
Output filename stem (recommended when input file is renamed/copied) |
|
-o, --output | Output directory (default: ~/.openclaw/workspace/WiseOCR) |
|
--dpi | PDF rendering DPI, 72-600 (default: 200) |
Data Privacy
What happens to your files:
- 1. Files are uploaded to WiseDiag's OCR API
- Files are processed on WiseDiag servers
- Processing results are returned to you
- Files are not permanently stored on WiseDiag servers
⚠️ Do NOT upload documents containing personal sensitive information, including but not limited to:
- - Identity information: ID card numbers, passport numbers, driver's license numbers
- Financial information: Bank account/card numbers, credit card numbers, tax IDs, financial statements
- Biometric data: Fingerprints, facial images, iris scans, voiceprints
- Account credentials: Passwords, PINs, security question answers, private keys
- Personal contact details: Home address, personal phone number, personal email
- Information about minors: Any personally identifiable information belonging to children under 18
For documents containing the above, use offline/local OCR tools instead.
License
MIT
⚠️ 隐私警告
重要提示——安装前请阅读:
此技能会将您的文件上传至WiseDiag的云服务器进行OCR处理。
请勿用于敏感或机密文件,除非:
- - 您信任WiseDiag的数据处理政策
- 您接受文件内容将被远程传输和处理
🚫 个人敏感信息警告
请勿上传包含以下任何内容的文件:
| 类别 | 示例 |
|---|
| 身份信息 | 身份证号码、护照号码、驾驶证号码 |
| 财务信息 |
银行账号、信用卡号、税务识别号 |
| 生物特征 | 指纹、面部识别数据、声纹 |
| 凭证信息 | 密码、PIN码、安全问题的答案 |
| 个人联系方式 | 家庭住址、个人电话号码、个人邮箱 |
| 未成年人信息 | 任何属于18岁以下儿童的信息 |
如果文件包含敏感个人信息,建议使用本地/离线OCR解决方案。
WiseOCR技能(由WiseDiag提供支持)
一款高精度的OCR工具,可将单个PDF或图像文件转换为Markdown格式。处理完成后,Markdown结果会自动保存到磁盘——无需额外保存。
支持的格式:PDF、jpg、jpeg、png、webp、gif、bmp、tiff。
安装
bash
pip install -r requirements.txt
🔑 API密钥设置(必需)
获取您的API密钥: 👉 https://console.wisediag.com/apiKeyManage
API密钥必须设置为环境变量。脚本会自动读取。
bash
export WISEDIAGAPIKEY=您的API密钥
如何处理文件(分步指南)
切勿直接调用任何API或HTTP端点。仅使用以下脚本。
第1步:设置API密钥(如果尚未设置):
bash
export WISEDIAGAPIKEY=您的API密钥
第2步:使用输入文件运行脚本:
bash
cd scripts
单个PDF
python3 wiseocr.py -i /path/to/输入文件名.pdf
单个图像
python3 wiseocr.py -i /path/to/扫描.png
重要提示: 如果输入文件已被复制或重命名(例如到临时路径),请始终使用-n参数传递原始文件名(不含扩展名),以便输出文件正确命名:
bash
python3 wiseocr.py -i /tmp/ocrinput.pdf -n myreport
输出保存至:~/.openclaw/workspace/WiseOCR/my_report.md
Markdown结果会自动保存到~/.openclaw/workspace/WiseOCR/{名称}.md。无需额外保存。
参数
| 标志 | 描述 |
|---|
| -i, --input | 输入文件:PDF或图像——单个文件路径(必需) |
| -n, --name |
输出文件名主干(当输入文件被重命名/复制时推荐使用) |
| -o, --output | 输出目录(默认:~/.openclaw/workspace/WiseOCR) |
| --dpi | PDF渲染DPI,72-600(默认:200) |
数据隐私
您的文件将经历以下过程:
- 1. 文件被上传至WiseDiag的OCR API
- 文件在WiseDiag服务器上处理
- 处理结果返回给您
- 文件不会永久存储在WiseDiag服务器上
⚠️ 请勿上传包含个人敏感信息的文件,包括但不限于:
- - 身份信息:身份证号码、护照号码、驾驶证号码
- 财务信息:银行账号/卡号、信用卡号、税务识别号、财务报表
- 生物特征数据:指纹、面部图像、虹膜扫描、声纹
- 账户凭证:密码、PIN码、安全问题的答案、私钥
- 个人联系方式:家庭住址、个人电话号码、个人邮箱
- 未成年人信息:任何属于18岁以下儿童的个人可识别信息
对于包含上述内容的文件,请改用离线/本地OCR工具。
许可证
MIT