ieeU - PDF智能解析工具
一键将PDF文件解析为Markdown,并使用VLM将图片替换为描述性文本。
功能特性
- PDF解析:调用MinerU云端API将PDF转换为Markdown
- 图片描述:使用VLM(视觉语言模型)生成图片的文字描述
- 一键处理:单条命令完成PDF→Markdown→图片描述替换的完整流程
安装
pip install ieeU
或从源码安装:
pip install -e .
快速开始
1. 配置API
在 ~/.ieeU/settings.json 中配置:
{
"endpoint": "https://openrouter.ai/api/v1/chat/completions",
"key": "your-vlm-api-key",
"modelName": "google/gemini-3-flash-preview",
"mineruToken": "your-mineru-token"
}
获取 MinerU Token:访问 mineru.net 注册并获取API Token。
2. 处理PDF
ieeU process paper.pdf
输出:paper.md(与PDF同目录)
命令行接口
ieeU --help # 显示帮助信息
ieeU --version # 显示版本号
# 主要命令:处理PDF文件
ieeU process paper.pdf # 处理PDF,输出到同目录
ieeU process paper.pdf -o ./output # 指定输出目录
ieeU process paper.pdf --verbose # 详细输出模式
# 向后兼容:处理已有的Markdown文件
ieeU run # 处理当前目录的full.md文件
ieeU run --verbose # 详细输出模式
配置文件
必填项
| 字段 | 说明 |
|---|---|
endpoint |
VLM API端点URL |
key |
VLM API密钥 |
modelName |
VLM模型名称 |
mineruToken |
MinerU API Token(process命令必需) |
可选项
| 字段 | 说明 | 默认值 |
|---|---|---|
timeout |
请求超时(秒) | 60 |
retries |
重试次数 | 3 |
maxConcurrency |
最大并发数 | 5 |
环境变量
可覆盖配置文件:
IEEU_ENDPOINTIEEU_KEYIEEU_MODELIEEU_MINERU_TOKEN
输出示例
处理前(PDF中的图片):

Figure 1 shows the architecture.
处理后:
```figure 1
This figure illustrates the overall architecture of the system,
showing three main components connected by data flow arrows...
```
Figure 1 shows the architecture.
开发
安装开发依赖
pip install -e ".[dev]"
运行测试
pytest tests/
构建发布包
pip install build
python -m build
twine check dist/*
发布到PyPI
# 构建
python -m build
# 发布
twine upload dist/*
支持的VLM
- OpenAI GPT-4V
- Google Gemini (via OpenRouter)
- Anthropic Claude (via OpenRouter)
- 其他OpenAI兼容的API
License
MIT License
Metadata
Release files for ieeU 2.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| ieeu-2.1.0.tar.gz | 18.4 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| ieeu-2.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 35.5 kB
Release files / ieeu-2.1.0.tar.gz
| Download URL | ieeu-2.1.0.tar.gz |
|---|---|
| Size | 18.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
2b10a79fbb6348ae1f686c302e5ae5fc048582dd2d9ddaa984e2241b303c52cb
|
|
BLAKE2b-256 checksum How to use checksums |
f4d12b576f80e5f1b5808722549ec2de7d31a233912c0afd497a8a9312bd2d98
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.2
|
Release files / ieeu-2.1.0-py3-none-any.whl
| Download URL | ieeu-2.1.0-py3-none-any.whl |
|---|---|
| Size | 17.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
5edae987db6316f755b41e0ba1453361f9e0d69d100524167410ad9533405e1c
|
|
BLAKE2b-256 checksum How to use checksums |
2689e09b69b474f8900f9bde003361cf454cd121f621de1f1b89b0a7b19feab9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.2
|
Security for ieeU 2.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.