# doc_convert_v2

**Repository Path**: kanyuxia/doc_convert_v2

## Basic Information

- **Project Name**: doc_convert_v2
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: develop
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-06-27
- **Last Updated**: 2026-03-31

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Doc

## Features
- Document conversion from various formats (PDF, HTML, etc.) to Markdown
- LLM-based document optimization
- Archive extraction (ZIP, RAR, TAR, etc.)
- Email notifications
- Database integration for document approval workflows
- Support for multiple LLM providers (OpenAI-compatible APIs and AWS Bedrock with optional credentials)

## Workflow

```mermaid
graph TD
    A[extract_archives<br>解压压缩文件] --> B[convert_to_markdown<br>转换为Markdown]
    B --> C[optimize_documents<br>使用LLM优化]
    C --> D[create_result_zip<br>创建结果ZIP]
    D --> E[send_result_email<br>发送结果邮件]
    E --> F[结束]

    subgraph 错误处理
        A -->|解压失败| Err1[记录错误]
        B -->|转换失败| Err2[记录错误]
        C -->|优化失败| Err3[记录错误]
        D -->|打包失败| Err4[记录错误]
        Err1 --> E
        Err2 --> E
        Err3 --> E
        Err4 --> E
    end

    subgraph 外部服务
        C -.-> LLM[LLM API]
        E -.-> SMTP[邮件服务器]
    end
```