anna4lucky-stack

---
name: laiye-doc-processing
description: Enterprise-grade agentic document processing API. Accurately extracts key fields and line items from invoices, receipts, orders and more across 10+ file formats, with confidence scoring. Zero-configuration, fast integration. Professionally optimized on massive enterprise documents.
License: Commercial license required. New users receive 100 free credits monthly to offset usage.
---

# Laiye Agentic Document Processing (ADP)

Agentic Document Processing API — convert 10+ file formats（.jpeg,.jpg,.png,.bmp,.tiff,.pdf,.doc,.docx,.xls,.xlsx） to structured JSON/Excel with per-field confidence scores using VLM and LLM.

> **Base URL:** `https://adp-global.laiye.com/?utm_source=github`

## Quick Start

```bash
curl -X POST "https://adp-global.laiye.com/open/agentic_doc_processor/laiye/v1/app/doc/extract" \
  -H "Content-Type: application/json" \
  -H "X-Access-Key: $ADP_ACCESS_KEY" \
  -H "X-Timestamp: $(date +%s)" \
  -H "X-Signature: $(uuidgen)" \
  -d '{
    "app_key": "$ADP_APP_KEY",
    "app_secret": "$ADP_APP_SECRET",
    "file_url": "https://example.com/invoice.pdf"
  }'
```

Response:
```json
{
  "status": "success",
  "extraction_result": [
    {
      "field_key": "invoice_number",
      "field_value": "INV-2024-001",
      "field_type": "text",
      "confidence": 0.95,
      "source_pages": [1]
    },
    {
      "field_key": "total_amount",
      "field_value": "1000.00",
      "field_type": "number",
      "confidence": 0.98,
      "source_pages": [1]
    }
  ]
}
```

## Setup

### 1. Get Your API Credentials

```bash
# Contact ADP service provider to obtain:
# - app_key: Application access key
# - app_secret: Application secret key
# - X-Access-Key: Tenant-level access key
```

Save your credentials:
```bash
export ADP_ACCESS_KEY="your_access_key_here"
export ADP_APP_KEY="your_app_key_here"
export ADP_APP_SECRET="your_app_secret_here"
```

### 2. Configuration (Optional)

**Recommended: Use environment variables** (most secure):
```json5
{
  skills: {
    entries: {
      "adp-doc-extraction": {
        enabled: true,
        // API credentials loaded from environment variables
      },
    },
  },
}
```

**Security Note:**
- Set file permissions: `chmod 600 ~/.openclaw/openclaw.json`
- Never commit this file to version control
- Prefer environment variables or secret stores
- Rotate credentials regularly

## Common Tasks

### Extract from File URL

```bash
curl -X POST "https://adp-global.laiye.com/open/agentic_doc_processor/laiye/v1/app/doc/extract" \
  -H "Content-Type: application/json" \
  -H "X-Access-Key: $ADP_ACCESS_KEY" \
  -H "X-Timestamp: $(date +%s)" \
  -H "X-Signature: $(uuidgen)" \
  -d '{
    "app_key": "'"$ADP_APP_KEY"'",
    "app_secret": "'"$ADP_APP_SECRET"'",
    "file_url": "https://example.com/document.pdf"
  }'
```

### Extract from Base64

```bash
# Convert file to base64
file_base64=$(base64 -i document.pdf | tr -d '\n')

curl -X POST "https://adp-global.laiye.com/open/agentic_doc_processor/laiye/v1/app/doc/extract" \
  -H "Content-Type: application/json" \
  -H "X-Access-Key: $ADP_ACCESS_KEY" \
  -H "X-Timestamp: $(date +%s)" \
  -H "X-Signature: $(uuidgen)" \
  -d "{
    \"app_key\": \"$ADP_APP_KEY\",
    \"app_secret\": \"$ADP_APP_SECRET\",
    \"file_base64\": \"$file_base64\",
    \"file_name\": \"document.pdf\"
  }"
```

### Extract with VLM Results

```bash
curl -X POST "https://adp-global.laiye.com/open/agentic_doc_processor/laiye/v1/app/doc/extract" \
  -H "Content-Type: application/json" \
  -H "X-Access-Key: $ADP_ACCESS_KEY" \
  -H "X-Timestamp: $(date +%s)" \
  -H "X-Signature: $(uuidgen)" \
  -d '{
    "app_key": "'"$ADP_APP_KEY"'",
    "app_secret": "'"$ADP_APP_SECRET"'",
    "file_url": "https://example.com/document.pdf",
    "with_rec_result": true
  }'
```

Access VLM results: `response["doc_recognize_result"]`

### Async Extraction (Large Documents)

**Create extraction task:**
```bash
curl -X POST "https://adp-global.laiye.com/open/agentic_doc_processor/laiye/v1/app/doc/extract/create/task" \
  -H "Content-Type: application/json" \
  -H "X-Access-Key: $ADP_ACCESS_KEY" \
  -H "X-Timestamp: $(date +%s)" \
  -H "X-Signature: $(uuidgen)" \
  -d '{
    "app_key": "'"$ADP_APP_KEY"'",
    "app_secret": "'"$ADP_APP_SECRET"'",
    "file_url": "https://example.com/large-document.pdf"
  }'

# Returns: {"task_id": "task_id_value", "metadata": {...}}
```

**Poll for results:**
```bash
curl -X GET "https://adp-global.laiye.com/open/agentic_doc_processor/laiye/v1/app/doc/extract/query/task/{task_id}" \
  -H "X-Access-Key: $ADP_ACCESS_KEY"
```

## Advanced Features

### Custom Scale Parameter

Enhance VLM quality with higher resolution:
```bash
# model_params: { "scale": 2.0 }
```

### Specify Config Version

Use a specific extraction configuration:
```bash
# model_params: { "version_id": "config_version_id" }
```

### Document Recognition Only

Get VLM results without extraction:
```bash
curl -X POST "https://adp-global.laiye.com/open/agentic_doc_processor/laiye/v1/app/doc/recognize" \
  -H "Content-Type: application/json" \
  -H "X-Access-Key: $ADP_ACCESS_KEY" \
  -H "X-Timestamp: $(date +%s)" \
  -H "X-Signature: $(uuidgen)" \
  -d '{
    "app_key": "'"$ADP_APP_KEY"'",
    "app_secret": "'"$ADP_APP_SECRET"'",
    "file_url": "https://example.com/document.pdf"
  }'
```

## When to Use

### Use ADP For:
- Invoice processing
- Order processing
- Receipt processing
- Financial document processing
- Logistics document processing
- Multi-table document data extraction

### Don't Use For:
- Video transcription
- audio transcription

## Best Practices

| Document Size | Endpoint | Notes |
|---------------|----------|-------|
| Small files | `/doc/extract` (sync) | Immediate response |
| Large files | `/doc/extract/create/task` (async) | Poll for results |

**File Input:**
- `file_url`: Prefer for large files (already hosted)
- `file_base64`: Use for direct upload (max 20MB)

**Confidence Scores:**
- Range: 0-1 per field
- Review fields with confidence <0.8 manually

**Response Structure:**
- `extraction_result`: Array of extracted fields
- `doc_recognize_result`: VLM results (when `with_rec_result=true`)
- `metadata`: Processing info (pages, time, model)

## Response Schema

### Success Response
```json
{
  "status": "success",
  "message": "string",
  "extraction_result": [
    {
      "field_key": "string",
      "field_value": "string",
      "field_type": "text|number|date|table",
      "confidence": 0.95,
      "source_pages": [1],
      "table_data": [...]  // for field_type="table"
    }
  ],
  "doc_recognize_result": [...],  // when with_rec_result=true
  "extract_config_version": "string",
  "metadata": {
    "total_pages": 5,
    "processing_time": 8.2,
    "model_used": "gpt-4o"
  }
}
```

### Error Response
```json
{
  "detail": "Error message description"
}
```

## Common Use Cases

### Invoice/Receipt Extraction
Extracts: invoice_number, invoice_date, vendor/customer_name, currency, vat_rate, total_amount_including_tax, total_amount_excluding_tax, line_items, etc.

### Purchase Order Extraction
Extracts: order_number, order_date, buyer_name/seller_name, address, total_amount, line_items, etc.

## Security & Privacy

### Data Handling

**Important:** Documents uploaded to ADP are transmitted to `https://adp-global.laiye.com/?utm_source=github` and processed on external servers.

**Before uploading sensitive documents:**
- Review ADP privacy policy and data retention policies
- Verify encryption in transit (HTTPS) and at rest
- Confirm data deletion/retention timelines
- Test with non-sensitive sample documents first

**Best practices:**
- Do not upload highly sensitive PII until you've confirmed security posture
- Use credentials with limited permissions if available
- Rotate credentials regularly (every 90 days recommended)
- Monitor API usage logs for unauthorized access
- Never log or commit credentials to repositories

### File Size Limits

- **Max file size:** 50MB
- **Supported formats:** .jpeg, .jpg, .png, .bmp, .tiff, .pdf, .doc, .docx, .xls, .xlsx
- **Concurrency limit:** Free users support 1 concurrent request, paid users support 2 concurrent requests
- **Timeout:** 10 minutes for sync requests

### Operational Safeguards

- Always use environment variables or secure secret stores for credentials
- Never include real credentials in code examples or documentation
- Use placeholder values like `"your_access_key_here"` in examples
- Set appropriate file permissions on configuration files (600)
- Enable credential rotation and monitor usage

## Billing

| Processing Stage | Cost |
|-----------------|------|
| Document Parsing | 0.5 credits/page |
| Purchase Order Extraction | 1.5 credits/page |
| Invoice/Receipt Extraction | 1.5 credits/page |
| Custom Extraction | 1 credit/page |

**New users:** 100 free credits per month, no application restrictions.

## Troubleshooting

| Error Code | Description | Common Causes & Solutions |
|------------|-------------|---------------------------|
| **400 Bad Request** | Invalid request parameters | • Missing `app_key` or `app_secret`<br>• Must provide exactly one input: `file_url` or `file_base64`<br>• Application has no published extraction config |
| **401 Unauthorized** | Authentication failed | • Invalid `X-Access-Key`<br>• Incorrect timestamp format (use Unix timestamp)<br>• Invalid signature format (must be UUID) |
| **404 Not Found** | Resource not found | • Application does not exist<br>• No published extraction config found for the application |
| **500 Internal Server Error** | Server-side processing error | • Document conversion failed<br>• VLM recognition timeout<br>• LLM extraction failure |
| **Sync Timeout** | Request processing timed out | • Large files should use async endpoint<br>• Poll `/query/task/{task_id}` for results |

## Pre-Publish Security Checklist

Before publishing or updating this skill, verify:

- [ ] `package.json` declares `requiredEnv` and `primaryEnv` for credentials
- [ ] `package.json` lists API endpoints in `endpoints` array
- [ ] All code examples use placeholder values not real credentials
- [ ] No credentials or secrets are embedded in `SKILL.md` or `package.json`
- [ ] Security & Privacy section documents data handling and risks
- [ ] Configuration examples include security warnings for plaintext storage
- [ ] File permission guidance is included for config files

## References

- **API Base URL:** https://adp-global.laiye.com/
- **Flow Documentation:** [ADP Flow Index](../../refers/backend/flows/ADP-Flow-Index.md)
- **Extraction Flow:** [Document Extraction Flow](../../refers/backend/flows/09-Doc-Extraction-Flow.md)
- **Recognition Flow:** [Document Recognition Flow](../../refers/backend/flows/08-Doc-Recognition-Flow.md)

FILE:package.json
{
  "name": "laiye-doc-processing",
  "version": "1.0.0",
  "description": "Enterprise-grade agentic document processing API. Accurately extracts key fields and line items from invoices, receipts, orders and more across 10+ file formats, with confidence scoring. Zero-configuration, fast integration. Professionally optimized on massive enterprise documents.",
  "author": "ADP Team",
  "homepage": "https://adp-global.laiye.com/?utm_source=github",
  "keywords": [
    "Document Processing",
    "Data Extraction",
    "Invoice Processing",
    "Order Processing",
    "Receipt Processing",
    "PDF to Markdown",
    "PDF to Json",
    "Structured Data",
    "Agentic AI",
    "Document AI",
    "LLM",
    "VLM",
    "OCR"
  ]
}

FILE:README-CN.md
<div align="center">

# 📄 来也智能体文档处理 (ADP)

**ADP（Agentic Document Processing，智能体文档处理）** 是基于大语言模型和视觉语言模型，结合智能体技术，实现文档端到端自动化处理的新一代平台。


[English](README.md) | [简体中文](README-CN.md)

</div>

---

## 🚀 关于 ADP

**来也智能体文档处理 (Agentic Document Processing，简称 ADP)** 基于大模型的通用理解能力，不依赖规则与标注，具备对多语言、多模态、多场景的通用理解能力；智能体的自主规划与执行，能够理解任务目标、自主规划步骤、调用工具、完成复杂任务；端到端的业务自动化，从文档输入到业务决策再到人机协同，形成完整闭环。

### 💡 核心功能

ADP 帮助 AI 智能体**像人类一样理解和提取文档数据**，但支持的语言更多、准确率更高。无论是处理发票、提取订单详情，还是解析收据，ADP 都能将杂乱的非结构化文档转化为干净的结构化 JSON，让您的 AI 立即投入使用。

### 🎯 适用人群

- **AI 智能体开发者** 构建文档处理能力
- **企业团队** 自动化发票/收据/订单处理
- **金融科技与财务应用** 需要财务数据提取
- **物流与供应链** 解决方案处理运输单据
- **RPA 平台** 集成智能文档理解

---

## ✨ 核心特性

### 📦 开箱即用产品

| 产品 | 提取内容 | 最佳场景 |
|---------|------------------|----------|
| **发票处理** | 发票号码、日期、供应商、明细项目、总额、税费 | 应付账款自动化、费用管理 |
| **订单处理** | 采购单号、商品、数量、价格、交付信息 | 采购自动化、电商集成 |
| **收据处理** | 商户、日期、金额、类别、明细项目 | 费用追踪、报销管理 |

### 🛠️ 技术能力

- **10+ 种文件格式** ： 支持 PDF、PNG、JPG、JPEG、BMP、TIFF、DOC、DOCX、XLS、XLSX
- **置信度评分** ： 每个字段包含 0-1 置信度评分，便于质量验证
- **同步与异步模式** ： 所有功能均对外开放同步、异步 API
- **VLM + LLM 双引擎** ： 视觉理解 + 语义提取，实现最大准确率
- **表格识别** ： 自动提取复杂表格和明细项目
- **零配置** ： 基于海量企业数据集预训练的专业模型
- **企业级方案** ： 我们为企业级客户提供私有化部署授权，如需试用，可联系邮箱：[email protected]

---

## 🌟 产品优势

### ✅ 生产级准确率
针对开箱即用的海外发票、收据、订单类型的文档，能实现准确率＞91%。

### ⚡ 零配置
无需模板设置、无需训练。**ADP 实现了海外发票/收据、订单场景下真正意义上的开箱即用。** 

### 🎯 智能体友好
ADP 专为 AI 智能体工作流而构建。结构化 JSON 响应、置信度评分和错误处理，专为 LLM 消费和决策而设计。

### 🔒 企业级安全
- 传输和存储的 HTTPS 加密
- 租户隔离处理环境
- 支持凭证轮换
- 明确的数据保留策略

### 🚀 差异化亮点

| 功能 | 通用 OCR | ADP |
|---------|-------------|-----|
| 表格提取 | ❌ 难以处理复杂表格 | ✅ 高级多表格识别 |
| 置信度评分 | ❌ 不支持 | ✅ 每字段置信度 (0-1) |
| 语义理解 | ❌ 仅文本 | ✅ VLM + LLM 上下文理解 |
| 零配置 | ❌ 需要模板 | ✅ 开箱即用 |
| 异步处理 | ❌ 仅同步 | ✅ 内置任务队列 |

---

## 🛠️ 支持平台

ADP Skill 可安装在任何支持自定义技能的 AI 智能体平台：

- ✅ **Claude Code** 
- ✅ **Manus** 
- ✅ **Openclaw**
- ✅ **Coze**
- ✅ 其他任何兼容 OpenAI 的智能体平台

---

## 📦 安装方式

### 手动安装（所有平台）

1. **下载 Skill 包**
   ```bash
   git clone https://github.com/laiye-ai-repos/adp-skill
   # 或从 Releases 页面下载 ZIP 压缩包
   ```

2. **上传到您的平台**
   - 导航到您智能体平台的技能/插件市场
   - 选择"上传自定义技能"或"从文件导入"
   - 选择 `ADP Skill` 文件夹或 `SKILL.md` 文件

3. **配置凭证**
   ```bash
   # 从以下地址获取您的 API 密钥：https://adp.laiye.com/?utm_source=github
   export ADP_ACCESS_KEY="your_access_key_here"
   export ADP_APP_KEY="your_app_key_here"
   export ADP_APP_SECRET="your_app_secret_here"
   ```

---

## 🎯 快速开始

### 从发票提取数据

```bash
curl -X POST "https://adp.laiye.com/open/agentic_doc_processor/laiye/v1/app/doc/extract" \
  -H "Content-Type: application/json" \
  -H "X-Access-Key: $ADP_ACCESS_KEY" \
  -H "X-Timestamp: $(date +%s)" \
  -H "X-Signature: $(uuidgen)" \
  -d '{
    "app_key": "'"$ADP_APP_KEY"'",
    "app_secret": "'"$ADP_APP_SECRET"'",
    "file_url": "https://example.com/invoice.pdf"
  }'
```

**响应示例：**
```json
{
  "status": "success",
  "extraction_result": [
    {
      "field_key": "invoice_number",
      "field_value": "INV-2024-001",
      "field_type": "text",
      "confidence": 0.95,
      "source_pages": [1]
    },
    {
      "field_key": "total_amount",
      "field_value": "1000.00",
      "field_type": "number",
      "confidence": 0.98,
      "source_pages": [1]
    }
  ]
}
```

---

## 📁 项目文件结构

```
laiye-doc-processing/
├── README.md
├── README-CN.md
├── SKILL.md
├── package.json
└── _meta.json
```

### 文件说明

| 文件 | 用途 |
|------|---------|
| `README.md` | 英文版：产品介绍、使用场景介绍、配置说明 |
| `README-CN.md` | 中文版：产品介绍、使用场景介绍、配置说明 |
| `SKILL.md` | ADP 技能定义：智能体平台用于加载技能 |
| `package.json` | 包元数据、关键词、必需环境变量、API 端点 |
| `_meta.json` | Skill 发布和版本追踪的内部元数据 |

---

## 📋 凭证设置

### 必需环境变量

| 变量 | 说明 | 示例 |
|----------|-------------|---------|
| `ADP_ACCESS_KEY` | 租户级访问密钥 | `c114c8*******63e358400` |
| `ADP_APP_KEY` | 应用访问密钥 | `UbCdDJ5*******kYoAVqHB` |
| `ADP_APP_SECRET` | 应用安全密钥 | `wbGLBuL*******m4L90T8u` |

### 获取凭证

1. 访问 [ADP 门户](https://adp.laiye.com/?utm_source=github)
2. 注册新账户（新用户每月 100 免费积分）
3. 直接使用开箱即用应用 API，或者创建新自定义应用获取 `APP_KEY` 和 `APP_SECRET`、`ACCESS_KEY`

---

## 💰 计费

| 处理阶段 | 费用 |
|-----------------|------|
| 文档解析 | 0.5 积分/页 |
| 采购订单抽取 | 1.5 积分/页 |
| 发票/收据抽取 | 1.5 积分/页 |
| 自定义抽取 | 1 积分/页 |

**新用户：** 每月获得 100 免费积分，不限制使用应用

---

## 🔐 安全与隐私

### 数据处理

- **加密：** 传输和存储均采用 HTTPS 加密
- **处理：** 文档在隔离的租户环境中处理
- **保留：** 可配置的数据保留策略
- **合规：** 遵循企业安全标准构建

### 最佳实践

```bash
# 1. 使用环境变量（绝不硬编码凭证）
export ADP_ACCESS_KEY="your_key"
export ADP_APP_KEY="your_key"
export ADP_APP_SECRET="your_key"

# 2. 设置限制性文件权限
chmod 600 ~/.openclaw/openclaw.json

# 3. 定期轮换凭证
# 建议：每 90 天一次

# 4. 永远不要将凭证提交到 git
echo "*.env" >> .gitignore
echo "openclaw.json" >> .gitignore
```

---

## 📚 相关文档

- **API 参考：** [完整 API 文档](https://adp.laiye.com/docs)
- **流程索引：** [ADP 流程文档](https://github.com/your-repo/docs)
- **示例代码：** [示例代码与集成](https://github.com/your-repo/examples)

---

## 📜 授权许可

**需要商业许可证**

本技能的使用需要商业许可证。新用户每月可获得 100 免费积分以评估服务。

如需购买更多积分，可直接在产品端内进行积分充值，如支付遇到问题，可以联系邮箱
- 邮箱：[email protected]

---

## 📞 支持与联系

- **ADP 产品操作手册：** [公有云操作手册](https://laiye-tech.feishu.cn/wiki/UDYIwG42pisBbFkJI39ctpeKnWh)
- **ADP API 接口文档：** [Open API 使用指南](https://laiye-tech.feishu.cn/wiki/PO9Jw4cH3iV2ThkMPW2c539pnkc)

- **问题反馈：** [GitHub Issues](https://github.com/laiye-ai-repos/adp-skill/issues)
- **邮箱：** [email protected]
- **官网：** [来也科技](https://laiye.com)

---

<div align="center">

**用 ❤️ 构建智能体 AI 的未来**

[⬆ 返回顶部](#-来也智能体文档处理-adp)

</div>

FILE:README.md
<div align="center">

# 📄 Laiye Agentic Document Processing (ADP)

**ADP (Agentic Document Processing)** is a next-generation platform based on Large Language Models and Vision Language Models, combined with agentic technology, to achieve end-to-end automated document processing.


[English](README.md) | [简体中文](README-CN.md)

</div>

---

## 🚀 About ADP

**Laiye Agentic Document Processing (ADP)** is built on the general understanding capabilities of large models, independent of rules and annotations, with universal understanding capabilities for multi-lingual, multi-modal, and multi-scenario contexts. With agentic autonomous planning and execution, it can understand task objectives, autonomously plan steps, call tools, and complete complex tasks. End-to-end business automation forms a complete loop from document input to business decisions and human-in-the-loop collaboration.

### 💡 Core Capabilities

ADP helps AI agents **understand and extract document data just like humans**, but with broader language support and higher accuracy. Whether processing invoices, extracting order details, or parsing receipts, ADP transforms messy unstructured documents into clean structured JSON that your AI can immediately use.

### 🎯 Target Audience

- **AI Agent Developers** building document processing capabilities
- **Enterprise Teams** automating invoice/receipt/order processing
- **FinTech & Accounting Applications** requiring financial data extraction
- **Logistics & Supply Chain** solutions processing shipping documents
- **RPA Platforms** integrating intelligent document understanding

---

## ✨ Core Features

### 📦 Out-of-the-Box Products

| Product | What It Extracts | Best For |
|---------|------------------|----------|
| **Invoice Processing** | Invoice number, date, vendor, line items, totals, tax | AP automation, expense management |
| **Order Processing** | PO number, items, quantities, prices, delivery info | Procurement, e-commerce integration |
| **Receipt Processing** | Merchant, date, amount, category, line items | Expense tracking, reimbursement |

### 🛠️ Technical Capabilities

- **10+ File Formats**: Supports PDF, PNG, JPG, JPEG, BMP, TIFF, DOC, DOCX, XLS, XLSX
- **Confidence Scoring**: Each field includes a 0-1 confidence score for quality validation
- **Sync & Async Modes**: All features exposed via both synchronous and asynchronous APIs
- **VLM + LLM Dual Engine**: Vision understanding + semantic extraction for maximum accuracy
- **Table Recognition**: Automatically extract complex tables and line items
- **Zero Configuration**: Professional models pre-trained on massive enterprise datasets
- **Enterprise Solutions**: We offer private deployment licensing for enterprise customers. For trials, contact: [email protected]

---

## 🌟 Product Advantages

### ✅ Production-Grade Accuracy
Achieves accuracy >91% for out-of-the-box overseas invoices, receipts, and order documents.

### ⚡ Zero Configuration
No template setup or training required. **ADP delivers truly out-of-the-box functionality for overseas invoices/receipts and order scenarios.**

### 🎯 Agentic-Friendly
ADP is built specifically for AI agent workflows. Structured JSON responses, confidence scoring, and error handling are designed for LLM consumption and decision-making.

### 🔒 Enterprise Security
- HTTPS encryption for transmission and storage
- Tenant-isolated processing environments
- Credential rotation support
- Clear data retention policies

### 🚀 Differential Highlights

| Feature | Generic OCR | ADP |
|---------|-------------|-----|
| Table Extraction | ❌ Struggles with complex tables | ✅ Advanced multi-table recognition |
| Confidence Scoring | ❌ Not available | ✅ Per-field confidence (0-1) |
| Semantic Understanding | ❌ Text-only | ✅ VLM + LLM for context |
| Zero Config | ❌ Requires templates | ✅ Works out of the box |
| Async Processing | ❌ Sync only | ✅ Built-in task queue |

---

## 🛠️ Supported Platforms

ADP Skill can be installed on any AI agent platform that supports custom skills:

- ✅ **Claude Code**
- ✅ **Manus**
- ✅ **Openclaw**
- ✅ **Coze**
- ✅ Any other OpenAI-compatible agent platform

---

## 📦 Installation

### Manual Installation (All Platforms)

1. **Download the Skill package**
   ```bash
   git clone https://github.com/laiye-ai-repos/adp-skill
   # Or download the ZIP from Releases
   ```

2. **Upload to Your Platform**
   - Navigate to your agent platform's Skills/Plugins marketplace
   - Select "Upload Custom Skill" or "Import from File"
   - Choose the `ADP Skill` folder or `SKILL.md` file

3. **Configure Credentials**
   ```bash
   # Get your API keys from: https://adp-global.laiye.com/?utm_source=github
   export ADP_ACCESS_KEY="your_access_key_here"
   export ADP_APP_KEY="your_app_key_here"
   export ADP_APP_SECRET="your_app_secret_here"
   ```

---

## 🎯 Quick Start

### Extract Data from an Invoice

```bash
curl -X POST "https://adp-global.laiye.com/open/agentic_doc_processor/laiye/v1/app/doc/extract" \
  -H "Content-Type: application/json" \
  -H "X-Access-Key: $ADP_ACCESS_KEY" \
  -H "X-Timestamp: $(date +%s)" \
  -H "X-Signature: $(uuidgen)" \
  -d '{
    "app_key": "'"$ADP_APP_KEY"'",
    "app_secret": "'"$ADP_APP_SECRET"'",
    "file_url": "https://example.com/invoice.pdf"
  }'
```

**Response Example:**
```json
{
  "status": "success",
  "extraction_result": [
    {
      "field_key": "invoice_number",
      "field_value": "INV-2024-001",
      "field_type": "text",
      "confidence": 0.95,
      "source_pages": [1]
    },
    {
      "field_key": "total_amount",
      "field_value": "1000.00",
      "field_type": "number",
      "confidence": 0.98,
      "source_pages": [1]
    }
  ]
}
```

---

## 📁 Project Structure

```
laiye-doc-processing/
├── README.md
├── README-CN.md
├── SKILL.md
├── package.json
└── _meta.json
```

### File Descriptions

| File | Purpose |
|------|---------|
| `README.md` | English: Product introduction, use cases, configuration guide |
| `README-CN.md` | Chinese: Product introduction, use cases, configuration guide |
| `SKILL.md` | ADP skill definition: Used by agent platforms to load the skill |
| `package.json` | Package metadata, keywords, required environment variables, API endpoints |
| `_meta.json` | Skill publication and version tracking internal metadata |

---

## 📋 Credential Setup

### Required Environment Variables

| Variable | Description | Example |
|----------|-------------|---------|
| `ADP_ACCESS_KEY` | Tenant-level access key | `c114c8*******63e358400` |
| `ADP_APP_KEY` | Application access key | `UbCdDJ5*******kYoAVqHB` |
| `ADP_APP_SECRET` | Application secret key | `wbGLBuL*******m4L90T8u` |

### Getting Your Credentials

1. Visit [ADP Portal](https://adp-global.laiye.com/?utm_source=github)
2. Register for a new account (100 free credits/month for new users)
3. Use out-of-the-box application API directly, or create a new custom application to get `APP_KEY`, `APP_SECRET`, and `ACCESS_KEY`

---

## 💰 Pricing

| Processing Stage | Cost |
|-----------------|------|
| Document Parsing | 0.5 credits/page |
| Purchase Order Extraction | 1.5 credits/page |
| Invoice/Receipt Extraction | 1.5 credits/page |
| Custom Extraction | 1 credit/page |

**New Users:** 100 free credits per month, no application restrictions.

---

## 🔐 Security & Privacy

### Data Handling

- **Encryption:** HTTPS encryption for transmission and storage
- **Processing:** Documents processed in isolated tenant environments
- **Retention:** Configurable data retention policies
- **Compliance:** Built following enterprise security standards

### Best Practices

```bash
# 1. Use environment variables (never hardcode credentials)
export ADP_ACCESS_KEY="your_key"
export ADP_APP_KEY="your_key"
export ADP_APP_SECRET="your_key"

# 2. Set restrictive file permissions
chmod 600 ~/.openclaw/openclaw.json

# 3. Rotate credentials regularly
# Recommended: Every 90 days

# 4. Never commit credentials to git
echo "*.env" >> .gitignore
echo "openclaw.json" >> .gitignore
```

---

## 📚 Related Documentation

- **API Reference:** [Complete API Documentation](https://laiye-tech.feishu.cn/wiki/S1t2wYR04ivndKkMDxxcp2SFnKd)


---

## 📜 License

**Commercial License Required**

This skill requires a commercial license for use. New users receive 100 free credits monthly to evaluate the service.

To purchase more credits, you can top up directly within the product. If you encounter payment issues, please contact:
- Email: [email protected]

---

## 📞 Support & Contact

- **ADP Product Manual:** [ADP Product Manual (SaaS)](https://laiye-tech.feishu.cn/wiki/OfexwgVUQiOpEek4kO7c7NEJnAe)
- **ADP API Documentation:** [Open API User Guide](https://laiye-tech.feishu.cn/wiki/S1t2wYR04ivndKkMDxxcp2SFnKd)
- **Issue Tracker:** [GitHub Issues](https://github.com/laiye-ai-repos/adp-skill/issues)
- **Email:** [email protected]
- **Website:** [Laiye Technology](https://laiye.com)

---

<div align="center">

**Built with ❤️ for the Agentic AI Future**

[⬆ Back to Top](#-laiye-agentic-document-processing-adp)

</div>

FILE:_meta.json
{
  "ownerId": "adp-team",
  "slug": "laiye-doc-processing",
  "version": "1.0.0",
  "publishedAt": 1740547200000
}