Global Purchase Order Recognition and Extraction Skill

Powered by Laiye ADP (Agentic Document Processing), this skill delivers intelligent recognition and key information extraction for various purchase orders (POs) and sales orders. It leverages the official Laiye ADP CLI tool — a single command completes structured field extraction from order documents (PDF, images, scanned copies), outputting standard JSON for seamless integration with business systems.

> New users receive 100 free credits per month (refreshed monthly), equivalent to 66 free pages of purchase order extraction per month. ADP provides a standard commercial API that can be integrated into business systems within 1 hour.

Register now: Global | China Mainland

Quick Start Guide

Core Workflow

1. Install dependencies: On first run, install the ADP CLI tool.
2. Authentication setup: On first run, execute adp config get to check credentials. If not configured, prompt the user to provide an API Key.
3. Get app list: On first run, retrieve the out-of-the-box app list via adp app-id list --app-type 0, find the order extraction app, and record its app_id (prefixed with ootb_). For subsequent runs, prefer adp app-id cache.
4. Execute extraction: Run adp extract url --app-id or adp extract local --app-id .
5. Process results: Parse the returned JSON to extract structured fields such as PO number, order date, seller name, buyer/customer name, buyer/customer address, receiver name, delivery address, currency, total amount, and line items (including material code, description, quantity, tax rate, unit price incl. tax, total amount incl. tax, delivery date).
6. Error handling: When a command fails, parse the stderr JSON to determine the error type and recovery action.

Scenario-to-Command Mapping

Single Order Recognition

Batch Recognition

Async Processing

> Concurrency Limit: Free users support a maximum of 2 documents for concurrent processing, while paid users support up to 10 documents concurrently.

Step 1: Install ADP CLI

# Method 1: npm (recommended, cross-platform)
npm install -g @laiye-adp/agentic-doc-parse-and-extract-cli

# Method 2: Shell script (Linux / macOS, when npm is not available)
curl -fsSL https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.sh | bash

# Method 3: PowerShell script (Windows, when npm is not available)
irm https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.ps1 | iex

Or download pre-compiled binaries from GitHub Releases.

Step 2: Get API Key & Authentication Setup

1. Access the ADP Portal for Credentials

Separate public cloud URLs are provided for China Mainland and Global users. Using the nearest region ensures optimal network performance.

2. Get API Key After Registration/Login

New users need to register an ADP account first; upon registration, you will receive 100 free credits per month.

• After logging in, click your profile avatar to access the API_Key entry.

3. Complete Authentication Setup

adp config set --api-key <your-api-key>
adp config set --api-base-url https://adp.laiye.com

4. Verify Configuration

adp config get

Notes:

1. If API Key and API Base URL are already configured, it is recommended to store the configuration in environment variables to avoid repeated setup.
2. If API Key and API Base URL are not yet configured, follow the steps above to complete the setup.

Step 3: Get the Order Extraction App ID

ADP provides a built-in, out-of-the-box extraction app for purchase orders — no additional configuration required.

App Type Description

ADP apps are divided into two types, distinguished by the app_type field:

Order recognition is an out-of-the-box app and can be queried with --app-type 0.

Query and Filter Order App

# Query OOTB apps only (recommended)
adp app-id list --app-type 0

# Or query all apps
adp app-id list

Find the app whose app_name contains "order" in the returned list and record its app_id:

[
  {
    "app_id": "ootb_******a2b5",
    "app_label": ["Order", "E-commerce Logistics", "Warehouse Management", "Information Extraction"],
    "app_name": "Order",
    "app_type": 0
  }
]

> In the example above, "app_id": "ootb_a2b5" is the order extraction app. app_type of 0 indicates an OOTB app, while 1 indicates a custom app.

Cache App ID (Recommended)

After the first query, prefer using the cache to avoid repeated requests:

# Use cached apps for subsequent calls
adp app-id cache

Important: The app_id for each account is unique and fixed — it will not change unless the user explicitly deletes the app. It is recommended that agents save the order app's app_id in context for direct reuse.

Step 4: Execute Purchase Order Extraction

Single Order Extraction (URL)

adp extract url https://example.com/purchase-order.pdf --app-id <order-app-id>

Single Order Extraction (Local File)

adp extract local ./purchase-order.pdf --app-id <order-app-id>

Single Order Extraction (Base64)

adp extract base64 <base64-string> --app-id <order-app-id> --file-name <filename.ext>

Response Example

ADP purchase order extraction returns unified structured JSON, accurately recognizing order header information (9 fields) and line item details table (7 columns), totaling 10 top-level fields.

[
  {
    "field_key": "po_number",
    "field_name": "PO Number",
    "field_values": [
      {
        "field_value": "PO-2025-003721"
      }
    ]
  },
  {
    "field_key": "order_date",
    "field_name": "Order Date",
    "field_values": [
      {
        "field_value": "2025-11-20"
      }
    ]
  },
  {
    "field_key": "seller_name",
    "field_name": "Seller Name",
    "field_values": [
      {
        "field_value": "Global Supply Chain Co., Ltd."
      }
    ]
  },
  {
    "field_key": "buyer_name",
    "field_name": "Buyer/Customer Name",
    "field_values": [
      {
        "field_value": "TechNova Innovation Inc."
      }
    ]
  },
  {
    "field_key": "buyer_address",
    "field_name": "Buyer/Customer Address",
    "field_values": [
      {
        "field_value": "1 Innovation Drive, Suite 200, San Jose, CA 95134"
      }
    ]
  },
  {
    "field_key": "receiver_name",
    "field_name": "Receiver Name",
    "field_values": [
      {
        "field_value": "TechNova Innovation Inc. — Warehouse Dept."
      }
    ]
  },
  {
    "field_key": "delivery_address",
    "field_name": "Delivery Address",
    "field_values": [
      {
        "field_value": "1 Innovation Drive, Building A, San Jose, CA 95134"
      }
    ]
  },
  {
    "field_key": "currency",
    "field_name": "Currency",
    "field_values": [
      {
        "field_value": "USD"
      }
    ]
  },
  {
    "field_key": "total_amount",
    "field_name": "Total Amount",
    "field_values": [
      {
        "field_value": "$87,623.00"
      }
    ]
  },
  {
    "field_key": "line_items",
    "field_name": "Line Items",
    "table_values": [
      [
        {
          "field_key": "line_items_material_code",
          "field_name": "Material Code",
          "field_values": [
            {
              "field_value": "MAT-A200-001"
            }
          ]
        },
        {
          "field_key": "line_items_description",
          "field_name": "Description",
          "field_values": [
            {
              "field_value": "Industrial Precision Sensor Module A-200"
            }
          ]
        },
        {
          "field_key": "line_items_quantity",
          "field_name": "Quantity",
          "field_values": [
            {
              "field_value": "500"
            }
          ]
        },
        {
          "field_key": "line_items_tax_rate",
          "field_name": "Tax Rate",
          "field_values": [
            {
              "field_value": "8%"
            }
          ]
        },
        {
          "field_key": "line_items_unit_price_inc_tax",
          "field_name": "Unit Price (Tax Incl.)",
          "field_values": [
            {
              "field_value": "$135.60"
            }
          ]
        },
        {
          "field_key": "line_items_total_amount_inc_tax",
          "field_name": "Total Amount (Tax Incl.)",
          "field_values": [
            {
              "field_value": "$67,800.00"
            }
          ]
        },
        {
          "field_key": "line_items_delivery_date",
          "field_name": "Delivery Date",
          "field_values": [
            {
              "field_value": "2025-12-20"
            }
          ]
        }
      ],
      [
        {
          "field_key": "line_items_material_code",
          "field_name": "Material Code",
          "field_values": [
            {
              "field_value": "MAT-B100-002"
            }
          ]
        },
        {
          "field_key": "line_items_description",
          "field_name": "Description",
          "field_values": [
            {
              "field_value": "High-Voltage Wiring Harness Assembly B-100"
            }
          ]
        },
        {
          "field_key": "line_items_quantity",
          "field_name": "Quantity",
          "field_values": [
            {
              "field_value": "200"
            }
          ]
        },
        {
          "field_key": "line_items_tax_rate",
          "field_name": "Tax Rate",
          "field_values": [
            {
              "field_value": "8%"
            }
          ]
        },
        {
          "field_key": "line_items_unit_price_inc_tax",
          "field_name": "Unit Price (Tax Incl.)",
          "field_values": [
            {
              "field_value": "$99.12"
            }
          ]
        },
        {
          "field_key": "line_items_total_amount_inc_tax",
          "field_name": "Total Amount (Tax Incl.)",
          "field_values": [
            {
              "field_value": "$19,823.00"
            }
          ]
        },
        {
          "field_key": "line_items_delivery_date",
          "field_name": "Delivery Date",
          "field_values": [
            {
              "field_value": "2025-12-25"
            }
          ]
        }
      ]
    ]
  }
]

Extraction Field Reference

ADP purchase order extraction returns the following fields. Each field contains field_key (machine-readable identifier), field_name (human-readable name), and field_values (extraction result array; field_value is an empty string when not recognized).

Order Header Fields

Line Item Table Fields (line_items)

The line_items field uses a table_values (2D array) structure — the outer array represents rows, and the inner array represents columns for each row. Each column also contains field_key, field_name, and field_values.

Step 5: Batch Processing & Async Mode

Batch Processing (Local Folder)

adp extract local ./purchase-orders/ --app-id <order-app-id> --export ./results/ 

Response summary:

{
  "total": 10,
  "success": 9,
  "failed": 1,
  "output_dir": "/absolute/path/to/results",
  "files": [
    {"input": "po-001.pdf", "output": "po-001.pdf.json", "status": "success"},
    {"input": "po-002.pdf", "output": "po-002.pdf.json", "status": "success"},
    {"input": "damaged.pdf", "output": "damaged.pdf.error.json", "status": "failed", "error": "..."}
  ]
}

Async Processing

# Submit async task
adp extract url https://example.com/purchase-order.pdf --app-id <order-app-id> --async

# Query task result
adp extract query <task_id>

Command Quick Reference

# Check installation
adp version

# View configuration
adp config get

# List all apps
adp app-id list

# List OOTB apps only (app_type=0)
adp app-id list --app-type 0

# Use cached apps
adp app-id cache

# Check credit balance
adp credit

# Order extraction (URL)
adp extract url <file-URL> --app-id <order-app-id>

# Order extraction (local file)
adp extract local <file-path> --app-id <order-app-id>

# Order extraction (Base64)
adp extract base64 <base64-string> --app-id <order-app-id> --file-name <filename.ext>

# Batch extraction
adp extract local <folder-path> --app-id <order-app-id> --export <output-path> 

# Async extraction
adp extract url <file-URL> --app-id <order-app-id> --async

# Query async result
adp extract query <task_id>

Error Handling

When a command fails, stderr outputs structured JSON:

{
  "type": "AUTH_ERROR",
  "message": "Authentication error: invalid API key",
  "fix": "Check your API key is correct and has not expired.",
  "retryable": false,
  "details": {"context": "extract"}
}

Exit Code Reference

Credits & Billing

More Laiye ADP Document Processing Capabilities

Order extraction is just one of many out-of-the-box capabilities on the Laiye ADP platform. Powered by large model general understanding, ADP provides intelligent document processing solutions covering all document categories:

All capabilities above can be accessed through the same ADP CLI tool, sharing the same ADP API Key and credit system.

For the full range of capabilities, visit:

• ADP Global: https://adp-global.laiye.com/
• ADP China Mainland: https://adp.laiye.com/

Important Notes

1. Data integrity: When using ADP output, present the returned data as-is — do not modify, add, or remove any fields during the extraction process.
2. API Key security: Keep your API Key secure and avoid sharing it with unauthorized third parties.
3. File size limit: Maximum 50 MB per file.
4. Supported formats: .jpg, .jpeg, .png, .bmp, .tiff, .tif, .pdf, .doc, .docx, .xls, .xlsx
5. App ID reuse: The order app's app_id is unique and fixed per account — save it for direct reuse without querying each time.
6. Line item fields: For line item fields such as product name, code, quantity, unit price, and line amount, each element in the field_values array corresponds to one product row, in sequential order.

Support & Contact

• CLI User Guide: ADP CLI User Guide
• API Documentation: Open API User Guide
• ADP Product Manual: Public Cloud Manual
• Issue Tracker: GitHub Issues
• Email: global_product@laiye.com
• Website: Laiye

Copyright © 2026 Laiye, Inc. All rights reserved.