Box AIを使用したサプライヤ契約書から構造化された調達データへの変換

mkdir supplier-extraction && cd supplier-extraction

python3 -m venv .venv
source .venv/bin/activate

pip install box-sdk-gen python-dotenv

BOX_CLIENT_ID=your_client_id
BOX_CLIENT_SECRET=your_client_secret
BOX_ENTERPRISE_ID=your_enterprise_id
AGREEMENT_FILE_ID=your_file_id

import os
from dotenv import load_dotenv
from box_sdk_gen import BoxClient, BoxCCGAuth, CCGConfig

load_dotenv()

def get_box_client() -> BoxClient:
    config = CCGConfig(
        client_id=os.getenv("BOX_CLIENT_ID"),
        client_secret=os.getenv("BOX_CLIENT_SECRET"),
        enterprise_id=os.getenv("BOX_ENTERPRISE_ID"),
    )
    auth = BoxCCGAuth(config=config)
    return BoxClient(auth=auth)

from box_sdk_gen import CreateAiExtractStructuredFields

EXTRACTION_FIELDS = [
    CreateAiExtractStructuredFields(
        key="agreement_effective_date",
        display_name="Effective date",
        type="date",
        prompt="The date the agreement takes effect.",
    ),
    CreateAiExtractStructuredFields(
        key="payment_terms",
        display_name="Payment terms",
        type="string",
        prompt="The payment terms, for example Net 30.",
    ),
    CreateAiExtractStructuredFields(
        key="vendor",
        display_name="Vendor",
        type="struct",
        prompt="The vendor or supplier issuing the agreement.",
        fields=[
            CreateAiExtractStructuredFields(key="legal_name", type="string", display_name="Legal name"),
            CreateAiExtractStructuredFields(key="address", type="string", display_name="Address"),
            CreateAiExtractStructuredFields(key="country", type="string", display_name="Country"),
            CreateAiExtractStructuredFields(key="contact_person", type="string", display_name="Contact person"),
            CreateAiExtractStructuredFields(key="email", type="string", display_name="Email"),
            CreateAiExtractStructuredFields(key="phone", type="string", display_name="Phone"),
        ],
    ),
    CreateAiExtractStructuredFields(
        key="delivery_schedule",
        display_name="Delivery schedule",
        type="table",
        prompt="Each delivery milestone defined in the agreement.",
        fields=[
            CreateAiExtractStructuredFields(key="phase", type="string", display_name="Phase"),
            CreateAiExtractStructuredFields(key="items", type="string", display_name="Items"),
            CreateAiExtractStructuredFields(key="delivery_date", type="date", display_name="Delivery date"),
            CreateAiExtractStructuredFields(key="destination", type="string", display_name="Destination"),
            CreateAiExtractStructuredFields(key="status", type="string", display_name="Status"),
        ],
    ),
]

from box_sdk_gen import AiItemBase, AiAgentReference, AiAgentReferenceTypeField
from box_client import get_box_client
from schema import EXTRACTION_FIELDS

def extract_agreement(file_id: str) -> dict:
    client = get_box_client()

    response = client.ai.create_ai_extract_structured(
        items=[AiItemBase(id=file_id)],
        fields=EXTRACTION_FIELDS,
        ai_agent=AiAgentReference(
            id="enhanced_extract_agent",
            type=AiAgentReferenceTypeField.AI_AGENT_ID,
        ),
    )

    return response.to_dict()["answer"]

import json
import os
from dotenv import load_dotenv
from extract import extract_agreement

load_dotenv()

def to_procurement_record(answer: dict) -> dict:
    vendor = answer.get("vendor", {})
    schedule = answer.get("delivery_schedule", [])

    return {
        "vendor_name": vendor.get("legal_name"),
        "vendor_country": vendor.get("country"),
        "vendor_contact": vendor.get("contact_person"),
        "vendor_email": vendor.get("email"),
        "payment_terms": answer.get("payment_terms"),
        "effective_date": answer.get("agreement_effective_date"),
        "milestones": [
            {
                "phase": row.get("phase"),
                "due": row.get("delivery_date"),
                "destination": row.get("destination"),
                "status": row.get("status"),
            }
            for row in schedule
        ],
    }

if __name__ == "__main__":
    file_id = os.getenv("AGREEMENT_FILE_ID")

    answer = extract_agreement(file_id)
    print("Raw extraction:")
    print(json.dumps(answer, indent=2))

    record = to_procurement_record(answer)
    print("\nProcurement record:")
    print(json.dumps(record, indent=2))

supplier-extraction/
├── .env
├── .venv/
├── app.py
├── box_client.py
├── extract.py
└── schema.py

python3 app.py

{
  "agreement_effective_date": "2026-06-01",
  "payment_terms": "Net 45",
  "vendor": {
    "legal_name": "Nexus Industrial Solutions Ltd.",
    "address": "47 Canary Wharf, Level 12, London, E14 5AB",
    "country": "United Kingdom",
    "contact_person": "Oliver Hartmann",
    "email": "o.hartmann@nexusindustrial.co.uk",
    "phone": "+44 20 7946 0832"
  },
  "delivery_schedule": [
    {
      "phase": "Phase 1 - Infrastructure",
      "items": "Server Racks (qty 6), UPS (qty 3)",
      "delivery_date": "2026-07-15",
      "destination": "Chicago, IL",
      "status": "Scheduled"
    },
    {
      "phase": "Phase 2 - Networking",
      "items": "48-Port Switches (all), Fibre Cables (all)",
      "delivery_date": "2026-08-01",
      "destination": "Chicago, IL",
      "status": "Scheduled"
    },
    {
      "phase": "Phase 3 - Security",
      "items": "NGFW Cluster (all), Remaining Racks",
      "delivery_date": "2026-08-20",
      "destination": "San Francisco, CA",
      "status": "Pending"
    },
    {
      "phase": "Phase 4 - Services",
      "items": "Installation, Training",
      "delivery_date": "2026-09-01",
      "destination": "San Francisco, CA",
      "status": "Pending"
    }
  ]
}