Box AI Extractを使用した請求書取り込みの自動化

mkdir invoice-intake && cd invoice-intake

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

pip install box-sdk-gen flask python-dotenv

BOX_CLIENT_ID=your_client_id
BOX_CLIENT_SECRET=your_client_secret
BOX_ENTERPRISE_ID=your_enterprise_id
BOX_METADATA_TEMPLATE_KEY=your_metadata_template_key
INVOICES_FOLDER_ID=your_folder_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)

import os
from dotenv import load_dotenv
from box_sdk_gen import (
    AiItemBase,
    BoxClient,
    CreateAiExtractStructuredMetadataTemplate,
    CreateAiExtractStructuredMetadataTemplateTypeField,
)

load_dotenv()

def extract_invoice_fields(client: BoxClient, file_id: str) -> dict:
    template_key = os.getenv("BOX_METADATA_TEMPLATE_KEY")

    result = client.ai.create_ai_extract_structured(
        items=[AiItemBase(id=file_id)],
        metadata_template=CreateAiExtractStructuredMetadataTemplate(
            template_key=template_key,
            type=CreateAiExtractStructuredMetadataTemplateTypeField.METADATA_TEMPLATE,
            scope="enterprise",
        ),
    )

    return result.to_dict()["answer"]

import os
from dotenv import load_dotenv
from box_sdk_gen import BoxClient, CreateFileMetadataByIdScope

load_dotenv()

def apply_metadata(client: BoxClient, file_id: str, metadata: dict) -> dict:
    template_key = os.getenv("BOX_METADATA_TEMPLATE_KEY")

    attached = client.file_metadata.create_file_metadata_by_id(
        file_id=file_id,
        scope=CreateFileMetadataByIdScope.ENTERPRISE,
        template_key=template_key,
        request_body=metadata,
    )

    return attached.to_dict()

import os
import json

from dotenv import load_dotenv
from flask import Flask, request, jsonify

from box_client import get_box_client
from extract import extract_invoice_fields
from metadata import apply_metadata

load_dotenv()
app = Flask(__name__)

@app.route("/webhook", methods=["POST"])
def handle_webhook():
    payload = request.get_json()

    if payload.get("trigger") != "FILE.UPLOADED":
        return jsonify({"status": "ignored"}), 200

    file_id = payload["source"]["id"]
    file_name = payload["source"]["name"]

    if not file_name.lower().endswith(".pdf"):
        return jsonify({"status": "skipped, not a PDF"}), 200

    client = get_box_client()

    extracted = extract_invoice_fields(client, file_id)
    print(f"Extracted from {file_name}: {json.dumps(extracted, indent=2)}")

    apply_metadata(client, file_id, extracted)
    print(f"Metadata applied to file {file_id}")

    return jsonify({"status": "processed", "file_id": file_id}), 200

if __name__ == "__main__":
    app.run(port=5000)

invoice-intake/
├── .env
├── .venv/
├── app.py
├── box_client.py
├── extract.py
└── metadata.py

cd ~/invoice-intake
source .venv/bin/activate
python3 app.py

* Running on http://127.0.0.1:5000

curl -X POST http://127.0.0.1:5000/webhook \
  -H "Content-Type: application/json" \
  -d '{
    "trigger": "FILE.UPLOADED",
    "source": {
      "id": "<FILE_ID>",
      "name": "sample-invoice.pdf"
    }
  }'

Extracted from sample-invoice.pdf: {
  "vendorName": "ACME Corp",
  "invoiceNumber": "INV-001",
  "invoiceDate": "2025-03-15T00:00:00Z",
  "dueDate": "2025-04-15T00:00:00Z",
  "totalAmount": 1250.00,
  "currency": "USD"
}
Metadata applied to file 123456789

curl -X POST https://api.box.com/2.0/webhooks \
  -H "Authorization: Bearer <ACCESS_TOKEN>" \
  -H "Content-Type: application/json" \
  -d '{
    "target": {
      "id": "<FOLDER_ID>",
      "type": "folder"
    },
    "address": "<webhook_url>",
    "triggers": ["FILE.UPLOADED"]
  }'