REST API for automated extraction

curl -X POST https://api.idpura.com/v1/ai-extract \
  -H "X-API-Key: ipd_your_api_key" \
  -F "files=@contract.pdf" \
  -F "files=@contract2.pdf" \
  -F 'template=[
    {"field":"full_name","type":"string","description":"Full name"},
    {"field":"sign_date","type":"date"},
    {"field":"amount","type":"currency"}
  ]' \
  -F "language_hint=en" \
  -F "output_format=json"

import requests, json, time

API_KEY = "ipd_your_api_key"
BASE    = "https://api.idpura.com"
headers = {"X-API-Key": API_KEY}

template = [
    {"field": "vat_id", "type": "string"},
    {"field": "total",  "type": "currency"},
    {"field": "date",   "type": "date"},
]

with open("invoice.pdf", "rb") as f:
    resp = requests.post(
        f"{BASE}/v1/ai-extract",
        headers=headers,
        files={"files": f},
        data={"template": json.dumps(template), "output_format": "json"},
    )
job = resp.json()
job_id = job["job_id"]

while True:
    status = requests.get(f"{BASE}/v1/jobs/{job_id}", headers=headers).json()
    if status["status"] == "done":
        break
    if status["status"] == "error":
        raise Exception(status.get("error_message"))
    time.sleep(3)

result = requests.get(
    f"{BASE}/v1/jobs/{job_id}/result",
    headers=headers,
    params={"format": "json"},
)
print(result.json())

# n8n flow in 4 nodes:

# 1. HTTP Request (POST /v1/ai-extract)
#    - Method: POST
#    - URL: https://api.idpura.com/v1/ai-extract
#    - Auth header: X-API-Key = {{ $vars.IDPURA_API_KEY }}
#    - Body: multipart/form-data
#      files: (Binary field with your document)
#      template: [{"field":"vat_id","type":"string"},{"field":"total","type":"currency"}]
#      output_format: json

# 2. Wait (1-5 seconds depending on batch size)

# 3. HTTP Request (GET /v1/jobs/{id})
#    - URL: https://api.idpura.com/v1/jobs/{{ $json.job_id }}
#    - Repeat with IF node until status = done

# 4. HTTP Request (GET /v1/jobs/{id}/result?format=json)
#    - Use data in next nodes (Spreadsheet, Database, etc.)