Upload File

from retab import Retab
from pathlib import Path

client = Retab()

# Create an upload session for a local file.
invoice_path = Path("invoice.pdf")
session = client.files.create_upload(
    filename=invoice_path.name,
    size_bytes=invoice_path.stat().st_size,
    content_type="application/pdf",
)
mime_data = session.mime_data
print(f"Filename: {mime_data.filename}")
print(f"URL: {mime_data.url}")

{
  "fileId": "file_a1b2c3d4e5f6",
  "uploadUrl": "https://storage.googleapis.com/...",
  "uploadMethod": "PUT",
  "uploadHeaders": {
    "Content-Type": "application/pdf"
  },
  "mimeData": {
    "filename": "invoice.pdf",
    "url": "https://storage.retab.com/file_a1b2c3d4e5f6"
  },
  "expiresAt": "2026-04-24T12:00:00Z"
}

from retab import Retab

client = Retab(api_key="YOUR_RETAB_API_KEY")

schema = {
    "type": "object",
    "properties": {
        "invoice_number": {"type": "string"},
        "total_amount": {"type": "number"},
    },
}

# Option 1: object-storage URL
azure_blob_url = "https://<account>.blob.core.windows.net/<container>/large_document.pdf?<sas_token>"

extraction = client.extractions.create(
    document=azure_blob_url,
    model="retab-small",
    json_schema=schema,
)

# Option 2: Retab upload session, then reuse the returned URL
session = client.files.create_upload(
    filename="large_document.pdf",
    size_bytes=12345,
    content_type="application/pdf",
)
mime_ref = session.mime_data

extraction = client.extractions.create(
    document=mime_ref.url,
    model="retab-small",
    json_schema=schema,
)

# This also works:
extraction = client.extractions.create(
    document=mime_ref,
    model="retab-small",
    json_schema=schema,
)