Getting Started

This guide walks through processing a document with a platform-managed configuration and reviewing the resulting data.

Prerequisites

• A Shipwell account with Document AI enabled
• Access to the Shipwell Sandbox
• A valid Shipwell user token
• A synthetic or non-sensitive PDF for testing

Step 1: Choose a platform-managed configuration

In Shipwell:

1. Open Document AI .
2. Select Configuration .
3. Open Processing Configuration .
4. Find a configuration marked Platform .
5. Open the configuration to review what it extracts and which processing features it enables.

Platform-managed configurations are maintained by Shipwell and are read-only. See Platform-Managed Configurations.

Step 2: Upload and process a document

1. Return to the Document AI document list.
2. Select Upload documents .
3. Add your test document.
4. In Upload behavior , select the platform-managed configuration.
5. Review the upload and submit it.

Only enabled configurations appear in the upload selector.

Step 3: Monitor processing

After upload, the document appears in the document list. Processing is asynchronous, so the status changes as work progresses.

Common statuses are:

• pending — processing has been requested
• processing — processing is in progress
• completed — results are ready
• failed — processing did not complete
• skipped or oversized — the file was stored but was not eligible for the requested processing

Open the document to view its latest processing status and progress.

Step 4: Review the results

When processing completes:

1. Open the document.
2. Select its latest run.
3. Review the summary and extracted schemas.
4. Select an extracted value to inspect its source when source regions are available.

The exact result depends on the selected configuration. See Reading Results.

API equivalent

Upload one document with a known processing configuration:

curl -X POST "https://sandbox-api.shipwell.com/document-store/documents" \
  -H "Authorization: Token <user-token>" \
  -F 'payload={
    "processing_config_id": "<processing-config-id>",
    "files": [{"filename": "sample-bol.pdf"}]
  }' \
  -F "files=@sample-bol.pdf"

import json

import requests

with open("sample-bol.pdf", "rb") as document_file:
    response = requests.post(
        "https://sandbox-api.shipwell.com/document-store/documents",
        headers={"Authorization": "Token <user-token>"},
        data={
            "payload": json.dumps(
                {
                    "processing_config_id": "<processing-config-id>",
                    "files": [{"filename": "sample-bol.pdf"}],
                }
            )
        },
        files={"files": ("sample-bol.pdf", document_file, "application/pdf")},
        timeout=60,
    )
response.raise_for_status()
document = response.json()["documents"][0]

Use the returned document id to monitor processing or retrieve results.

Next steps

• Learn how to choose a processing configuration
• Review every upload option in Uploading Documents
• Learn how processing works
• Learn how to create new runs and reprocess documents