Inferences
Models
Shipping Label Model
The shipping-label represents a single image that was scanned and data extracted.
Extracting the weight and dimension values is still experimental. We not only want to extract the raw strings, but also parse them into meaningful numbers that you can use.
object "shipping_label_inference"
The description of the model.
raw_text string
The raw text that was extracted from the image with the OCR before being added to the model.
created_at integer
Time in epoch seconds when this scan was created.
hash string
A unique hash for this shipping-label that can be used to identify duplicate scanned labels.
id string
Unique identifier for the shipping-label.
image_url string
The URL to the image used for this shipping-label.
location_id string
The hub location to which this delivery is assigned.
layout object
Details of the layout of the specified location
metadata object
Key value pairs of data that you can set for this shipping-label.
organization_id string
Unique identifier for the organization that owns this shipping-label. This will always be your organization ID.
recipient object
Details about the contact receiving this delivery.
Show Details
sender object
Details about the contact sending this delivery.
Show Details
provider_name string
The name of the shipping provider.
service_level_name string
The name of the service level for this package.
tracking_number string
Provider-specific string used to track this delivery.
purchase_order string
Any extracted purchase order numbers from the shipping-label.
reference_number string
Any extracted reference number from the shipping-label.
rma_number string
Return material authorization if included on the document.
extracted_labels Array.<String>
A list of all labels extracted from the document. Options include: perishable
, legal_document
, pay_stub
, confidential
, fragile
, oversized
, time_sensitive
, return_to_sender
, alcohol
, lithium
, cannabis
, dry_cleaning
weight string
The weight in pounds of the item that was scanned, if exists.
dimensions object
The dimensions in inches of the item that was scanned, if they exist.
Show Details
matches Object
Lists of contacts who have been matched to senders and recipients for the shipping-label if the match_contacts was set to true when creating the scan.
Show Details
errors Array.<String>
The list of errors, the possible values are:
- "no_matches",
- "partial_matches",
- "multiple_matches",
- "missing_matches",
- "server_error",
- "duplicate",
- "missing_location",
- "inference_missing_value",
- "match_missing_value",
- "invalid_model_keys",
- "missing_rate_id",
Bill Of Lading Model
object "bill_of_lading_inference"
The description of the model.
raw_text string
The raw text that was extracted from the image with the OCR before being added to the model.
created_at integer
Time in epoch seconds when this scan was created.
checksum string
A unique hash for this BOL that can be used to identify duplicate scanned labels.
id string
Unique identifier for the BOL.
image_url string
The URL to the image used for this BOL.
location_id string
The hub location to which this scanned BOL was assigned.
metadata object
Key value pairs of data that you can set for this BOL.
organization_id string
Unique identifier for the organization that owns this BOL. This will always be your organization ID.
recipient object
Details about the contact receiving this delivery.
Show Details
sender object
Details about the contact sending this delivery.
Show Details
tables object
The tables
object represents a structured list of tables, where each table consists of multiple items. Each item is a collection of key-value pairs that define specific attributes.
Show Details
Structure
The tables
object is a list of tables, where:
- Each table is a list of items.
- Each item is an object containing key-value pairs that represent attributes such as quantity, description, or other relevant details.
Example
logistics_attributes object
Details about the logistics information associated with this BOL.
Show Details
Item Label Model
object "item_labels_inference"
The description of the model.
raw_text string
The raw text that was extracted from the image with the OCR before being added to the model.
created_at integer
Time in epoch seconds when this scan was created.
checksum string
A unique hash for this item label that can be used to identify duplicate scanned labels.
id string
Unique identifier for the item label.
image_url string
The URL to the image used for this item label.
location_id string
The hub location to which this scanned item label was assigned.
metadata object
Key value pairs of data that you can set for this item label.
organization_id string
Unique identifier for the organization that owns this item label. This will always be your organization ID.
recipient object
Details about the contact receiving this delivery.
Show Details
sender object
Details about the contact sending this delivery.
Show Details
customer object
Contains customer-related information.
Show Details
item object
Contains details of the item on the label.
Show Details
package object
Contains package-related information.
Show Details
pallet object
Contains pallet-related information.
Show Details
carton object
Contains carton-related information.
Show Details
lot object
Contains lot-related information.
Show Details
barcode_values array
List of barcode values associated with the scanned item label.
purchase_orders array
List of purchase orders associated with the scanned item label.
sales_orders array
List of sales orders associated with the scanned item label.
serial_numbers array
List of serial numbers associated with the scanned item label.
origin object
Contains origin-related information.
Show Details
dates object
Contains manufacturing and expiry dates.
Show Details
additional_attributes array
A list of additional attributes related to the shipment. Each item in the list is an object containing key-value pairs. These are those key value pairs which are present on the scanned label but not part of the object above
Show Details
Each object in additional_attributes
may contain different key-value pairs. Examples include: