Skip to main content
The Documents tab shows every document used to set up, train, and test a Document skill and its activities.
When the Documents tab loads, a notification appears: N documents being copied…” When copying finishes, the message updates to N documents copied” and shows how long the operation took. The same message also appears in the notifications panel. N counts every document being copied — including demo documents added on the Publish tab — so it can be larger than the total across all document sets.

Document sets

Documents are organized into sets. Each skill has an All Documents set, created by default, that contains every uploaded document. You can also create custom sets to use in individual activities or to test a skill. A custom set is always a subset of All Documents, and a single document can belong to multiple custom sets. When a new activity is created, it uses All Documents by default. Custom sets are useful when a skill needs different extraction rules for different document variants — see Classify By Text and Image activity.
The tab name reflects the active set. With All Documents selected, it reads All Documents. With a custom set selected, it reads Documents: <Set name>.

Create a custom document set

1

Open the Documents tab

On the skill, switch to the Documents tab.
2

Add a new set

Click the add button in the list of document sets.
3

Name the set

Provide a name for the custom set.
4

Add documents

Add the documents you want the set to contain. The new set appears alongside All Documents and can be edited at any time.

Test sets

You can create a document set used only for testing — for example, a balanced set of documents from one client. A test set isn’t linked to any activity.

Create a test set

1

Add a new set

On the Documents tab, click the add button in the list of document sets. If the documents you want are already uploaded, select them and choose Create Set from Selection on the shortcut menu.
2

Name the test set

Provide a name that identifies the set’s purpose.
3

Run the test

Select the set, and then choose Test Skill Using This Set on the shortcut menu.
To test against an ad-hoc selection instead, choose Test Skill on the shortcut menu of one or more selected documents. Test sets are also selectable when labeling documents and when reviewing test results. When you edit a skill that was created in Vantage, its document set also appears on the Documents tab.

Upload and process documents

You can upload documents at any point by returning to the Documents tab. If the skill has a processing flow on the Activities tab, new uploads are processed automatically. Once processing completes, predicted labeling appears on the Fields tab, and reference labeling is generated from the predicted values. Uploads inside an activity editor also trigger processing. Auto-generated reference labeling is unconfirmed until you copy predicted labeling to reference using the corresponding option on the documents’ shortcut menu. Documents with unconfirmed labeling can’t be used for training and are excluded from test results. To confirm labeling, review it on the Fields tab.

View options

  • List View — shows documents as a list with the upload date, the sets each document belongs to, and labeling status (in the Reference Fields column). For more on labeling, see Fields.
  • Thumbnail View — shows documents as thumbnails.
To preview a thumbnail at full size, use the preview button. Rotate the page from the preview window using the more options menu.

Toolbar commands

Use the toolbar to edit the active document set.
Sets that have fewer than 10 documents cannot be divided.

Limits

Don’t upload more than 10,000 documents to a single skill — beyond that, the skill may become unstable.