ixp

latest

false

Unstructured and complex documents user guide

Last updated Dec 22, 2025

Managing the taxonomy

This section describes how to manage field groups, fields, and field types, as well as how to add prompt instructions.

Overview of prompt instructions

Overall extraction instructions - provide context to the model that is relevant across the taxonomy, including details on the overall extraction task and the documents in the project.
Instructions - provide context for the model on how to successfully extract data from the document. Iterating on instructions helps to improve predictions.

Managing field groups

You can manage field groups from the following locations:

Manage Taxonomy page.
Annotation pane of the Validate predictions page.

From Manage Taxonomy

Manage field groups directly in the inline table. This allows you to create, edit, move, or delete multiple items before saving your edits. All changes are applied at once when you save them and are saved as a single project version update, instead of generating a new version for each individual change.

Creating and configuring field groups

To create and configure field groups from the Manage Taxonomy page, proceed as follows:

Under the Fields and field groups tab, enter your instructions in the Overall extraction instructions field.
Note: Project-level instructions can include a description of the industry or document type, or document-specific considerations, such as multiple occurrences of the document within one file.
Select Field group and fill in the following required fields in the inline table:
Note: You can only add individual fields within their respective field groups after you create the field groups.
- Name - Give your field group a name using natural language.
- Instructions - Give your field group a description, using natural language.
Under the new field group, select Add to add a New field or a New field group. The New field group option creates a child field group under the parent field group you created.
Note: For more details on adding new fields, check Creating and configuring fields.
To define a hierarchy between field groups, create a parent field group and then add one or more child field groups within it. This structure establishes the relationship between them, which means that if no predictions are returned for the parent field group, the child field groups will also return no predictions. The parent field group effectively serves as the primary classification, with its children providing additional levels of detail.
Note: The instructions for a parent field group do not influence a child field group.
After making all of the changes, select Save. Changes are saved and applied in bulk.

You can add and configure additional field groups, fields, and field types directly from the Validate predictions page at any point during the annotation process.

Example of field groups and their hierarchies

The following example shows field groups and their hierarchies:

Invoice
- Invoice Number
Invoice > Line Items
- Unit Price
- Quantity
- Line Amount

Note: If the model cannot find any Invoice field group in a document, that is the document is not an invoice, no Invoice > Line Items is returned.

Editing field groups

You can edit your field groups directly in the inline table as follows:

In the Manage Taxonomy page, under the Fields and field groups tab, select the name of your field group or instructions.
Make your modifications.
Select Save.

Moving field groups

To move your field groups, proceed as follows:

In the Manage Taxonomy page, under the Fields and field groups tab, select the ellipsis button on the field group you want to move.
Select Move.
In the Move field group window that appears, select the dropdown list.
Select the new parent for your field group.
Note: The greater-than sign > is used to define the field group hierarchy. This sign establishes a relationship between the parent field group and the child field group.
If the field group is a child, you can also select None from the dropdown list to make it a parent field group instead.
Select Move field group.
Select Save.

Deleting field groups

To delete your field groups, proceed as follows:

In the Manage Taxonomy page, under the Fields and field groups tab, select the ellipsis button for the field group you want to remove.
Select Delete.
In the Confirm delete window that appears, select Delete.
Important: Deleting a field group will result in the loss of its annotations. This action can only be undone by reverting to a previously published model version. Publish the latest model version before making significant changes.

From the annotation pane

Creating and configuring field groups

To create and configure field groups from the annotations pane in the Validate predictions page, proceed as follows:

In the annotation pane, select Add field group.
Select New field group.
In the Add field group side panel, fill in the following fields:
- Field group name - Give your field group a name using natural language.
- Instructions - Give your field group a description, using natural language.
Select Add, which turns the current
In the Edit field group side panel, you can edit the field group you created and add new fields using the New field button.

Editing field groups

To edit your field groups, proceed as follows:

In the annotation pane, hover over your field group and select the ellipsis button.
Select Edit field group.
In the side panel that appears, under Field group details, you can edit the instructions, as well as edit and delete fields.
Select Save after you perform your modifications.

Dismissing field groups

If you want the model to exclude a field group, proceed as follows:

In the annotation pane, hover over your field group and select the ellipsis button.
Select Dismiss field group. This action makes the field group appear with a crossed line.
To revert the changes, select Revert field group dismissal from the ellipsis for the same field group.

Managing fields

You can manage fields from the following locations:

Manage Taxonomy page.
Annotation pane of the Validate predictions page.

From Manage Taxonomy

Manage fields directly in the inline table. This allows you to create, edit, move, or delete multiple items before saving your edits. All changes are applied at once and saved as a single project version update, instead of generating a new version for each individual change.

Creating and configuring fields

To create and configure fields from the Manage Taxonomy page, proceed as follows:

Under the Fields and field groups tab, expand the field group to which you want to add fields.
Select Add.
Select New field to create individual fields.
In the inline table, fill in and configure the required details as follows:
- Name - Give your field a name that accurately describes the data it represents.
- Instructions - Give your field a relevant and detailed description to provide the necessary context for extraction.
- Field type - Each field must have assigned a field type, which can be one of the pre-configured or custom field types. Use the Field type drop-down menu and select one of the pre-configured options: Date, Exact Text, Inferred Text, Monetary Quantity, Number, or Boolean.
  Note:
  - You can reuse field types across different fields, which allows you to share the instructions.
  - You can change the field types once the field is created. However, changing the field type will result in the loss of any existing annotations.
  - Text field type can have input values that are present in the document and extracted as-is (Exact Text), or can be inferred from the document, if it is not explicitly stated in the text (Inferred Text).
  If you want to create a custom field type, select the New field type option from the drop-down list. For more details, check Creating and configuring field types.
- Data type - This field is filled in automatically, depending on the field type you select.
Select Save.

Editing fields

You can edit your fields directly in the inline table as follows:

In the Manage Taxonomy page, under the Fields and field groups tab, expand the field group where the field is.
Select the field name, instructions, or field type.
Make your modifications.
Select Save.

Moving fields

To move your fields within the same field group they are part of, proceed as follows:

In the Manage Taxonomy page, under the Fields and field groups tab, hover over your field.
Use the drag handle to move your field anywhere within the field group it is part of.
Once you are happy with the new order, select Save.

To move your fields to other field groups, proceed as follows:

Select the ellipsis button for the field you want to move.
Select Copy field definition, which copies the entire field along with its details.
Next, select the field groups where you want to paste the copied field.
Once you select the field groups, select Paste in the window that appears.

Alternatively, to move all fields from one field group to another, follow the same steps as previously described, but make sure to select the ellipsis button for the field group where the fields you want to move are located.

Deleting fields

To delete your fields, proceed as follows:

In the Manage Taxonomy page, under the Fields and field groups tab, select the ellipsis button for the field you want to remove.
Select Delete.
In the Confirm delete window that appears, select Delete.
Important: Deleting a field will result in the loss of its annotations. This action can only be undone by reverting to a previously published model version. Publish the latest model version before making significant changes.

From the annotation pane

Creating and configuring fields

To create and configure fields from the annotations pane in the Validate predictions page, proceed as follows:

In the annotation pane, hover over your field group and select the ellipsis button.
Select Edit field group.
In the side panel that appears, select New field and fill in the required fields:
- Name - Give your field a name.
- Field type - Select from the dropdown list one of the pre-configured options: Date, Exact Text, Inferred Text, Monetary Quantity, Number, or Boolean.
  Note:
  - You can reuse field types across different fields, which allows you to share the instructions.
  - You can change the field types once the field is created. However, changing the field type will result in the loss of any existing annotations.
  - Text field type can have input values that are present in the document and extracted as-is (Exact Text), or can be inferred from the document, if it is not explicitly stated in the text (Inferred Text).
  If you want to create a custom field type, select the New field type option from the drop-down list. For more details, check Creating and configuring field types.
- Instruction - Describe what you want to extract from the documents and how to extract the details.
Select Save.

Note: You can also edit fields from the same Edit field group side panel.

Deleting fields

To delete fields from the annotation pane, proceed as follows:

In the annotation pane, hover over your field group and select the ellipsis button.
Select Edit field group.
In the side panel that appears, select the ellipsis for the field you want to remove.
Select Delete.
In the Confirm delete window that appears, select Delete.
Note: Deleting a field will result in the loss of its training data. This action can only be undone by reverting to a previous pinned model version. Pin the latest model version before making significant changes.

Managing field types

Creating and configuring field types

To create and configure new field types, follow these steps:

Select New field type in the Field types tab from the Manage taxonomy page.
Fill in the required fields:
- Name - the name of the field type.
- Instruction - should include common instructions on how the data is formatted and should be extracted for all fields that share the field type.
Note:
- You can reuse field types across different fields, which allows you to share the instructions.
- The field type instruction is used as a formatting instruction to normalize the outputs into a specific format. For example, to extract all dates as YYYY-MM-DD.
Use the Data type drop-down list to select one of the following values:
- String: can include any characters such as letters, numbers, and so on. It can also have input values that are explicitly present in or inferred from the document. For example, organization name, first name, address line, or phone number.
  - Select one of the following for the Input value:
    - Must be present in the document: the value must be extracted exactly as it appears within the document.
    - Inferred from the document: the extracted value can be inferred from context and does not need to exactly match the text within the document.
- Date: comes in unstructured formats that vary, and uses the UiPath pre-trained date field. For example, start dates, expiration dates.
- Number: comes in unstructured formats that vary, and uses the UiPath pre-configured field type to structure the values in a standardized format. For example, the number of items, change in percentage, decimal values.
- Monetary Quantity: comes in unstructured formats that vary, and uses the UiPath pre-trained monetary quantity model. For example, total premium value, fees due.
- Boolean: True or False values that are inferred from documents. For example, True can be for an existing customer and False for a non-existent customer.
- Choice: the Inferred or Exact values that are mapped to a set of pre-defined values. For example:
  - Languages: English, German, French.
  - Document types: water bill, gas bill, energy bill.
  - Product categories: investment account, savings account, current account.
  - Customer types: tier 1, tier 2, tier 3.
  Once you select Choice as your data type, the following options are displayed:
  - Display value
  - Alternate Values
  - Add choice
  You can input values and optionally annotate evidence. The value will be mapped to a set of given values where possible.
Important: Once the data type is configured, you cannot change it. Make sure you select the correct data type, otherwise, you must delete the field type and recreate it with the correct data type. This is because you cannot remap annotations for incompatible field types that have different data types.
Select Save.

Example of inferred and exact fields

Inferred fields

I work for the underwriting operations team at an insurance company, and we have hundreds of set policy categories, for example, automotive, home, health, luxury goods, and so on, that we offer to customers, each corresponding to a Type category, for example, Type A, B, C, and so on.

Based on the content of the document, I want to be able to extract and identify the Type category of the policy that needs to be processed.

In this example, there is nowhere in the message that explicitly states that this email pertains to Type E. In the instructions, context is provided for each insurance type to inform the predictions of the model. For example, claims related to luxury goods all belong to the Type E category.

Examples of fields that might need to be set up as Inferred:

Values that are not present anywhere in a document, but are implied from its context
Values that need to be concatenated across different areas in a document.
Values that span across multiple paragraphs, lines, or columns.

Exact fields

To facilitate this request, I may need the existing policy number, name, and the value claimed. These are values that I know need to be explicitly stated in the document itself and extracted into a downstream process.

Figure 1. Example of inferred and exact fields