AI actions - Extract information from document or image
- The AI actions feature is available only when the feature is selected in the AI features for the tenant.
-
AI Actions have input limits to ensure safe and predictable results. Each action that analyzes or extracts information from text can process up to 100,000 characters and up to 1,000 repetitive pattern occurrences. Any input that exceeds these limits will not be processed. Some actions that only convert documents or images to text without analyzing the content, do not enforce these limits.
Use the Extract information from document or image action A tool for building the processes, logic, and direction within workflows. Actions are the steps the workflow performs to complete a process. to extract specific information from a file. The output can be plain text or JSON, based on the details you provide. You can use the result later in the workflow to store values or evaluate conditions.
For example, a user uploads a vendor invoice through a Nintex form. You want to extract the vendor name, invoice date, items, and total from the form. Use the Extract information from document or image action to extract these fields and send the result to the finance team for approval.
Video: Extract information from document or image
Jump to:
Configure the Extract information from document or image action
-
Add the action to the workflow and open the action configuration panel. For more information, see Add an action to the workflow.
-
Select a variable in the File field that contains the document or image.
-
In the Information to extract field, enter the fields or details to extract from the file.
-
In the Output type field, choose either Text or JSON.
-
Select or create a variable in the Extracted text field to store the result.
-
Type the information you want to extract using plain language, a list of field names, or a JSON schema A format that defines the structure, required fields, and data types of JSON data..
-
To ensure consistent JSON output, enter a JSON schema or example in the Information to extract field.
- When the output type is set to JSON, the result is returned as a JSON string, not a structured JSON object. Use the Query JSON action to extract individual values. Repeat this step for each field you want to use.
AI actions - Extract information from document or image action fields and settings
| Section | Field | Description |
Variable |
|---|---|---|---|
| (Unlabeled) | File |
A variable that contains the document or image to extract text from.
|
File |
| Information to extract | The fields or values to extract from the file. Describe using plain language, a list of field names, or a JSON schema. | Text | |
| Output type | The format for the extracted result. Choose Text or JSON. | Text, JSON | |
| Output | Extracted text |
Stores the result as unstructured text or structured JSON string.
|
Object |