Text or LongText) using AI by adding the Extract AI task in an automation.Examples of extracting information using AI:
- Have technicians snap a photo of equipment and use AI to automatically extract the serial number, model number, or meter reading into your AppSheet table.
- Process uploaded purchase orders (as PDFs) or photos of shipping labels to extract PO numbers, company names, tracking numbers, or addresses.
- From incident reports, extract key details like location, date, or names.
Extract information using AI as described in the following sections:
See also:
Get started
To get started using the Extract AI task, step through a quick start or explore an app template.
Add and configure the Extract AI task
To extract data from an uploaded image (such as a photo), file (PDF), or text (description), add and configure the Extract AI task by performing the following steps.
- Add the Extract AI task to a bot, as described in Add a task to a bot.
- Configure the Extract AI task by using the settings described in the following table.
- Save the app.
|
Setting |
Description |
|
Task type |
Select AI task. |
|
Table |
Table defined in the event and used by the task. See Tables: The Essentials for more information about tables. |
|
AI task |
Type of AI task. Select Extract. |
|
Input column |
Column in the table that is used as input to the AI task. For the Extract task, this must be one of the following types: To view or edit the structure of the selected column, position your cursor in the field and click |
|
Output |
Select one of the following:
Then, select one or more columns to define the information to extract, up to a maximum of 12. Select a column from the drop-down. Click Add to add more columns. Notes:
For best practices when saving content, see Manage updates to row data by multiple bots. |
|
Additional instructions |
Recommended. Do the following:
Supports up to 2000 characters. For example: If not sure of Make, Model, or Year, make best guess |
to