Extract information from an uploaded image (such as a photo) or a file (PDF), and save it to rows in an existing table using AI by adding the Extract rows 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 and save to rows in an existing table using AI as described in the following sections:
See also:
Add and configure the Extract rows AI task
To extract data from an uploaded image (such as a photo) or file (PDF), add and configure the Extract rows AI task by performing the following steps.
- Add the Extract rows AI task to a bot, as described in Add a task to a bot.
- Configure the Extract rows AI task by using the settings described in the following table.
- Save the app.
To extract data from an uploaded image (such as a photo) or a file (such as a PDF) and save it to rows in an existing table, configure the settings described in the following table.
|
Setting |
Description |
|
Task type |
Select AI task. |
|
Table |
Table defined in the event and used by the task. To view or edit the structure of the selected table, position your cursor in the field and click |
|
AI task |
Type of AI task. Select Extract rows. |
|
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: |
|
Add rows to |
Table to which you want to add the extracted rows. Select a referenced table from the drop-down. |
|
Output |
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. |
|
Additional instructions |
Recommended. Do the following:
Supports up to 2000 characters. For example: From the PDF file extract the items in the receipt that are above fifty dollars |
. See