Fetch Labels from a Document

Fetches specified labels from a document using OCR technology.

Overview

This procedure fetches specified labels or keywords from a document using OCR technology. It extracts text based on given labels from documents that have been processed by OCR, returning matching text snippets sorted by their location within the document.

Syntax

Below is a line-by-line overview of the automation syntax. Expand each line to learn more.

the department's OCR confidence threshold is "confidence-threshold"

What does it do?

Specifies the minimum confidence level for OCR text recognition.

Where does it go?

This phrase should be written on a new line.

Is it required?

❌ No — This phrase is optional.

Does it require data?

✅ Yes — Replace confidence-threshold with a numeric value between 0 and 100. The default is 20. Note: This confidence threshold will be the default for all processes in the agent.

Example

the department's OCR confidence threshold is 85
the labels are "label1", "label2", "label3"

What does it do?

Specifies the labels or keywords to look for within the document.

Where does it go?

This phrase should be written on a new line.

Is it required?

✅ Yes — This phrase is required.

Does it require data?

✅ Yes — Replace label1, label2, label3, etc. with the labels or keywords to search for in the document.

Example

the labels are "Invoice Number", "Total Amount"
fetch the labels from the document

What does it do?

Begins the label extraction process from the document.

Where does it go?

This phrase should be written on a new line.

Is it required?

✅ Yes — This phrase is required.

Does it require data?

✅ Yes — References to the document and the labels must be defined in the automation.

the labels are "label1", "label2", "label3"

What does it do?

Specifies the labels or keywords to look for within the document.

Where does it go?

Indented under fetch the labels from the document where.

Is it required?

✅ Yes — This phrase is required.

Does it require data?

✅ Yes — Replace label1, label2, label3 with the labels or keywords to search for.

Example

the labels are "Invoice Number", "Total Amount"

Examples

1. Fetch Invoice Labels

This example fetches invoice-related labels from a document.

get the file as a scanned document
the labels are "Invoice Number", "Total Amount"
fetch the labels from the document

2. Fetch Customer Information Labels

This example fetches customer-related labels with a higher confidence threshold.

get the file as a scanned document
the labels are "Date", "Customer Name"
the department's OCR confidence threshold is 95
fetch the labels from the document

3. Fetch Multiple Document Fields

This example fetches various document fields for comprehensive extraction.

get the file as a scanned document
the labels are "Contract Number", "Effective Date", "Expiration Date", "Party Names"
fetch the labels from the document

Last updated

Was this helpful?