How to convert the content of the file(may be PDF) into a text format that Pega can process.

General
, , , , , ,
1

Hi,

We have requirement where we need to get the content from PDF and pass it as a input to pxRunTextAnalyzer in order to extract entities from PDF.

Could anyone let me know,how we can achieve this!

2

@CharithaR To extract content from a PDF, you can use Pega’s PDF Connector or Pega OCR component.

Once you have the content, you can pass it as an input to the pxRunTextAnalyzer activity.

This activity is used to analyze the text and extract entities based on the Text Analyzer rule you have configured. The extracted entities can then be used as per your business requirements.

This is a GenAI-powered tool. All generated answers require validation against the provided references.

Read PDF Data

Table data extraction in pdf

Reading a Scanned PDF Document using Pega Robotics OCR

ow to call text extraction model in activity

Intelligent interaction in text analytics

3

@CharithaR Email channel allows you do all this automatically and more. Have you given it a go?

4

@VikasRaidhan Hi Vikas, Yes Email channel allows to analyze and extract entities from PDF automatically.

But we have a requirement where where we have to extract and analyze text through utility which would plug in a flow.

I have found this article helpful to achieve this scenario.

Read PDF Data | Support Center (pega.com)

Thank you