Process a PDF using NLP Text Analyzer
Hi,
I have a requirement to process a PDF to find certain keywords using text analyzer.
I am using Pega v8.1.0.
https://community.pega.com/knowledgebase/articles/conversational-channels/84/exploring-text-analyzers I have referred this and it suggests that text analyzers can only be used in emails, chat text messages or voice commands.
Is there any workaround that can be used for this?
TIA
***Edited by Moderator: Pallavi to update platform capability tags***
Pegasystems Inc.
US
You will need to convert pdf to text first, e.g., this link has some sample code there: https://collaborate.pega.com/question/need-read-data-doc-and-pdf
Unfortunately some java code involved.
After that, you can follow this link to get started for Pega NLP: https://community.pega.com/knowledgebase/articles/decision-management-overview/learn-natural-language-processing-nlp-sample
Pegasystems Inc.
PL
As it comes to PDF to text conversion, you have 3 options:
- for PDFs with textual layer one may use Rule-File-Binary#pyExtractText extension point (which is using PDFBox to extract the text)
- for PDFs that require OCR (non-textual layers) or PNGs or JPGs one may use either PegaOCR component (for on-prem solutions) or DPS (for cloud solutions) - pyExtractText will then invoke pyOcrAttachmentAnalysis to do OCR.
The activity pyExtractText returns text that can be then fed into Pega NLP. As it comes to DPS (Document Processing Service) this is yet unreleased, but you can contact @grabm - our product owner to have early access.