Is it possible to run this fully local, so sensitive PII PDFs dont leave the network?

nlmatics / nlm-ingestor

This repo provides the server side code for llmsherpa API to connect. It includes parsers for various file formats.

https://www.nlmatics.com

Apache License 2.0

1.05k stars 152 forks source link

Is it possible to run this fully local, so sensitive PII PDFs dont leave the network? #57

Open AIMads opened 5 months ago

AIMads commented 5 months ago

Hey I work with some PII data PDFs, I would love to use this tool for handling them, but is it possible to run it without the PDF data leaving the network?

pratiksinghchauhan commented 4 months ago

@AIMads Do you mean removing the Flask server in between, merging the nlm-ingestor and llmsherpa, and integrating it directly into the application without any additional server? I am thinking along similar lines and feel it is possible here.