presidio
presidio copied to clipboard
microsoft
Context aware, pluggable and customizable data protection and de-identification SDK for text and images
## Change Description Added the ability to support HaggingFace Transformers, for Name Entity Recognition task, integrated in spacy pipeline. ## Issue reference This PR fixes issue #887 ## Checklist -...
**Describe the bug** I have a custom entity A which with the regex 'AAA', and another custom entity B with the regex 'BBB' ... custom entity D with the regex...
**Describe the bug** Receiving “ImportError: cannot import name dataclasses” upon execution of “from presidio_analyzer.entity_recognizer import EntityRecognizer” Appears to be coming from “init pydantic.__init__()” under the hood. Researched known issues with...
## Change Description Describe your changes ## Issue reference This PR fixes issue #882 ## Checklist - [x] I have reviewed the [contribution guidelines](https://github.com/microsoft/presidio/blob/main/CONTRIBUTING.md) - [x] I have signed the...
We are using Presidio to recognize PII, Firstly we choose a server which configuration is: 15GB RAM，20 vCPU, no GPU， In this server, we use Stanza NLP model to recognize...
**Describe the bug** The problem is that when I want to load a model and use it in python everything works correctly. But when I want to use it in...
**Describe the bug** The longer the running time, the higher the memory footprint. **To Reproduce** Steps to reproduce the behavior: 1. Create a analyzer `analyzer = AnalyzerEngine(nlp_engine=NLP_Engine, supported_languages=['zh'])` 2. Any...
## Background Presidio currently leverages spaCy for NER. It is possible to [switch to a stanza model](https://microsoft.github.io/presidio/tutorial/05_languages/), or to create additional NER recognizers using 3rd party packages such as Flair...
As agreed with the folks who developed [Presidio CLI](https://github.com/insightsengineering/presidio-cli) and did an amazing job on it, we'd like to integrate it into Presidio. Tagging @dinakar29 and @knightdave. Let's use this...