This package features data-science related tasks for developing new recognizers for Presidio. It is used for the evaluation of the entire system, as well as for evaluating specific PII recognizers or PII detection models.
MIT License
Generation of protein sequences and evolutionary alignments via discrete diffusion models
AI-Sentry: A lightweight, pluggable facade layer for Azure Open AI, addressing common cross-cutti...
End-to-end Presidio evaluation toolkit uses Presidio, hugging face transformers, Azure Language S...
AICI: Prompts as (Wasm) Programs
Context aware, pluggable and customizable data protection and de-identification SDK for text and ...
GenAIOps with Prompt Flow is a "GenAIOps template and guidance" to help you build LLM-infused app...
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
A unified evaluation framework for large language models
This repo centralizes assets used by Microsoft CSAs. It is available to all organizations for edu...
Utilities used by the Deep Program Understanding team
Repo for WWW 2022 paper: Progressively Optimized Bi-Granular Document Representation for Scalable...
A versatile tool designed to help prototype intelligent assistants, agents and multi-agentic systems
Generates synthetic data and user interfaces for privacy-preserving data sharing and analysis.