Safe RAG with HydroX AI and Zilliz: PII Masking for Responsible GenAI

Zilliz and HydroX AI have partnered to introduce PII Masker, an advanced tool designed to enhance data privacy in AI applications. The collaboration aims to protect Personally Identifiable Information (PII) during model training and inference for Generative AI (GenAI) models like Retrieval Augmented Generation (RAG). With the increasing use of unstructured data in AI, ensuring PII safety is crucial for responsible GenAI usage. PII Masker automatically detects and masks sensitive information with high precision using DeBERTa-v3 NLP model. The tool has seamlessly integrated with both Milvus and Zilliz Cloud vector databases, allowing users to build compliant GenAI applications while protecting user data. Future iterations of PII Masker will expand language support and improve the detection of contextually implied PII.