Private AI has developed a new product, which helps companies safely leverage OpenAI's chatbot without compromising customer or employee privacy. This new model provides a privacy layer for large language models (LLMs) that automatically redacts sensitive information and personally identifiable information (PII) from user prompts. This helps businesses safely leverage generative AI while ensuring data privacy and security.
The major contribution to this project was the development of privateGPT.py, a script that uses a local language model based on GPT4All-J to interact with documents stored in a local vector store. privateGPT.py is a powerful tool that can be used to redact PII from a variety of documents, including text files, PDFs, and images. It's going to be a valuable tool for businesses that want to use generative AI without compromising data privacy. This new model is called "PrivateGPT".
Continue Reading