We are pleased to announce that Private AI's Document Redaction has been integrated into Eden AI API.
Private AI is a leading technology company specializing in advanced data privacy solutions. Their innovative approach focuses on the identification, anonymization, and replacement of personally identifiable information (PII) across various data types, ensuring compliance with global privacy regulations.
Among their suite of products, Private AI offers a Document Redaction API, designed to remove sensitive information from documents, including PDFs, office documents, images, and audio recordings. This capability is crucial for businesses looking to protect customer data and maintain trust, while also leveraging the benefits of cutting-edge technology without compromising privacy.
Eden AI offers Private AI's Document Redaction API on its platform amongst several other OCR & Document Parsers. We want our users to have access to multiple AI engines and manage them in one place so they can reach high performance, optimize cost and cover all their needs.
.gif)
There are many reasons for using multiple AI APIs :
You need to set up an AI API that is requested if and only if the main AI API does not perform well (or is down). You can use the confidence score returned or other methods to check provider accuracy.
After the testing phase, you will be able to build a mapping of AI vendors' performance that depends on the criteria that you chose. Each data that you need to process will be then sent to the best API.
This method allows you to choose the cheapest provider that performs well for your data. Let's imagine that you choose Google Cloud API for customer "A" because they all perform well and this is the cheapest. You will then choose Microsoft Azure for customer "B", a more expensive API but Google performances are not satisfying for customer "B". (this is a random example)
This approach is required if you look for extremely high accuracy. The combination leads to higher costs but allows your AI service to be safe and accurate because AI APIs will validate and invalidate each other for each piece of data.
Founded in 2019 by privacy and machine learning experts from the University of Toronto, Private AI’s mission is to create a privacy layer for software and enhance compliance with current data privacy regulations. We believe that privacy is a fundamental aspect of every application, and so we focus on making data privacy as easy as using an API. With our product, builders can innovate with confidence, knowing that privacy is at the forefront of everything we do.
Private AI is backed by M12 (Microsoft’s venture fund), and BDC, and has been named a World Economic Forum 2023 Technology Pioneer, GartnerⓇ Cool Vendor™ in Privacy, as well as one of the 2022 CB Insights AI 100, CIX Top 20, Regtech100, and more. Learn more at: https://www.private-ai.com/
Private AI provides software teams with an intuitive, scalable, high-performance API that can detect, redact, and replace over 50 personally identifiable information (PII) in over 50 languages with higher accuracy than any alternative. It seamlessly fits existing architectures, allowing app builders to deliver privacy-preserving, compliant products quickly.
Private AI works with technology builders of all shapes and sizes—from startups to enterprises. Our clients include a leading social media network, a customer engagement platform, a major disease control organization, a pharmaceutical giant, one of the top three Canadian financial institutions, and a leading insurance provider.
Private AI offers a unique way of detecting Personally Identifiable Information (PII), Protected Health Information (PHI), and Payment Card Industry (PCI) data. Unlike typical regular expression-based approaches, Private AI leverages a sophisticated AI model that relies on understanding the context to determine what is PII. This approach enables customers to solve problems for a wide range of data types, including simple database records and complex legal contracts, as well as multiple languages (52 and counting), media formats (text, audio, and documents), and software deployments like LLMs, all through a single API which runs within the customers’ environment.
As a result, Private AI enables control and understanding of data at ingest and anywhere within an organization’s software pipelines, so PII can be dealt with proactively rather than as an afterthought.
We made our models available via Eden AI because we believe that it should be easy to embed privacy wherever our customers are using data. With strong privacy protections in place, data can be safely shared across use cases. Private AI is proud that Eden AI users will now be able to leverage our state-of-the-art de-identification and redaction models across 52 languages and 50 entities.
.jpg)
Broadly, we are focused on continuing to improve the flexibility, performance and ease of use of the platform. For example, our 3.5 and 3.6 updates brought significant enhancements across various domains Key updates included seamless integration through OpenAPI, self-serve availability, Audio processing with voice distortion, and various model improvements.
AI took the world by storm, with over 80% of companies making it a top priority in their business. At the same time, governments have recognized the importance of regulating AI technology, especially given the growing influence of generative AI. Addressing the inherent risks at the core of AI is essential. In this context, it is crucial to strike a balance between encouraging innovation and ensuring responsible use.
To use Private AI on Eden AI, you just need to access to the documentation and call the API:
Eden AI is the future of AI usage in companies. Our platform not only allows you to call multiple AI APIs but also gives you :
You can see Eden AI documentation here.
You can directly start building now. If you have any questions, feel free to schedule a call with us!
Get startedContact salesDrop your email and we'll get back to you ASAP to answer any questions you have or just to say hi —we promise not to spam you!
-p-500.webp){kind=small}
-p-500.webp){kind=small}
%20(1).png)
