Privacy Impact Assessment (PIA) Requirements under Law25

PIA Law25

Quebec’s commitment to modernizing its data protection measures is evident in the provisions of Law25, the most important provisions of which came into effect on September 22, 2023. A significant component of this new legislation is the requirement for private companies to conduct Privacy Impact Assessments (PIAs). While already mandatory in certain circumstances for public … Read more

Elevate Your Experience with Version 3.5

Version 3.5 features

Hello, dear community! We are thrilled to announce the release of Version 3.5. Packed with new features, improvements, and fixes that are crafted based on your feedback and our commitment to enhancing your experience and productivity. Let’s dive in and explore what’s new and enhanced in this version! Now Available on Azure Marketplace Great news for … Read more

Fine-Tuning LLMs with a Focus on Privacy

fine tuning llms

This blog has an accompanying Jupyter Notebook! Access the notebook Large Language Models (LLMs) like Azure’s OpenAI service have become pivotal technology, enabling machines to understand and generate human-like replies to questions posed in a chat format. For organizations looking to augment those models with domain specific knowledge or for traditional ML applications such as … Read more

Comply with US Executive Order on Safe, Secure, and Trustworthy Artificial Intelligence using Private AI

biden trustworthy AI

The Biden-Harris Administration recently enacted a sweeping Executive Order to forge America’s path in responsible AI development, encouraging both innovation and risk mitigation. The Executive Order spells out a multi-faceted plan touching upon AI safety and security, privacy, equity, civil rights, and more, with profound implications for organizations that are already embedded in the AI … Read more

How to Comply with EU AI Act using PrivateGPT

eu ai act

The recently amended EU AI Act proposal we introduced in this blog post, would regulate “foundational models,” defined in Art. 3(1c) as “an AI model that is trained on broad data at scale, is designed for generality of output, and can be adapted to a wide range of distinctive tasks.” This blog post sets out … Read more

Navigating the Privacy Paradox: A Guide to Ethical Fine-Tuning of Large Language Models

fine tuning llm

In the field of artificial intelligence, Large Language Models (LLMs) such as GPT-4 stand out as a major innovation, proving useful in a range of areas including automated customer support and creative content generation. Nonetheless, there exists a notable challenge in leveraging the capabilities of these models while also maintaining data privacy. This blog aims … Read more

Adding Privacy to LangChain with Private AI

langchain privacy

LangChain is a powerful tool that allows you to setup a conversation with your favourite LLMs with ease. If you’re worried about what that LLM is doing with your information, Private AI makes it easy to integrate a privacy layer into your conversation, keeping your sensitive information safe. Getting Started If you don’t already have access … Read more

BYO LLM: Privacy Concerns and Other Challenges with Self Hosting

llm privacy

In the digital transformation era, Large Language Models (LLMs) like ChatGPT are increasingly being integrated into organizational workflows to boost efficiency and enrich customer experience. Self hosting these LLMs appears to be a viable solution to address privacy concerns, but it’s not entirely without its challenges. This article explores the residual privacy issues that persist … Read more

Generative AI Impact on Governments (Part 3/3)

AI in Government

How Are Governments Using Generative AI? Generative AI has found a multitude of use cases across industries. As of now, approximately 70% of companies are either experimenting with or actively implementing Generative AI into their operations. From content generation to data analysis and customer service automation, this technology is being harnessed to streamline processes and … Read more

Introducing Product Version 3.4: More Features, More Power!

release

Hello, dear community! We are thrilled to announce the release of version 3.4 of our product. This release isn’t just about refining our product; it’s about introducing powerful new capabilities that promise to redefine the way you interact with our platform. Let’s dive into what’s new! Comprehensive DICOM Images Support Our newly introduced DICOM image … Read more

Download the Free Report

Request an API Key

Fill out the form below and we’ll send you a free API key for 500 calls (approx. 50k words). No commitment, no credit card required!

Language Packs

Expand the categories below to see which languages are included within each language pack.
Note: English capabilities are automatically included within the Enterprise pricing tier. 

French
Spanish
Portuguese

Arabic
Hebrew
Persian (Farsi)
Swahili

French
German
Italian
Portuguese
Russian
Spanish
Ukrainian
Belarusian
Bulgarian
Catalan
Croatian
Czech
Danish
Dutch
Estonian
Finnish
Greek
Hungarian
Icelandic
Latvian
Lithuanian
Luxembourgish
Polish
Romanian
Slovak
Slovenian
Swedish
Turkish

Hindi
Korean
Tagalog
Bengali
Burmese
Indonesian
Khmer
Japanese
Malay
Moldovan
Norwegian (Bokmål)
Punjabi
Tamil
Thai
Vietnamese
Mandarin (simplified)

Arabic
Belarusian
Bengali
Bulgarian
Burmese
Catalan
Croatian
Czech
Danish
Dutch
Estonian
Finnish
French
German
Greek
Hebrew
Hindi
Hungarian
Icelandic
Indonesian
Italian
Japanese
Khmer
Korean
Latvian
Lithuanian
Luxembourgish
Malay
Mandarin (simplified)
Moldovan
Norwegian (Bokmål)
Persian (Farsi)
Polish
Portuguese
Punjabi
Romanian
Russian
Slovak
Slovenian
Spanish
Swahili
Swedish
Tagalog
Tamil
Thai
Turkish
Ukrainian
Vietnamese

Rappel

Testé sur un ensemble de données composé de données conversationnelles désordonnées contenant des informations de santé sensibles. Téléchargez notre livre blanc pour plus de détails, ainsi que nos performances en termes d’exactitude et de score F1, ou contactez-nous pour obtenir une copie du code d’évaluation.

99.5%+ Accuracy

Number quoted is the number of PII words missed as a fraction of total number of words. Computed on a 268 thousand word internal test dataset, comprising data from over 50 different sources, including web scrapes, emails and ASR transcripts.

Please contact us for a copy of the code used to compute these metrics, try it yourself here, or download our whitepaper.