The Sarus Blog

Welcome to the Sarus Blog. Here we discuss product updates, industry examples, privacy, data protection, data governance, math, machine learning, and much more! 

[Product Update] Sarus Data Catalog

Introducing the Catalog feature: Empowering Data Consumers for Data Collaboration

Considerations around Privacy in RAG-Based Architectures

Taking RAG to production? Here are the key privacy and security considerations

Generate Time-Series Data with Fine-Tuned Mistral 7B Instruct

Small open-weights vs OpenAI API for synthetic data

David vs. Goliath in AI

Can Fine-Tuned Smaller Models like XLNet, DistilBERT and T5 Compete with Large Models for Classification Tasks?

Quickly Generate Time-Series Synthetic Data with OpenAI’s Fine-Tuning API

Beyond Few-Shot Learning: How LLMs Excel in Synthetic Data Generation Through Fine-Tuning

Easy PII replacement for OpenAI, Mistral and Anthropic APIs

With Sarus Arena open-source application

Clean Rooms Differential Privacy: user protection backed by math

Empowering organizations to safeguard user privacy with confidence and ease

Sarus+MongoDB: Privacy-safe AI and Analytics for healthcare

Unlocking the power of healthcare data with MongoDB and Sarus. Enabling privacy-safe AI and analytics for improved patient outcomes.

EIC selects Sarus for funding through its prestigious Accelerator Program

Pioneering privacy in data analytics & AI: Sarus Technologies and the European Innovation Council Accelerator journey.

Qrlew: the library that turns any SQL query into a privacy-safe one

A new open source product to easily rewrite a wide variety of SQL queries into differentially private ones.

The LLM Dilemma: Self-Hosted vs. Public API Solutions

How to chose the best LLM for your use-case: in-house vs public API comparison.

[NEW] SarusLLM: Unleash the power of Generative AI while keeping private data safe

SarusLLM is intended for businesses and developers who are interested in leveraging the full power of open source LLMs while ensuring no sensitive information is accessed, embarked in the model weights and will be revealed.