How To

Evaluate Small Language Models for RAG using Azure Prompt Flow (LLama3 vs Phi3)

Introduction: Recently, small language models have made significant progress in terms of quality and context size. These advancements have enabled new possibilities, making it increasingly viable to leverage these models for retrieval-augmented generation (RAG) use cases. Particularly in scenarios where cost sensitivity is a key consideration, small language models offer an attractive alternative.   This post […]

Evaluate Small Language Models for RAG using Azure Prompt Flow (LLama3 vs Phi3) Continue Reading

Completing DFSR SYSVOL migration of domains that use Entra ID passwordless SSO

Heya folks, Ned here again. A customer recently reached out to me in the comments section of the well-worn Streamlined Migration of FRS to DFSR SYSVOL article, asking about a problem he was seeing with a single DC that wouldn’t complete the process. Today I’ll explain how to fix the issue introduced by a very modern authentication add-on. Background  Decades

Completing DFSR SYSVOL migration of domains that use Entra ID passwordless SSO Continue Reading

SuperRAG – How to achieve higher accuracy with Retrieval Augmented Generation

One of the most common use cases for generative AI is Retrieval Augmented Generation (RAG).  RAG enables you to inform the LLM about your business data without the need to retrain it.  It happens in 3 basic steps:  Retrieve relevant documents based on a query or chat message from your user.  This is usually done

SuperRAG – How to achieve higher accuracy with Retrieval Augmented Generation Continue Reading

First Issuance manual, with automated renewals

Hey all Rob Greene again. Seems like I have been on this PKI kick lately, and today is not going to be any different. Occasionally, I will get a customer who must get certificates issued for things like Web sites, and they must have custom Subject Alternative Name (SAN) DNS values on the issued certificate. 

First Issuance manual, with automated renewals Continue Reading

How implementing a trust fabric strengthens identity and network

The identity security landscape is transforming rapidly. Every digital experience and interaction is an opportunity for people to connect, share, and collaborate. But first, we need to know we can trust those digital experiences and interactions. Customers note a massive rise in the sheer number of identities they need to enable, connect, and protect. These

How implementing a trust fabric strengthens identity and network Continue Reading

Microsoft Defender for Cloud Extends Support to Enable Increased API Security Testing Visibility

Expanded API Security Testing Collaboration and Environment Support  At Microsoft Ignite 2023, Microsoft Defender for Cloud announced the support of API security testing integration, enabling Defender for Cloud to provide full lifecycle API protection from code to cloud, which makes Microsoft the only cloud provider that enables organizations to assess risk and address API threats

Microsoft Defender for Cloud Extends Support to Enable Increased API Security Testing Visibility Continue Reading

New capabilities to help you secure your AI transformation

AI is transforming our world, unlocking new possibilities to enhance human abilities and to extend opportunities globally. At the same time, we are also facing an unprecedented threat landscape with the speed, scale, and sophistication of attacks increasing rapidly. To meet these challenges, we must ensure that AI is built, deployed, and used responsibly with

New capabilities to help you secure your AI transformation Continue Reading

Finetune Small Language Model (SLM) Phi-3 using Azure Machine Learning

Motivations for Small Language Models: Efficiency: SLMs are computationally more efficient, requiring less memory and storage, and can operate faster due to fewer parameters to process. Cost: Training and deploying SLMs is less expensive, making them accessible to a wider range of businesses and suitable for applications in edge computing. Customizability: SLMs are more adaptable

Finetune Small Language Model (SLM) Phi-3 using Azure Machine Learning Continue Reading

Security above all else—expanding Microsoft’s Secure Future Initiative

Last November, we launched the Secure Future Initiative (SFI) to prepare for the increasing scale and high stakes of cyberattacks. SFI brings together every part of Microsoft to advance cybersecurity protection across our company and products. Since then, the threat landscape has continued to rapidly evolve, and we have learned a lot. The recent findings

Security above all else—expanding Microsoft’s Secure Future Initiative Continue Reading

Unlocking the Potential: The Benefits and Requirements of a Vector Database

Generative AI is revolutionizing our interaction with data, enabling dynamic new ways to engage with information—from conversational interfaces to generating content like code snippets or summaries. Vector databases, particularly pivotal in this evolution, play a critical role in enabling these sophisticated interactions. Understanding the value of vector databases  Vector databases are responsible for advanced data

Unlocking the Potential: The Benefits and Requirements of a Vector Database Continue Reading