Blog | Advertise | View Online

Your trusted source for Cloud, DevOps, and SRE guidance with Chris Pietschmann!

Sponsor: Are you interested in sponsoring the Build5Nines Newsletter? Contact us for opportunities.

Build an AI-Ready Infrastructure in Microsoft Azure

An AI-ready infrastructure involves hardware, software, and services optimized for AI workloads, providing robust data handling, high computational power, and real-time analytics. Microsoft Azure networking and infrastructure offers scalable cloud services, secure data management, and specialized compute resources like GPUs. Key services include Azure OpenAI Service for hosting Large Language Models (LLMs), Azure Data Factory for data integration, and a diverse set of compute options. This article explains how Microsoft Azure services apply towards setting up an AI-Ready Infrastructure in the cloud.

What are AI Agents and Agentic AI?

AI Agents are more advanced implementations of artificial intelligence (AI) built to more autonomously perform tasks, make decisions, and interact with users or other systems. These agents are designed to simulate human-like “cognitive” functions, enabling them to process information, learn from interactions, and adapt to new scenarios without direct human intervention.

Introduction to Building AI Agents with Microsoft Semantic Kernel

Microsoft Semantic Kernel is an innovative, open-source SDK designed to seamlessly integrate Large Language Models (LLMs) with conventional programming languages like C#, Python, and Java. By utilizing Semantic Kernel, developers can create powerful, AI-driven applications without needing to become AI experts. This introduction will guide you through the fundamental concepts, features, and benefits of using Microsoft Semantic Kernel, along with practical examples to get you started.

Introduction to Building AI Agents with LangChain and Python

This article introduces you to the process of building AI agents with LangChain. We’ll walk you through the essential steps from setting up your environment all the way to an introduction of more advanced features. After reading, you’ll have a great understanding of how to use LangChain to build AI agents using Python.

Detecting AI Hallucinations using Semantic Entropy

Artificial Intelligence (AI) and the use of Large Language Models (LLMs) has transformed numerous fields, from healthcare to entertainment, by enabling machines to understand and generate human-like text. However, one significant challenge in deploying AI, especially LLMs, is the phenomenon of AI “hallucinations.” These are instances where the AI generates plausible-sounding but factually incorrect or nonsensical responses. Addressing this issue is crucial for the reliability and trustworthiness of AI systems.

This article looks at a newly published method to detect AI hallucinations using semantic entropy, and how this technique helps identify unreliable outputs enabling increased dependability of LLM generated responses.