AI Agents using Semantic Kernel SDK

 >dotnet new console (After creating a folder in VSCode run this command to create a C# project)

>dotnet add package Microsoft.SemanticKernel --version 1.30.0 (This command will install the Semantic Kernal SDK

>dotnet run

Create Azure OpenAI end-point and deployment and the following code is a hello-world code to test your setup:

using Microsoft.SemanticKernel;

// Populate values from your OpenAI deployment

var modelId = "<Model Name From Deployment>";

var endpoint = "<EndPoint URL>";

var apiKey = "<API KEY>";

// Create a kernel with Azure OpenAI chat completion

var builder = Kernel.CreateBuilder().AddAzureOpenAIChatCompletion(modelId, endpoint, apiKey);

// Build the kernel

Kernel kernel = builder.Build();

var result = await kernel.InvokePromptAsync("Give me a list of breakfast foods with eggs and cheese");

Console.WriteLine(result);

How to write a good prompt?

 

Links to LLM Articles

• Crescendo Attack: 2404.01833
• The Price of Intelligence: The Price of Intelligence - ACM Queue
• https://arxiv.org/abs/2502.11371v1
• https://techcommunity.microsoft.com/blog/adforpostgresql/introducing-the-graphrag-solution-for-azure-database-for-postgresql/4299871
• https://www.microsoft.com/en-us/research/blog/lazygraphrag-setting-a-new-standard-for-quality-and-cost/?msockid=3a065a80a9a960181f744951a89b618b
• https://techcommunity.microsoft.com/blog/azure-ai-services-blog/graphrag-costs-explained-what-you-need-to-know/4207978
• https://github.com/Azure-Samples/graphrag-accelerator
• https://microsoft.github.io/graphrag/
• https://techcommunity.microsoft.com/blog/azure-ai-services-blog/announcing-new-fine-tuning-capabilities-with-o1-mini-model-on-azure-openai-servi/4358186

Azure OpenAI Architecture Patterns & Deployment Patterns

Sharing some useful links that will help customers architect Azure OpenAI solution using the best practices:

(1) Azure OpenAI Landing Zone reference architecture (microsoft.com),

(2) Protect Azure OpenAI using Azure Web Application Firewall on Azure Front Door | Microsoft Learn, 

(3) Azure OpenAI Architecture Patterns and implementation steps - Microsoft Community Hub,

(4) Baseline OpenAI end-to-end chat reference architecture - Azure Reference Architectures | Microsoft Learn,

(5) Azure security baseline for Azure OpenAI | Microsoft Learn .

Visual Studio Code | You don't have permissions to push username/repository on GitHub

If you get the following error message when you are trying to commit code from Visual Studio Code to GitHub Repo. The following is an easy fix:

[Step # 1] Go to your control panel -> Credential Manager:

[Step # 2] remove all the GitHub related credentials.

[Step # 3] Then go back to Visual Studio Code and try to commit your code again.

[Step # 4] You will be given a pop-up screen to login to GitHub. Do it and it will solve this problem. 

Installing and Uninstalling Windows Subsystem for Linux (WSL) on Windows 11

 

Installing WSL : (56) Installing Windows Subsystem for Linux (WSL) on Windows 11 - YouTube

Uninstalling WSL : (56) Uninstall Windows Subsystem for Linux (WSL) on Windows 11 Machine - YouTube

Microsoft Azure | Key Phrase Extraction using Azure.AI.TextAnalytics;

Problem Statement:  Extract key phrases from a sentence or a paragraph.

Solution:

Azure documentation link : What is key phrase extraction in Azure Cognitive Service for Language? - Azure Cognitive Services | Microsoft Learn

(Step-1) In Azure Portal create a 'Language Service' under 'cognitive services'.

(Step-2) Select 'Custom text classification & Custom names entity recognition' as shown above.

(Step-3) Create a service.

(Step-4) When the services is created extract the key & uri:

(Step-5) Use the following C# code, insert the key, URI and a sentence. [I used visual studio and installed all the right packages]. That's it :)

using Azure;

using System;

using Azure.AI.TextAnalytics;

namespace KeyPhraseExtractionExample

{

    class Program

    {

        private static readonly AzureKeyCredential credentials = new AzureKeyCredential(<<INSERT KEY>>);

        private static readonly Uri endpoint = new Uri(<<INSERT URI>>);

        // Example method for extracting key phrases from text

        static void KeyPhraseExtractionExample(TextAnalyticsClient client)

        {

            try

            {

                var response = client.ExtractKeyPhrases(<<INSERT SENTENSE>>);

            

                // Printing key phrases

                Console.WriteLine("Key phrases:");

                foreach (string keyphrase in response.Value)

                {

                    Console.WriteLine($"\t{keyphrase}");

                }

            }

            catch (RequestFailedException e)

            {

                Console.WriteLine(e);

            }

        }

        static void Main(string[] args)

        {

            var client = new TextAnalyticsClient(endpoint, credentials);

            KeyPhraseExtractionExample(client);

            Console.Write("Press any key to exit.");

            Console.ReadKey();

        }

    }

}