Posts

ML.NET Predictions with In-Memory Data, CSV Files and SQL Server

-
Image
In this article, we will see the ML.NET with the prediction implementation with In-Memory Data, CSV file data, and SQL Server. We will create one solution that has four projects. The first one, mllib , is a class library with a reusable class named DataTrainer . It takes the data, prepares the columns and trains a model. The other three projects are console applications and all of them use DataTrainer . The only thing that changes from one project to another is the place where the data comes from. mllib : class library that has the DataTrainer class. mlnetdemo : data is kept in memory in a C# list. It predicts the price of a house from its size. loadtextfiledemo : data is read from a CSV file named orders.csv. It predicts whether an order will be returned. mlnet_sql : data is read from the Sales.SalesOrderHeader table of the AdventureWorks2025 database in SQL Server. It predicts whether an order was placed online or through a reseller. What is ML.NET? ML.NET is an open sou...
Read more

ASP.NET Core 10: Build an AdventureWorks AI Agent with Microsoft Agent Framework, ASP.NET Core 10, and Blazor WebAssembly

-
Image
A useful business assistant must do more than generate a convincing paragraph. It must understand a request, ask for missing details, choose an allowed operation, and return trustworthy data. In this walkthrough, we build that assistant around AdventureWorks using a .NET 10 API, Azure OpenAI, Microsoft Agent Framework, and a Blazor WebAssembly chat interface. The solution is named AdventureWorks_Agents . Its API project is AdventureWorksTool , and its browser application is AdventureWorksClient . The agent selects from 22 read-only database tools. The browser displays the agent's message and the actual SQL result rows separately. What is Microsoft Agent Framework? The official product name is Microsoft Agent Framework , abbreviated as MAF in this article. “Microsoft Agentic Framework” describes the idea, but is not the official name. It is an SDK for building agents and agent workflows. An agent combines model access, instructions, tools, and conversation context so it can dec...
Read more