Categoría: IA

Implementing Embeddings via ONNX with Semantic Kernel for Local RAG Solutions in .NET

Flowchart diagram showing a RAG pipeline: a user sends a request to a .NET API, which performs embedding generation (highlighted with a large magnifying glass), then queries a vector database, and finally uses Phi-3 LLM to generate the response.

Introduction In our previous article "Building a RAG API with .NET, Semantic Kernel, Phi-3 and Qdrant", we focused on setting up a local Retrieval-Augmented Generation (RAG) API with minimal dependencies on external services. One key piece of that architecture, which we only briefly touched upon, is the embedding service. In this follow-up, we'll dive deeper … Sigue leyendo Implementing Embeddings via ONNX with Semantic Kernel for Local RAG Solutions in .NET →

Automate Unit Tests in .NET with GitHub Copilot Agents: Prompt, Iterate, and Win!

Running .NET unit tests generated by Copilot using dotnet test

Introduction Writing effective unit tests is a crucial part of professional software development, especially in modern .NET projects. Lately, I have been refining my approach to unit testing by leveraging GitHub Copilot and the new Copilot Agents feature in Visual Studio Code. Instead of manually writing every test, I discovered a powerful workflow where AI … Sigue leyendo Automate Unit Tests in .NET with GitHub Copilot Agents: Prompt, Iterate, and Win! →

🚀 Building a RAG API with .NET, Semantic Kernel, Phi-3, and Qdrant: Enrich Your E-commerce Experience

Basic flow of a RAG

Learn how to build a powerful RAG (Retrieval-Augmented Generation) API using .NET, Microsoft Semantic Kernel, Phi-3, and Qdrant. Combine your private e-commerce data with LLMs to create smarter, grounded responses. Simple and easy step-by-step! Introduction In previous articles we explored the power of Phi-3 for image analysis and automating e-commerce product descriptions. Now, let's take … Sigue leyendo 🚀 Building a RAG API with .NET, Semantic Kernel, Phi-3, and Qdrant: Enrich Your E-commerce Experience →

Extend GitHub Copilot in VS Code with Custom .NET Tools via MCP

Learn how to create a custom MCP (Model Context Protocol) server with .NET and integrate it into Visual Studio Code. Step-by-step guide with a simple code example. Introduction As GitHub Copilot and AI-powered agents become key components of modern development workflows, integrating custom logic into your IDE is more valuable than ever. Model Context Protocol … Sigue leyendo Extend GitHub Copilot in VS Code with Custom .NET Tools via MCP →

Automate E-Commerce Product Descriptions with .NET, Microsoft Semantic Kernel & SLM (Phi-3)

In the highly competitive world of e-commerce, the quality and accuracy of product descriptions can make the difference between a successful sale and an abandoned cart. Detailed, attractive, and well-written descriptions not only inform customers but also enhance your site's SEO, driving more organic traffic. In this post, I'll demonstrate how you can automate the … Sigue leyendo Automate E-Commerce Product Descriptions with .NET, Microsoft Semantic Kernel & SLM (Phi-3) →

Image analysis with «Phi-3 Vision»

In this blog post, we'll explore how to leverage the new Phi-3 Vision model within a .NET application. I'll walk you through the entire process from downloading the model to writing and executing the code. Step 1: Download the Phi-3 Model To get started, we need to download the Phi-3 Vision model using the huggingface-cli … Sigue leyendo Image analysis with «Phi-3 Vision» →