Cloud LLMs: Microsoft Foundry and Amazon Bedrock
This article wires up two big cloud providers, Microsoft Foundry and Amazon Bedrock and builds the factory that routes between…
On-device LLMs with Microsoft.Maui.Essentials.AI
Modern phones and Macs ship their own neural hardware and their own on-device models. Here how to use them from…
Vector stores and completing the RAG loop
Persist embeddings in a vector store, search them, and use what you find to ground a chat model's answers, the…
Generating images with IImageGenerator
Text is not the only thing models generate. Microsoft.Extensions.AI abstracts image generation behind IImageGenerator. With troubleshooting.
Ingesting data with IEmbeddingGenerator
How IEmbeddingGenerator works in NET10: turn a PDF into chunks, chunks into vectors, and a question into ranked results, with…
Unit testing and evaluating LLMs
How can we test a component based on Microsoft.Extension.AI that gives a different answer every time it runs? Here an…
Tool calling with AIFunctionFactory
A language model knows what was in its training data and nothing else. Tool calling closes that gap with custom…
Your first IChatClient
Second post where using Microsoft.Extensions.AI I build the first AI client keeping the history of the chats and instruct the…
Why Microsoft.Extensions.AI exists
Microsoft.Extensions.AI is a small set of abstractions in the box, and providers that plug in behind the common AI providers…