AI-in-a-Box leverages the expertise of Microsoft across the globe to develop and provide AI and ML solutions to the technical community. Our intent is to present a curated collection of solution accelerators that can help engineers establish their AI/ML environments and solutions rapidly and with minimal friction.

This repo helps you to build a team of AI agents with Autogen

Serverless AI agent using LangChain.js and Model Context Protocol (MCP) integration to order burgers from a burger restaurant

eShopLite is a set of reference .NET applications implementing an eCommerce site with features like Semantic Search, MCP, Reasoning models and more.

A centralized hub for platform engineering teams, providing resources, best practices, and automation tools. Includes IaC templates, blueprints, and operational guides to help build scalable, secure, and efficient platforms for cloud-native environments and DevSecOps workflows.

Simple starting point function to host LangChains with LLMs and other tools in an Azure Function.

Packaged app samples to accelerate devs journey to cloud

Sample MCP Server and MCP client with Aspire

The Doc Intelligence in-a-Box project leverages Azure AI Document Intelligence to extract data from PDF forms and store the data in a Azure Cosmos DB. This solution, part of the AI-in-a-Box framework by Microsoft Customer Engineers and Architects, ensures quality, efficiency, and rapid deployment of AI and ML solutions across various industries.

eShopLite - Semantic Search is a reference .NET application implementing an eCommerce site with Search features using Keyword Search and Semantic Search.

This Quickstart uses Azure Developer command-line (azd) tools to create functions that respond to HTTP requests. After testing the code locally, you deploy it to a new serverless function app you create running in a Flex Consumption plan in Azure Functions. This follows current best practices for secure and scalable Azure Functions deployments

An `azd` (Azure Developer CLI) template for getting a Next.js app running on Azure Container Apps with CDN and Application Insights.

This C# demo is based on azure-search-openai-demo and uses a static web app for the frontend and Azure functions for the backend API's. This solution uses the Azure Functions OpenAI triggers and binding extension for the backend capabilities.

This sample shows how to take text documents as a input via BlobTrigger, does Text Summarization & Sentiment Score processing using the AI Congnitive Language service, and then outputs to another text document using BlobOutput binding. Uses Azure Functions Python v2 programming model.

This Quickstart uses Azure Developer command-line (azd) tools to create functions that respond to HTTP requests. After testing the code locally, you deploy it to a new serverless function app you create running in a Flex Consumption plan in Azure Functions. This follows current best practices for secure and scalable Azure Functions deployments

This provides some reference use cases while using Azure API Center

This provides sample .NET apps to be deployed to Azure Container Apps

Demo repository to show how to use Managed Identity on Azure Functions to connect to Power Apps Web API.

Reusable OpenAI secure UI and infrastructure for AI Chat with Azure

Azure Developer CLI extension for local development. One command starts all services with auto-detected dependencies, real-time dashboard, health monitoring, and GitHub Copilot AI integration via MCP.

Web App to collect thoughts about articles, and blob posts read and then aggregate them in a Reading Notes blog post

This repository contains the implementation of an order processing workflow with Durable Functions in C#. The sample is deployed to Azure Functions Flex Consumption using the Azure Developer CLI (azd) and is configured with managed identity as the authentication mechanism.

eShopLite - Semantic Search is a reference .NET application implementing an eCommerce site with Search features using Keyword Search and Semantic Search using ChromaDB

This Quickstart uses Azure Developer command-line (azd) tools to create functions that respond to HTTP requests. After testing the code locally, you deploy it to a new serverless function app you create running in a Flex Consumption plan in Azure Functions. This follows current best practices for secure and scalable Azure Functions deployments

This sample shows how to take text documents as a input via BlobTrigger, does Text Summarization & Sentiment Score processing using the AI Congnitive Language service, and then outputs to another text document using BlobOutput binding.

This workshop will guide you on how to fast start your dev experience, how to deploy to Azure, and how to detect potential issues with your code during runtime.

Sample repository that shows how to use azd with Logic Apps and Dataverse API

This Quickstart uses Azure Developer command-line (azd) tools to create functions that respond to HTTP requests. After testing the code locally, you deploy it to a new serverless function app you create running in a Flex Consumption plan in Azure Functions. This follows current best practices for secure and scalable Azure Functions deployments

An azd template (Bicep) for deploying Azure Integration Services, including Azure API Management, Function App, Logic App, Service Bus and Event Hubs namespace, along with supporting resources such as Application Insights, Key Vault and Storage Account. This template is ideal for demos, testing or getting started with Azure Integration Services.

This Quickstart uses Azure Developer command-line (azd) tools to create functions that respond to HTTP requests. After testing the code locally, you deploy it to a new serverless function app you create running in a Flex Consumption plan in Azure Functions. This follows current best practices for secure and scalable Azure Functions deployments