Build with AI

Creates a ChatGPT-like frontend with API backend that uses OpenAI chat models to answer questions about uploaded documents.

Shows how Contoso Real Estate uses enterprise documents to generate responses to user queries with a LangChain serverless application.

Creates a ChatGPT-like frontend with API backend that uses OpenAI chat models to answer questions about uploaded documents.

Creates a chat frontend with an API backend using OpenAI chat models to answer questions about rows in a PostgreSQL database.

Demonstrates a GenAI chat application using managed identity for Azure OpenAI access.

Creates a ChatGPT-like frontend with API backend that uses OpenAI chat models to answer questions about uploaded documents.

A foundation for building RAG applications with LlamaIndex.ai and Python.

Demonstrates debugging responses, restyling, revisiting chat history, and resetting the chat.

Build simple AI assistants tailored to your needs via function calling, allowing for connection of LLMs to external tools and systems, including tasks such as: sending emails, running custom functions, and answering questions.

A foundation for building advanced RAG applications with LlamaIndex.ai and JavaScript.

Demonstrates monitoring models and LLM applications, troubleshooting retrieval and tool execution issues, and improving the RAG pipeline.

Shows how to chat with uploaded images using OpenAI vision models such as GPT-4o.

Shows how bank users can use GenAI chat to check account balances, review transactions, and initiate payments.

A simple C#/.NET chat application that uses the Semantic Kernel library and managed identity for Azure OpenAI access.

Example Azure OpenAI deployment and RBAC role for your user account for keyless access.

Provision an Azure OpenAI resource with keyless authentication and use the Python OpenAI SDK to connect to it with your locally logged in Azure account.

Shows how to build a Generative-AI application using Azure Cosmos DB for NoSQL using its new vector search capabilities and Azure OpenAI Service and Semantic Kernel

This project integrates SignalR with Azure OpenAI. It showcases how to create a seamless group chat experience using SignalR for real-time communication, enhanced by the intelligence of Azure OpenAI.

A Spring Petclinic Microservice with OpenAI running on Azure Container Apps environment, with additional Azure services and Azure Container Apps features.

A C#/.NET chat application using .NET Aspire and the Microsoft.Extensions.AI library with OpenAI. It uses managed identity for Azure OpenAI access

Reusable OpenAI secure UI and infrastructure for AI Chat with Azure

Perform entity extraction on text, PDFs, images, and webpages using Azure OpenAI structured outputs and the Python openai package.

Use OpenAI models securely without API keys using keyless (Entra) authentication.

A customer assistant application using Semantic Kernel, that allows a customer support person to query and make changes to customer information.

An app that lets users ask questions about a knowledge base over a real-time voice interface, using Azure AI Search and GPT-4o Realtime API.

Contoso-Creative-Writer: a creative writing assistant that shows how to orchestrate multiple models together using Prompty and Azure OpenAI. Includes the full GenAIOps: CI/CD, evaluation, tracing, monitoring, and experimentation!

A Jakarta EE based Cargo Tracker application with Open Liberty running on Azure Kubernetes Service (AKS) with Azure Database for PostgreSQL and Azure OpenAI.

This template demonstrates Dall-E text to image generation with Azure Redis semantic caching, which enables the same picture to be reused for text inputs that are similar in meaning but different in syntax. Azure Redis semantic cache improves the consistency and performance of the content generation.

Leverage advanced content understanding capabilities to uncover insights, relationships, and patterns from large audio and text-based data sets.

This solution contains a simple chat application that is deployed to Azure Container Apps. There are instructions for deployment through GitHub Codespaces, VS Code Dev Containers, and your local development environment.

This solution deploys a web-based chat application with an AI agent running in Azure Container Apps. The agent leverages the Azure AI Agent service and utilizes Azure AI Search for knowledge retrieval from uploaded files, enabling it to generate responses with citations.

A solution accelerator project harnessing the capabilities of Azure AI Language to augment an existing Azure OpenAI RAG chat app. Utilize Conversational Language Understanding (CLU) and Custom Question Answering (CQA) to dynamically improve a RAG chat experience.

Process claims, invoices, contracts and other documents with speed and accuracy by extracting information from unstructured content and mapping to a structured format.

Accelerate the migration of legacy code to modern languages by leveraging a team of autonomous agents

A web-based chat application with an API backend that leverages OpenAI chat models to answer questions using Neon Serverless Postgres.

Chainlit Agent: Intelligent Assistant with Azure AI Agent. With Frontend with chainlit and backend with fastapi. Using Azure AI Agent service for RAG pattern.

This project is designed as a Proof of Concept (PoC) to explore the innovative realm of generative AI within the context of multi-agent architectures. By leveraging .NET and Microsoft Semantic Kernel AI orchestration framework.

The Multi-Agent Custom Automation Engine Solution Accelerator is an AI-driven orchestration system that manages a group of AI agents to accomplish tasks based on user input. Powered by AutoGen, Azure OpenAI, Cosmos, and infrastructure services, it provides a ready to go application to use as a reference, allowing you to hit the ground running.

Enable intelligent, memory-enhanced LLM chat experiences using Azure Managed Redis. This template demonstrates how to persist and recall user conversations using AMR as a vector database or key-value store—ideal for building contextual, stateful AI assistants. Built with Azure Developer CLI (azd) for streamlined deployment.

The sample is forked from https://github.com/Azure-Samples/serverless-chat-langchainjs and updated to demonstrate the integration with Purview APIs to support Data Security and Compliance policy enforcement from within the application.

Healthcare Agent Orchestrator is a multi-agent accelerator that coordinates modular specialized agents across diverse data types and tools like M365 and Teams to assist multi-disciplinary healthcare workflows—such as cancer care.

This sample showcases how Purview API can be integrated to audit and secure AI prompts and responses

This solution accelerator empowers organizations to make faster, smarter decisions at scale by leveraging agentic AI solutions built on a unified data foundation with Microsoft Fabric. With seamless integration of Azure AI Foundry agents and Semantic Kernel orchestration, teams can design intelligent workflows that automate routine processes, streamline operations, and enable natural language querying across enterprise datasets. This ensures that governed, high-quality data is accessible not only to technical specialists but also to business users, creating a shared environment where insights are surfaced more easily and decisions are grounded in trusted information. By unifying data access and applying AI in the flow of work, organizations gain the agility to respond rapidly to changing business needs, foster collaboration across teams, and drive innovation with greater confidence.

This template creates a working medallion architecture in Microsoft Fabric with data models in multiple domains (customer, product, sales, finance), sample data uploaded bronze lakehouse, PySpark notebooks with automated execution to load data into bronze, validate in silver, and be ready in gold. Pre-built Power BI dashboard for sales analysis is created and uploaded to Fabric, ready for sales analysis.

The Release Manager Assistant (RMA) is a solution accelerator designed to augment release managers with AI-driven intelligence, multi-system integration, and real-time decision support. It simplifies the release lifecycle from planning to post-deployment analysis, all through a unified and contextual interface.

Call Center Real-time Voice Agent solution accelerator is a lightweight template to create speech-to-speech voice agents that deliver personalized self-service experiences and natural-sounding voices, seamlessly integrated with telephony systems. This solution accelerator uses Azure Voice Live API and Azure Communication Services.

This project features a web application and an agent designed to help users process information from their SharePoint content and generate summary reports. The application leverages the Azure AI Foundry SDK to host and communicate with the agent, which utilizes the Copilot Retrieval API for semantic queries of relevant SharePoint content. The Retrieval API relies on SharePoint’s built-in semantic index and access control.

AZD template for deploying Azure Copilot Studio with Azure AI search

NLWeb is an open project developed by Microsoft that aims to make it simple to create a rich, natural language interface for websites using the model of their choice and their own data. This sample demonstrates developers can easily deploy the NLWeb as a foundry agent.

This solution accelerator empowers organizations to build intelligent, conversational customer service experiences by leveraging Azure AI Foundry's agent framework. With seamless integration of specialized AI agents, and enterprise-grade data services, teams can create chatbots that provide personalized product recommendations, answer policy questions, and deliver exceptional customer support. The solution combines a modern e-commerce frontend with an intelligent backend that uses an orchestrator agent to route customer queries to specialized agents (Product Lookup and Policy/Knowledge), ensuring accurate, contextual responses grounded in product catalogs and policy documents. By unifying AI capabilities with scalable cloud infrastructure, organizations can deliver 24/7 customer support that understands context, maintains conversation history, and provides actionable insights to improve customer satisfaction and operational efficiency.

This solution accelerator provides a working solution for manufacturing asset performance monitoring, real-time anomaly detection, and anomaly notification. The manufacturing facility telemetry data is synthetically generated with the Telemetry Data Simulator. This architecture can be extended to other industries as long as the appropriate data is generated or actual operations data is ingested into the Azure Event Hub, and related component configurations and Kusto Query Language (KQL) code are updated accordingly.

Shows how bank users can use conversational agents to check account balances, credit cards, review transactions, and initiate payments. It's built with Microsoft Agent Framework (python) and Microsoft Foundry.

A multi-agent AI solution that automates prior authorization for health plan payers. Four specialized Foundry Hosted Agents — Compliance, Clinical Reviewer, Coverage, and Synthesis — evaluate PA requests against coverage policies and produce auditable approve/pend recommendations in under 2 minutes. Built with Microsoft Foundry, Microsoft Agent Framework, Azure Container Apps, and MCP healthcare data servers. Deploy with a single azd up command.

A reusable Chat UI for AI experiences, built on the Azure OpenAI Responses API standard and Fluent AI components. It connects to a Microsoft Foundry project and is designed to be deployed on Azure Kubernetes Service (AKS) clusters. The application features a chat interface, chat history, streaming responses, and a pluggable provider architecture that supports both live Microsoft Foundry backends and an in-memory mock mode for offline development.

Deploy AI-powered video analysis at the edge using Azure Video Indexer on Arc-enabled AKS clusters with GPU support, combined with AI agents built on Azure OpenAI for automated video analysis workflows.

The Microsoft IQ Solution Accelerator is an AI-powered enterprise intelligence accelerator that enables faster, more informed decisions by unifying enterprise data, business knowledge, and execution workflows into a shared context. It connects unified data, semantic models and ontologies in Fabric IQ, enterprise knowledge and retrieval in Foundry IQ, and work context in Work IQ to identify signals, assess impact, and recommend disruption mitigation, supporting human decision-making and coordinated responses.