Build-Modern-AI-Apps

Build-Modern-AI-Apps

Microsoft Official Build Modern AI Apps reference solutions and content. Demonstrate how to build Copilot applications that incorporate Hero Azure Services including Azure OpenAI Service, Azure Container Apps (or AKS) and Azure Cosmos DB for NoSQL with Vector Search.

Stars: 142

Visit
 screenshot

This repository serves as a hub for Microsoft Official Build & Modernize AI Applications reference solutions and content. It provides access to projects demonstrating how to build Generative AI applications using Azure services like Azure OpenAI, Azure Container Apps, Azure Kubernetes, and Azure Cosmos DB. The solutions include Vector Search & AI Assistant, Real-Time Payment and Transaction Processing, and Medical Claims Processing. Additionally, there are workshops like the Intelligent App Workshop for Microsoft Copilot Stack, focusing on infusing intelligence into traditional software systems using foundation models and design thinking.

README:

Build & Modernize AI Applications

This page is intended as a home page for all of the Microsoft Official Build & Modernize AI Applications reference solutions and content. The projects listed below provide access to the published Microsoft content on how to build Generative AId applications using Azure OpenAI Service, Azure Container Apps (or Azure Kubernetes Service), Azure Cosmos DB for NoSQL with vector search and Semantic Kernel providing LLM Orchestration and connectivity.

Solutions

The Solution Accelerators below are designed to demonstrate how to build AI-enabled applications and services in Azure. These solutions can be forked or cloned to help build prototypes for your organizations, helping you get started and reduce time to market. Each of the solution accelerator solutions below are also accompanied by a 1-2 day hackathon that provide a series of challenges for users to learn the concepts, technical skills and Azure Services used to build these types of applications.

Vector Search & AI Assistant (Official Solution Accelerator)

Navigate to Vector Search & AI Assistant

This is an in-depth production-quality solution accelerator with an advanced implemention. The scenario centers around a retail "Intelligent Agent" that allows users to ask questions (RAG Pattern) on vectorized product, customer and sales order data stored in Azure Cosmos DB. This solution demonstrates key concepts including how to manage conversational context (chat history), token and LLM payload management, how to implement a semantic cache for improved performance and data-model management to drive what gets vectorized and made available for vector search.

Build Modern AI Apps Hackathon Content

alt

Real-Time Payment and Transaction Processing

Navigate to Real-Time Transaction Payment Processing

The scenario centers around a payments and transactions solution. Members having accounts, each account with corresponding balances, overdraft limits and credit/debit transactions. Transaction data is replicated across multiple geographic regions for both reads and writes, while maintaining consistency. Updates are made efficiently with the patch operation. Business rules govern if a transaction is allowed. An AI powered co-pilot enables agents to analyze transactions using natural language.

Real Time Transactions Hackathon Content

Medical Claims Processing

Navigate to Medical Claims Processing

The scenario centers around a medical claims management solution. Members having coverage and making claims, providers who deliver services to the member and payers who provide the insurance coverage that pays providers for services to the members. Claims submitted are submitted in a stream and loaded into the backing database for review and approval. Business rules govern the automated or human approval of claims. An AI powered co-pilot empowers agents with recommendations on how to process the claim.

Claims Processing Hackathon Content

Workshops

Intelligent App Workshop for Microsoft Copilot Stack

The Intelligent App Workshop for Microsoft Copilot Stack is inspired by Github Copilot's impact on developer productivity. This experiential workshop is designed to demonstrate how you can infuse similar intelligence and product experience into traditional software systems. Using Microsoft's Copilot stack and practical use cases, this workshop will guide you in envisioning and creating intelligent systems that integrate foundation models throughout all stages of application development - from design and user experience to deployment.

By leveraging design thinking, Project Miyagi which provides the underlying samples for this workshop, and art-of-the-possible examples (with samples and skills from Semantic Kernel (SK), Project Miyagi, and Reddog), this workshop offers a comprehensive, hands-on exploration of how foundation models can augment your applications with intelligence to create hyper-personalized product experiences and improve productivity. We will also have an Architecture Design Session (ADS) to unlock and operationalize the full potential of AI-infused applications for your organization.

alt

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments.

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.

For Tasks:

Click tags to check more tools for each tasks

For Jobs:

Alternative AI tools for Build-Modern-AI-Apps

Similar Open Source Tools

For similar tasks

For similar jobs