Getting Started with Agents Using Microsoft Foundry
A sample Azure solution that deploys a web-based chat application backed by Microsoft Foundry's Agent Service, using file search over uploaded documents for cited, retrieval-grounded answers with built-in monitoring.
This sample deploys a web-based chat application with an AI agent running in an Azure Container App, built on Microsoft Foundry's Agent Service. The agent uses file search or Azure AI Search to retrieve knowledge from uploaded files and generates responses with citations, and includes built-in monitoring and tracing for troubleshooting and performance analysis.
The solution allows configuring and deploying different AI models, with adjustable model capacity and knowledge-retrieval methods. It can be deployed through GitHub Codespaces, VS Code Dev Containers, or a local development environment, and creates a Microsoft Foundry project and Foundry Tools as part of the deployment.
It is defined with Bicep infrastructure-as-code templates and licensed under MIT.