mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00

Files

T

Stephen Toub dc2b109b50 .NET: Upgrade to .NET 10 (#2128 )

* Upgrade to .NET 10

- Require .NET 10 SDK
- Include net10.0 assets in all assemblies
- Move net9.0-only targets to net10.0
- Update LangVersion to latest
- Remove complicated distinctions between debug target TFMs and release target TFMs
- Remove unnecessary package dependencies when built into netcoreapp
- Clean up some ifdefs
- Clean up some analyzer warnings

* Fix CI

2025-11-22 04:14:15 +00:00

1.9 KiB

Raw Permalink Blame History

Structured Output with AI Agents

This sample demonstrates how to configure AI agents to produce structured output in JSON format using JSON schemas.

What this sample demonstrates

Configuring agents with JSON schema response formats
Using generic RunAsync method for structured output
Deserializing structured responses into typed objects
Running agents with streaming and structured output
Managing agent lifecycle (creation and deletion)

Prerequisites

Before you begin, ensure you have the following prerequisites:

.NET 10 SDK or later
Azure Foundry service endpoint and deployment configured
Azure CLI installed and authenticated (for Azure credential authentication)

Note: This demo uses Azure CLI credentials for authentication. Make sure you're logged in with az login and have access to the Azure Foundry resource. For more information, see the Azure CLI documentation.

Set the following environment variables:

$env:AZURE_FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project" # Replace with your Azure Foundry resource endpoint
$env:AZURE_FOUNDRY_PROJECT_DEPLOYMENT_NAME="gpt-4o-mini"  # Optional, defaults to gpt-4o-mini

Run the sample

Navigate to the FoundryAgents sample directory and run:

cd dotnet/samples/GettingStarted/FoundryAgents
dotnet run --project .\FoundryAgents_Step05_StructuredOutput

Expected behavior

The sample will:

Create an agent named "StructuredOutputAssistant" configured to produce JSON output
Run the agent with a prompt to extract person information
Deserialize the JSON response into a PersonInfo object
Display the structured data (Name, Age, Occupation)
Run the agent again with streaming and deserialize the streamed JSON response
Clean up resources by deleting the agent

1.9 KiB Raw Permalink Blame History