chore: import upstream snapshot with attribution
dotnet-build-and-test / dotnet-test-functions (push) Has been cancelled
dotnet-build-and-test / paths-filter (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Debug, windows-latest, net9.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Release, ubuntu-latest, net10.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Release, ubuntu-latest, net8.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Release, windows-latest, net472) (push) Has been cancelled
dotnet-build-and-test / dotnet-test (Release, integration, true, ubuntu-latest, net10.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-test (Release, integration, true, windows-latest, net472) (push) Has been cancelled
dotnet-build-and-test / dotnet-foundry-hosted-it (push) Has been cancelled
dotnet-build-and-test / dotnet-build-and-test-check (push) Has been cancelled
dotnet-build-and-test / Integration Test Report (push) Has been cancelled
CodeQL / Analyze (csharp) (push) Has been cancelled
CodeQL / Analyze (python) (push) Has been cancelled
dotnet-build-and-test / dotnet-test-functions (push) Has been cancelled
dotnet-build-and-test / paths-filter (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Debug, windows-latest, net9.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Release, ubuntu-latest, net10.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Release, ubuntu-latest, net8.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Release, windows-latest, net472) (push) Has been cancelled
dotnet-build-and-test / dotnet-test (Release, integration, true, ubuntu-latest, net10.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-test (Release, integration, true, windows-latest, net472) (push) Has been cancelled
dotnet-build-and-test / dotnet-foundry-hosted-it (push) Has been cancelled
dotnet-build-and-test / dotnet-build-and-test-check (push) Has been cancelled
dotnet-build-and-test / Integration Test Report (push) Has been cancelled
CodeQL / Analyze (csharp) (push) Has been cancelled
CodeQL / Analyze (python) (push) Has been cancelled
This commit is contained in:
wehub-resource-sync
@@ -0,0 +1,98 @@
|
||||
# Creating an AIAgent with various providers
|
||||
|
||||
These samples show how to create an AIAgent instance using various providers,
|
||||
organized by provider. This is not an exhaustive list, but shows a variety of
|
||||
the more popular options.
|
||||
|
||||
For other samples that demonstrate how to use AIAgent instances,
|
||||
see the [Getting Started With Agents](../Agents/README.md) samples.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
See the README.md for each sample for the prerequisites for that sample.
|
||||
|
||||
## Providers
|
||||
|
||||
### [A2A](./a2a/)
|
||||
|
||||
| Sample | Description |
|
||||
| --- | --- |
|
||||
| [Agent with A2A](./a2a/Agent_With_A2A/) | Create an AIAgent for an existing A2A agent |
|
||||
|
||||
### [Anthropic](./anthropic/)
|
||||
|
||||
| Sample | Description |
|
||||
| --- | --- |
|
||||
| [Agent with Anthropic](./anthropic/Agent_With_Anthropic/) | Create an AIAgent using Anthropic Claude models |
|
||||
| [Running](./anthropic/Agent_Anthropic_Step01_Running/) | Basic Anthropic agent usage |
|
||||
| [Reasoning](./anthropic/Agent_Anthropic_Step02_Reasoning/) | Using Anthropic reasoning capabilities |
|
||||
| [Function Tools](./anthropic/Agent_Anthropic_Step03_UsingFunctionTools/) | Using function tools with Anthropic |
|
||||
| [Skills](./anthropic/Agent_Anthropic_Step04_UsingSkills/) | Using skills with Anthropic agents |
|
||||
|
||||
### [Azure](./azure/)
|
||||
|
||||
| Sample | Description |
|
||||
| --- | --- |
|
||||
| [Azure AI Project](./azure/Agent_With_AzureAIProject/) | Create a Foundry Project agent using the Azure.AI.Project SDK |
|
||||
| [Azure Foundry Model](./azure/Agent_With_AzureFoundryModel/) | Use any model deployed to Microsoft Foundry |
|
||||
| [Azure OpenAI ChatCompletion](./azure/Agent_With_AzureOpenAIChatCompletion/) | Create an AIAgent using Azure OpenAI ChatCompletion |
|
||||
| [Azure OpenAI Responses](./azure/Agent_With_AzureOpenAIResponses/) | Create an AIAgent using Azure OpenAI Responses |
|
||||
|
||||
### [Custom](./custom/)
|
||||
|
||||
| Sample | Description |
|
||||
| --- | --- |
|
||||
| [Custom Implementation](./custom/Agent_With_CustomImplementation/) | Create an AIAgent with a custom implementation |
|
||||
|
||||
### [Foundry](./foundry/)
|
||||
|
||||
See [foundry/README.md](./foundry/README.md) for the full list of Foundry agent samples,
|
||||
covering basics, function tools, structured output, middleware, MCP, code interpreter, and more.
|
||||
|
||||
### [GitHub Copilot](./github-copilot/)
|
||||
|
||||
| Sample | Description |
|
||||
| --- | --- |
|
||||
| [GitHub Copilot](./github-copilot/Agent_With_GitHubCopilot/) | Create an AIAgent using GitHub Copilot SDK |
|
||||
|
||||
### [Google Gemini](./google-gemini/)
|
||||
|
||||
| Sample | Description |
|
||||
| --- | --- |
|
||||
| [Google Gemini](./google-gemini/Agent_With_GoogleGemini/) | Create an AIAgent using Google Gemini |
|
||||
|
||||
### [Ollama](./ollama/)
|
||||
|
||||
| Sample | Description |
|
||||
| --- | --- |
|
||||
| [Ollama](./ollama/Agent_With_Ollama/) | Create an AIAgent using Ollama |
|
||||
|
||||
### [ONNX](./onnx/)
|
||||
|
||||
| Sample | Description |
|
||||
| --- | --- |
|
||||
| [ONNX](./onnx/Agent_With_ONNX/) | Create an AIAgent using ONNX Runtime |
|
||||
|
||||
### [OpenAI](./openai/)
|
||||
|
||||
| Sample | Description |
|
||||
| --- | --- |
|
||||
| [OpenAI ChatCompletion](./openai/Agent_With_OpenAIChatCompletion/) | Create an AIAgent using OpenAI ChatCompletion |
|
||||
| [OpenAI Responses](./openai/Agent_With_OpenAIResponses/) | Create an AIAgent using OpenAI Responses |
|
||||
| [Running](./openai/Agent_OpenAI_Step01_Running/) | Basic OpenAI agent usage |
|
||||
| [Reasoning](./openai/Agent_OpenAI_Step02_Reasoning/) | Using OpenAI reasoning capabilities |
|
||||
| [Create from ChatClient](./openai/Agent_OpenAI_Step03_CreateFromChatClient/) | Create agent from IChatClient |
|
||||
| [Create from Response Client](./openai/Agent_OpenAI_Step04_CreateFromOpenAIResponseClient/) | Create agent from OpenAI Response client |
|
||||
| [Conversation](./openai/Agent_OpenAI_Step05_Conversation/) | Multi-turn conversations with OpenAI |
|
||||
| [Code Interpreter](./openai/Agent_OpenAI_Step06_CodeInterpreterFileDownload/) | Code interpreter with file downloads |
|
||||
|
||||
## Running the samples
|
||||
|
||||
Navigate to a sample directory and run:
|
||||
|
||||
```powershell
|
||||
dotnet run
|
||||
```
|
||||
|
||||
Set the required environment variables as documented in each sample's README.
|
||||
If the variables are not set, you will be prompted for the values when running the samples.
|
||||
@@ -0,0 +1,19 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<PackageReference Include="A2A" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.A2A\Microsoft.Agents.AI.A2A.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
@@ -0,0 +1,18 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to create and use a simple AI agent with an existing A2A agent.
|
||||
|
||||
using A2A;
|
||||
using Microsoft.Agents.AI;
|
||||
|
||||
var a2aAgentHost = Environment.GetEnvironmentVariable("A2A_AGENT_HOST") ?? throw new InvalidOperationException("A2A_AGENT_HOST is not set.");
|
||||
|
||||
// Initialize an A2ACardResolver to get an A2A agent card.
|
||||
A2ACardResolver agentCardResolver = new(new Uri(a2aAgentHost));
|
||||
|
||||
// Create an instance of the AIAgent for an existing A2A agent specified by the agent card.
|
||||
AIAgent agent = await agentCardResolver.GetAIAgentAsync();
|
||||
|
||||
// Invoke the agent and output the text result.
|
||||
AgentResponse response = await agent.RunAsync("Tell me a joke about a pirate.");
|
||||
Console.WriteLine(response);
|
||||
@@ -0,0 +1,34 @@
|
||||
# Prerequisites
|
||||
|
||||
Before you begin, ensure you have the following prerequisites:
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Access to the A2A agent host service
|
||||
|
||||
**Note**: These samples need to be run against a valid A2A server. If no A2A server is available, they can be run against the echo-agent that can be spun up locally by following the guidelines at: https://github.com/a2aproject/a2a-dotnet/blob/main/samples/AgentServer/README.md
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:A2A_AGENT_HOST="https://your-a2a-agent-host" # Replace with your A2A agent host endpoint
|
||||
```
|
||||
|
||||
## Advanced scenario
|
||||
|
||||
This method can be used to create AI agents for A2A agents whose hosts support the [Direct Configuration / Private Discovery](https://github.com/a2aproject/A2A/blob/main/docs/topics/agent-discovery.md#3-direct-configuration--private-discovery) discovery mechanism.
|
||||
|
||||
```csharp
|
||||
using A2A;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Agents.AI.A2A;
|
||||
|
||||
// Create an A2AClient pointing to your `echo` A2A agent endpoint
|
||||
A2AClient a2aClient = new(new Uri("https://your-a2a-agent-host/echo"));
|
||||
|
||||
// Create an AIAgent from the A2AClient
|
||||
AIAgent agent = a2aClient.AsAIAgent();
|
||||
|
||||
// Run the agent
|
||||
AgentResponse response = await agent.RunAsync("Tell me a joke about a pirate.");
|
||||
Console.WriteLine(response);
|
||||
```
|
||||
+15
@@ -0,0 +1,15 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFramework>net10.0</TargetFramework>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Anthropic\Microsoft.Agents.AI.Anthropic.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
+17
@@ -0,0 +1,17 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to create and use a simple AI agent with Anthropic as the backend.
|
||||
|
||||
using Anthropic;
|
||||
using Anthropic.Core;
|
||||
using Microsoft.Agents.AI;
|
||||
|
||||
var apiKey = Environment.GetEnvironmentVariable("ANTHROPIC_API_KEY") ?? throw new InvalidOperationException("ANTHROPIC_API_KEY is not set.");
|
||||
var model = Environment.GetEnvironmentVariable("ANTHROPIC_CHAT_MODEL_NAME") ?? "claude-haiku-4-5";
|
||||
|
||||
AIAgent agent =
|
||||
new AnthropicClient(new ClientOptions { ApiKey = apiKey })
|
||||
.AsAIAgent(model: model, instructions: "You are good at telling jokes.", name: "Joker");
|
||||
|
||||
// Invoke the agent and output the text result.
|
||||
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));
|
||||
+44
@@ -0,0 +1,44 @@
|
||||
# Running a simple agent with Anthropic
|
||||
|
||||
This sample demonstrates how to create and run a basic agent with Anthropic Claude models.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Creating an AI agent with Anthropic Claude
|
||||
- Running a simple agent with instructions
|
||||
- Managing agent lifecycle
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Before you begin, ensure you have the following prerequisites:
|
||||
|
||||
- .NET 8.0 SDK or later
|
||||
- Anthropic API key configured
|
||||
|
||||
**Note**: This sample uses Anthropic Claude models. For more information, see [Anthropic documentation](https://docs.anthropic.com/).
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:ANTHROPIC_API_KEY="your-anthropic-api-key" # Replace with your Anthropic API key
|
||||
$env:ANTHROPIC_CHAT_MODEL_NAME="your-anthropic-model" # Replace with your Anthropic model
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
Navigate to the Anthropic sample directory and run:
|
||||
|
||||
```powershell
|
||||
cd dotnet\samples\02-agents\AgentProviders\anthropic
|
||||
dotnet run --project .\Agent_Anthropic_Step01_Running
|
||||
```
|
||||
|
||||
## Expected behavior
|
||||
|
||||
The sample will:
|
||||
|
||||
1. Create an agent with Anthropic Claude
|
||||
2. Run the agent with a simple prompt
|
||||
3. Display the agent's response
|
||||
|
||||
|
||||
+15
@@ -0,0 +1,15 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFramework>net10.0</TargetFramework>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Anthropic\Microsoft.Agents.AI.Anthropic.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
+59
@@ -0,0 +1,59 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to create and use an AI agent with reasoning capabilities.
|
||||
|
||||
using Anthropic;
|
||||
using Anthropic.Core;
|
||||
using Anthropic.Models.Messages;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Extensions.AI;
|
||||
|
||||
var apiKey = Environment.GetEnvironmentVariable("ANTHROPIC_API_KEY") ?? throw new InvalidOperationException("ANTHROPIC_API_KEY is not set.");
|
||||
var model = Environment.GetEnvironmentVariable("ANTHROPIC_CHAT_MODEL_NAME") ?? "claude-haiku-4-5";
|
||||
var maxTokens = 4096;
|
||||
var thinkingTokens = 2048;
|
||||
|
||||
var agent = new AnthropicClient(new ClientOptions { ApiKey = apiKey })
|
||||
.AsAIAgent(
|
||||
model: model,
|
||||
clientFactory: (chatClient) => chatClient
|
||||
.AsBuilder()
|
||||
.ConfigureOptions(
|
||||
options => options.RawRepresentationFactory = (_) => new MessageCreateParams()
|
||||
{
|
||||
Model = options.ModelId ?? model,
|
||||
MaxTokens = options.MaxOutputTokens ?? maxTokens,
|
||||
Messages = [],
|
||||
Thinking = new ThinkingConfigParam(new ThinkingConfigEnabled(budgetTokens: thinkingTokens))
|
||||
})
|
||||
.Build());
|
||||
|
||||
Console.WriteLine("1. Non-streaming:");
|
||||
var response = await agent.RunAsync("Solve this problem step by step: If a train travels 60 miles per hour and needs to cover 180 miles, how long will the journey take? Show your reasoning.");
|
||||
|
||||
Console.WriteLine("#### Start Thinking ####");
|
||||
Console.WriteLine($"\e[92m{string.Join("\n", response.Messages.SelectMany(m => m.Contents.OfType<TextReasoningContent>().Select(c => c.Text)))}\e[0m");
|
||||
Console.WriteLine("#### End Thinking ####");
|
||||
|
||||
Console.WriteLine("\n#### Final Answer ####");
|
||||
Console.WriteLine(response.Text);
|
||||
|
||||
Console.WriteLine("Token usage:");
|
||||
Console.WriteLine($"Input: {response.Usage?.InputTokenCount}, Output: {response.Usage?.OutputTokenCount}, {string.Join(", ", response.Usage?.AdditionalCounts ?? [])}");
|
||||
Console.WriteLine();
|
||||
|
||||
Console.WriteLine("2. Streaming");
|
||||
await foreach (var update in agent.RunStreamingAsync("Explain the theory of relativity in simple terms."))
|
||||
{
|
||||
foreach (var item in update.Contents)
|
||||
{
|
||||
if (item is TextReasoningContent reasoningContent)
|
||||
{
|
||||
Console.WriteLine($"\e[92m{reasoningContent.Text}\e[0m");
|
||||
}
|
||||
else if (item is TextContent textContent)
|
||||
{
|
||||
Console.WriteLine(textContent.Text);
|
||||
}
|
||||
}
|
||||
}
|
||||
+47
@@ -0,0 +1,47 @@
|
||||
# Using reasoning with Anthropic agents
|
||||
|
||||
This sample demonstrates how to use extended thinking/reasoning capabilities with Anthropic Claude agents.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Creating an AI agent with Anthropic Claude extended thinking
|
||||
- Using reasoning capabilities for complex problem solving
|
||||
- Extracting thinking and response content from agent output
|
||||
- Managing agent lifecycle
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Before you begin, ensure you have the following prerequisites:
|
||||
|
||||
- .NET 8.0 SDK or later
|
||||
- Anthropic API key configured
|
||||
- Access to Anthropic Claude models with extended thinking support
|
||||
|
||||
**Note**: This sample uses Anthropic Claude models with extended thinking. For more information, see [Anthropic documentation](https://docs.anthropic.com/).
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:ANTHROPIC_API_KEY="your-anthropic-api-key" # Replace with your Anthropic API key
|
||||
$env:ANTHROPIC_CHAT_MODEL_NAME="your-anthropic-model" # Replace with your Anthropic model
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
Navigate to the Anthropic sample directory and run:
|
||||
|
||||
```powershell
|
||||
cd dotnet\samples\02-agents\AgentProviders\anthropic
|
||||
dotnet run --project .\Agent_Anthropic_Step02_Reasoning
|
||||
```
|
||||
|
||||
## Expected behavior
|
||||
|
||||
The sample will:
|
||||
|
||||
1. Create an agent with Anthropic Claude extended thinking enabled
|
||||
2. Run the agent with a complex reasoning prompt
|
||||
3. Display the agent's thinking process
|
||||
4. Display the agent's final response
|
||||
|
||||
|
||||
+15
@@ -0,0 +1,15 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFramework>net10.0</TargetFramework>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Anthropic\Microsoft.Agents.AI.Anthropic.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
+37
@@ -0,0 +1,37 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample demonstrates how to use an agent with function tools.
|
||||
// It shows both non-streaming and streaming agent interactions using weather-related tools.
|
||||
|
||||
using System.ComponentModel;
|
||||
using Anthropic;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Extensions.AI;
|
||||
|
||||
var apiKey = Environment.GetEnvironmentVariable("ANTHROPIC_API_KEY") ?? throw new InvalidOperationException("ANTHROPIC_API_KEY is not set.");
|
||||
var model = Environment.GetEnvironmentVariable("ANTHROPIC_CHAT_MODEL_NAME") ?? "claude-haiku-4-5";
|
||||
|
||||
[Description("Get the weather for a given location.")]
|
||||
static string GetWeather([Description("The location to get the weather for.")] string location)
|
||||
=> $"The weather in {location} is cloudy with a high of 15°C.";
|
||||
|
||||
const string AssistantInstructions = "You are a helpful assistant that can get weather information.";
|
||||
const string AssistantName = "WeatherAssistant";
|
||||
|
||||
// Define the agent with function tools.
|
||||
AITool tool = AIFunctionFactory.Create(GetWeather);
|
||||
|
||||
// Get anthropic client to create agents.
|
||||
AIAgent agent = new AnthropicClient { ApiKey = apiKey }
|
||||
.AsAIAgent(model: model, instructions: AssistantInstructions, name: AssistantName, tools: [tool]);
|
||||
|
||||
// Non-streaming agent interaction with function tools.
|
||||
AgentSession session = await agent.CreateSessionAsync();
|
||||
Console.WriteLine(await agent.RunAsync("What is the weather like in Amsterdam?", session));
|
||||
|
||||
// Streaming agent interaction with function tools.
|
||||
session = await agent.CreateSessionAsync();
|
||||
await foreach (AgentResponseUpdate update in agent.RunStreamingAsync("What is the weather like in Amsterdam?", session))
|
||||
{
|
||||
Console.WriteLine(update);
|
||||
}
|
||||
+48
@@ -0,0 +1,48 @@
|
||||
# Using Function Tools with Anthropic agents
|
||||
|
||||
This sample demonstrates how to use function tools with Anthropic Claude agents, allowing agents to call custom functions to retrieve information.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Creating function tools using AIFunctionFactory
|
||||
- Passing function tools to an Anthropic Claude agent
|
||||
- Running agents with function tools (text output)
|
||||
- Running agents with function tools (streaming output)
|
||||
- Managing agent lifecycle
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Before you begin, ensure you have the following prerequisites:
|
||||
|
||||
- .NET 8.0 SDK or later
|
||||
- Anthropic API key configured
|
||||
|
||||
**Note**: This sample uses Anthropic Claude models. For more information, see [Anthropic documentation](https://docs.anthropic.com/).
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:ANTHROPIC_API_KEY="your-anthropic-api-key" # Replace with your Anthropic API key
|
||||
$env:ANTHROPIC_CHAT_MODEL_NAME="your-anthropic-model" # Replace with your Anthropic model
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
Navigate to the Anthropic sample directory and run:
|
||||
|
||||
```powershell
|
||||
cd dotnet\samples\02-agents\AgentProviders\anthropic
|
||||
dotnet run --project .\Agent_Anthropic_Step03_UsingFunctionTools
|
||||
```
|
||||
|
||||
## Expected behavior
|
||||
|
||||
The sample will:
|
||||
|
||||
1. Create an agent named "WeatherAssistant" with a GetWeather function tool
|
||||
2. Run the agent with a text prompt asking about weather
|
||||
3. The agent will invoke the GetWeather function tool to retrieve weather information
|
||||
4. Run the agent again with streaming to display the response as it's generated
|
||||
5. Clean up resources by deleting the agent
|
||||
|
||||
|
||||
+15
@@ -0,0 +1,15 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFramework>net10.0</TargetFramework>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Anthropic\Microsoft.Agents.AI.Anthropic.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
+127
@@ -0,0 +1,127 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample demonstrates how to use Anthropic-managed Skills with an AI agent.
|
||||
// Skills are pre-built capabilities provided by Anthropic that can be used with the Claude API.
|
||||
// This sample shows how to:
|
||||
// 1. List available Anthropic-managed skills
|
||||
// 2. Use the pptx skill to create PowerPoint presentations
|
||||
// 3. Download and save generated files
|
||||
|
||||
using Anthropic;
|
||||
using Anthropic.Core;
|
||||
using Anthropic.Models.Beta;
|
||||
using Anthropic.Models.Beta.Files;
|
||||
using Anthropic.Models.Beta.Messages;
|
||||
using Anthropic.Models.Beta.Skills;
|
||||
using Anthropic.Services;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Extensions.AI;
|
||||
|
||||
string apiKey = Environment.GetEnvironmentVariable("ANTHROPIC_API_KEY") ?? throw new InvalidOperationException("ANTHROPIC_API_KEY is not set.");
|
||||
// Skills require Claude 4.5 models (Sonnet 4.5, Haiku 4.5, or Opus 4.5)
|
||||
string model = Environment.GetEnvironmentVariable("ANTHROPIC_CHAT_MODEL_NAME") ?? "claude-sonnet-4-5-20250929";
|
||||
|
||||
// Create the Anthropic client
|
||||
AnthropicClient anthropicClient = new() { ApiKey = apiKey };
|
||||
|
||||
// List available Anthropic-managed skills (optional - API may not be available in all regions)
|
||||
Console.WriteLine("Available Anthropic-managed skills:");
|
||||
try
|
||||
{
|
||||
SkillListPage skills = await anthropicClient.Beta.Skills.List(
|
||||
new SkillListParams { Source = "anthropic", Betas = [AnthropicBeta.Skills2025_10_02] });
|
||||
|
||||
foreach (var skill in skills.Items)
|
||||
{
|
||||
Console.WriteLine($" {skill.Source}: {skill.ID} (version: {skill.LatestVersion})");
|
||||
}
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
Console.WriteLine($" (Skills listing not available: {ex.Message})");
|
||||
}
|
||||
|
||||
Console.WriteLine();
|
||||
|
||||
// Define the pptx skill - the SDK handles all beta flags and container configuration automatically
|
||||
// when using AsAITool(), so no manual RawRepresentationFactory configuration is needed.
|
||||
BetaSkillParams pptxSkill = new()
|
||||
{
|
||||
Type = BetaSkillParamsType.Anthropic,
|
||||
SkillID = "pptx",
|
||||
Version = "latest"
|
||||
};
|
||||
|
||||
// Create an agent with the pptx skill enabled.
|
||||
// Skills require extended thinking and higher max tokens for complex file generation.
|
||||
// The SDK's AsAITool() handles beta flags and container config automatically.
|
||||
ChatClientAgent agent = anthropicClient.Beta.AsAIAgent(
|
||||
model: model,
|
||||
instructions: "You are a helpful agent for creating PowerPoint presentations.",
|
||||
tools: [pptxSkill.AsAITool()],
|
||||
clientFactory: (chatClient) => chatClient
|
||||
.AsBuilder()
|
||||
.ConfigureOptions(options =>
|
||||
{
|
||||
options.RawRepresentationFactory = (_) => new MessageCreateParams()
|
||||
{
|
||||
Model = model,
|
||||
MaxTokens = 20000,
|
||||
Messages = [],
|
||||
Thinking = new BetaThinkingConfigParam(
|
||||
new BetaThinkingConfigEnabled(budgetTokens: 10000))
|
||||
};
|
||||
})
|
||||
.Build());
|
||||
|
||||
Console.WriteLine("Creating a presentation about renewable energy...\n");
|
||||
|
||||
// Run the agent with a request to create a presentation
|
||||
AgentResponse response = await agent.RunAsync("Create a simple 3-slide presentation about renewable energy sources. Include a title slide, a slide about solar energy, and a slide about wind energy.");
|
||||
|
||||
Console.WriteLine("#### Agent Response ####");
|
||||
Console.WriteLine(response.Text);
|
||||
|
||||
// Display any reasoning/thinking content
|
||||
List<TextReasoningContent> reasoningContents = response.Messages.SelectMany(m => m.Contents.OfType<TextReasoningContent>()).ToList();
|
||||
if (reasoningContents.Count > 0)
|
||||
{
|
||||
Console.WriteLine("\n#### Agent Reasoning ####");
|
||||
Console.WriteLine($"\e[92m{string.Join("\n", reasoningContents.Select(c => c.Text))}\e[0m");
|
||||
}
|
||||
|
||||
// Collect generated files from CodeInterpreterToolResultContent outputs
|
||||
List<HostedFileContent> hostedFiles = response.Messages
|
||||
.SelectMany(m => m.Contents.OfType<CodeInterpreterToolResultContent>())
|
||||
.Where(c => c.Outputs is not null)
|
||||
.SelectMany(c => c.Outputs!.OfType<HostedFileContent>())
|
||||
.ToList();
|
||||
|
||||
if (hostedFiles.Count > 0)
|
||||
{
|
||||
Console.WriteLine("\n#### Generated Files ####");
|
||||
foreach (HostedFileContent file in hostedFiles)
|
||||
{
|
||||
Console.WriteLine($" FileId: {file.FileId}");
|
||||
|
||||
// Download the file using the Anthropic Files API
|
||||
using HttpResponse fileResponse = await anthropicClient.Beta.Files.Download(
|
||||
file.FileId,
|
||||
new FileDownloadParams { Betas = ["files-api-2025-04-14"] });
|
||||
|
||||
// Save the file to disk
|
||||
string fileName = $"presentation_{file.FileId.Substring(0, 8)}.pptx";
|
||||
using FileStream fileStream = File.Create(fileName);
|
||||
Stream contentStream = await fileResponse.ReadAsStream();
|
||||
await contentStream.CopyToAsync(fileStream);
|
||||
|
||||
Console.WriteLine($" Saved to: {fileName}");
|
||||
}
|
||||
}
|
||||
|
||||
Console.WriteLine("\nToken usage:");
|
||||
Console.WriteLine($"Input: {response.Usage?.InputTokenCount}, Output: {response.Usage?.OutputTokenCount}");
|
||||
if (response.Usage?.AdditionalCounts is not null)
|
||||
{
|
||||
Console.WriteLine($"Additional: {string.Join(", ", response.Usage.AdditionalCounts)}");
|
||||
}
|
||||
+120
@@ -0,0 +1,120 @@
|
||||
# Using Anthropic Skills with agents
|
||||
|
||||
This sample demonstrates how to use Anthropic-managed Skills with AI agents. Skills are pre-built capabilities provided by Anthropic that can be used with the Claude API.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Listing available Anthropic-managed skills
|
||||
- Creating an AI agent with Anthropic Claude Skills support using the simplified `AsAITool()` approach
|
||||
- Using the pptx skill to create PowerPoint presentations
|
||||
- Downloading and saving generated files to disk
|
||||
- Handling agent responses with generated content
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Before you begin, ensure you have the following prerequisites:
|
||||
|
||||
- .NET 10.0 SDK or later
|
||||
- Anthropic API key configured
|
||||
- Access to Anthropic Claude models with Skills support
|
||||
|
||||
**Note**: This sample uses Anthropic Claude models with Skills. Skills are a beta feature. For more information, see [Anthropic documentation](https://docs.anthropic.com/).
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:ANTHROPIC_API_KEY="your-anthropic-api-key" # Replace with your Anthropic API key
|
||||
$env:ANTHROPIC_CHAT_MODEL_NAME="your-anthropic-model" # Replace with your Anthropic model (e.g., claude-sonnet-4-5-20250929)
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
Navigate to the Anthropic sample directory and run:
|
||||
|
||||
```powershell
|
||||
cd dotnet\samples\02-agents\AgentProviders\anthropic
|
||||
dotnet run --project .\Agent_Anthropic_Step04_UsingSkills
|
||||
```
|
||||
|
||||
## Available Anthropic Skills
|
||||
|
||||
Anthropic provides several managed skills that can be used with the Claude API:
|
||||
|
||||
- `pptx` - Create PowerPoint presentations
|
||||
- `xlsx` - Create Excel spreadsheets
|
||||
- `docx` - Create Word documents
|
||||
- `pdf` - Create and analyze PDF documents
|
||||
|
||||
You can list available skills using the Anthropic SDK:
|
||||
|
||||
```csharp
|
||||
SkillListPage skills = await anthropicClient.Beta.Skills.List(
|
||||
new SkillListParams { Source = "anthropic", Betas = [AnthropicBeta.Skills2025_10_02] });
|
||||
|
||||
foreach (var skill in skills.Items)
|
||||
{
|
||||
Console.WriteLine($"{skill.Source}: {skill.ID} (version: {skill.LatestVersion})");
|
||||
}
|
||||
```
|
||||
|
||||
## Expected behavior
|
||||
|
||||
The sample will:
|
||||
|
||||
1. List all available Anthropic-managed skills
|
||||
2. Create an agent with the pptx skill enabled
|
||||
3. Run the agent with a request to create a presentation
|
||||
4. Display the agent's response text
|
||||
5. Download any generated files and save them to disk
|
||||
6. Display token usage statistics
|
||||
|
||||
## Code highlights
|
||||
|
||||
### Simplified skill configuration
|
||||
|
||||
The Anthropic SDK handles all beta flags and container configuration automatically when using `AsAITool()`:
|
||||
|
||||
```csharp
|
||||
// Define the pptx skill
|
||||
BetaSkillParams pptxSkill = new()
|
||||
{
|
||||
Type = BetaSkillParamsType.Anthropic,
|
||||
SkillID = "pptx",
|
||||
Version = "latest"
|
||||
};
|
||||
|
||||
// Create an agent - the SDK handles beta flags automatically!
|
||||
ChatClientAgent agent = anthropicClient.Beta.AsAIAgent(
|
||||
model: model,
|
||||
instructions: "You are a helpful agent for creating PowerPoint presentations.",
|
||||
tools: [pptxSkill.AsAITool()]);
|
||||
```
|
||||
|
||||
**Note**: No manual `RawRepresentationFactory`, `Betas`, or `Container` configuration is needed. The SDK automatically adds the required beta headers (`skills-2025-10-02`, `code-execution-2025-08-25`) and configures the container with the skill.
|
||||
|
||||
### Handling generated files
|
||||
|
||||
Generated files are returned as `HostedFileContent` within `CodeInterpreterToolResultContent`:
|
||||
|
||||
```csharp
|
||||
// Collect generated files from response
|
||||
List<HostedFileContent> hostedFiles = response.Messages
|
||||
.SelectMany(m => m.Contents.OfType<CodeInterpreterToolResultContent>())
|
||||
.Where(c => c.Outputs is not null)
|
||||
.SelectMany(c => c.Outputs!.OfType<HostedFileContent>())
|
||||
.ToList();
|
||||
|
||||
// Download and save each file
|
||||
foreach (HostedFileContent file in hostedFiles)
|
||||
{
|
||||
using HttpResponse fileResponse = await anthropicClient.Beta.Files.Download(
|
||||
file.FileId,
|
||||
new FileDownloadParams { Betas = ["files-api-2025-04-14"] });
|
||||
|
||||
string fileName = $"presentation_{file.FileId.Substring(0, 8)}.pptx";
|
||||
await using FileStream fileStream = File.Create(fileName);
|
||||
Stream contentStream = await fileResponse.ReadAsStream();
|
||||
await contentStream.CopyToAsync(fileStream);
|
||||
}
|
||||
```
|
||||
|
||||
+21
@@ -0,0 +1,21 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
<NoWarn>$(NoWarn);IDE0059</NoWarn>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<PackageReference Include="Azure.Identity" />
|
||||
<PackageReference Include="Anthropic.Foundry" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Anthropic\Microsoft.Agents.AI.Anthropic.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
@@ -0,0 +1,32 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to create and use an AI agent with Anthropic as the backend.
|
||||
|
||||
using Anthropic;
|
||||
using Anthropic.Foundry;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
|
||||
string deploymentName = Environment.GetEnvironmentVariable("ANTHROPIC_CHAT_MODEL_NAME") ?? "claude-haiku-4-5";
|
||||
|
||||
// The resource is the subdomain name / first name coming before '.services.ai.azure.com' in the endpoint Uri
|
||||
// ie: https://(resource name).services.ai.azure.com/anthropic/v1/chat/completions
|
||||
string? resource = Environment.GetEnvironmentVariable("ANTHROPIC_RESOURCE");
|
||||
string? apiKey = Environment.GetEnvironmentVariable("ANTHROPIC_API_KEY");
|
||||
|
||||
const string JokerInstructions = "You are good at telling jokes.";
|
||||
const string JokerName = "JokerAgent";
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
using AnthropicClient client = (resource is null)
|
||||
? new AnthropicClient() { ApiKey = apiKey ?? throw new InvalidOperationException("ANTHROPIC_API_KEY is required when no ANTHROPIC_RESOURCE is provided") } // If no resource is provided, use Anthropic public API
|
||||
: (apiKey is not null)
|
||||
? new AnthropicFoundryClient(new AnthropicFoundryApiKeyCredentials(apiKey, resource)) // If an apiKey is provided, use Foundry with ApiKey authentication
|
||||
: new AnthropicFoundryClient(new AnthropicFoundryIdentityTokenCredentials(new DefaultAzureCredential(), resource, ["https://ai.azure.com/.default"])); // Otherwise, use Foundry with Azure TokenCredential authentication
|
||||
|
||||
AIAgent agent = client.AsAIAgent(model: deploymentName, instructions: JokerInstructions, name: JokerName);
|
||||
|
||||
// Invoke the agent and output the text result.
|
||||
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));
|
||||
@@ -0,0 +1,54 @@
|
||||
# Creating an AIAgent with Anthropic
|
||||
|
||||
This sample demonstrates how to create an AIAgent using Anthropic Claude models as the underlying inference service.
|
||||
|
||||
The sample supports three deployment scenarios:
|
||||
|
||||
1. **Anthropic Public API** - Direct connection to Anthropic's public API
|
||||
2. **Microsoft Foundry with API Key** - Anthropic models deployed through Microsoft Foundry using API key authentication
|
||||
3. **Microsoft Foundry with Azure CLI** - Anthropic models deployed through Microsoft Foundry using Azure CLI credentials
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Before you begin, ensure you have the following prerequisites:
|
||||
|
||||
- .NET 8.0 SDK or later
|
||||
|
||||
### For Anthropic Public API
|
||||
|
||||
- Anthropic API key
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:ANTHROPIC_API_KEY="your-anthropic-api-key" # Replace with your Anthropic API key
|
||||
$env:ANTHROPIC_CHAT_MODEL_NAME="claude-haiku-4-5" # Optional, defaults to claude-haiku-4-5
|
||||
```
|
||||
|
||||
### For Microsoft Foundry with API Key
|
||||
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- Anthropic API key
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:ANTHROPIC_RESOURCE="your-foundry-resource-name" # Replace with your Microsoft Foundry resource name (subdomain before .services.ai.azure.com)
|
||||
$env:ANTHROPIC_API_KEY="your-anthropic-api-key" # Replace with your Anthropic API key
|
||||
$env:ANTHROPIC_CHAT_MODEL_NAME="claude-haiku-4-5" # Optional, defaults to claude-haiku-4-5
|
||||
```
|
||||
|
||||
### For Microsoft Foundry with Azure CLI
|
||||
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- Azure CLI installed and authenticated (for Azure credential authentication)
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:ANTHROPIC_RESOURCE="your-foundry-resource-name" # Replace with your Microsoft Foundry resource name (subdomain before .services.ai.azure.com)
|
||||
$env:ANTHROPIC_CHAT_MODEL_NAME="claude-haiku-4-5" # Optional, defaults to claude-haiku-4-5
|
||||
```
|
||||
|
||||
**Note**: When using Microsoft Foundry with Azure CLI, make sure you're logged in with `az login` and have access to the Microsoft Foundry resource. For more information, see the [Azure CLI documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
|
||||
|
||||
@@ -0,0 +1,73 @@
|
||||
# Getting started with agents using Anthropic
|
||||
|
||||
The getting started with agents using Anthropic samples demonstrate the fundamental concepts and functionalities
|
||||
of single agents using Anthropic as the AI provider.
|
||||
|
||||
These samples use Anthropic Claude models as the AI provider and use ChatCompletion as the type of service.
|
||||
|
||||
For other samples that demonstrate how to create and configure each type of agent that come with the agent framework,
|
||||
see the [How to create an agent for each provider](../README.md) samples.
|
||||
|
||||
## Getting started with agents using Anthropic prerequisites
|
||||
|
||||
Before you begin, ensure you have the following prerequisites:
|
||||
|
||||
- .NET 8.0 SDK or later
|
||||
- Anthropic API key configured
|
||||
- User has access to Anthropic Claude models
|
||||
|
||||
**Note**: These samples use Anthropic Claude models. For more information, see [Anthropic documentation](https://docs.anthropic.com/).
|
||||
|
||||
## Using Anthropic with Microsoft Foundry
|
||||
|
||||
To use Anthropic with Microsoft Foundry, you can check the sample [providers/Agent_With_Anthropic](./Agent_With_Anthropic/README.md) for more details.
|
||||
|
||||
## Samples
|
||||
|
||||
|Sample|Description|
|
||||
|---|---|
|
||||
|[Running a simple agent](./Agent_Anthropic_Step01_Running/)|This sample demonstrates how to create and run a basic agent with Anthropic Claude|
|
||||
|[Using reasoning with an agent](./Agent_Anthropic_Step02_Reasoning/)|This sample demonstrates how to use extended thinking/reasoning capabilities with Anthropic Claude agents|
|
||||
|[Using function tools with an agent](./Agent_Anthropic_Step03_UsingFunctionTools/)|This sample demonstrates how to use function tools with an Anthropic Claude agent|
|
||||
|[Using Skills with an agent](./Agent_Anthropic_Step04_UsingSkills/)|This sample demonstrates how to use Anthropic-managed Skills (e.g., pptx) with an Anthropic Claude agent|
|
||||
|
||||
## Running the samples from the console
|
||||
|
||||
To run the samples, navigate to the desired sample directory, e.g.
|
||||
|
||||
```powershell
|
||||
cd Agent_Anthropic_Step01_Running
|
||||
```
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:ANTHROPIC_API_KEY="your-anthropic-api-key" # Replace with your Anthropic API key
|
||||
```
|
||||
|
||||
If the variables are not set, you will be prompted for the values when running the samples.
|
||||
|
||||
Execute the following command to build the sample:
|
||||
|
||||
```powershell
|
||||
dotnet build
|
||||
```
|
||||
|
||||
Execute the following command to run the sample:
|
||||
|
||||
```powershell
|
||||
dotnet run --no-build
|
||||
```
|
||||
|
||||
Or just build and run in one step:
|
||||
|
||||
```powershell
|
||||
dotnet run
|
||||
```
|
||||
|
||||
## Running the samples from Visual Studio
|
||||
|
||||
Open the solution in Visual Studio and set the desired sample project as the startup project. Then, run the project using the built-in debugger or by pressing `F5`.
|
||||
|
||||
You will be prompted for any required environment variables if they are not already set.
|
||||
|
||||
+21
@@ -0,0 +1,21 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
<NoWarn>$(NoWarn);IDE0059</NoWarn>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<PackageReference Include="Azure.AI.Projects" />
|
||||
<PackageReference Include="Azure.Identity" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
@@ -0,0 +1,58 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to create and use AI agents with Microsoft Foundry Agents as the backend.
|
||||
|
||||
using Azure.AI.Projects;
|
||||
using Azure.AI.Projects.Agents;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Agents.AI.Foundry;
|
||||
|
||||
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
const string JokerName = "JokerAgent";
|
||||
|
||||
// Get a client to create/retrieve/delete server side agents with Microsoft Foundry Agents.
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
var aiProjectClient = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
// Define the agent you want to create. (Prompt Agent in this case)
|
||||
var agentVersionCreationOptions = new ProjectsAgentVersionCreationOptions(new DeclarativeAgentDefinition(model: deploymentName) { Instructions = "You are good at telling jokes." });
|
||||
// Azure.AI.Agents SDK creates and manages agent by name and versions.
|
||||
// You can create a server side agent version with the Azure.AI.Agents SDK client below.
|
||||
var createdAgentVersion = aiProjectClient.AgentAdministrationClient.CreateAgentVersion(agentName: JokerName, options: agentVersionCreationOptions);
|
||||
|
||||
// Note:
|
||||
// agentVersion.Id = "<agentName>:<versionNumber>",
|
||||
// agentVersion.Version = <versionNumber>,
|
||||
// agentVersion.Name = <agentName>
|
||||
|
||||
// You can use an AIAgent with an already created server side agent version.
|
||||
FoundryAgent existingJokerAgent = aiProjectClient.AsAIAgent(createdAgentVersion);
|
||||
|
||||
// You can also create another AIAgent version by providing the same name with a different definition.
|
||||
ProjectsAgentVersion newJokerAgentVersion = await aiProjectClient.AgentAdministrationClient.CreateAgentVersionAsync(
|
||||
JokerName,
|
||||
new ProjectsAgentVersionCreationOptions(new DeclarativeAgentDefinition(model: deploymentName) { Instructions = "You are extremely hilarious at telling jokes." }));
|
||||
FoundryAgent newJokerAgent = aiProjectClient.AsAIAgent(newJokerAgentVersion);
|
||||
|
||||
// You can also get the AIAgent latest version just providing its name.
|
||||
ProjectsAgentRecord jokerAgentRecord = await aiProjectClient.AgentAdministrationClient.GetAgentAsync(JokerName);
|
||||
FoundryAgent jokerAgentLatest = aiProjectClient.AsAIAgent(jokerAgentRecord);
|
||||
ProjectsAgentVersion latestAgentVersion = jokerAgentRecord.GetLatestVersion();
|
||||
|
||||
// The AIAgent version can be accessed via the GetService method.
|
||||
Console.WriteLine($"Latest agent version id: {latestAgentVersion.Id}");
|
||||
|
||||
// Once you have the AIAgent, you can invoke it like any other AIAgent.
|
||||
AgentSession session = await jokerAgentLatest.CreateSessionAsync();
|
||||
Console.WriteLine(await jokerAgentLatest.RunAsync("Tell me a joke about a pirate.", session));
|
||||
|
||||
// This will use the same session to continue the conversation.
|
||||
Console.WriteLine(await jokerAgentLatest.RunAsync("Now tell me a joke about a cat and a dog using last joke as the anchor.", session));
|
||||
|
||||
// Cleanup by agent name removes both agent versions created.
|
||||
aiProjectClient.AgentAdministrationClient.DeleteAgent(existingJokerAgent.Name);
|
||||
@@ -0,0 +1,26 @@
|
||||
# New Foundry Agents
|
||||
|
||||
This sample demonstrates how to create an agent using the new Foundry Agents experience.
|
||||
|
||||
# Classic vs New Foundry Agents
|
||||
|
||||
Below is a comparison between the classic and new Foundry Agents approaches:
|
||||
|
||||
[Migration Guide](https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/migrate?view=foundry)
|
||||
|
||||
# Prerequisites
|
||||
|
||||
Before you begin, ensure you have the following prerequisites:
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft 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 Microsoft Foundry resource. For more information, see the [Azure CLI documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project" # Replace with your Microsoft Foundry resource endpoint
|
||||
$env:FOUNDRY_MODEL="gpt-5.4-mini" # Optional, defaults to gpt-5.4-mini
|
||||
```
|
||||
+19
@@ -0,0 +1,19 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<PackageReference Include="Azure.Identity" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
@@ -0,0 +1,34 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to use the OpenAI SDK to create and use a simple AI agent with any model hosted in Microsoft Foundry.
|
||||
// You could use models from Microsoft, OpenAI, DeepSeek, Hugging Face, Meta, xAI or any other model you have deployed in your Microsoft Foundry resource.
|
||||
// Note: Ensure that you pick a model that suits your needs. For example, if you want to use function calling, ensure that the model you pick supports function calling.
|
||||
|
||||
using System.ClientModel;
|
||||
using System.ClientModel.Primitives;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
using OpenAI;
|
||||
using OpenAI.Chat;
|
||||
|
||||
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
|
||||
var apiKey = Environment.GetEnvironmentVariable("AZURE_OPENAI_API_KEY");
|
||||
var model = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "Phi-4-mini-instruct";
|
||||
|
||||
// Since we are using the OpenAI Client SDK, we need to override the default endpoint to point to Microsoft Foundry.
|
||||
var clientOptions = new OpenAIClientOptions() { Endpoint = new Uri(endpoint) };
|
||||
|
||||
// Create the OpenAI client with either an API key or Azure CLI credential.
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
OpenAIClient client = string.IsNullOrWhiteSpace(apiKey)
|
||||
? new OpenAIClient(new BearerTokenPolicy(new DefaultAzureCredential(), "https://ai.azure.com/.default"), clientOptions)
|
||||
: new OpenAIClient(new ApiKeyCredential(apiKey), clientOptions);
|
||||
|
||||
AIAgent agent = client
|
||||
.GetChatClient(model)
|
||||
.AsAIAgent(instructions: "You are good at telling jokes.", name: "Joker");
|
||||
|
||||
// Invoke the agent and output the text result.
|
||||
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));
|
||||
@@ -0,0 +1,34 @@
|
||||
## Overview
|
||||
|
||||
This sample shows how to use the OpenAI SDK to create and use a simple AI agent with any model hosted in Microsoft Foundry.
|
||||
|
||||
You could use models from Microsoft, OpenAI, DeepSeek, Hugging Face, Meta, xAI or any other model you have deployed in Microsoft Foundry.
|
||||
|
||||
**Note**: Ensure that you pick a model that suits your needs. For example, if you want to use function calling, ensure that the model you pick supports function calling.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Before you begin, ensure you have the following prerequisites:
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry resource
|
||||
- A model deployment in your Microsoft Foundry resource. This example defaults to using the `Phi-4-mini-instruct` model,
|
||||
so if you want to use a different model, ensure that you set your `FOUNDRY_MODEL` environment
|
||||
variable to the name of your deployed model.
|
||||
- An API key or role based authentication to access the Microsoft Foundry resource
|
||||
|
||||
See [here](https://learn.microsoft.com/en-us/azure/ai-foundry/quickstarts/get-started-code?tabs=csharp) for more info on setting up these prerequisites
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
# Replace with your Microsoft Foundry resource endpoint
|
||||
# Ensure that you have the "/openai/v1/" path in the URL, since this is required when using the OpenAI SDK to access Microsoft Foundry models.
|
||||
$env:AZURE_OPENAI_ENDPOINT="https://ai-foundry-<myresourcename>.services.ai.azure.com/openai/v1/"
|
||||
|
||||
# Optional, defaults to using Azure CLI for authentication if not provided
|
||||
$env:AZURE_OPENAI_API_KEY="************"
|
||||
|
||||
# Optional, defaults to Phi-4-mini-instruct
|
||||
$env:FOUNDRY_MODEL="Phi-4-mini-instruct"
|
||||
```
|
||||
+20
@@ -0,0 +1,20 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<PackageReference Include="Azure.AI.OpenAI" />
|
||||
<PackageReference Include="Azure.Identity" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
+23
@@ -0,0 +1,23 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to create and use a simple AI agent with Azure OpenAI Chat Completion as the backend.
|
||||
|
||||
using Azure.AI.OpenAI;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
using OpenAI.Chat;
|
||||
|
||||
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
|
||||
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIAgent agent = new AzureOpenAIClient(
|
||||
new Uri(endpoint),
|
||||
new DefaultAzureCredential())
|
||||
.GetChatClient(deploymentName)
|
||||
.AsAIAgent(instructions: "You are good at telling jokes.", name: "Joker");
|
||||
|
||||
// Invoke the agent and output the text result.
|
||||
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
# Prerequisites
|
||||
|
||||
Before you begin, ensure you have the following prerequisites:
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Azure OpenAI 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 OpenAI resource. For more information, see the [Azure CLI documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com/" # Replace with your Azure OpenAI resource endpoint
|
||||
$env:AZURE_OPENAI_DEPLOYMENT_NAME="gpt-5.4-mini" # Optional, defaults to gpt-5.4-mini
|
||||
```
|
||||
+20
@@ -0,0 +1,20 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<PackageReference Include="Azure.AI.OpenAI" />
|
||||
<PackageReference Include="Azure.Identity" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
+38
@@ -0,0 +1,38 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to create and use a simple AI agent with Azure OpenAI Responses as the backend.
|
||||
|
||||
using Azure.AI.OpenAI;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Extensions.AI;
|
||||
using OpenAI.Responses;
|
||||
|
||||
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
|
||||
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
// You must dissable client side conversation storage for clients that support it
|
||||
AIAgent agent = new AzureOpenAIClient(
|
||||
new Uri(endpoint),
|
||||
new DefaultAzureCredential())
|
||||
.GetResponsesClient()
|
||||
.AsAIAgent(model: deploymentName, instructions: "You are good at telling jokes.", name: "Joker");
|
||||
|
||||
// Invoke the agent and output the text result.
|
||||
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));
|
||||
|
||||
// Create a responses based agent with "store"=false.
|
||||
// This means that chat history is managed locally by Agent Framework
|
||||
// instead of being stored in the service (default).
|
||||
AIAgent agentStoreFalse = new AzureOpenAIClient(
|
||||
new Uri(endpoint),
|
||||
new DefaultAzureCredential())
|
||||
.GetResponsesClient()
|
||||
.AsIChatClientWithStoredOutputDisabled(model: deploymentName)
|
||||
.AsAIAgent(instructions: "You are good at telling jokes.", name: "Joker");
|
||||
|
||||
// Invoke the agent and output the text result.
|
||||
Console.WriteLine(await agentStoreFalse.RunAsync("Tell me a joke about a pirate."));
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
# Prerequisites
|
||||
|
||||
Before you begin, ensure you have the following prerequisites:
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Azure OpenAI 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 OpenAI resource. For more information, see the [Azure CLI documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com/" # Replace with your Azure OpenAI resource endpoint
|
||||
$env:AZURE_OPENAI_DEPLOYMENT_NAME="gpt-5.4-mini" # Optional, defaults to gpt-5.4-mini
|
||||
```
|
||||
+15
@@ -0,0 +1,15 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Abstractions\Microsoft.Agents.AI.Abstractions.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
+152
@@ -0,0 +1,152 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows all the required steps to create a fully custom agent implementation.
|
||||
// In this case the agent doesn't use AI at all, and simply parrots back the user input in upper case.
|
||||
// You can however, build a fully custom agent that uses AI in any way you want.
|
||||
|
||||
using System.Runtime.CompilerServices;
|
||||
using System.Text.Json;
|
||||
using System.Text.Json.Serialization;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Extensions.AI;
|
||||
using SampleApp;
|
||||
|
||||
AIAgent agent = new UpperCaseParrotAgent();
|
||||
|
||||
// Invoke the agent and output the text result.
|
||||
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));
|
||||
|
||||
// Invoke the agent with streaming support.
|
||||
await foreach (var update in agent.RunStreamingAsync("Tell me a joke about a pirate."))
|
||||
{
|
||||
Console.WriteLine(update);
|
||||
}
|
||||
|
||||
namespace SampleApp
|
||||
{
|
||||
// Custom agent that parrot's the user input back in upper case.
|
||||
internal sealed class UpperCaseParrotAgent : AIAgent
|
||||
{
|
||||
public override string? Name => "UpperCaseParrotAgent";
|
||||
|
||||
public readonly ChatHistoryProvider ChatHistoryProvider = new InMemoryChatHistoryProvider();
|
||||
|
||||
protected override ValueTask<AgentSession> CreateSessionCoreAsync(CancellationToken cancellationToken = default)
|
||||
=> new(new CustomAgentSession());
|
||||
|
||||
protected override ValueTask<JsonElement> SerializeSessionCoreAsync(AgentSession session, JsonSerializerOptions? jsonSerializerOptions = null, CancellationToken cancellationToken = default)
|
||||
{
|
||||
if (session is not CustomAgentSession typedSession)
|
||||
{
|
||||
throw new ArgumentException($"The provided session is not of type {nameof(CustomAgentSession)}.", nameof(session));
|
||||
}
|
||||
|
||||
return new(JsonSerializer.SerializeToElement(typedSession, jsonSerializerOptions));
|
||||
}
|
||||
|
||||
protected override ValueTask<AgentSession> DeserializeSessionCoreAsync(JsonElement serializedState, JsonSerializerOptions? jsonSerializerOptions = null, CancellationToken cancellationToken = default)
|
||||
=> new(serializedState.Deserialize<CustomAgentSession>(jsonSerializerOptions)!);
|
||||
|
||||
protected override async Task<AgentResponse> RunCoreAsync(IEnumerable<ChatMessage> messages, AgentSession? session = null, AgentRunOptions? options = null, CancellationToken cancellationToken = default)
|
||||
{
|
||||
// Create a session if the user didn't supply one.
|
||||
session ??= await this.CreateSessionAsync(cancellationToken);
|
||||
|
||||
if (session is not CustomAgentSession typedSession)
|
||||
{
|
||||
throw new ArgumentException($"The provided session is not of type {nameof(CustomAgentSession)}.", nameof(session));
|
||||
}
|
||||
|
||||
// Get existing messages from the store
|
||||
var invokingContext = new ChatHistoryProvider.InvokingContext(this, session, messages);
|
||||
var userAndChatHistoryMessages = await this.ChatHistoryProvider.InvokingAsync(invokingContext, cancellationToken);
|
||||
|
||||
// Clone the input messages and turn them into response messages with upper case text.
|
||||
List<ChatMessage> responseMessages = CloneAndToUpperCase(messages, this.Name).ToList();
|
||||
|
||||
// Notify the session of the input and output messages.
|
||||
var invokedContext = new ChatHistoryProvider.InvokedContext(this, session, userAndChatHistoryMessages, responseMessages);
|
||||
await this.ChatHistoryProvider.InvokedAsync(invokedContext, cancellationToken);
|
||||
|
||||
return new AgentResponse
|
||||
{
|
||||
AgentId = this.Id,
|
||||
ResponseId = Guid.NewGuid().ToString("N"),
|
||||
Messages = responseMessages
|
||||
};
|
||||
}
|
||||
|
||||
protected override async IAsyncEnumerable<AgentResponseUpdate> RunCoreStreamingAsync(IEnumerable<ChatMessage> messages, AgentSession? session = null, AgentRunOptions? options = null, [EnumeratorCancellation] CancellationToken cancellationToken = default)
|
||||
{
|
||||
// Create a session if the user didn't supply one.
|
||||
session ??= await this.CreateSessionAsync(cancellationToken);
|
||||
|
||||
if (session is not CustomAgentSession typedSession)
|
||||
{
|
||||
throw new ArgumentException($"The provided session is not of type {nameof(CustomAgentSession)}.", nameof(session));
|
||||
}
|
||||
|
||||
// Get existing messages from the store
|
||||
var invokingContext = new ChatHistoryProvider.InvokingContext(this, session, messages);
|
||||
var userAndChatHistoryMessages = await this.ChatHistoryProvider.InvokingAsync(invokingContext, cancellationToken);
|
||||
|
||||
// Clone the input messages and turn them into response messages with upper case text.
|
||||
List<ChatMessage> responseMessages = CloneAndToUpperCase(messages, this.Name).ToList();
|
||||
|
||||
// Notify the session of the input and output messages.
|
||||
var invokedContext = new ChatHistoryProvider.InvokedContext(this, session, userAndChatHistoryMessages, responseMessages);
|
||||
await this.ChatHistoryProvider.InvokedAsync(invokedContext, cancellationToken);
|
||||
|
||||
foreach (var message in responseMessages)
|
||||
{
|
||||
yield return new AgentResponseUpdate
|
||||
{
|
||||
AgentId = this.Id,
|
||||
AuthorName = message.AuthorName,
|
||||
Role = ChatRole.Assistant,
|
||||
Contents = message.Contents,
|
||||
ResponseId = Guid.NewGuid().ToString("N"),
|
||||
MessageId = Guid.NewGuid().ToString("N")
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
private static IEnumerable<ChatMessage> CloneAndToUpperCase(IEnumerable<ChatMessage> messages, string? agentName) => messages.Select(x =>
|
||||
{
|
||||
// Clone the message and update its author to be the agent.
|
||||
var messageClone = x.Clone();
|
||||
messageClone.Role = ChatRole.Assistant;
|
||||
messageClone.MessageId = Guid.NewGuid().ToString("N");
|
||||
messageClone.AuthorName = agentName;
|
||||
|
||||
// Clone and convert any text content to upper case.
|
||||
messageClone.Contents = x.Contents.Select(c => c switch
|
||||
{
|
||||
TextContent tc => new TextContent(tc.Text.ToUpperInvariant())
|
||||
{
|
||||
AdditionalProperties = tc.AdditionalProperties,
|
||||
Annotations = tc.Annotations,
|
||||
RawRepresentation = tc.RawRepresentation
|
||||
},
|
||||
_ => c
|
||||
}).ToList();
|
||||
|
||||
return messageClone;
|
||||
});
|
||||
|
||||
/// <summary>
|
||||
/// A session type for our custom agent that only supports in memory storage of messages.
|
||||
/// </summary>
|
||||
internal sealed class CustomAgentSession : AgentSession
|
||||
{
|
||||
internal CustomAgentSession()
|
||||
{
|
||||
}
|
||||
|
||||
[JsonConstructor]
|
||||
internal CustomAgentSession(AgentSessionStateBag stateBag) : base(stateBag)
|
||||
{
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
# Agent with Custom Implementation
|
||||
|
||||
This sample demonstrates how to create a fully custom agent implementation without relying on external AI services.
|
||||
|
||||
## Overview
|
||||
|
||||
The sample creates a simple "parrot" agent that:
|
||||
- Converts user input to uppercase
|
||||
- Supports both synchronous and streaming invocation modes
|
||||
- Demonstrates the complete implementation requirements for a custom agent
|
||||
|
||||
This pattern is useful when you need to:
|
||||
- Integrate with custom AI models or services
|
||||
- Create rule-based agents without AI
|
||||
- Build agents with specific custom logic
|
||||
|
||||
+20
@@ -0,0 +1,20 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<PackageReference Include="Azure.AI.Projects" />
|
||||
<PackageReference Include="Azure.Identity" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
+39
@@ -0,0 +1,39 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to create, use, and clean up a FoundryAgent backed by a server-side
|
||||
// versioned agent in Microsoft Foundry. It demonstrates the full lifecycle:
|
||||
// create agent version -> wrap as FoundryAgent -> run -> delete.
|
||||
|
||||
using Azure.AI.Projects;
|
||||
using Azure.AI.Projects.Agents;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI.Foundry;
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
const string JokerName = "JokerAgent";
|
||||
|
||||
// Create the AIProjectClient to manage server-side agents.
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
// Create a server-side agent version using the native SDK.
|
||||
ProjectsAgentVersion agentVersion = await aiProjectClient.AgentAdministrationClient.CreateAgentVersionAsync(
|
||||
JokerName,
|
||||
new ProjectsAgentVersionCreationOptions(
|
||||
new DeclarativeAgentDefinition(model: deploymentName)
|
||||
{
|
||||
Instructions = "You are good at telling jokes.",
|
||||
}));
|
||||
|
||||
// Wrap the agent version as a FoundryAgent using the AsAIAgent extension.
|
||||
FoundryAgent agent = aiProjectClient.AsAIAgent(agentVersion);
|
||||
|
||||
// Once you have the agent, you can invoke it like any other AIAgent.
|
||||
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));
|
||||
|
||||
// Cleanup: deletes the agent and all its versions.
|
||||
await aiProjectClient.AgentAdministrationClient.DeleteAgentAsync(agent.Name);
|
||||
+24
@@ -0,0 +1,24 @@
|
||||
# Agent Step 00 - FoundryAgent Lifecycle
|
||||
|
||||
This sample demonstrates the full lifecycle of a `FoundryAgent` backed by a server-side versioned agent in Microsoft Foundry: create → run → delete.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- A Microsoft Foundry project endpoint
|
||||
- A model deployment name (defaults to `gpt-5.4-mini`)
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
|
||||
## Environment Variables
|
||||
|
||||
| Variable | Description | Required |
|
||||
| --- | --- | --- |
|
||||
| `FOUNDRY_PROJECT_ENDPOINT` | Microsoft Foundry project endpoint | Yes |
|
||||
| `FOUNDRY_MODEL` | Model deployment name | No (defaults to `gpt-5.4-mini`) |
|
||||
|
||||
## Running the sample
|
||||
|
||||
```powershell
|
||||
cd dotnet/samples/02-agents/AgentProviders/foundry
|
||||
dotnet run --project .\Agent_Step00_FoundryAgentLifecycle
|
||||
```
|
||||
|
||||
+15
@@ -0,0 +1,15 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
@@ -0,0 +1,20 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to create and run a basic agent with AIProjectClient.AsAIAgent(...).
|
||||
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIAgent agent =
|
||||
new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
|
||||
.AsAIAgent(model: deploymentName, instructions: "You are good at telling jokes.", name: "JokerAgent");
|
||||
|
||||
// Once you have the agent, you can invoke it like any other AIAgent.
|
||||
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));
|
||||
@@ -0,0 +1,56 @@
|
||||
# Creating and Running a Basic Agent with the Responses API
|
||||
|
||||
This sample demonstrates how to create and run a basic AI agent using the `ChatClientAgent`, which uses the Microsoft Foundry Responses API directly without creating server-side agent definitions.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Creating a `ChatClientAgent` with instructions and a model
|
||||
- Running a simple single-turn conversation
|
||||
- No server-side agent creation or cleanup required
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Before you begin, ensure you have the following prerequisites:
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
|
||||
**Note**: This sample uses `DefaultAzureCredential`. `az login` is the easiest local development path, but Visual Studio, VS Code, and managed identity credentials also work when available.
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-5.4-mini"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
Navigate to the Foundry sample directory and run:
|
||||
|
||||
```powershell
|
||||
cd dotnet/samples/02-agents/AgentProviders/foundry
|
||||
dotnet run --project .\Agent_Step01_Basics
|
||||
```
|
||||
|
||||
## Alternative: Composable approach
|
||||
|
||||
You can also create the same agent by composing the underlying `IChatClient` directly. This gives you full control over the chat client pipeline:
|
||||
|
||||
```csharp
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Extensions.AI;
|
||||
|
||||
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
AIAgent agent = new ChatClientAgent(
|
||||
chatClient: aiProjectClient.GetProjectOpenAIClient().GetProjectResponsesClient().AsIChatClient(deploymentName),
|
||||
instructions: "You are good at telling jokes.",
|
||||
name: "JokerAgent");
|
||||
```
|
||||
|
||||
This approach is useful when you need to customize the chat client pipeline or swap providers (e.g., Anthropic, OpenAI) while keeping the same agent code.
|
||||
|
||||
+15
@@ -0,0 +1,15 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
+26
@@ -0,0 +1,26 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to create a multi-turn conversation agent using sessions.
|
||||
// Context is preserved across multiple runs via response ID chaining in the session.
|
||||
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIAgent agent = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
|
||||
.AsAIAgent(deploymentName, instructions: "You are good at telling jokes.", name: "JokerAgent");
|
||||
|
||||
// Create a session to maintain context across multiple runs.
|
||||
AgentSession session = await agent.CreateSessionAsync();
|
||||
|
||||
// First turn
|
||||
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate.", session));
|
||||
|
||||
// Second turn — the agent remembers the first turn via the session.
|
||||
Console.WriteLine(await agent.RunAsync("Now add some emojis to the joke and tell it in the voice of a pirate's parrot.", session));
|
||||
+37
@@ -0,0 +1,37 @@
|
||||
# Multi-turn Conversation
|
||||
|
||||
This sample demonstrates how to implement multi-turn conversations where context is preserved across multiple agent runs using sessions and response ID chaining.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Creating an agent with instructions
|
||||
- Using sessions to maintain conversation context across multiple runs
|
||||
- Response ID chaining for multi-turn conversations
|
||||
- No server-side conversation creation required
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Before you begin, ensure you have the following prerequisites:
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
|
||||
**Note**: This sample uses `DefaultAzureCredential`. `az login` is the easiest local development path, but Visual Studio, VS Code, and managed identity credentials also work when available.
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-5.4-mini"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
Navigate to the Foundry sample directory and run:
|
||||
|
||||
```powershell
|
||||
cd dotnet/samples/02-agents/AgentProviders/foundry
|
||||
dotnet run --project .\Agent_Step02.1_MultiturnConversation
|
||||
```
|
||||
|
||||
+15
@@ -0,0 +1,15 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
+42
@@ -0,0 +1,42 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to use server-side conversations with a FoundryAgent.
|
||||
// Server-side conversations persist on the Foundry service and are visible in the Foundry Project UI.
|
||||
// Use this when you need conversation history to be stored and accessible server-side.
|
||||
|
||||
using Azure.AI.Extensions.OpenAI;
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
ChatClientAgent agent = aiProjectClient
|
||||
.AsAIAgent(deploymentName, instructions: "You are good at telling jokes.", name: "JokerAgent");
|
||||
|
||||
ProjectConversationsClient conversationsClient = aiProjectClient
|
||||
.GetProjectOpenAIClient()
|
||||
.GetProjectConversationsClient();
|
||||
|
||||
ProjectConversation conversation = (await conversationsClient.CreateProjectConversationAsync().ConfigureAwait(false)).Value;
|
||||
|
||||
// CreateConversationSessionAsync creates a server-side ProjectConversation
|
||||
// that persists on the Foundry service and is visible in the Foundry Project UI.
|
||||
AgentSession session = await agent.CreateSessionAsync(conversation.Id);
|
||||
|
||||
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate.", session));
|
||||
Console.WriteLine(await agent.RunAsync("Now add some emojis to the joke and tell it in the voice of a pirate's parrot.", session));
|
||||
|
||||
// Streaming with server-side conversation context.
|
||||
await foreach (AgentResponseUpdate update in agent.RunStreamingAsync("Tell me another joke, but about a ninja this time.", session))
|
||||
{
|
||||
Console.Write(update);
|
||||
}
|
||||
|
||||
Console.WriteLine();
|
||||
+37
@@ -0,0 +1,37 @@
|
||||
# Multi-turn Conversation with Server-Side Conversations
|
||||
|
||||
This sample demonstrates how to use server-side conversations with a `FoundryAgent`. Server-side conversations persist on the Foundry service and are visible in the Foundry Project UI, making them ideal when you need conversation history to be stored and accessible server-side.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Creating a `FoundryAgent` with instructions
|
||||
- Using `CreateConversationSessionAsync` to create a server-side `ProjectConversation`
|
||||
- Multi-turn conversations with both text and streaming output
|
||||
- Server-side conversation persistence visible in the Foundry Project UI
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Before you begin, ensure you have the following prerequisites:
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
|
||||
**Note**: This sample uses `DefaultAzureCredential`. `az login` is the easiest local development path, but Visual Studio, VS Code, and managed identity credentials also work when available.
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-5.4-mini"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
Navigate to the Foundry sample directory and run:
|
||||
|
||||
```powershell
|
||||
cd dotnet/samples/02-agents/AgentProviders/foundry
|
||||
dotnet run --project .\Agent_Step02.2_MultiturnWithServerConversations
|
||||
```
|
||||
|
||||
+15
@@ -0,0 +1,15 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
+41
@@ -0,0 +1,41 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample demonstrates how to use function tools.
|
||||
|
||||
using System.ComponentModel;
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Extensions.AI;
|
||||
|
||||
[Description("Get the weather for a given location.")]
|
||||
static string GetWeather([Description("The location to get the weather for.")] string location)
|
||||
=> $"The weather in {location} is cloudy with a high of 15°C.";
|
||||
|
||||
// Define the function tool.
|
||||
AITool tool = AIFunctionFactory.Create(GetWeather);
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
// Create a AIAgent with function tools.
|
||||
AIAgent agent = aiProjectClient.AsAIAgent(deploymentName,
|
||||
instructions: "You are a helpful assistant that can get weather information.",
|
||||
name: "WeatherAssistant",
|
||||
tools: [tool]);
|
||||
|
||||
// Non-streaming agent interaction with function tools.
|
||||
AgentSession session = await agent.CreateSessionAsync();
|
||||
Console.WriteLine(await agent.RunAsync("What is the weather like in Amsterdam?", session));
|
||||
|
||||
// Streaming agent interaction with function tools.
|
||||
session = await agent.CreateSessionAsync();
|
||||
await foreach (AgentResponseUpdate update in agent.RunStreamingAsync("What is the weather like in Amsterdam?", session))
|
||||
{
|
||||
Console.Write(update);
|
||||
}
|
||||
+38
@@ -0,0 +1,38 @@
|
||||
# Using Function Tools with the Responses API
|
||||
|
||||
This sample demonstrates how to use function tools with the `ChatClientAgent`, allowing the agent to call custom functions to retrieve information.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Creating function tools using `AIFunctionFactory`
|
||||
- Passing function tools to a `ChatClientAgent`
|
||||
- Running agents with function tools (text output)
|
||||
- Running agents with function tools (streaming output)
|
||||
- No server-side agent creation or cleanup required
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Before you begin, ensure you have the following prerequisites:
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
|
||||
**Note**: This sample uses `DefaultAzureCredential`. `az login` is the easiest local development path, but Visual Studio, VS Code, and managed identity credentials also work when available.
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-5.4-mini"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
Navigate to the Foundry sample directory and run:
|
||||
|
||||
```powershell
|
||||
cd dotnet/samples/02-agents/AgentProviders/foundry
|
||||
dotnet run --project .\Agent_Step03_UsingFunctionTools
|
||||
```
|
||||
|
||||
+15
@@ -0,0 +1,15 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
+52
@@ -0,0 +1,52 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample demonstrates how to use an agent with function tools that require a human in the loop for approvals.
|
||||
|
||||
using System.ComponentModel;
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Extensions.AI;
|
||||
|
||||
[Description("Get the weather for a given location.")]
|
||||
static string GetWeather([Description("The location to get the weather for.")] string location)
|
||||
=> $"The weather in {location} is cloudy with a high of 15°C.";
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
ApprovalRequiredAIFunction approvalTool = new(AIFunctionFactory.Create(GetWeather, name: nameof(GetWeather)));
|
||||
|
||||
AIAgent agent = aiProjectClient.AsAIAgent(deploymentName,
|
||||
instructions: "You are a helpful assistant that can get weather information.",
|
||||
name: "WeatherAssistant",
|
||||
tools: [approvalTool]);
|
||||
|
||||
// Call the agent with approval-required function tools.
|
||||
AgentSession session = await agent.CreateSessionAsync();
|
||||
AgentResponse response = await agent.RunAsync("What is the weather like in Amsterdam?", session);
|
||||
|
||||
// Check if there are any approval requests.
|
||||
List<ToolApprovalRequestContent> approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
|
||||
|
||||
while (approvalRequests.Count > 0)
|
||||
{
|
||||
// Ask the user to approve each function call request.
|
||||
List<ChatMessage> userInputMessages = approvalRequests
|
||||
.ConvertAll(functionApprovalRequest =>
|
||||
{
|
||||
Console.WriteLine($"The agent would like to invoke the following function, please reply Y to approve: Name {((FunctionCallContent)functionApprovalRequest.ToolCall).Name}");
|
||||
bool approved = Console.ReadLine()?.Equals("Y", StringComparison.OrdinalIgnoreCase) ?? false;
|
||||
return new ChatMessage(ChatRole.User, [functionApprovalRequest.CreateResponse(approved)]);
|
||||
});
|
||||
|
||||
response = await agent.RunAsync(userInputMessages, session);
|
||||
approvalRequests = response.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
|
||||
}
|
||||
|
||||
Console.WriteLine($"\nAgent: {response}");
|
||||
+31
@@ -0,0 +1,31 @@
|
||||
# Using Function Tools with Approvals via the Responses API
|
||||
|
||||
This sample demonstrates how to use function tools that require human-in-the-loop approval before execution.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Creating function tools that require approval using `ApprovalRequiredAIFunction`
|
||||
- Handling approval requests from the agent
|
||||
- Passing approval responses back to the agent
|
||||
- No server-side agent creation or cleanup required
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-5.4-mini"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
```powershell
|
||||
cd dotnet/samples/02-agents/AgentProviders/foundry
|
||||
dotnet run --project .\Agent_Step04_UsingFunctionToolsWithApprovals
|
||||
```
|
||||
|
||||
+15
@@ -0,0 +1,15 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
+71
@@ -0,0 +1,71 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to configure an agent to produce structured output.
|
||||
|
||||
using System.ComponentModel;
|
||||
using System.Text.Json;
|
||||
using System.Text.Json.Serialization;
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
using SampleApp;
|
||||
|
||||
#pragma warning disable CA5399
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
AIAgent agent = aiProjectClient.AsAIAgent(new ChatClientAgentOptions
|
||||
{
|
||||
Name = "StructuredOutputAssistant",
|
||||
ChatOptions = new()
|
||||
{
|
||||
ModelId = deploymentName,
|
||||
Instructions = "You are a helpful assistant that extracts structured information about people.",
|
||||
ResponseFormat = Microsoft.Extensions.AI.ChatResponseFormat.ForJsonSchema<PersonInfo>()
|
||||
}
|
||||
});
|
||||
|
||||
// Set PersonInfo as the type parameter of RunAsync method to specify the expected structured output.
|
||||
AgentResponse<PersonInfo> response = await agent.RunAsync<PersonInfo>("Please provide information about John Smith, who is a 35-year-old software engineer.");
|
||||
|
||||
// Access the structured output via the Result property of the agent response.
|
||||
Console.WriteLine("Assistant Output:");
|
||||
Console.WriteLine($"Name: {response.Result.Name}");
|
||||
Console.WriteLine($"Age: {response.Result.Age}");
|
||||
Console.WriteLine($"Occupation: {response.Result.Occupation}");
|
||||
|
||||
// Invoke the agent with streaming support, then deserialize the assembled response.
|
||||
IAsyncEnumerable<AgentResponseUpdate> updates = agent.RunStreamingAsync("Please provide information about Jane Doe, who is a 28-year-old data scientist.");
|
||||
|
||||
PersonInfo personInfo = JsonSerializer.Deserialize<PersonInfo>((await updates.ToAgentResponseAsync()).Text, JsonSerializerOptions.Web)
|
||||
?? throw new InvalidOperationException("Failed to deserialize the streamed response into PersonInfo.");
|
||||
|
||||
Console.WriteLine("\nStreaming Assistant Output:");
|
||||
Console.WriteLine($"Name: {personInfo.Name}");
|
||||
Console.WriteLine($"Age: {personInfo.Age}");
|
||||
Console.WriteLine($"Occupation: {personInfo.Occupation}");
|
||||
|
||||
namespace SampleApp
|
||||
{
|
||||
/// <summary>
|
||||
/// Represents information about a person.
|
||||
/// </summary>
|
||||
[Description("Information about a person including their name, age, and occupation")]
|
||||
public class PersonInfo
|
||||
{
|
||||
[JsonPropertyName("name")]
|
||||
public string? Name { get; set; }
|
||||
|
||||
[JsonPropertyName("age")]
|
||||
public int? Age { get; set; }
|
||||
|
||||
[JsonPropertyName("occupation")]
|
||||
public string? Occupation { get; set; }
|
||||
}
|
||||
}
|
||||
+30
@@ -0,0 +1,30 @@
|
||||
# Structured Output with the Responses API
|
||||
|
||||
This sample demonstrates how to configure an agent to produce structured output using JSON schema.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Using `RunAsync<T>()` to get typed structured output from the agent
|
||||
- Deserializing streamed responses into structured types
|
||||
- No server-side agent creation or cleanup required
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-5.4-mini"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
```powershell
|
||||
cd dotnet/samples/02-agents/AgentProviders/foundry
|
||||
dotnet run --project .\Agent_Step05_StructuredOutput
|
||||
```
|
||||
|
||||
+15
@@ -0,0 +1,15 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
+42
@@ -0,0 +1,42 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to persist and resume conversations.
|
||||
|
||||
using System.Text.Json;
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
AIAgent agent = aiProjectClient.AsAIAgent(deploymentName,
|
||||
instructions: "You are good at telling jokes.",
|
||||
name: "JokerAgent");
|
||||
|
||||
// Start a new session for the agent conversation.
|
||||
AgentSession session = await agent.CreateSessionAsync();
|
||||
|
||||
// Run the agent with a new session.
|
||||
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate.", session));
|
||||
|
||||
// Serialize the session state to a JsonElement, so it can be stored for later use.
|
||||
JsonElement serializedSession = await agent.SerializeSessionAsync(session);
|
||||
|
||||
// Save the serialized session to a temporary file (for demonstration purposes).
|
||||
string tempFilePath = Path.GetTempFileName();
|
||||
await File.WriteAllTextAsync(tempFilePath, JsonSerializer.Serialize(serializedSession));
|
||||
|
||||
// Load the serialized session from the temporary file (for demonstration purposes).
|
||||
JsonElement reloadedSerializedSession = JsonElement.Parse(await File.ReadAllTextAsync(tempFilePath))!;
|
||||
|
||||
// Deserialize the session state after loading from storage.
|
||||
AgentSession resumedSession = await agent.DeserializeSessionAsync(reloadedSerializedSession);
|
||||
|
||||
// Run the agent again with the resumed session.
|
||||
Console.WriteLine(await agent.RunAsync("Now tell the same joke in the voice of a pirate, and add some emojis to the joke.", resumedSession));
|
||||
+31
@@ -0,0 +1,31 @@
|
||||
# Persisted Conversations with the Responses API
|
||||
|
||||
This sample demonstrates how to persist and resume agent conversations using session serialization.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Serializing agent sessions to JSON for persistence
|
||||
- Saving and loading sessions from disk
|
||||
- Resuming conversations with preserved context
|
||||
- No server-side agent creation or cleanup required
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-5.4-mini"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
```powershell
|
||||
cd dotnet/samples/02-agents/AgentProviders/foundry
|
||||
dotnet run --project .\Agent_Step06_PersistedConversations
|
||||
```
|
||||
|
||||
+21
@@ -0,0 +1,21 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<PackageReference Include="Azure.Monitor.OpenTelemetry.Exporter" />
|
||||
<PackageReference Include="OpenTelemetry" />
|
||||
<PackageReference Include="OpenTelemetry.Exporter.Console" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
@@ -0,0 +1,52 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to add OpenTelemetry observability to an agent.
|
||||
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Azure.Monitor.OpenTelemetry.Exporter;
|
||||
using Microsoft.Agents.AI;
|
||||
using OpenTelemetry;
|
||||
using OpenTelemetry.Trace;
|
||||
|
||||
string? applicationInsightsConnectionString = Environment.GetEnvironmentVariable("APPLICATIONINSIGHTS_CONNECTION_STRING");
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
// Create TracerProvider with console exporter.
|
||||
string sourceName = Guid.NewGuid().ToString("N");
|
||||
TracerProviderBuilder tracerProviderBuilder = Sdk.CreateTracerProviderBuilder()
|
||||
.AddSource(sourceName)
|
||||
.AddConsoleExporter();
|
||||
if (!string.IsNullOrWhiteSpace(applicationInsightsConnectionString))
|
||||
{
|
||||
tracerProviderBuilder.AddAzureMonitorTraceExporter(options => options.ConnectionString = applicationInsightsConnectionString);
|
||||
}
|
||||
using var tracerProvider = tracerProviderBuilder.Build();
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
AIAgent agent = aiProjectClient
|
||||
.AsAIAgent(
|
||||
deploymentName,
|
||||
instructions: "You are good at telling jokes.",
|
||||
name: "JokerAgent")
|
||||
.AsBuilder()
|
||||
.UseOpenTelemetry(sourceName: sourceName)
|
||||
.Build();
|
||||
|
||||
// Invoke the agent and output the text result.
|
||||
AgentSession session = await agent.CreateSessionAsync();
|
||||
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate.", session));
|
||||
|
||||
// Invoke the agent with streaming support.
|
||||
session = await agent.CreateSessionAsync();
|
||||
await foreach (AgentResponseUpdate update in agent.RunStreamingAsync("Tell me a joke about a pirate.", session))
|
||||
{
|
||||
Console.Write(update);
|
||||
}
|
||||
|
||||
Console.WriteLine();
|
||||
@@ -0,0 +1,32 @@
|
||||
# Observability with the Responses API
|
||||
|
||||
This sample demonstrates how to add OpenTelemetry observability to an agent using console and Azure Monitor exporters.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Configuring OpenTelemetry tracing with console exporter
|
||||
- Optional Azure Application Insights integration
|
||||
- Using `.AsBuilder().UseOpenTelemetry()` to add telemetry to the agent
|
||||
- No server-side agent creation or cleanup required
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-5.4-mini"
|
||||
$env:APPLICATIONINSIGHTS_CONNECTION_STRING="..." # Optional
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
```powershell
|
||||
cd dotnet/samples/02-agents/AgentProviders/foundry
|
||||
dotnet run --project .\Agent_Step07_Observability
|
||||
```
|
||||
|
||||
+21
@@ -0,0 +1,21 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
|
||||
<NoWarn>$(NoWarn);CA1812</NoWarn>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<PackageReference Include="Microsoft.Extensions.Hosting" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
+83
@@ -0,0 +1,83 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to use dependency injection to register a AIAgent and use it from a hosted service.
|
||||
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Extensions.DependencyInjection;
|
||||
using Microsoft.Extensions.Hosting;
|
||||
using SampleApp;
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
AIAgent agent = aiProjectClient.AsAIAgent(deploymentName,
|
||||
instructions: "You are good at telling jokes.",
|
||||
name: "JokerAgent");
|
||||
|
||||
// Create a host builder that we will register services with and then run.
|
||||
HostApplicationBuilder builder = Host.CreateApplicationBuilder(args);
|
||||
|
||||
// Add the AI agent to the service collection.
|
||||
builder.Services.AddSingleton(agent);
|
||||
|
||||
// Add a sample service that will use the agent to respond to user input.
|
||||
builder.Services.AddHostedService<SampleService>();
|
||||
|
||||
// Build and run the host.
|
||||
using IHost host = builder.Build();
|
||||
await host.RunAsync().ConfigureAwait(false);
|
||||
|
||||
namespace SampleApp
|
||||
{
|
||||
/// <summary>
|
||||
/// A sample service that uses an AI agent to respond to user input.
|
||||
/// </summary>
|
||||
internal sealed class SampleService(AIAgent agent, IHostApplicationLifetime appLifetime) : IHostedService
|
||||
{
|
||||
private AgentSession? _session;
|
||||
|
||||
public async Task StartAsync(CancellationToken cancellationToken)
|
||||
{
|
||||
this._session = await agent.CreateSessionAsync(cancellationToken);
|
||||
_ = this.RunAsync(appLifetime.ApplicationStopping);
|
||||
}
|
||||
|
||||
public async Task RunAsync(CancellationToken cancellationToken)
|
||||
{
|
||||
await Task.Delay(100, cancellationToken);
|
||||
|
||||
while (!cancellationToken.IsCancellationRequested)
|
||||
{
|
||||
Console.WriteLine("\nAgent: Ask me to tell you a joke about a specific topic. To exit just press Ctrl+C or enter without any input.\n");
|
||||
Console.Write("> ");
|
||||
string? input = Console.ReadLine();
|
||||
|
||||
if (string.IsNullOrWhiteSpace(input))
|
||||
{
|
||||
appLifetime.StopApplication();
|
||||
break;
|
||||
}
|
||||
|
||||
await foreach (AgentResponseUpdate update in agent.RunStreamingAsync(input, this._session, cancellationToken: cancellationToken))
|
||||
{
|
||||
Console.Write(update);
|
||||
}
|
||||
|
||||
Console.WriteLine();
|
||||
}
|
||||
}
|
||||
|
||||
public Task StopAsync(CancellationToken cancellationToken)
|
||||
{
|
||||
Console.WriteLine("\nShutting down...");
|
||||
return Task.CompletedTask;
|
||||
}
|
||||
}
|
||||
}
|
||||
+31
@@ -0,0 +1,31 @@
|
||||
# Dependency Injection with the Responses API
|
||||
|
||||
This sample demonstrates how to register a `ChatClientAgent` in a dependency injection container and use it from a hosted service.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Registering `ChatClientAgent` as an `AIAgent` in the service collection
|
||||
- Using the agent from a `IHostedService` with an interactive chat loop
|
||||
- Streaming responses in a hosted service context
|
||||
- No server-side agent creation or cleanup required
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-5.4-mini"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
```powershell
|
||||
cd dotnet/samples/02-agents/AgentProviders/foundry
|
||||
dotnet run --project .\Agent_Step08_DependencyInjection
|
||||
```
|
||||
|
||||
+21
@@ -0,0 +1,21 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<PackageReference Include="Azure.Identity" />
|
||||
<PackageReference Include="ModelContextProtocol" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI\Microsoft.Agents.AI.csproj" />
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
+44
@@ -0,0 +1,44 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to use MCP client tools with an agent.
|
||||
// It connects to the Microsoft Learn MCP server via HTTP and uses its tools.
|
||||
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Extensions.AI;
|
||||
using ModelContextProtocol.Client;
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
// Connect to the Microsoft Learn MCP server via HTTP (Streamable HTTP transport).
|
||||
Console.WriteLine("Connecting to MCP server at https://learn.microsoft.com/api/mcp ...");
|
||||
|
||||
await using McpClient mcpClient = await McpClient.CreateAsync(new HttpClientTransport(new()
|
||||
{
|
||||
Endpoint = new Uri("https://learn.microsoft.com/api/mcp"),
|
||||
Name = "Microsoft Learn MCP",
|
||||
}));
|
||||
|
||||
// Retrieve the list of tools available on the MCP server.
|
||||
IList<McpClientTool> mcpTools = await mcpClient.ListToolsAsync();
|
||||
Console.WriteLine($"MCP tools available: {string.Join(", ", mcpTools.Select(t => t.Name))}");
|
||||
|
||||
List<AITool> agentTools = [.. mcpTools.Cast<AITool>()];
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
AIAgent agent = aiProjectClient.AsAIAgent(deploymentName,
|
||||
instructions: "You are a helpful assistant that can help with Microsoft documentation questions. Use the Microsoft Learn MCP tool to search for documentation. In the output, indicate which tool you used if any.",
|
||||
name: "DocsAgent",
|
||||
tools: agentTools);
|
||||
|
||||
Console.WriteLine($"Agent '{agent.Name}' created. Asking a question...\n");
|
||||
|
||||
const string Prompt = "How does one create an Azure storage account using az cli?";
|
||||
Console.WriteLine($"User: {Prompt}\n");
|
||||
Console.WriteLine($"Agent: {await agent.RunAsync(Prompt)}");
|
||||
+30
@@ -0,0 +1,30 @@
|
||||
# Using MCP Client as Tools with the Responses API
|
||||
|
||||
This sample shows how to use MCP (Model Context Protocol) client tools with a `ChatClientAgent` using the Responses API directly.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Connecting to an MCP server via HTTP client transport
|
||||
- Retrieving MCP tools and passing them to a `ChatClientAgent`
|
||||
- Using MCP tools for agent interactions without server-side agent creation
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
- Node.js installed (for npx/MCP server)
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-5.4-mini"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
```powershell
|
||||
dotnet run
|
||||
```
|
||||
|
||||
+21
@@ -0,0 +1,21 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<None Update="assets\walkway.jpg">
|
||||
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
|
||||
</None>
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
@@ -0,0 +1,34 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to use image multi-modality with an agent.
|
||||
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Extensions.AI;
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
AIAgent agent = aiProjectClient.AsAIAgent(deploymentName,
|
||||
instructions: "You are a helpful agent that can analyze images.",
|
||||
name: "VisionAgent");
|
||||
|
||||
ChatMessage message = new(ChatRole.User, [
|
||||
new TextContent("What do you see in this image?"),
|
||||
await DataContent.LoadFromAsync("assets/walkway.jpg"),
|
||||
]);
|
||||
|
||||
AgentSession session = await agent.CreateSessionAsync();
|
||||
|
||||
await foreach (AgentResponseUpdate update in agent.RunStreamingAsync(message, session))
|
||||
{
|
||||
Console.Write(update);
|
||||
}
|
||||
|
||||
Console.WriteLine();
|
||||
@@ -0,0 +1,31 @@
|
||||
# Using Images with the Responses API
|
||||
|
||||
This sample demonstrates how to use image multi-modality with an agent.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Loading images using `DataContent.LoadFromAsync`
|
||||
- Sending images alongside text to the agent
|
||||
- Streaming the agent's image analysis response
|
||||
- No server-side agent creation or cleanup required
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry service endpoint and a vision-capable model deployment (e.g., `gpt-5.4-mini`)
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-5.4-mini"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
```powershell
|
||||
cd dotnet/samples/02-agents/AgentProviders/foundry
|
||||
dotnet run --project .\Agent_Step10_UsingImages
|
||||
```
|
||||
|
||||
BIN
Binary file not shown.
|
After Width: | Height: | Size: 37 KiB |
+15
@@ -0,0 +1,15 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
+36
@@ -0,0 +1,36 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to use one agent as a function tool for another agent.
|
||||
|
||||
using System.ComponentModel;
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Extensions.AI;
|
||||
|
||||
[Description("Get the weather for a given location.")]
|
||||
static string GetWeather([Description("The location to get the weather for.")] string location)
|
||||
=> $"The weather in {location} is cloudy with a high of 15°C.";
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
AITool weatherTool = AIFunctionFactory.Create(GetWeather);
|
||||
AIAgent weatherAgent = aiProjectClient.AsAIAgent(deploymentName,
|
||||
instructions: "You answer questions about the weather.",
|
||||
name: "WeatherAgent",
|
||||
tools: [weatherTool]);
|
||||
|
||||
AIAgent agent = aiProjectClient.AsAIAgent(deploymentName,
|
||||
instructions: "You are a helpful assistant who responds in French.",
|
||||
name: "MainAgent",
|
||||
tools: [weatherAgent.AsAIFunction()]);
|
||||
|
||||
// Invoke the agent and output the text result.
|
||||
AgentSession session = await agent.CreateSessionAsync();
|
||||
Console.WriteLine(await agent.RunAsync("What is the weather like in Amsterdam?", session));
|
||||
@@ -0,0 +1,31 @@
|
||||
# Agent as a Function Tool with the Responses API
|
||||
|
||||
This sample demonstrates how to use one agent as a function tool for another agent.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Creating a specialized agent (weather) with function tools
|
||||
- Exposing an agent as a function tool using `.AsAIFunction()`
|
||||
- Composing agents where one agent delegates to another
|
||||
- No server-side agent creation or cleanup required
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-5.4-mini"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
```powershell
|
||||
cd dotnet/samples/02-agents/AgentProviders/foundry
|
||||
dotnet run --project .\Agent_Step11_AsFunctionTool
|
||||
```
|
||||
|
||||
+19
@@ -0,0 +1,19 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<PackageReference Include="Microsoft.Extensions.Logging.Console" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
@@ -0,0 +1,208 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows multiple middleware layers working together with a ChatClientAgent:
|
||||
// agent run (PII filtering and guardrails),
|
||||
// function invocation (logging and result overrides), and human-in-the-loop
|
||||
// approval workflows for sensitive function calls.
|
||||
|
||||
using System.ComponentModel;
|
||||
using System.Text.RegularExpressions;
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Extensions.AI;
|
||||
|
||||
[Description("Get the weather for a given location.")]
|
||||
static string GetWeather([Description("The location to get the weather for.")] string location)
|
||||
=> $"The weather in {location} is cloudy with a high of 15°C.";
|
||||
|
||||
[Description("The current datetime offset.")]
|
||||
static string GetDateTime()
|
||||
=> DateTimeOffset.Now.ToString();
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
AITool dateTimeTool = AIFunctionFactory.Create(GetDateTime, name: nameof(GetDateTime));
|
||||
AITool getWeatherTool = AIFunctionFactory.Create(GetWeather, name: nameof(GetWeather));
|
||||
|
||||
AIAgent originalAgent = aiProjectClient.AsAIAgent(deploymentName,
|
||||
instructions: "You are an AI assistant that helps people find information.",
|
||||
name: "InformationAssistant",
|
||||
tools: [getWeatherTool, dateTimeTool]);
|
||||
|
||||
// Adding middleware to the agent level
|
||||
AIAgent middlewareEnabledAgent = originalAgent
|
||||
.AsBuilder()
|
||||
.Use(FunctionCallMiddleware)
|
||||
.Use(FunctionCallOverrideWeather)
|
||||
.Use(PIIMiddleware, null)
|
||||
.Use(GuardrailMiddleware, null)
|
||||
.Build();
|
||||
|
||||
AgentSession session = await middlewareEnabledAgent.CreateSessionAsync();
|
||||
|
||||
Console.WriteLine("\n\n=== Example 1: Wording Guardrail ===");
|
||||
AgentResponse guardRailedResponse = await middlewareEnabledAgent.RunAsync("Tell me something harmful.");
|
||||
Console.WriteLine($"Guard railed response: {guardRailedResponse}");
|
||||
|
||||
Console.WriteLine("\n\n=== Example 2: PII detection ===");
|
||||
AgentResponse piiResponse = await middlewareEnabledAgent.RunAsync("My name is John Doe, call me at 123-456-7890 or email me at john@something.com");
|
||||
Console.WriteLine($"Pii filtered response: {piiResponse}");
|
||||
|
||||
Console.WriteLine("\n\n=== Example 3: Agent function middleware ===");
|
||||
AgentResponse functionCallResponse = await middlewareEnabledAgent.RunAsync("What's the current time and the weather in Seattle?", session);
|
||||
Console.WriteLine($"Function calling response: {functionCallResponse}");
|
||||
|
||||
// Special per-request middleware agent.
|
||||
Console.WriteLine("\n\n=== Example 4: Middleware with human in the loop function approval ===");
|
||||
|
||||
AIAgent humanInTheLoopAgent = aiProjectClient.AsAIAgent(deploymentName,
|
||||
instructions: "You are a Human in the loop testing AI assistant that helps people find information.",
|
||||
name: "HumanInTheLoopAgent",
|
||||
tools: [new ApprovalRequiredAIFunction(AIFunctionFactory.Create(GetWeather, name: nameof(GetWeather)))]);
|
||||
|
||||
AgentResponse response = await humanInTheLoopAgent
|
||||
.AsBuilder()
|
||||
.Use(ConsolePromptingApprovalMiddleware, null)
|
||||
.Build()
|
||||
.RunAsync("What's the current time and the weather in Seattle?");
|
||||
|
||||
Console.WriteLine($"HumanInTheLoopAgent agent middleware response: {response}");
|
||||
|
||||
// Function invocation middleware that logs before and after function calls.
|
||||
async ValueTask<object?> FunctionCallMiddleware(AIAgent agent, FunctionInvocationContext context, Func<FunctionInvocationContext, CancellationToken, ValueTask<object?>> next, CancellationToken cancellationToken)
|
||||
{
|
||||
Console.WriteLine($"Function Name: {context!.Function.Name} - Middleware 1 Pre-Invoke");
|
||||
var result = await next(context, cancellationToken);
|
||||
Console.WriteLine($"Function Name: {context!.Function.Name} - Middleware 1 Post-Invoke");
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
// Function invocation middleware that overrides the result of the GetWeather function.
|
||||
async ValueTask<object?> FunctionCallOverrideWeather(AIAgent agent, FunctionInvocationContext context, Func<FunctionInvocationContext, CancellationToken, ValueTask<object?>> next, CancellationToken cancellationToken)
|
||||
{
|
||||
Console.WriteLine($"Function Name: {context!.Function.Name} - Middleware 2 Pre-Invoke");
|
||||
|
||||
var result = await next(context, cancellationToken);
|
||||
|
||||
if (context.Function.Name == nameof(GetWeather))
|
||||
{
|
||||
result = "The weather is sunny with a high of 25°C.";
|
||||
}
|
||||
Console.WriteLine($"Function Name: {context!.Function.Name} - Middleware 2 Post-Invoke");
|
||||
return result;
|
||||
}
|
||||
|
||||
// This middleware redacts PII information from input and output messages.
|
||||
async Task<AgentResponse> PIIMiddleware(IEnumerable<ChatMessage> messages, AgentSession? session, AgentRunOptions? options, AIAgent innerAgent, CancellationToken cancellationToken)
|
||||
{
|
||||
var filteredMessages = FilterMessages(messages);
|
||||
Console.WriteLine("Pii Middleware - Filtered Messages Pre-Run");
|
||||
|
||||
var agentResponse = await innerAgent.RunAsync(filteredMessages, session, options, cancellationToken).ConfigureAwait(false);
|
||||
|
||||
agentResponse.Messages = FilterMessages(agentResponse.Messages);
|
||||
|
||||
Console.WriteLine("Pii Middleware - Filtered Messages Post-Run");
|
||||
|
||||
return agentResponse;
|
||||
|
||||
static IList<ChatMessage> FilterMessages(IEnumerable<ChatMessage> messages)
|
||||
{
|
||||
return messages.Select(m => new ChatMessage(m.Role, FilterPii(m.Text))).ToList();
|
||||
}
|
||||
|
||||
static string FilterPii(string content)
|
||||
{
|
||||
Regex[] piiPatterns = [
|
||||
MyRegex(),
|
||||
EmailRegex(),
|
||||
FullNameRegex()
|
||||
];
|
||||
|
||||
foreach (var pattern in piiPatterns)
|
||||
{
|
||||
content = pattern.Replace(content, "[REDACTED: PII]");
|
||||
}
|
||||
|
||||
return content;
|
||||
}
|
||||
}
|
||||
|
||||
// This middleware enforces guardrails by redacting certain keywords from input and output messages.
|
||||
async Task<AgentResponse> GuardrailMiddleware(IEnumerable<ChatMessage> messages, AgentSession? session, AgentRunOptions? options, AIAgent innerAgent, CancellationToken cancellationToken)
|
||||
{
|
||||
var filteredMessages = FilterMessages(messages);
|
||||
|
||||
Console.WriteLine("Guardrail Middleware - Filtered messages Pre-Run");
|
||||
|
||||
var agentResponse = await innerAgent.RunAsync(filteredMessages, session, options, cancellationToken);
|
||||
|
||||
agentResponse.Messages = FilterMessages(agentResponse.Messages);
|
||||
|
||||
Console.WriteLine("Guardrail Middleware - Filtered messages Post-Run");
|
||||
|
||||
return agentResponse;
|
||||
|
||||
List<ChatMessage> FilterMessages(IEnumerable<ChatMessage> messages)
|
||||
{
|
||||
return messages.Select(m => new ChatMessage(m.Role, FilterContent(m.Text))).ToList();
|
||||
}
|
||||
|
||||
static string FilterContent(string content)
|
||||
{
|
||||
foreach (var keyword in new[] { "harmful", "illegal", "violence" })
|
||||
{
|
||||
if (content.Contains(keyword, StringComparison.OrdinalIgnoreCase))
|
||||
{
|
||||
return "[REDACTED: Forbidden content]";
|
||||
}
|
||||
}
|
||||
|
||||
return content;
|
||||
}
|
||||
}
|
||||
|
||||
// This middleware handles Human in the loop console interaction for any user approval required during function calling.
|
||||
async Task<AgentResponse> ConsolePromptingApprovalMiddleware(IEnumerable<ChatMessage> messages, AgentSession? session, AgentRunOptions? options, AIAgent innerAgent, CancellationToken cancellationToken)
|
||||
{
|
||||
AgentResponse agentResponse = await innerAgent.RunAsync(messages, session, options, cancellationToken);
|
||||
|
||||
List<ToolApprovalRequestContent> approvalRequests = agentResponse.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
|
||||
|
||||
while (approvalRequests.Count > 0)
|
||||
{
|
||||
agentResponse.Messages = approvalRequests
|
||||
.ConvertAll(functionApprovalRequest =>
|
||||
{
|
||||
Console.WriteLine($"The agent would like to invoke the following function, please reply Y to approve: Name {((FunctionCallContent)functionApprovalRequest.ToolCall).Name}");
|
||||
bool approved = Console.ReadLine()?.Equals("Y", StringComparison.OrdinalIgnoreCase) ?? false;
|
||||
return new ChatMessage(ChatRole.User, [functionApprovalRequest.CreateResponse(approved)]);
|
||||
});
|
||||
|
||||
agentResponse = await innerAgent.RunAsync(agentResponse.Messages, session, options, cancellationToken);
|
||||
|
||||
approvalRequests = agentResponse.Messages.SelectMany(m => m.Contents).OfType<ToolApprovalRequestContent>().ToList();
|
||||
}
|
||||
|
||||
return agentResponse;
|
||||
}
|
||||
|
||||
internal partial class Program
|
||||
{
|
||||
[GeneratedRegex(@"\b\d{3}-\d{3}-\d{4}\b", RegexOptions.Compiled)]
|
||||
private static partial Regex MyRegex();
|
||||
|
||||
[GeneratedRegex(@"\b[\w\.-]+@[\w\.-]+\.\w+\b", RegexOptions.Compiled)]
|
||||
private static partial Regex EmailRegex();
|
||||
|
||||
[GeneratedRegex(@"\b[A-Z][a-z]+\s[A-Z][a-z]+\b", RegexOptions.Compiled)]
|
||||
private static partial Regex FullNameRegex();
|
||||
}
|
||||
@@ -0,0 +1,32 @@
|
||||
# Middleware with the Responses API
|
||||
|
||||
This sample demonstrates multiple middleware layers working together: PII filtering, guardrails, function invocation logging, and human-in-the-loop approval.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Agent-level run middleware (PII filtering, guardrail enforcement)
|
||||
- Function-level middleware (logging, result overrides)
|
||||
- Human-in-the-loop approval workflows for sensitive function calls
|
||||
- Using `.AsBuilder().Use()` to compose middleware
|
||||
- No server-side agent creation or cleanup required
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-5.4-mini"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
```powershell
|
||||
cd dotnet/samples/02-agents/AgentProviders/foundry
|
||||
dotnet run --project .\Agent_Step12_Middleware
|
||||
```
|
||||
|
||||
+21
@@ -0,0 +1,21 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
<NoWarn>$(NoWarn);CA1812</NoWarn>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<PackageReference Include="Azure.Identity" />
|
||||
<PackageReference Include="Microsoft.Extensions.Logging.Console" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
@@ -0,0 +1,153 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to use plugins with an AI agent. Plugin classes can
|
||||
// depend on other services that need to be injected. In this sample, the
|
||||
// AgentPlugin class uses the WeatherProvider and CurrentTimeProvider classes
|
||||
// to get weather and current time information. Both services are registered
|
||||
// in the service collection and injected into the plugin.
|
||||
// Plugin classes may have many methods, but only some are intended to be used
|
||||
// as AI functions. The AsAITools method of the plugin class shows how to specify
|
||||
// which methods should be exposed to the AI agent.
|
||||
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Extensions.AI;
|
||||
using Microsoft.Extensions.DependencyInjection;
|
||||
using SampleApp;
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
const string AssistantInstructions = "You are a helpful assistant that helps people find information.";
|
||||
const string AssistantName = "PluginAssistant";
|
||||
|
||||
// Create a service collection to hold the agent plugin and its dependencies.
|
||||
ServiceCollection services = new();
|
||||
services.AddSingleton<WeatherProvider>();
|
||||
services.AddSingleton<CurrentTimeProvider>();
|
||||
services.AddSingleton<AgentPlugin>(); // The plugin depends on WeatherProvider and CurrentTimeProvider registered above.
|
||||
|
||||
IServiceProvider serviceProvider = services.BuildServiceProvider();
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
// Create a ChatClientAgent with the options-based constructor to pass services.
|
||||
AIAgent agent = aiProjectClient.AsAIAgent(new ChatClientAgentOptions
|
||||
{
|
||||
Name = AssistantName,
|
||||
ChatOptions = new() { ModelId = deploymentName, Instructions = AssistantInstructions, Tools = serviceProvider.GetRequiredService<AgentPlugin>().AsAITools().ToList() }
|
||||
},
|
||||
services: serviceProvider);
|
||||
|
||||
// Invoke the agent and output the text result.
|
||||
AgentSession session = await agent.CreateSessionAsync();
|
||||
Console.WriteLine(await agent.RunAsync("Tell me current time and weather in Seattle.", session));
|
||||
|
||||
namespace SampleApp
|
||||
{
|
||||
/// <summary>
|
||||
/// The agent plugin that provides weather and current time information.
|
||||
/// </summary>
|
||||
internal sealed class AgentPlugin
|
||||
{
|
||||
private readonly WeatherProvider _weatherProvider;
|
||||
|
||||
/// <summary>
|
||||
/// Initializes a new instance of the <see cref="AgentPlugin"/> class.
|
||||
/// </summary>
|
||||
/// <param name="weatherProvider">The weather provider to get weather information.</param>
|
||||
public AgentPlugin(WeatherProvider weatherProvider)
|
||||
{
|
||||
this._weatherProvider = weatherProvider;
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Gets the weather information for the specified location.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// This method demonstrates how to use the dependency that was injected into the plugin class.
|
||||
/// </remarks>
|
||||
/// <param name="location">The location to get the weather for.</param>
|
||||
/// <returns>The weather information for the specified location.</returns>
|
||||
public string GetWeather(string location)
|
||||
{
|
||||
return this._weatherProvider.GetWeather(location);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Gets the current date and time for the specified location.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// This method demonstrates how to resolve a dependency using the service provider passed to the method.
|
||||
/// </remarks>
|
||||
/// <param name="sp">The service provider to resolve the <see cref="CurrentTimeProvider"/>.</param>
|
||||
/// <param name="location">The location to get the current time for.</param>
|
||||
/// <returns>The current date and time as a <see cref="DateTimeOffset"/>.</returns>
|
||||
public DateTimeOffset GetCurrentTime(IServiceProvider sp, string location)
|
||||
{
|
||||
CurrentTimeProvider currentTimeProvider = sp.GetRequiredService<CurrentTimeProvider>();
|
||||
return currentTimeProvider.GetCurrentTime(location);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Returns the functions provided by this plugin.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// In real world scenarios, a class may have many methods and only a subset of them may be intended to be exposed as AI functions.
|
||||
/// This method demonstrates how to explicitly specify which methods should be exposed to the AI agent.
|
||||
/// </remarks>
|
||||
/// <returns>The functions provided by this plugin.</returns>
|
||||
public IEnumerable<AITool> AsAITools()
|
||||
{
|
||||
yield return AIFunctionFactory.Create(this.GetWeather);
|
||||
yield return AIFunctionFactory.Create(this.GetCurrentTime);
|
||||
}
|
||||
}
|
||||
|
||||
internal sealed class WeatherProvider
|
||||
{
|
||||
private readonly string _weatherSummary = "cloudy with a high of 15°C";
|
||||
|
||||
/// <summary>
|
||||
/// The weather provider that returns weather information.
|
||||
/// </summary>
|
||||
/// <summary>
|
||||
/// Gets the weather information for the specified location.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// The weather information is hardcoded for demonstration purposes.
|
||||
/// In a real application, this could call a weather API to get actual weather data.
|
||||
/// </remarks>
|
||||
/// <param name="location">The location to get the weather for.</param>
|
||||
/// <returns>The weather information for the specified location.</returns>
|
||||
public string GetWeather(string location)
|
||||
{
|
||||
return $"The weather in {location} is {this._weatherSummary}.";
|
||||
}
|
||||
}
|
||||
|
||||
internal sealed class CurrentTimeProvider
|
||||
{
|
||||
private readonly TimeProvider _timeProvider = TimeProvider.System;
|
||||
|
||||
/// <summary>
|
||||
/// Provides the current date and time.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// This class returns the current date and time using the system's clock.
|
||||
/// </remarks>
|
||||
/// <summary>
|
||||
/// Gets the current date and time.
|
||||
/// </summary>
|
||||
/// <param name="location">The location to get the current time for (not used in this implementation).</param>
|
||||
/// <returns>The current date and time as a <see cref="DateTimeOffset"/>.</returns>
|
||||
public DateTimeOffset GetCurrentTime(string location)
|
||||
{
|
||||
return this._timeProvider.GetLocalNow();
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,30 @@
|
||||
# Using Plugins with the Responses API
|
||||
|
||||
This sample shows how to use plugins with a `ChatClientAgent` using the Responses API directly, with dependency injection for plugin services.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Creating plugin classes with injected dependencies
|
||||
- Registering services and building a service provider
|
||||
- Passing `services` to the `ChatClientAgent` via the options-based constructor
|
||||
- Using `AIFunctionFactory` to expose plugin methods as AI tools
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-5.4-mini"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
```powershell
|
||||
dotnet run
|
||||
```
|
||||
|
||||
+19
@@ -0,0 +1,19 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<PackageReference Include="Azure.Identity" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
+90
@@ -0,0 +1,90 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to use Code Interpreter Tool with AIProjectClient.AsAIAgent(...).
|
||||
|
||||
using System.Text;
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Extensions.AI;
|
||||
using OpenAI.Assistants;
|
||||
using OpenAI.Responses;
|
||||
|
||||
const string AgentInstructions = "You are a personal math tutor. When asked a math question, write and run code using the python tool to answer the question.";
|
||||
const string AgentName = "CoderAgent-RAPI";
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
// The easiest way to add the hosted code interpreter is as follows:
|
||||
/*
|
||||
AIAgent agent = aiProjectClient.AsAIAgent(
|
||||
deploymentName,
|
||||
instructions: AgentInstructions,
|
||||
name: AgentName,
|
||||
tools: [new HostedCodeInterpreterTool() { Inputs = [] }]);
|
||||
*/
|
||||
|
||||
// However, by default the reponses API does not return the output items from the hosted code interpreter tool.
|
||||
// This is generally fine but for this sample we want to explicitly request those in the response generation configuration.
|
||||
AIAgent agent = aiProjectClient
|
||||
.GetProjectOpenAIClient()
|
||||
.GetProjectResponsesClient()
|
||||
.AsIChatClient(deploymentName)
|
||||
.AsBuilder()
|
||||
.ConfigureOptions(x =>
|
||||
{
|
||||
var previousFactory = x.RawRepresentationFactory;
|
||||
x.RawRepresentationFactory = state =>
|
||||
{
|
||||
var responseOptions = previousFactory?.Invoke(state) as CreateResponseOptions ?? new CreateResponseOptions();
|
||||
|
||||
// Ensure that the response includes tool output items from the hosted code interpreter
|
||||
responseOptions.IncludedProperties.Add(IncludedResponseProperty.CodeInterpreterCallOutputs);
|
||||
|
||||
return responseOptions;
|
||||
};
|
||||
})
|
||||
.Build()
|
||||
.AsAIAgent(
|
||||
instructions: AgentInstructions,
|
||||
name: AgentName,
|
||||
tools: [new HostedCodeInterpreterTool() { Inputs = [] }]);
|
||||
|
||||
AgentResponse response = await agent.RunAsync("I need to solve the equation sin(x) + x^2 = 42");
|
||||
|
||||
// Get the CodeInterpreterToolCallContent
|
||||
CodeInterpreterToolCallContent? toolCallContent = response.Messages.SelectMany(m => m.Contents).OfType<CodeInterpreterToolCallContent>().FirstOrDefault();
|
||||
if (toolCallContent?.Inputs is not null)
|
||||
{
|
||||
DataContent? codeInput = toolCallContent.Inputs.OfType<DataContent>().FirstOrDefault();
|
||||
if (codeInput?.HasTopLevelMediaType("text") ?? false)
|
||||
{
|
||||
Console.WriteLine($"Code Input: {Encoding.UTF8.GetString(codeInput.Data.ToArray()) ?? "Not available"}");
|
||||
}
|
||||
}
|
||||
|
||||
// Get the CodeInterpreterToolResultContent
|
||||
CodeInterpreterToolResultContent? toolResultContent = response.Messages.SelectMany(m => m.Contents).OfType<CodeInterpreterToolResultContent>().FirstOrDefault();
|
||||
if (toolResultContent?.Outputs is not null && toolResultContent.Outputs.OfType<TextContent>().FirstOrDefault() is { } resultOutput)
|
||||
{
|
||||
Console.WriteLine($"Code Tool Result: {resultOutput.Text}");
|
||||
}
|
||||
|
||||
// Getting any annotations generated by the tool
|
||||
foreach (AIAnnotation annotation in response.Messages.SelectMany(m => m.Contents).SelectMany(C => C.Annotations ?? []))
|
||||
{
|
||||
if (annotation.RawRepresentation is TextAnnotationUpdate citationAnnotation)
|
||||
{
|
||||
Console.WriteLine($$"""
|
||||
File Id: {{citationAnnotation.OutputFileId}}
|
||||
Text to Replace: {{citationAnnotation.TextToReplace}}
|
||||
Filename: {{Path.GetFileName(citationAnnotation.TextToReplace)}}
|
||||
""");
|
||||
}
|
||||
}
|
||||
+29
@@ -0,0 +1,29 @@
|
||||
# Code Interpreter with the Responses API
|
||||
|
||||
This sample shows how to use the Code Interpreter tool with a `ChatClientAgent` using the Responses API directly.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Using `HostedCodeInterpreterTool` with `ChatClientAgent`
|
||||
- Extracting code input and output from agent responses
|
||||
- Handling code interpreter annotations and file citations
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-5.4-mini"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
```powershell
|
||||
dotnet run
|
||||
```
|
||||
|
||||
+33
@@ -0,0 +1,33 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
<NoWarn>$(NoWarn);OPENAICUA001;MEAI001</NoWarn>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<PackageReference Include="Azure.Identity" />
|
||||
<PackageReference Include="Microsoft.Extensions.Logging.Console" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<None Update="Assets\cua_browser_search.jpg">
|
||||
<CopyToOutputDirectory>Always</CopyToOutputDirectory>
|
||||
</None>
|
||||
<None Update="Assets\cua_search_results.jpg">
|
||||
<CopyToOutputDirectory>Always</CopyToOutputDirectory>
|
||||
</None>
|
||||
<None Update="Assets\cua_search_typed.jpg">
|
||||
<CopyToOutputDirectory>Always</CopyToOutputDirectory>
|
||||
</None>
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
BIN
Binary file not shown.
|
After Width: | Height: | Size: 402 KiB |
BIN
Binary file not shown.
|
After Width: | Height: | Size: 85 KiB |
BIN
Binary file not shown.
|
After Width: | Height: | Size: 357 KiB |
+93
@@ -0,0 +1,93 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
using Microsoft.Extensions.AI;
|
||||
using OpenAI.Responses;
|
||||
|
||||
namespace Demo.ComputerUse;
|
||||
|
||||
/// <summary>
|
||||
/// Enum for tracking the state of the simulated web search flow.
|
||||
/// </summary>
|
||||
internal enum SearchState
|
||||
{
|
||||
Initial, // Browser search page
|
||||
Typed, // Text entered in search box
|
||||
PressedEnter // Enter key pressed, transitioning to results
|
||||
}
|
||||
|
||||
internal static class ComputerUseUtil
|
||||
{
|
||||
internal static async Task<Dictionary<string, string>> UploadScreenshotAssetsAsync(IHostedFileClient fileClient)
|
||||
{
|
||||
string assetsDir = Path.Combine(AppDomain.CurrentDomain.BaseDirectory, "Assets");
|
||||
|
||||
(string key, string fileName)[] files =
|
||||
[
|
||||
("browser_search", "cua_browser_search.jpg"),
|
||||
("search_typed", "cua_search_typed.jpg"),
|
||||
("search_results", "cua_search_results.jpg")
|
||||
];
|
||||
|
||||
Dictionary<string, string> screenshots = [];
|
||||
|
||||
foreach (var (key, fileName) in files)
|
||||
{
|
||||
HostedFileContent result = await fileClient.UploadAsync(
|
||||
Path.Combine(assetsDir, fileName), new HostedFileClientOptions() { Purpose = "assistants" });
|
||||
screenshots[key] = result.FileId;
|
||||
}
|
||||
|
||||
return screenshots;
|
||||
}
|
||||
|
||||
internal static async Task EnsureDeleteScreenshotAssetsAsync(IHostedFileClient fileClient, Dictionary<string, string> screenshots)
|
||||
{
|
||||
foreach (var (_, fileId) in screenshots)
|
||||
{
|
||||
try
|
||||
{
|
||||
await fileClient.DeleteAsync(fileId);
|
||||
}
|
||||
catch
|
||||
{
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Simulates executing a computer action by advancing the state
|
||||
/// and returning the screenshot file ID for the new state.
|
||||
/// </summary>
|
||||
internal static async Task<(SearchState State, string FileId)> GetScreenshotAsync(
|
||||
ComputerCallAction action,
|
||||
SearchState currentState,
|
||||
Dictionary<string, string> screenshots)
|
||||
{
|
||||
if (action.Kind == ComputerCallActionKind.Wait)
|
||||
{
|
||||
await Task.Delay(TimeSpan.FromSeconds(5));
|
||||
}
|
||||
|
||||
SearchState nextState = action.Kind switch
|
||||
{
|
||||
ComputerCallActionKind.Click when currentState == SearchState.Typed => SearchState.PressedEnter,
|
||||
ComputerCallActionKind.Type when action.TypeText is not null => SearchState.Typed,
|
||||
ComputerCallActionKind.KeyPress when IsEnterKey(action) => SearchState.PressedEnter,
|
||||
_ => currentState
|
||||
};
|
||||
|
||||
string imageKey = nextState switch
|
||||
{
|
||||
SearchState.PressedEnter => "search_results",
|
||||
SearchState.Typed => "search_typed",
|
||||
_ => "browser_search"
|
||||
};
|
||||
|
||||
return (nextState, screenshots[imageKey]);
|
||||
}
|
||||
|
||||
private static bool IsEnterKey(ComputerCallAction action) =>
|
||||
action.KeyPressKeyCodes is not null &&
|
||||
(action.KeyPressKeyCodes.Contains("Return", StringComparer.OrdinalIgnoreCase) ||
|
||||
action.KeyPressKeyCodes.Contains("Enter", StringComparer.OrdinalIgnoreCase));
|
||||
}
|
||||
@@ -0,0 +1,112 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to use the Computer Use tool with AIProjectClient.AsAIAgent(...).
|
||||
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Demo.ComputerUse;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Agents.AI.Foundry;
|
||||
using Microsoft.Extensions.AI;
|
||||
using OpenAI.Responses;
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("AZURE_AI_COMPUTER_USE_DEPLOYMENT_NAME") ?? "computer-use-preview";
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient projectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
using IHostedFileClient fileClient = projectClient.GetProjectOpenAIClient().AsIHostedFileClient();
|
||||
|
||||
AIAgent agent = projectClient.AsAIAgent(
|
||||
model: deploymentName,
|
||||
name: "ComputerAgent",
|
||||
instructions: "You are a computer automation assistant.",
|
||||
tools: [FoundryAITool.CreateComputerTool(ComputerToolEnvironment.Browser, 1026, 769)]);
|
||||
|
||||
Dictionary<string, string> screenshots = [];
|
||||
|
||||
try
|
||||
{
|
||||
// Upload pre-captured screenshots that simulate browser state transitions.
|
||||
screenshots = await ComputerUseUtil.UploadScreenshotAssetsAsync(fileClient);
|
||||
|
||||
// Enable auto-truncation for the Responses API.
|
||||
ChatClientAgentRunOptions runOptions = new()
|
||||
{
|
||||
ChatOptions = new ChatOptions
|
||||
{
|
||||
RawRepresentationFactory = (_) => new CreateResponseOptions() { TruncationMode = ResponseTruncationMode.Auto },
|
||||
}
|
||||
};
|
||||
|
||||
// Send the initial request with a screenshot of the browser.
|
||||
ChatMessage message = new(ChatRole.User, [
|
||||
new TextContent("Search for 'OpenAI news'. Type it and submit. Once you see results, the task is complete."),
|
||||
new AIContent() { RawRepresentation = ResponseContentPart.CreateInputImagePart(imageFileId: screenshots["browser_search"], imageDetailLevel: ResponseImageDetailLevel.High) }
|
||||
]);
|
||||
|
||||
Console.WriteLine("Starting computer use session...");
|
||||
|
||||
AgentSession session = await agent.CreateSessionAsync();
|
||||
AgentResponse response = await agent.RunAsync(message, session: session, options: runOptions);
|
||||
|
||||
SearchState currentState = SearchState.Initial;
|
||||
|
||||
for (int i = 0; i < 10; i++)
|
||||
{
|
||||
// Find the next computer call action.
|
||||
ComputerCallResponseItem? computerCall = response.Messages
|
||||
.SelectMany(m => m.Contents)
|
||||
.Select(c => c.RawRepresentation as ComputerCallResponseItem)
|
||||
.FirstOrDefault(item => item is not null);
|
||||
|
||||
if (computerCall is null)
|
||||
{
|
||||
if (currentState == SearchState.PressedEnter)
|
||||
{
|
||||
Console.WriteLine("No more computer actions. Done.");
|
||||
Console.WriteLine(response);
|
||||
break;
|
||||
}
|
||||
|
||||
// Check if the agent is asking for confirmation to proceed, and if so, respond affirmatively.
|
||||
TextContent? textContent = response.Messages
|
||||
.Where(m => m.Role == ChatRole.Assistant)
|
||||
.SelectMany(m => m.Contents.OfType<TextContent>())
|
||||
.FirstOrDefault();
|
||||
|
||||
if (textContent?.Text is { } text && (
|
||||
text.Contains("Would you like me") ||
|
||||
text.Contains("Should I") ||
|
||||
text.Contains("proceed") ||
|
||||
text.Contains('?')))
|
||||
{
|
||||
response = await agent.RunAsync("Please proceed.", session, runOptions);
|
||||
continue;
|
||||
}
|
||||
|
||||
break;
|
||||
}
|
||||
|
||||
Console.WriteLine($"[{i + 1}] Action: {computerCall!.Action.Kind}");
|
||||
|
||||
// Simulate the action and get the resulting screenshot.
|
||||
(currentState, string fileId) = await ComputerUseUtil.GetScreenshotAsync(computerCall.Action, currentState, screenshots);
|
||||
|
||||
// Send the screenshot back as the computer call output.
|
||||
AIContent callOutput = new()
|
||||
{
|
||||
RawRepresentation = new ComputerCallOutputResponseItem(
|
||||
computerCall.CallId,
|
||||
output: ComputerCallOutput.CreateScreenshotOutput(screenshotImageFileId: fileId))
|
||||
};
|
||||
|
||||
response = await agent.RunAsync([new ChatMessage(ChatRole.User, [callOutput])], session: session, options: runOptions);
|
||||
}
|
||||
}
|
||||
finally
|
||||
{
|
||||
await ComputerUseUtil.EnsureDeleteScreenshotAssetsAsync(fileClient, screenshots);
|
||||
}
|
||||
@@ -0,0 +1,56 @@
|
||||
# Computer Use with the Responses API
|
||||
|
||||
This sample shows how to use the Computer Use tool with `AIProjectClient.AsAIAgent(...)`.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Using `FoundryAITool.CreateComputerTool()` to add computer use capabilities
|
||||
- Processing computer call actions (click, type, key press)
|
||||
- Managing the computer use interaction loop with screenshots
|
||||
|
||||
For more information, see [Use the computer tool](https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/computer-use?pivots=csharp).
|
||||
|
||||
## How the simulation works
|
||||
|
||||
In a real computer use scenario, the model controls a virtual keyboard and mouse to interact with a live browser — typing text, clicking buttons, and pressing keys. The host application captures a screenshot after each action and sends it back to the model so it can decide what to do next.
|
||||
|
||||
**This sample does not connect to a real browser.** Instead, it intercepts the model's actions and returns pre-captured screenshots as if the actions were actually performed. No real typing, clicking, or key presses happen — the sample fakes the environment so you can explore the computer use protocol without any browser automation setup.
|
||||
|
||||
### State transitions
|
||||
|
||||
The model receives a screenshot as input, analyzes it, and responds with a computer action as output. The sample maps each action to a new state and returns the corresponding screenshot:
|
||||
|
||||
| Step | Model Action | What Happens | Screenshot Sent Back to Model |
|
||||
|------|-----------------|-------------------------------------------|--------------------------------------------------------------|
|
||||
| 1 | | Session starts with the user prompt | `cua_browser_search.jpg` — empty search page |
|
||||
| 2 | Click | Model clicks the search box to focus it | `cua_browser_search.jpg` — same page |
|
||||
| 3 | Type | Model types the search query into the box | `cua_search_typed.jpg` — search text visible in the box |
|
||||
| 3a | *(text response)* | Model may ask for confirmation instead of acting | `cua_search_typed.jpg` — same page |
|
||||
| 4 | KeyPress Enter | Model presses Enter to submit the search | `cua_search_results.jpg` — search results page |
|
||||
|
||||
### Interaction loop
|
||||
|
||||
1. The user prompt and the initial screenshot (`cua_browser_search.jpg` — an empty search page) are sent to the model as input.
|
||||
2. The model analyzes the screenshot and responds with a computer action (e.g., click on the search box to focus it, then type search text, then press Enter).
|
||||
3. The sample intercepts the action, advances the state, and sends back the next pre-captured screenshot as if the action was performed on a real browser.
|
||||
4. Steps 2–3 repeat until the model stops requesting actions or the iteration limit is reached.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:AZURE_AI_COMPUTER_USE_DEPLOYMENT_NAME="computer-use-preview"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
```powershell
|
||||
dotnet run
|
||||
```
|
||||
|
||||
+19
@@ -0,0 +1,19 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<PackageReference Include="Azure.Identity" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
@@ -0,0 +1,82 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to use File Search Tool with a ChatClientAgent.
|
||||
|
||||
using Azure.AI.Projects;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Extensions.AI;
|
||||
using OpenAI.Assistants;
|
||||
using OpenAI.Files;
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
const string AgentInstructions = "You are a helpful assistant that can search through uploaded files to answer questions.";
|
||||
|
||||
// We need the AIProjectClient to upload files and create vector stores.
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
var projectOpenAIClient = aiProjectClient.GetProjectOpenAIClient();
|
||||
var filesClient = projectOpenAIClient.GetProjectFilesClient();
|
||||
var vectorStoresClient = projectOpenAIClient.GetProjectVectorStoresClient();
|
||||
|
||||
// 1. Create a temp file with test content and upload it.
|
||||
string searchFilePath = Path.Combine(Path.GetTempPath(), Path.GetRandomFileName() + "_lookup.txt");
|
||||
File.WriteAllText(
|
||||
path: searchFilePath,
|
||||
contents: """
|
||||
Employee Directory:
|
||||
- Alice Johnson, 28 years old, Software Engineer, Engineering Department
|
||||
- Bob Smith, 35 years old, Sales Manager, Sales Department
|
||||
- Carol Williams, 42 years old, HR Director, Human Resources Department
|
||||
- David Brown, 31 years old, Customer Support Lead, Support Department
|
||||
"""
|
||||
);
|
||||
|
||||
Console.WriteLine($"Uploading file: {searchFilePath}");
|
||||
OpenAIFile uploadedFile = filesClient.UploadFile(
|
||||
filePath: searchFilePath,
|
||||
purpose: FileUploadPurpose.Assistants
|
||||
);
|
||||
Console.WriteLine($"Uploaded file, file ID: {uploadedFile.Id}");
|
||||
|
||||
// 2. Create a vector store with the uploaded file.
|
||||
var vectorStoreResult = await vectorStoresClient.CreateVectorStoreAsync(
|
||||
options: new() { FileIds = { uploadedFile.Id }, Name = "EmployeeDirectory_VectorStore" }
|
||||
);
|
||||
string vectorStoreId = vectorStoreResult.Value.Id;
|
||||
Console.WriteLine($"Created vector store, vector store ID: {vectorStoreId}");
|
||||
|
||||
// Create a AIAgent with HostedFileSearchTool.
|
||||
AIAgent agent = aiProjectClient.AsAIAgent(deploymentName,
|
||||
instructions: AgentInstructions,
|
||||
name: "FileSearchAgent-RAPI",
|
||||
tools: [new HostedFileSearchTool() { Inputs = [new HostedVectorStoreContent(vectorStoreId)] }]);
|
||||
|
||||
// Run the agent
|
||||
Console.WriteLine("\n--- Running File Search Agent ---");
|
||||
AgentResponse response = await agent.RunAsync("Who is the youngest employee?");
|
||||
Console.WriteLine($"Response: {response}");
|
||||
|
||||
// Getting any file citation annotations generated by the tool
|
||||
foreach (AIAnnotation annotation in response.Messages.SelectMany(m => m.Contents).SelectMany(c => c.Annotations ?? []))
|
||||
{
|
||||
if (annotation.RawRepresentation is TextAnnotationUpdate citationAnnotation)
|
||||
{
|
||||
Console.WriteLine($$"""
|
||||
File Citation:
|
||||
File Id: {{citationAnnotation.OutputFileId}}
|
||||
Text to Replace: {{citationAnnotation.TextToReplace}}
|
||||
""");
|
||||
}
|
||||
}
|
||||
|
||||
// Cleanup file resources.
|
||||
Console.WriteLine("\n--- Cleanup ---");
|
||||
await vectorStoresClient.DeleteVectorStoreAsync(vectorStoreId);
|
||||
await filesClient.DeleteFileAsync(uploadedFile.Id);
|
||||
File.Delete(searchFilePath);
|
||||
Console.WriteLine("Cleanup completed successfully.");
|
||||
@@ -0,0 +1,30 @@
|
||||
# File Search with the Responses API
|
||||
|
||||
This sample shows how to use the File Search tool with a `ChatClientAgent` using the Responses API directly.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Uploading files and creating vector stores via `AIProjectClient`
|
||||
- Using `HostedFileSearchTool` with `ChatClientAgent`
|
||||
- Handling file citation annotations in agent responses
|
||||
- Cleaning up file resources after use
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-5.4-mini"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
```powershell
|
||||
dotnet run
|
||||
```
|
||||
|
||||
+20
@@ -0,0 +1,20 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<PackageReference Include="Azure.Identity" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI\Microsoft.Agents.AI.csproj" />
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
@@ -0,0 +1,98 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to use OpenAPI Tools with AI Agents.
|
||||
|
||||
using Azure.AI.Projects;
|
||||
using Azure.AI.Projects.Agents;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Agents.AI.Foundry;
|
||||
using Microsoft.Extensions.AI;
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
const string AgentInstructions = "You are a helpful assistant that can retrieve the latest currency exchange rates using the Frankfurter API. Always call the API to get live data rather than guessing.";
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
AITool openApiTool = FoundryAITool.CreateOpenApiTool(CreateOpenAPIFunctionDefinition());
|
||||
|
||||
AIAgent agent = aiProjectClient.AsAIAgent(deploymentName,
|
||||
instructions: AgentInstructions,
|
||||
name: "OpenAPIToolsAgent",
|
||||
tools: [openApiTool]);
|
||||
|
||||
// Run the agent with a question about EUR exchange rates
|
||||
Console.WriteLine(await agent.RunAsync("What is the latest EUR exchange rate against the US Dollar (USD) and British Pound (GBP)?"));
|
||||
|
||||
OpenApiFunctionDefinition CreateOpenAPIFunctionDefinition()
|
||||
{
|
||||
// OpenAPI spec for Frankfurter — a free, no-auth exchange rate API backed by ECB data.
|
||||
// See https://www.frankfurter.dev/ for documentation.
|
||||
const string FrankfurterOpenApiSpec = """
|
||||
{
|
||||
"openapi": "3.1.0",
|
||||
"info": {
|
||||
"title": "Frankfurter Exchange Rate API",
|
||||
"description": "Free currency exchange rates from the European Central Bank",
|
||||
"version": "v1"
|
||||
},
|
||||
"servers": [
|
||||
{
|
||||
"url": "https://api.frankfurter.dev/v1"
|
||||
}
|
||||
],
|
||||
"paths": {
|
||||
"/latest": {
|
||||
"get": {
|
||||
"description": "Get the latest exchange rates for a given base currency",
|
||||
"operationId": "GetLatestExchangeRates",
|
||||
"parameters": [
|
||||
{
|
||||
"name": "from",
|
||||
"in": "query",
|
||||
"description": "Base currency code (e.g. EUR, USD, GBP). Defaults to EUR.",
|
||||
"required": false,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "to",
|
||||
"in": "query",
|
||||
"description": "Comma-separated list of target currency codes (e.g. USD,GBP,JPY).",
|
||||
"required": false,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
],
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "Latest exchange rates",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"type": "object"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
""";
|
||||
|
||||
return new(
|
||||
"get_exchange_rates",
|
||||
BinaryData.FromString(FrankfurterOpenApiSpec),
|
||||
new OpenAPIAnonymousAuthenticationDetails())
|
||||
{
|
||||
Description = "Get live currency exchange rates from the European Central Bank via Frankfurter"
|
||||
};
|
||||
}
|
||||
@@ -0,0 +1,30 @@
|
||||
# OpenAPI Tools with the Responses API
|
||||
|
||||
This sample shows how to use OpenAPI tools with a `ChatClientAgent` using the Responses API directly.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Defining an OpenAPI specification inline
|
||||
- Creating an `OpenAPIFunctionDefinition` for the Frankfurter exchange rate API
|
||||
- Using `FoundryAITool.CreateOpenApiTool()` with `ChatClientAgent`
|
||||
- Server-side execution of OpenAPI tool calls
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-5.4-mini"
|
||||
```
|
||||
|
||||
## Run the sample
|
||||
|
||||
```powershell
|
||||
dotnet run
|
||||
```
|
||||
|
||||
+19
@@ -0,0 +1,19 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<PropertyGroup>
|
||||
<OutputType>Exe</OutputType>
|
||||
<TargetFrameworks>net10.0</TargetFrameworks>
|
||||
|
||||
<Nullable>enable</Nullable>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<PackageReference Include="Azure.Identity" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
+47
@@ -0,0 +1,47 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
// This sample shows how to use Bing Custom Search Tool with a ChatClientAgent.
|
||||
|
||||
using Azure.AI.Projects;
|
||||
using Azure.AI.Projects.Agents;
|
||||
using Azure.Identity;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Agents.AI.Foundry;
|
||||
|
||||
string connectionId = Environment.GetEnvironmentVariable("AZURE_AI_CUSTOM_SEARCH_CONNECTION_ID") ?? throw new InvalidOperationException("AZURE_AI_CUSTOM_SEARCH_CONNECTION_ID is not set.");
|
||||
string instanceName = Environment.GetEnvironmentVariable("AZURE_AI_CUSTOM_SEARCH_INSTANCE_NAME") ?? throw new InvalidOperationException("AZURE_AI_CUSTOM_SEARCH_INSTANCE_NAME is not set.");
|
||||
|
||||
const string AgentInstructions = """
|
||||
You are a helpful agent that can use Bing Custom Search tools to assist users.
|
||||
Use the available Bing Custom Search tools to answer questions and perform tasks.
|
||||
""";
|
||||
|
||||
// Bing Custom Search tool parameters
|
||||
BingCustomSearchToolOptions bingCustomSearchToolParameters = new([
|
||||
new BingCustomSearchConfiguration(connectionId, instanceName)
|
||||
]);
|
||||
|
||||
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
||||
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
|
||||
|
||||
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
||||
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
||||
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
||||
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
||||
|
||||
// Create a AIAgent with Bing Custom Search tool.
|
||||
AIAgent agent = aiProjectClient.AsAIAgent(deploymentName,
|
||||
instructions: AgentInstructions,
|
||||
name: "BingCustomSearchAgent-RAPI",
|
||||
tools: [FoundryAITool.CreateBingCustomSearchTool(bingCustomSearchToolParameters)]);
|
||||
|
||||
Console.WriteLine($"Created agent: {agent.Name}");
|
||||
|
||||
// Run the agent with a search query
|
||||
AgentResponse response = await agent.RunAsync("Search for the latest news about Microsoft AI");
|
||||
|
||||
Console.WriteLine("\n=== Agent Response ===");
|
||||
foreach (var message in response.Messages)
|
||||
{
|
||||
Console.WriteLine(message.Text);
|
||||
}
|
||||
+37
@@ -0,0 +1,37 @@
|
||||
# Bing Custom Search with the Responses API
|
||||
|
||||
This sample shows how to use the Bing Custom Search tool with a `ChatClientAgent` using the Responses API directly.
|
||||
|
||||
## What this sample demonstrates
|
||||
|
||||
- Configuring `BingCustomSearchToolParameters` with connection ID and instance name
|
||||
- Using `FoundryAITool.CreateBingCustomSearchTool()` with `ChatClientAgent`
|
||||
- Processing search results from agent responses
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- .NET 10 SDK or later
|
||||
- Microsoft Foundry service endpoint and deployment configured
|
||||
- An authenticated Azure identity (for example, sign in with `az login`)
|
||||
- Bing Custom Search resource configured with a connection ID
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
```powershell
|
||||
$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
|
||||
$env:FOUNDRY_MODEL="gpt-5.4-mini"
|
||||
$env:AZURE_AI_CUSTOM_SEARCH_CONNECTION_ID="your-connection-id" # The full ARM resource URI, e.g., "/subscriptions/.../connections/your-bing-connection"
|
||||
$env:AZURE_AI_CUSTOM_SEARCH_INSTANCE_NAME="your-instance-name" # The Bing Custom Search configuration name (from Azure portal)
|
||||
```
|
||||
|
||||
### Finding the connection ID and instance name
|
||||
|
||||
- **Connection ID** (`AZURE_AI_CUSTOM_SEARCH_CONNECTION_ID`): The full ARM resource URI including the `/projects/<name>/connections/<connection-name>` segment. Find the connection name in your Foundry project under **Management center** → **Connected resources**.
|
||||
- **Instance Name** (`AZURE_AI_CUSTOM_SEARCH_INSTANCE_NAME`): The **configuration name** from your Bing Custom Search resource (Azure portal → your Bing Custom Search resource → **Configurations**). This is _not_ the Azure resource name or the connection name — it's the name of the specific search configuration that defines which domains/sites to search against.
|
||||
|
||||
## Run the sample
|
||||
|
||||
```powershell
|
||||
dotnet run
|
||||
```
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user