.NET: Add samples for OpenAIChatClientAgent and OpenAIResponseClientAgent (#2638)

* add samples for OpenAIChatClientAgent and OpenAIResponseClientAgent * Update dotnet/samples/GettingStarted/AgentWithOpenAI/README.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/samples/GettingStarted/AgentWithOpenAI/Agent_OpenAI_Step03_CreateFromChatClient/README.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/samples/GettingStarted/AgentWithOpenAI/Agent_OpenAI_Step03_CreateFromChatClient/README.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-06-16 21:04:09 +08:00 · 2025-12-05 11:03:59 +00:00
parent db36809744
commit 51721bd9f6
8 changed files with 142 additions and 2 deletions
@@ -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.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
+  </ItemGroup>
+
+</Project>
@@ -0,0 +1,31 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+// This sample demonstrates how to create OpenAIResponseClientAgent directly from an OpenAIResponseClient instance.
+
+using OpenAI;
+using OpenAI.Responses;
+
+var apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY") ?? throw new InvalidOperationException("OPENAI_API_KEY is not set.");
+var model = Environment.GetEnvironmentVariable("OPENAI_MODEL") ?? "gpt-4o-mini";
+
+// Create an OpenAIResponseClient directly from OpenAIClient
+OpenAIResponseClient responseClient = new OpenAIClient(apiKey).GetOpenAIResponseClient(model);
+
+// Create an agent directly from the OpenAIResponseClient using OpenAIResponseClientAgent
+OpenAIResponseClientAgent agent = new(responseClient, instructions: "You are good at telling jokes.", name: "Joker");
+
+ResponseItem userMessage = ResponseItem.CreateUserMessageItem("Tell me a joke about a pirate.");
+
+// Invoke the agent and output the text result.
+OpenAIResponse response = await agent.RunAsync([userMessage]);
+Console.WriteLine(response.GetOutputText());
+
+// Invoke the agent with streaming support.
+IAsyncEnumerable<StreamingResponseUpdate> responseUpdates = agent.RunStreamingAsync([userMessage]);
+await foreach (StreamingResponseUpdate responseUpdate in responseUpdates)
+{
+    if (responseUpdate is StreamingResponseOutputTextDeltaUpdate textUpdate)
+    {
+        Console.WriteLine(textUpdate.Delta);
+    }
+}
@@ -0,0 +1,22 @@
+# Creating an Agent from an OpenAIResponseClient
+
+This sample demonstrates how to create an AI agent directly from an `OpenAI.Responses.OpenAIResponseClient` instance using the `OpenAIResponseClientAgent` class.
+
+## What This Sample Shows
+
+- **Direct OpenAIResponseClient Creation**: Shows how to create an `OpenAI.Responses.OpenAIResponseClient` from `OpenAI.OpenAIClient` and then use it to instantiate an agent
+- **OpenAIResponseClientAgent**: Demonstrates using the OpenAI SDK primitives instead of the ones from Microsoft.Extensions.AI and Microsoft.Agents.AI abstractions
+- **Full Agent Capabilities**: Shows both regular and streaming invocation of the agent
+
+## Running the Sample
+
+1. Set the required environment variables:
+   ```bash
+   set OPENAI_API_KEY=your_api_key_here
+   set OPENAI_MODEL=gpt-4o-mini
+   ```
+
+2. Run the sample:
+   ```bash
+   dotnet run
+   ```