.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>
This commit is contained in:
SergeyMenshykh
2025-12-05 03:03:59 -08:00
committed by GitHub
Unverified
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 an AI agent directly from an OpenAI.Chat.ChatClient instance using OpenAIChatClientAgent.
using OpenAI;
using OpenAI.Chat;
string apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY") ?? throw new InvalidOperationException("OPENAI_API_KEY is not set.");
string model = Environment.GetEnvironmentVariable("OPENAI_MODEL") ?? "gpt-4o-mini";
// Create a ChatClient directly from OpenAIClient
ChatClient chatClient = new OpenAIClient(apiKey).GetChatClient(model);
// Create an agent directly from the ChatClient using OpenAIChatClientAgent
OpenAIChatClientAgent agent = new(chatClient, instructions: "You are good at telling jokes.", name: "Joker");
UserChatMessage chatMessage = new("Tell me a joke about a pirate.");
// Invoke the agent and output the text result.
ChatCompletion chatCompletion = await agent.RunAsync([chatMessage]);
Console.WriteLine(chatCompletion.Content.Last().Text);
// Invoke the agent with streaming support.
IAsyncEnumerable<StreamingChatCompletionUpdate> completionUpdates = agent.RunStreamingAsync([chatMessage]);
await foreach (StreamingChatCompletionUpdate completionUpdate in completionUpdates)
{
if (completionUpdate.ContentUpdate.Count > 0)
{
Console.WriteLine(completionUpdate.ContentUpdate[0].Text);
}
}
@@ -0,0 +1,22 @@
# Creating an Agent from a ChatClient
This sample demonstrates how to create an AI agent directly from an `OpenAI.Chat.ChatClient` instance using the `OpenAIChatClientAgent` class.
## What This Sample Shows
- **Direct ChatClient Creation**: Shows how to create an `OpenAI.Chat.ChatClient` from `OpenAI.OpenAIClient` and then use it to instantiate an agent
- **OpenAIChatClientAgent**: 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
```