AssistantAgent

AssistantAgent is a built-in agent in AutoGen that acts as an AI assistant. It uses LLM to generate response to user input. It also supports function call if the underlying LLM model supports it (e.g. gpt-3.5-turbo-0613).

Create an AssistantAgent using OpenAI model.

// get OpenAI Key and create config
var openAIKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY") ?? throw new Exception("Please set OPENAI_API_KEY environment variable.");
var llmConfig = new OpenAIConfig(openAIKey, "gpt-3.5-turbo");

// create assistant agent
var assistantAgent = new AssistantAgent(
    name: "assistant",
    systemMessage: "You are an assistant that help user to do some tasks.",
    llmConfig: new ConversableAgentConfig
    {
        Temperature = 0,
        ConfigList = new[] { llmConfig },
    });

Create an AssistantAgent using Azure OpenAI model.

// get OpenAI Key and create config
var apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY");
var model = "gpt-4o-mini";

var openAIClient = new OpenAIClient(apiKey);

// create assistant agent
var assistantAgent = new OpenAIChatAgent(
    name: "assistant",
    systemMessage: "You are an assistant that help user to do some tasks.",
    chatClient: openAIClient.GetChatClient(model))
    .RegisterMessageConnector()
    .RegisterPrintMessage();