AI Agentic Design Patterns with AutoGen（上）：顺序对话、代理反思

• 课程主页《AI Agentic Design Patterns with AutoGen》、bilibili中文视频
• microsoft/autogen、autogen文档

一、多代理对话：单口喜剧

1.1 Agent的基本功能

  在AutoGen中，Agent是一个可以代表人类意图执行操作的实体，发送消息，接收消息，执行操作，生成回复，并与其他代理交互。AutoGen具有一个名为Conversible Agent的内置代理类，它将不同类型的代理统一在同一个编程抽象中。

  Conversible Agent带有许多内置功能，如使用大型语言模型配置生成回复、执行代码或函数、保持人工干预并检查停止响应等。你可以打开或关闭每个组件，并根据应用程序的需求进行定制，通过这些不同的功能，你可以使用相同的接口创建具有不同角色的代理。

  下面先演示agent的基本功能，以下代码，可以直接在《AI Agentic Design Patterns with AutoGen》中成功运行。

1. 导入OpenAI API密钥，配置LLM
   使用getOpenAI API key函数从环境中导入OpenAI API密钥，并定义一个LLM配置。在本课程中，我们将使用GPT-3.5 Turbo作为模型。

from utils import get_openai_api_key
OPENAI_API_KEY = get_openai_api_key()
llm_config = {
   "model": "gpt-3.5-turbo"}

2. 定义一个AutoGen agent
   我们使用ConversibleAgent类定义一个名为chatbot的代理。将前面定义的LLM配置传递给这个ConversibleAgent，使其能够使用大型语言模型生成回复。

from autogen import ConversableAgent

agent = ConversableAgent(
    name="chatbot",
    llm_config=llm_config,
    human_input_mode="NEVER",
)

  human_input_mode（人类输入模式）设置为“NEVER”，这意味着agent将不会寻求人工输入，而是只使用大型语言模型生成回复。你也可以设置为“ALWAYS”，那么代理在生成回复之前总是会询问人工输入。这是该代理的基本设置，你还可以添加代码执行配置、函数执行和其他设置。

3. 使用generate_reply方法生成回复
   调用agent的generateReply函数，并给它一个消息列表，例如“tell me a joke”，角色为用户。运行后，agent将回复一个笑话。

reply = agent.generate_reply(
    messages=[{
   "content": "Tell me a joke.", "role": "user"}]
)
print(reply)

Sure! Here's a joke for you: Why did the math book look sad? Because it had too many problems.

  如果再次调用generate_reply函数，并将内容更改为“repeat the joke”，代理不会重复笑话，因为每次调用generateReply函数时，它都会生成一个新的回复，而不会记住之前的回复。

reply = agent.generate_reply(
    messages=[{
   "content": "Repeat the joke.", "role": "user"}]
)
print(reply)

Of course! Please provide me with the joke you would like me to repeat.

1.2 多代理对话示例：单口喜剧

  接下来，我们创建一个多代理对话示例。我们将创建两个ConversibleAgent，模拟两个单口喜剧演员之间的对话。

1.2.1 创建Agent

创建两个agent，分别命名为Cassie和Joe，并给它们一个系统消息，让代理知道它们的名字并且它是一个单口喜剧演员。后者增加一个指示：“从上一个笑话的笑点开始下一个笑话”。

cathy = ConversableAgent(
    name="cathy",
    system_message=
    "Your name is Cathy and you are a stand-up comedian.",
    llm_config=llm_config,
    human_input_mode="NEVER",
)

joe = ConversableAgent(
    name="joe",
    system_message=
    "Your name is Joe and you are a stand-up comedian. "
    "Start the next joke from the punchline of the previous joke.",
    llm_config=llm_config,
    human_input_mode="NEVER",
)

1.2.2 开始对话

  调用agent的initiate_chat函数初始化对话信息。例如，让Joe开始对话，设置接收人为Cassie，并设置初始消息和对话的最大轮数。

chat_result = joe.initiate_chat(
    recipient=cathy, 
    message="I'm Joe. Cathy, let's keep the jokes rolling.",
    max_turns=2,
)

joe (to cathy):

I'm Joe. Cathy, let's keep the jokes rolling.

--------------------------------------------------------------------------------
cathy (to joe):

Sure thing, Joe! So, did you know that I tried to write a joke about the wind, but it just ended up being too drafty? It was full of holes!

--------------------------------------------------------------------------------
joe (to cathy):

Well, Cathy, that joke might have been breezy, but I like to think of it as a breath of fresh air!

--------------------------------------------------------------------------------
cathy (to joe):

I'm glad you found it refreshing, Joe! But let me ask you this - why did the math book look sad? Because it had too many problems!

--------------------------------------------------------------------------------

1.2.3 查看对话信息，自定义对话摘要

  我们还可以检查对话历史和消耗的token数，比如使用pprint库打印对话历史，并检查tokens使用情况和总成本。

import pprint

pprint.pprint(chat_result.chat_history)

[{
   'content': "I'm Joe. Cathy, let's keep the jokes rolling.",
  'role': 'assistant'},
 {
   'content': 'Sure thing, Joe! So, did you know that I tried to write a joke '
             'about the wind, but it just ended up being too drafty? It was '
             'full of holes!',
  'role': 'user'},
 {
   'content': 'Well, Cathy, that joke might have been breezy, but I like to '
             'think of it as a breath of fresh air!',
  'role': 'assistant'},
 {
   'content': "I'm glad you found it refreshing, Joe! But let me ask you this - "
             'why did the math book look sad? Because it had too many '
             'problems!',
  'role': 'user'}]