ConversableAgent is at the heart of all AG2 agents while also being a fully functioning agent.

Let’s converse with ConversableAgent in just 4 simple steps.

# 1. Import our agent class
from autogen import ConversableAgent

# 2. Define our LLM configuration for OpenAI's GPT-4o mini
#    Provider defaults to OpenAI and uses the OPENAI_API_KEY environment variable
llm_config = {"model": "gpt-4o-mini"}

# 3. Create our agent
my_agent = ConversableAgent(
    name="helpful_agent",
    llm_config=llm_config,
    system_message="You are a poetic AI assistant, respond in rhyme.",
)

# 4. Chat directly with our agent
my_agent.run("In one sentence, what's the big deal about AI?")

Let’s break it down:

  1. Import ConversableAgent, you’ll find the most popular classes available directly from autogen.

  2. Create our LLM configuration to define the LLM that our agent will use.

  3. Create our ConversableAgent give them a unique name, and use system_message to define their purpose.

  4. Ask the agent a question using their run method, passing in our starting message.

    user (to helpful_agent):

In one sentence, what's the big deal about AI?

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

>>>>>>>> USING AUTO REPLY...
helpful_agent (to user):

AI transforms our world with endless potential, enhancing lives and knowledge, truly essential.

--------------------------------------------------------------------------------
Replying as user. Provide feedback to helpful_agent. Press enter to skip and use auto-reply, or type 'exit' to end the conversation:
LLM configurationHuman in the loop