AutoGen

# v0.4 (autogen-agentchat). The extra installs autogen-agentchat only.
pip install 'risicare[autogen]' 'autogen-ext[openai]'
 
# v0.2 (pyautogen), on Python 3.12 or earlier
pip install risicare 'pyautogen>=0.2,<0.3'

import risicare
from autogen import AssistantAgent, UserProxyAgent
 
risicare.init()
 
# Define agents as usual - they're automatically traced
assistant = AssistantAgent(
    name="assistant",
    llm_config={"model": "gpt-4o"}
)
 
# code_execution_config=False: no code execution. The default needs Docker.
user_proxy = UserProxyAgent(
    name="user_proxy",
    human_input_mode="NEVER",
    code_execution_config=False
)
 
# Start conversation - fully traced.
# max_turns=1: one answer. Without a limit, the two agents continue until the
# assistant answers exactly "TERMINATE", for up to 100 model calls.
user_proxy.initiate_chat(
    assistant,
    message="Write a Python function to calculate fibonacci",
    max_turns=1
)

import risicare
from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.teams import RoundRobinGroupChat
from autogen_ext.models.openai import OpenAIChatCompletionClient
 
risicare.init()
 
model_client = OpenAIChatCompletionClient(model="gpt-4o")
 
assistant = AssistantAgent(
    name="assistant",
    model_client=model_client,
)
 
# v0.4 uses an async, task-based API
team = RoundRobinGroupChat([assistant], max_turns=1)
result = await team.run(task="Write a Python function to calculate fibonacci")

from autogen import GroupChat, GroupChatManager
 
coder = AssistantAgent(name="coder", llm_config={"model": "gpt-4o"})
reviewer = AssistantAgent(name="reviewer", llm_config={"model": "gpt-4o"})
 
agents = [user_proxy, coder, reviewer]
 
groupchat = GroupChat(
    agents=agents,
    messages=[],
    max_round=10
)
 
manager = GroupChatManager(groupchat=groupchat)
 
# All agent interactions traced
user_proxy.initiate_chat(
    manager,
    message="Build a web scraper"
)

def get_weather(location: str) -> str:
    return f"Weather in {location}: Sunny"
 
assistant = AssistantAgent(
    name="assistant",
    llm_config={
        "model": "gpt-4o",
        "functions": [{
            "name": "get_weather",
            "parameters": {...}
        }]
    }
)
 
assistant.register_function(
    function_map={"get_weather": get_weather}
)

from autogen.coding import LocalCommandLineCodeExecutor
 
executor = LocalCommandLineCodeExecutor(work_dir="coding")
 
user_proxy = UserProxyAgent(
    name="user_proxy",
    code_execution_config={"executor": executor}
)
 
# Code execution is visible in the span timeline,
# but code-specific attributes (content, language,
# output, errors) are not captured.

specialist = AssistantAgent(name="specialist", llm_config={"model": "gpt-4o"})
 
assistant.register_nested_chats(
    # max_turns=1 limits the nested chat to one answer
    [{"recipient": specialist, "message": "Help with this", "max_turns": 1}],
    trigger=user_proxy  # AutoGen calls a trigger function with the sending agent, not with the message
)
 
# Nested chats traced as child spans