AutoGen

import asyncio
import os

from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.conditions import TextMentionTermination
from autogen_agentchat.teams import RoundRobinGroupChat
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient


async def main() -> None:
    model_client = OpenAIChatCompletionClient(
        model="Meta-Llama-3.3-70B-Instruct",
        base_url="https://api.sambanova.ai/v1",
        api_key=os.environ["SAMBANOVA_API_KEY"],
        model_info={
            "vision": False,
            "function_calling": True,
            "json_output": False,
            "structured_output": False,
            "family": "unknown",
        },
    )

    writer = AssistantAgent(
        "writer",
        model_client=model_client,
        description="Drafts short technical explanations.",
        system_message="You draft short technical explanations. Keep them under 120 words.",
    )

    reviewer = AssistantAgent(
        "reviewer",
        model_client=model_client,
        description="Reviews drafts for accuracy and clarity.",
        system_message=(
            "You review the draft for accuracy and clarity. "
            "If it is correct and clear, reply with APPROVED. "
            "Otherwise, list the specific fixes needed."
        ),
    )

    team = RoundRobinGroupChat(
        [writer, reviewer],
        termination_condition=TextMentionTermination("APPROVED"),
        max_turns=4,
    )

    await Console(team.run_stream(task="Explain what a mixture-of-experts model is."))
    await model_client.close()


asyncio.run(main())

# Expected output
---------- TextMessage (user) ----------
Explain what a mixture-of-experts model is.
---------- TextMessage (writer) ----------
A mixture-of-experts model routes each token to a small subset of specialist
subnetworks, so only a fraction of parameters activate per token. That keeps
compute per token low while total capacity stays high.
---------- TextMessage (reviewer) ----------
APPROVED