퀵스타트: 맞춤형 에이전트 관측성 설정

from openai import OpenAI

openai_client = OpenAI()
MODEL = "gpt-4o-mini"

def run_turn(history, user_message):
    history.append({"role": "user", "content": user_message})

    with weave.start_turn(user_message=user_message, model=MODEL):
        # LLM Call 1: 모델이 도구를 사용하기로 결정할 수 있습니다.
        with weave.start_llm(model=MODEL, provider_name="openai") as llm:
            resp = openai_client.chat.completions.create(
                model=MODEL, messages=history, tools=[wikipedia_tool_schema],
            )
            msg = resp.choices[0].message
            llm.output(msg.content or "")
            llm.usage = weave.Usage(
                input_tokens=resp.usage.prompt_tokens,
                output_tokens=resp.usage.completion_tokens,
            )
            history.append(msg.model_dump(exclude_none=True))

        # 도구가 요청되지 않은 경우, 첫 번째 LLM 응답이 최종 답변입니다.
        if not msg.tool_calls:
            return msg.content

        # 요청된 각 도구 Call을 실행합니다.
        for tc in msg.tool_calls:
            with weave.start_tool(
                name=tc.function.name,
                arguments=tc.function.arguments,
                tool_call_id=tc.id,
            ) as tool:
                tool.result = wikipedia_search(**json.loads(tc.function.arguments))
                history.append({
                    "role": "tool",
                    "tool_call_id": tc.id,
                    "content": tool.result,
                })

        # LLM Call 2: 최종 답변을 종합합니다.
        with weave.start_llm(model=MODEL, provider_name="openai") as llm:
            resp = openai_client.chat.completions.create(model=MODEL, messages=history)
            msg = resp.choices[0].message
            llm.output(msg.content)
            llm.usage = weave.Usage(
                input_tokens=resp.usage.prompt_tokens,
                output_tokens=resp.usage.completion_tokens,
            )
            history.append({"role": "assistant", "content": msg.content})
            return msg.content

with weave.start_session(agent_name="research-bot") as session:
    history = []
    for question in [
        "Who founded Anthropic?",
        "What is Claude (the AI assistant)?",
        "Summarize what we discussed in one sentence.",
    ]:
        print(f"USER: {question}")
        print(f"AGENT: {run_turn(history, question)}\n")