CrewAI

import weave
from crewai import Agent, Task, Crew, LLM, Process

# プロジェクト名を指定して Weave を初期化します
weave.init(project_name="crewai_demo")

# 出力を決定論的にするため、temperature を 0 に設定して LLM を作成します
llm = LLM(model="gpt-4o-mini", temperature=0)

# エージェントを作成します
researcher = Agent(
    role='Research Analyst',
    goal='Find and analyze the best investment opportunities',
    backstory='Expert in financial analysis and market research',
    llm=llm,
    verbose=True,
    allow_delegation=False,
)

writer = Agent(
    role='Report Writer',
    goal='Write clear and concise investment reports',
    backstory='Experienced in creating detailed financial reports',
    llm=llm,
    verbose=True,
    allow_delegation=False,
)

# タスクを作成します
research_task = Task(
    description='Deep research on the {topic}',
    expected_output='Comprehensive market data including key players, market size, and growth trends.',
    agent=researcher
)

writing_task = Task(
    description='Write a detailed report based on the research',
    expected_output='The report should be easy to read and understand. Use bullet points where applicable.',
    agent=writer
)

# crew を作成します
crew = Crew(
    agents=[researcher, writer],
    tasks=[research_task, writing_task],
    verbose=True,
    process=Process.sequential,
)

# crew を実行します
result = crew.kickoff(inputs={"topic": "AI in material science"})
print(result)

# .... 既存のインポート ....
from crewai_tools import SerperDevTool

# エージェントにツールを渡します。
researcher = Agent(
    role='Research Analyst',
    goal='Find and analyze the best investment opportunities',
    backstory='Expert in financial analysis and market research',
    llm=llm,
    verbose=True,
    allow_delegation=False,
    tools=[SerperDevTool()],
)

# .... 既存のコード ....

import weave
# プロジェクト名を指定して Weave を初期化します
weave.init("crewai_demo")

from crewai.flow.flow import Flow, listen, router, start
from litellm import completion


class CustomerFeedbackFlow(Flow):
    model = "gpt-4o-mini"

    @start()
    def fetch_feedback(self):
        print("Fetching customer feedback")
        # 実際の運用では、ここを API 呼び出しに置き換えることができます。
        # この例では、顧客フィードバックを模擬的に生成します。
        feedback = (
            "I had a terrible experience with the product. "
            "It broke after one use and customer service was unhelpful."
        )
        self.state["feedback"] = feedback
        return feedback

    @router(fetch_feedback)
    def analyze_feedback(self, feedback):
        # 言語モデルを使用して感情分析を行います
        prompt = (
            f"Analyze the sentiment of this customer feedback and "
            "return only 'positive' or 'negative':\n\n"
            f"Feedback: {feedback}"
        )
        response = completion(
            model=self.model,
            messages=[{"role": "user", "content": prompt}],
        )
        sentiment = response["choices"][0]["message"]["content"].strip().lower()
        # 応答があいまいな場合は、negative として扱います
        if sentiment not in ["positive", "negative"]:
            sentiment = "negative"
        return sentiment

    @listen("positive")
    def handle_positive_feedback(self):
        # 肯定的なフィードバックに対するお礼のメッセージを生成します
        prompt = "Generate a thank you message for a customer who provided positive feedback."
        response = completion(
            model=self.model,
            messages=[{"role": "user", "content": prompt}],
        )
        thank_you_message = response["choices"][0]["message"]["content"].strip()
        self.state["response"] = thank_you_message
        return thank_you_message

    @listen("negative")
    def handle_negative_feedback(self):
        # 否定的なフィードバックに対して、サービス改善を約束するお詫びのメッセージを生成します
        prompt = (
            "Generate an apology message to a customer who provided negative feedback and offer assistance or a solution."
        )
        response = completion(
            model=self.model,
            messages=[{"role": "user", "content": prompt}],
        )
        apology_message = response["choices"][0]["message"]["content"].strip()
        self.state["response"] = apology_message
        return apology_message

# Flow をインスタンス化して実行を開始します
flow = CustomerFeedbackFlow()
result = flow.kickoff()
print(result)

# .... 既存のインポートと weave の初期化 ....

# guardrail 関数を `@weave.op()` でデコレートします
@weave.op(name="guardrail-validate_blog_content")
def validate_blog_content(result: TaskOutput) -> Tuple[bool, Any]:
    # 結果を生の string として取得します
    result = result.raw

    """Validate blog content meets requirements."""
    try:
        # 単語数を確認します
        word_count = len(result.split())

        if word_count > 200:
            return (False, {
                "error": "Blog content exceeds 200 words",
                "code": "WORD_COUNT_ERROR",
                "context": {"word_count": word_count}
            })

        # 追加の検証ロジックはここに記述します
        return (True, result.strip())
    except Exception as e:
        return (False, {
            "error": "Unexpected error during validation",
            "code": "SYSTEM_ERROR"
        })


# .... 既存のエージェントとリサーチアナリストのタスク ....

writing_task = Task(
    description='Write a detailed report based on the research under 200 words',
    expected_output='The report should be easy to read and understand. Use bullet points where applicable.',
    agent=writer,
    guardrail=validate_blog_content,
)

# .... crew を実行する既存のコード ....