Alat kustom untuk agen

Mengembangkan Aplikasi LLM dengan LangChain

Jonathan Bennion

AI Engineer & LangChain Contributor

Format alat

from langchain_community.agent_toolkits.load_tools import load_tools

tools = load_tools(["llm-math"], llm=llm)

print(tools[0].name)

Calculator

print(tools[0].description)

Berguna saat Anda perlu menjawab pertanyaan matematika.

Dipakai oleh LLM/agen sebagai konteks untuk memutuskan kapan memanggilnya

Format alat

print(tools[0].return_direct)

False

Mendefinisikan fungsi kustom

def financial_report(company_name: str, revenue: int, expenses: int) -> str:
    """Generate a financial report for a company that calculates net income."""
    net_income = revenue - expenses

    report = f"Financial Report for {company_name}:\n"
    report += f"Revenue: ${revenue}\n"
    report += f"Expenses: ${expenses}\n"
    report += f"Net Income: ${net_income}\n"
    return report

Memanggil fungsi

print(financial_report(company_name="LemonadeStand", revenue=100, expenses=50))

Laporan Keuangan untuk LemonadeStand:
Pendapatan: $100
Biaya: $50
Laba Bersih: $50

Dari fungsi ke alat

from langchain_core.tools import tool


@tool

def financial_report(company_name: str, revenue: int, expenses: int) -> str:
    """Generate a financial report for a company that calculates net income."""
    net_income = revenue - expenses

    report = f"Financial Report for {company_name}:\n"
    report += f"Revenue: ${revenue}\n"
    report += f"Expenses: ${expenses}\n"
    report += f"Net Income: ${net_income}\n"
    return report

Menelaah alat baru kita

print(financial_report.name)

print(financial_report.description)

print(financial_report.return_direct)

print(financial_report.args)

financial_report

Hasilkan laporan keuangan untuk perusahaan yang menghitung laba bersih.

False

{'company_name': {'title': 'Company Name', 'type': 'string'},
 'revenue': {'title': 'Revenue', 'type': 'integer'},
 'expenses': {'title': 'Expenses', 'type': 'integer'}}

Mengintegrasikan alat kustom

from langgraph.prebuilt import create_react_agent

llm = ChatOpenAI(model="gpt-4o-mini", api_key=openai_api_key, temperature=0)
agent = create_react_agent(llm, [financial_report])


messages = agent.invoke({"messages": [("human", "TechStack generated made $10 million
with $8 million of costs. Generate a financial report.")]})
print(messages)

Mengintegrasikan alat kustom

{'messages': [
    HumanMessage(content='TechStack generated made $10 million dollars with $8 million of...', ...),
    AIMessage(content='', ..., tool_calls=[{'name': 'financial_report',
                                            'args': {'company_name': 'TechStack',
                                                     'revenue': 10000000, 'expenses': 8000000}, ...),
    ToolMessage(content='Financial Report for TechStack:\nRevenue: $10000000\nExpenses...', ...),
    AIMessage(content='Here is the financial report for TechStack...', ...)
]}

Keluaran alat

print(messages['messages'][-1].content)

Berikut laporan keuangan untuk TechStack:
- Pendapatan: $10.000.000
- Biaya: $8.000.000
- Laba Bersih: $2.000.000

Laporan Keuangan untuk TechStack:
Pendapatan: $10000000
Biaya: $8000000
Laba Bersih: $2000000

Ayo berlatih!

Mengembangkan Aplikasi LLM dengan LangChain