Strumenti personalizzati per gli agenti

Sviluppare applicazioni LLM con LangChain

Jonathan Bennion

AI Engineer & LangChain Contributor

Formati degli strumenti

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)

Utile quando devi rispondere a domande di matematica.

Usato da LLM/agent come contesto per sapere quando chiamarlo

Formati degli strumenti

print(tools[0].return_direct)

False

Definire una funzione personalizzata

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

Chiamare la funzione

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

Financial Report for LemonadeStand:
Revenue: $100
Expenses: $50
Net Income: $50

Da funzioni a strumenti

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

Esaminare il nuovo strumento

print(financial_report.name)

print(financial_report.description)

print(financial_report.return_direct)

print(financial_report.args)

financial_report

Genera un report finanziario per un'azienda che calcola l'utile netto.

False

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

Integrare lo strumento personalizzato

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)

Integrare lo strumento personalizzato

{'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...', ...)
]}

Output dello strumento

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

Ecco il report finanziario per TechStack:
- Ricavi: $10,000,000
- Costi: $8,000,000
- Utile netto: $2,000,000

Financial Report for TechStack:
Revenue: $10000000
Expenses: $8000000
Net Income: $2000000

Passiamo alla pratica !

Sviluppare applicazioni LLM con LangChain