Aangepaste tools voor agents

LLM-toepassingen ontwikkelen met LangChain

Jonathan Bennion

AI Engineer & LangChain Contributor

Toolformaten

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)

Handig wanneer je wiskundevragen moet beantwoorden.

Gebruikt door LLM/agent als context om te bepalen wanneer het te gebruiken

Toolformaten

print(tools[0].return_direct)

False

Een aangepaste functie definiëren

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

De functie aanroepen

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

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

Van functies naar tools

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

Onze nieuwe tool bekijken

print(financial_report.name)

print(financial_report.description)

print(financial_report.return_direct)

print(financial_report.args)

financial_report

Genereer een financieel rapport voor een bedrijf dat de nettowinst berekent.

False

{'company_name': {'title': 'Bedrijfsnaam', 'type': 'string'},
 'revenue': {'title': 'Omzet', 'type': 'integer'},
 'expenses': {'title': 'Kosten', 'type': 'integer'}}

De aangepaste tool integreren

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)

De aangepaste tool integreren

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

Tool-uitvoer

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

Here is the financial report for TechStack:
- Revenue: $10,000,000
- Expenses: $8,000,000
- Net Income: $2,000,000

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

Laten we oefenen!

LLM-toepassingen ontwikkelen met LangChain