The `@tool` decorator turns a Python function into a tool an agent can invoke. Place it directly before the function. Give the function a clear name and annotate its parameters and return value: the agent uses this information to understand the tool and call it with appropriately typed inputs. section 10.5.1
Convert game-sale amounts
A data-analysis agent working with video-game sales in US dollars can use a `convert_currency` function to return an amount in a target currency. Its `USD_amount: float` and `currency: str` parameters make the expected inputs explicit; its result can be a converted amount or an error message. section 10.5.1
Listing 10.3 Data-analysis agent with currency-converter tool
import argparse
from langchain.agents.load_tools import load_tools
from langchain.tools import tool
from langchain_community.utilities.sql_database import SQLDatabase
from langchain_community.agent_toolkits.sql.base import create_sql_agent
from langchain_openai import ChatOpenAI
from typing import Union
@tool #1
#2
def convert_currency(USD_amount: float, currency: str)->Union[float, str]:
#3
""" Converts an amount in US dollars to another currency.
Args:
USD_amount: amount in US dollars.
currency: name of target currency (e.g., "Yen").
Returns:
input amount in target currency.
"""
conversion_factors = {
'Euro':0.93, 'Yen':151.28, 'Yun':0.14,
'Pound':1.26, 'Won':0.00074, 'Rupee':0.012}
if currency not in conversion_factors:
#4
error_message = (
f'Unknown currency: {currency}!'
f'Use one of {conversion_factors.keys()}')
return error_message
#5
conversion_factor = conversion_factors[currency]
converted_amount = USD_amount * conversion_factor
return converted_amount
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('serpaikey', type=str, help='SERP API access key')
parser.add_argument('dbpath', type=str, help='Path to SQLite database')
parser.add_argument('question', type=str, help='A question to answer')
args = parser.parse_args()
llm = ChatOpenAI(
temperature=0, model='gpt-4o')
db = SQLDatabase.from_uri(f'sqlite:///{args.dbpath}')
extra_tools = load_tools(
['serpapi'], serpapi_api_key=args.serpaikey, llm=llm)
#6
extra_tools.append(convert_currency)
agent = create_sql_agent(
llm=llm, db=db, verbose=True,
agent_type='openai-tools',
extra_tools=extra_tools)
agent.invoke({'input':args.question})
See the currency-converter implementation and how the decorated function is added to a data-analysis agent. section 10.5.1
