How do I validate an IBAN in a LangChain Python agent?

Steps

1. Install langchain-strale and a chat-model package.
2. Create the toolkit with your Strale API key.
3. Keep the iban-validate tool and bind it to your model.
4. Ask about an IBAN, then run the tool call the model returns.

The solution

# pip install langchain-strale langchain-openai
from langchain_strale import StraleToolkit
from langchain_openai import ChatOpenAI

toolkit = StraleToolkit(api_key="sk_live_YOUR_KEY")
tools = [t for t in toolkit.get_tools() if t.name == "iban-validate"]

llm = ChatOpenAI(model="gpt-4o").bind_tools(tools)
result = llm.invoke("Validate this IBAN: DE89370400440532013000")

# The model picks the tool and its arguments; your code runs the call.
for call in result.tool_calls:
    tool = next(t for t in tools if t.name == call["name"])
    print(tool.invoke(call["args"]))

How it works

The tool checks an IBAN's structure, country code and check digits. Where it holds the bank's registry entry it also returns the bank code and branch code. It does not confirm that the account exists or is open.

The toolkit turns each Strale tool into a LangChain tool named after its slug. The model picks iban-validate and fills in the iban argument. tool.invoke(call["args"]) runs the call and returns a dictionary with valid, country_code and bank_code.

The check is algorithmic, so the same IBAN always gives the same answer.

bind_tools only lets the model propose a call. To have the model read the result and answer in words, put the same tools in one of LangChain's agent loops.

Tools in this guide