How do I look up Swedish company data in a LangChain agent?

Steps

1. Install langchain-strale and a chat-model package.
2. Create the toolkit with your Strale API key.
3. Bind swedish-company-data to your model.
4. Ask about an organisation number and 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 == "swedish-company-data"]

llm = ChatOpenAI(model="gpt-4o").bind_tools(tools)
result = llm.invoke("Look up Swedish company 556703-7485")

# 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

Given an organisationsnummer, the tool returns the company name, legal form, status, registration and deregistration dates, SNI industry codes, the VAT number, the registered address and a business description, and any ongoing insolvency or restructuring procedures.

It does not return revenue, employee numbers or board members, and it takes the organisation number only, not a company name.

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

Company records for Sweden: inputs, output fields, source and last test.