Modern Treasury simplifies complex payment operations. It is a unified platform to power products and processes that move money.

• Connect to banks and payment systems
• Track transactions and balances in real-time
• Automate payment operations for scale

This notebook covers how to load data from theModern Treasury REST API into a format that can be ingested into LangChain, along with example usage for vectorization.

from langchain.indexesimport VectorstoreIndexCreator
from langchain_community.document_loadersimport ModernTreasuryLoader

The Modern Treasury API requires an organization ID and API key, which can be found in the Modern Treasury dashboard within developer settings.

This document loader also requires aresource option which defines what data you want to load.

Following resources are available:

payment_ordersDocumentation

expected_paymentsDocumentation

returnsDocumentation

incoming_payment_detailsDocumentation

counterpartiesDocumentation

internal_accountsDocumentation

external_accountsDocumentation

transactionsDocumentation

ledgersDocumentation

ledger_accountsDocumentation

ledger_transactionsDocumentation

eventsDocumentation

invoicesDocumentation

modern_treasury_loader= ModernTreasuryLoader("payment_orders")

# Create a vectorstore retriever from the loader
# see https://python.langchain.com/en/latest/modules/data_connection/getting_started.html for more details

index= VectorstoreIndexCreator().from_loaders([modern_treasury_loader])
modern_treasury_doc_retriever= index.vectorstore.as_retriever()

Related​

• Document loaderconceptual guide
• Document loaderhow-to guides