Skip to main content


Stripe is an Irish-American financial services and software as a service (SaaS) company. It offers payment-processing software and application programming interfaces for e-commerce websites and mobile applications.

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

from langchain.document_loaders import StripeLoader
from langchain.indexes import VectorstoreIndexCreator

The Stripe API requires an access token, which can be found inside of the Stripe dashboard.

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

Following resources are available:

balance_transations Documentation

charges Documentation

customers Documentation

events Documentation

refunds Documentation

disputes Documentation

stripe_loader = StripeLoader("charges")
# Create a vectorstore retriever from the loader
# see for more details

index = VectorstoreIndexCreator().from_loaders([stripe_loader])
stripe_doc_retriever = index.vectorstore.as_retriever()