Document loaders are designed to load document objects. LangChain has hundreds of integrations with various data sources to load data from: Slack, Notion, Google Drive, etc.

Integrations​

You can find available integrations on theDocument loaders integrations page.

Interface​

Documents loaders implement theBaseLoader interface.

Each DocumentLoader has its own specific parameters, but they can all be invoked in the same way with the.load method or.lazy_load.

Here's a simple example:

from langchain_community.document_loaders.csv_loaderimport CSVLoader

loader= CSVLoader(
...# <-- Integration specific parameters here
)
data= loader.load()

When working with large datasets, you can use the.lazy_load method:

for documentin loader.lazy_load():
print(document)

Related resources​

Please see the following resources for more information:

• How-to guides for document loaders
• Document API reference
• Document loaders integrations