langchain/docs/modules/document_loaders/examples/directory_loader.ipynb

Directory Loader

This covers how to use the DirectoryLoader to load all documents in a directory. Under the hood, by default this uses the UnstructuredLoader

In [1]:

from langchain.document_loaders import DirectoryLoader

We can use the glob parameter to control which files to load. Note that here it doesn't load the .rst file or the .ipynb files.

In [2]:

loader = DirectoryLoader('../', glob="**/*.md")

In [3]:

docs = loader.load()

In [4]:

len(docs)

Out [4]:

1

Change loader class

By default this uses the UnstructuredLoader class. However, you can change up the type of loader pretty easily.

In [5]:

from langchain.document_loaders import TextLoader

In [6]:

loader = DirectoryLoader('../', glob="**/*.md", loader_cls=TextLoader)

In [7]:

docs = loader.load()

In [8]:

len(docs)

Out [8]:

1

In [ ]: