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

Microsoft Word

This notebook shows how to load text from Microsoft word documents.

In [1]:

from langchain.document_loaders import UnstructuredDocxLoader

In [2]:

loader = UnstructuredDocxLoader('example_data/fake.docx')

In [3]:

data = loader.load()

In [4]:

data

Out [4]:

[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 'example_data/fake.docx'}, lookup_index=0)]

Retain Elements

Under the hood, Unstructured creates different "elements" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying mode="elements".

In [2]:

loader = UnstructuredDocxLoader('example_data/fake.docx', mode="elements")

In [3]:

data = loader.load()

In [4]:

data

Out [4]:

[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 'example_data/fake.docx'}, lookup_index=0)]

In [ ]: