langchain/docs/modules/indexes/document_loaders/examples/word_document.ipynb

Word Documents

This covers how to load Word documents into a document format that we can use downstream.

In [1]:

from langchain.document_loaders import UnstructuredWordDocumentLoader

In [2]:

loader = UnstructuredWordDocumentLoader("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': '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 [5]:

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

In [6]:

data = loader.load()

In [7]:

data[0]

Out [7]:

Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 'fake.docx', 'filename': 'fake.docx', 'category': 'Title'}, lookup_index=0)