Microsoft Word is a word processor developed by Microsoft.

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

Using Docx2txt​

Load .docx usingDocx2txt into a document.

%pip install--upgrade--quiet  docx2txt

from langchain_community.document_loadersimport Docx2txtLoader

loader= Docx2txtLoader("./example_data/fake.docx")

data= loader.load()

data

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

Using Unstructured​

Please seethis guide for more instructions on setting up Unstructured locally, including setting up required system dependencies.

from langchain_community.document_loadersimport UnstructuredWordDocumentLoader

loader= UnstructuredWordDocumentLoader("example_data/fake.docx")

data= loader.load()

data

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

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 specifyingmode="elements".

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

data= loader.load()

data[0]

Document(page_content='Lorem ipsum dolor sit amet.', metadata={'source': './example_data/fake.docx', 'category_depth': 0, 'file_directory': './example_data', 'filename': 'fake.docx', 'last_modified': '2023-12-19T13:42:18', 'languages': ['por', 'cat'], 'filetype': 'application/vnd.openxmlformats-officedocument.wordprocessingml.document', 'category': 'Title'})

Using Azure AI Document Intelligence​

Azure AI Document Intelligence (formerly known asAzure Form Recognizer) is machine-learningbased service that extracts texts (including handwriting), tables, document structures (e.g., titles, section headings, etc.) and key-value-pairs fromdigital or scanned PDFs, images, Office and HTML files.

Document Intelligence supportsPDF,JPEG/JPG,PNG,BMP,TIFF,HEIF,DOCX,XLSX,PPTX andHTML.

This current implementation of a loader usingDocument Intelligence can incorporate content page-wise and turn it into LangChain documents. The default output format is markdown, which can be easily chained withMarkdownHeaderTextSplitter for semantic document chunking. You can also usemode="single" ormode="page" to return pure texts in a single page or document split by page.

Prerequisite​

An Azure AI Document Intelligence resource in one of the 3 preview regions:East US,West US2,West Europe - followthis document to create one if you don't have. You will be passing<endpoint> and<key> as parameters to the loader.

%pip install --upgrade --quiet langchain langchain-community azure-ai-documentintelligence

from langchain_community.document_loadersimport AzureAIDocumentIntelligenceLoader

file_path="<filepath>"
endpoint="<endpoint>"
key="<key>"
loader= AzureAIDocumentIntelligenceLoader(
    api_endpoint=endpoint, api_key=key, file_path=file_path, api_model="prebuilt-layout"
)

documents= loader.load()

Related​

• Document loaderconceptual guide
• Document loaderhow-to guides