Microsoft Word Integration - Crewai

Overview

Enable your agents to create, read, and manage Word documents and text files in OneDrive or SharePoint. Automate document creation, retrieve content, manage document properties, and streamline your document workflows with AI-powered automation.

Prerequisites

Before using the Microsoft Word integration, ensure you have:

A CrewAI AMP account with an active subscription
A Microsoft account with Word and OneDrive/SharePoint access
Connected your Microsoft account through the Integrations page

Setting Up Microsoft Word Integration

1. Connect Your Microsoft Account

Navigate to CrewAI AMP Integrations
Find Microsoft Word in the Authentication Integrations section
Click Connect and complete the OAuth flow
Grant the necessary permissions for file access
Copy your Enterprise Token from Integration Settings

2. Install Required Package

bash

uv add crewai-tools

3. Environment Variable Setup

<Note> To use integrations with `Agent(apps=[])`, you must set the `CREWAI_PLATFORM_INTEGRATION_TOKEN` environment variable with your Enterprise Token. </Note>

bash

export CREWAI_PLATFORM_INTEGRATION_TOKEN="your_enterprise_token"

Or add it to your .env file:

CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token

Available Actions

<AccordionGroup> <Accordion title="microsoft_word/get_documents"> **Description:** Get all Word documents from OneDrive or SharePoint.

**Parameters:**
- `select` (string, optional): Select specific properties to return.
- `filter` (string, optional): Filter results using OData syntax.
- `expand` (string, optional): Expand related resources inline.
- `top` (integer, optional): Number of items to return (min 1, max 999).
- `orderby` (string, optional): Order results by specified properties.

</Accordion> <Accordion title="microsoft_word/create_text_document"> **Description:** Create a text document (.txt) with content. RECOMMENDED for programmatic content creation that needs to be readable and editable.

**Parameters:**
- `file_name` (string, required): Name of the text document (should end with .txt).
- `content` (string, optional): Text content for the document. Default is "This is a new text document created via API."

</Accordion> <Accordion title="microsoft_word/get_document_content"> **Description:** Get the content of a document (works best with text files).

**Parameters:**
- `file_id` (string, required): The ID of the document.

</Accordion> <Accordion title="microsoft_word/get_document_properties"> **Description:** Get properties and metadata of a document.

**Parameters:**
- `file_id` (string, required): The ID of the document.

</Accordion> <Accordion title="microsoft_word/delete_document"> **Description:** Delete a document.

**Parameters:**
- `file_id` (string, required): The ID of the document to delete.

</Accordion> <Accordion title="microsoft_word/copy_document"> **Description:** Copy a document to a new location in OneDrive.

**Parameters:**
- `file_id` (string, required): The ID of the document to copy
- `name` (string, optional): New name for the copied document
- `parent_id` (string, optional): The ID of the destination folder (defaults to root)

</Accordion> <Accordion title="microsoft_word/move_document"> **Description:** Move a document to a new location in OneDrive.

**Parameters:**
- `file_id` (string, required): The ID of the document to move
- `parent_id` (string, required): The ID of the destination folder
- `name` (string, optional): New name for the moved document

</Accordion> </AccordionGroup>

Usage Examples

Basic Microsoft Word Agent Setup

python

from crewai import Agent, Task, Crew

# Create an agent with Microsoft Word capabilities
word_agent = Agent(
    role="Document Manager",
    goal="Manage Word documents and text files efficiently",
    backstory="An AI assistant specialized in Microsoft Word document operations and content management.",
    apps=['microsoft_word']  # All Word actions will be available
)

# Task to create a new text document
create_doc_task = Task(
    description="Create a new text document named 'meeting_notes.txt' with content 'Meeting Notes from January 2024: Key discussion points and action items.'",
    agent=word_agent,
    expected_output="New text document 'meeting_notes.txt' created successfully."
)

# Run the task
crew = Crew(
    agents=[word_agent],
    tasks=[create_doc_task]
)

crew.kickoff()

Reading and Managing Documents

python

from crewai import Agent, Task, Crew

# Create an agent focused on document operations
document_reader = Agent(
    role="Document Reader",
    goal="Retrieve and analyze document content and properties",
    backstory="An AI assistant skilled in reading and analyzing document content.",
    apps=['microsoft_word/get_documents', 'microsoft_word/get_document_content', 'microsoft_word/get_document_properties']
)

# Task to list and read documents
read_docs_task = Task(
    description="List all Word documents in my OneDrive, then get the content and properties of the first document found.",
    agent=document_reader,
    expected_output="List of documents with content and properties of the first document."
)

crew = Crew(
    agents=[document_reader],
    tasks=[read_docs_task]
)

crew.kickoff()

Document Cleanup and Organization

python

from crewai import Agent, Task, Crew

# Create an agent for document management
document_organizer = Agent(
    role="Document Organizer",
    goal="Organize and clean up document collections",
    backstory="An AI assistant that helps maintain organized document libraries.",
    apps=['microsoft_word/get_documents', 'microsoft_word/get_document_properties', 'microsoft_word/delete_document']
)

# Task to organize documents
organize_task = Task(
    description="List all documents, check their properties, and identify any documents that might be duplicates or outdated for potential cleanup.",
    agent=document_organizer,
    expected_output="Analysis of document library with recommendations for organization."
)

crew = Crew(
    agents=[document_organizer],
    tasks=[organize_task]
)

crew.kickoff()

Troubleshooting

Common Issues

Authentication Errors

Ensure your Microsoft account has the necessary permissions for file access (e.g., Files.Read.All, Files.ReadWrite.All).
Verify that the OAuth connection includes all required scopes.

File Creation Issues

When creating text documents, ensure the file_name ends with .txt extension.
Verify that you have write permissions to the target location (OneDrive/SharePoint).

Document Access Issues

Double-check document IDs for correctness when accessing specific documents.
Ensure the referenced documents exist and are accessible.
Note that this integration works best with text files (.txt) for content operations.

Content Retrieval Limitations

The get_document_content action works best with text files (.txt).
For complex Word documents (.docx), consider using the document properties action to get metadata.

Getting Help

<Card title="Need Help?" icon="headset" href="mailto:[email protected]"> Contact our support team for assistance with Microsoft Word integration setup or troubleshooting. </Card>