> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.airweave.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.airweave.ai/_mcp/server.

# Word

> Word integration with Airweave

{/* AUTO-GENERATED CONTENT START */}

<img src="https://fdr-prod-docs-files-public.s3.us-east-1.amazonaws.com/airweave.docs.buildwithfern.com/2026-05-20T11%3A36%3A51.367Z/docs/pages/connectors/word/icon.svg?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Credential=AKIA6KXJSKKNFOCF7G4B%2F20260807%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260807T163031Z&X-Amz-Expires=604800&X-Amz-Signature=45fe1bd72fe58852787f93659fff640cc56f5b0d2fdf385162a05f6d3a9e11d3&X-Amz-SignedHeaders=host&x-amz-checksum-mode=ENABLED&x-id=GetObject" alt="Word logo" width="48" height="48" />

<h1>
  Word
</h1>

This connector enables AI agents and RAG systems to retrieve context from Word through Airweave's unified search layer.

## Configuration

Microsoft Word source connector integrates with the Microsoft Graph API.

Synchronizes Word documents from Microsoft OneDrive and SharePoint.
Documents are processed through Airweave's file handling pipeline which
downloads, converts to markdown, chunks, and indexes for semantic search.

#### [View Source Code](https://github.com/airweave-ai/airweave/tree/main/backend/airweave/platform/sources/word.py)

Explore the Word connector implementation

### Authentication

This connector uses **OAuth 2.0 authentication**. You can connect through the Airweave UI or API using the OAuth flow.

**Supported authentication methods:**

* OAuth Browser Flow (recommended for UI)
* OAuth Token (for programmatic access)
* Auth Provider (enterprise SSO)

### Configuration Options

This connector does not have any additional configuration options.

## Data Models

The following data models are available for this connector:

#### WordDocumentEntity

Schema for a Microsoft Word document as a file entity.

Represents Word documents (.docx, .doc) stored in OneDrive/SharePoint.
Extends FileEntity to leverage Airweave's file processing pipeline which will:

* Download the Word document
* Convert it to markdown using document converters
* Chunk the content for indexing

Reference:
[https://learn.microsoft.com/en-us/graph/api/resources/driveitem](https://learn.microsoft.com/en-us/graph/api/resources/driveitem)

| Field                    | Type                       | Description                                          |
| ------------------------ | -------------------------- | ---------------------------------------------------- |
| id                       | str                        | Drive item ID for the Word document.                 |
| title                    | str                        | Human-readable title for the document.               |
| created\_datetime        | Optional\[datetime]        | When the document was created.                       |
| last\_modified\_datetime | Optional\[datetime]        | When the document was last modified.                 |
| web\_url\_override       | Optional\[str]             | URL to open the document in Word Online.             |
| content\_download\_url   | Optional\[str]             | Direct download URL for the document content.        |
| created\_by              | Optional\[Dict\[str, Any]] | Identity of the user who created the document.       |
| last\_modified\_by       | Optional\[Dict\[str, Any]] | Identity of the user who last modified the document. |
| parent\_reference        | Optional\[Dict\[str, Any]] | Information about the parent folder/drive location.  |
| drive\_id                | Optional\[str]             | ID of the drive containing this document.            |
| folder\_path             | Optional\[str]             | Full path to the parent folder.                      |
| description              | Optional\[str]             | Description of the document if available.            |
| shared                   | Optional\[Dict\[str, Any]] | Information about sharing status of the document.    |

{/* AUTO-GENERATED CONTENT END */}