Google Docs

This connector enables AI agents and RAG systems to retrieve context from Google Docs through Airweave’s unified search layer.

Configuration

Google Docs source connector integrates with Google Drive API to extract Google Docs.

Connects to your Google Drive account to retrieve Google Docs documents. Documents are exported as DOCX and processed through Airweave’s file processing pipeline to enable full-text semantic search across document content.

The connector handles:

Document listing and filtering
Content export and download (DOCX format)
Metadata preservation (ownership, sharing, timestamps)
Incremental sync via Drive Changes API

View Source Code

Explore the Google Docs connector implementation

Authentication

This connector uses OAuth 2.0 with custom credentials. You need to provide your OAuth application’s Client ID and Client Secret, then complete the OAuth consent flow.

OAuth Setup Required

Create an OAuth application in your provider’s developer console
Enter your Client ID and Client Secret when configuring the connection
Complete the OAuth consent flow

Configuration Options

This connector does not have any additional configuration options.

Data Models

The following data models are available for this connector:

GoogleDocsDocumentEntity

Schema for a Google Docs document.

Represents a Google Doc file retrieved via the Google Drive API. The document content is exported as DOCX and processed through Airweave’s file processing pipeline to create searchable chunks.

Reference: https://developers.google.com/drive/api/v3/reference/files https://developers.google.com/drive/api/guides/manage-downloads

Field	Type	Description
document_key	str	Stable Google Docs file ID.
title	str	Display title of the document (without .docx extension).
created_timestamp	datetime	Document creation timestamp.
modified_timestamp	datetime	Last modification timestamp.
description	Optional[str]	Optional description of the document.
starred	bool	Whether the user has starred this document.
trashed	bool	Whether the document is in the trash.
explicitly_trashed	bool	Whether the document was explicitly trashed by the user.
shared	bool	Whether the document is shared with others.
shared_with_me_time	Optional[datetime]	Time when this document was shared with the user.
sharing_user	Optional[Dict[str, Any]]	User who shared this document.
owners	List[Dict[str, Any]]	Owners of the document.
permissions	Optional[List[Dict[str, Any]]]	Permissions for this document.
parents	List[str]	IDs of parent folders containing this document.
web_view_link	Optional[str]	Link to open the document in Google Docs editor.
icon_link	Optional[str]	Link to the document’s icon.
created_time	Optional[datetime]	When the document was created.
modified_time	Optional[datetime]	When the document was last modified.
modified_by_me_time	Optional[datetime]	Last time the user modified the document.
viewed_by_me_time	Optional[datetime]	Last time the user viewed the document.
version	Optional[int]	Version number of the document.
export_mime_type	Optional[str]	MIME type used for exporting the document content (DOCX).
web_url_value	Optional[str]	Direct link to the Google Docs editor.