GoogleDriveRetriever

Search Google Drive and retrieve matching files as Haystack Document objects. Use this component to find files by full-text search before fetching or indexing their content.

Key Features

• Runs full-text search over the user's Google Drive via the Drive API v3.
• Returns file metadata including file_name, file_id, web_url, mime_type, and timestamps.
• Optionally exports native Google Docs, Sheets, and Slides to text for document content.
• Supports shared drives, query filters, and custom field selection.
• Works with OAuthTokenResolver for per-user delegated access.

Configuration

Add Workspace-Level Integration

1. Click your profile icon and choose Settings.
2. Go to Workspace>Integrations.
3. Find the provider you want to connect and click Connect next to them.
4. Enter the API key and any other required details.
5. Click Connect. You can use this integration in pipelines and indexes in the current workspace.

Add Organization-Level Integration

1. Click your profile icon and choose Settings.
2. Go to Organization>Integrations.
3. Find the provider you want to connect and click Connect next to them.
4. Enter the API key and any other required details.
5. Click Connect. You can use this integration in pipelines and indexes in all workspaces in the current organization.

1. Drag the GoogleDriveRetriever component onto the canvas from the Component Library.
2. Wire an upstream OAuthTokenResolver to provide a delegated Google OAuth bearer token on the access_token input.
3. Set top_k to control the number of results.
4. Go to the Advanced tab to configure query_filter, include_shared_drives, include_content, and other options.

The access token must carry a scope that allows search, for example https://www.googleapis.com/auth/drive.readonly. The metadata-only drive.metadata.readonly scope cannot search file content or export documents.

Connections

GoogleDriveRetriever receives a search query and an access_token. It outputs a list of Document objects. Connect the documents output to GoogleDriveFetcher for full file content, or to downstream components that process metadata and snippets.

Source Code

To check this component's source code, open retriever.py in the Haystack Core Integrations repository.

Usage Examples

Basic Configuration

  GoogleDriveRetriever:
    type: haystack_integrations.components.retrievers.google_drive.retriever.GoogleDriveRetriever
    init_parameters:
      top_k: 10

Using the Component in a Pipeline

# haystack-pipeline
components:
  oauth_resolver:
    type: haystack_integrations.components.connectors.oauth.resolver.OAuthTokenResolver
    init_parameters:
      token_source:
        type: haystack_integrations.utils.oauth.sources.OAuthRefreshTokenSource
        init_parameters:
          token_url: https://oauth2.googleapis.com/token
          client_id: your-client-id
          refresh_token:
            type: env_var
            env_vars:
            - GOOGLE_REFRESH_TOKEN
            strict: false
          scopes:
          - https://www.googleapis.com/auth/drive.readonly

  retriever:
    type: haystack_integrations.components.retrievers.google_drive.retriever.GoogleDriveRetriever
    init_parameters:
      top_k: 5

connections:
- sender: oauth_resolver.access_token
  receiver: retriever.access_token

inputs:
  query:
  - retriever.query

outputs:
  documents: retriever.documents

Parameters

Inputs

Parameter	Type	Description
query	str	Search query string, matched against file full text via fullText contains.
access_token	str | Secret	Delegated Google OAuth bearer token for the user whose Drive is searched.
top_k	int | None	Overrides the init-time top_k for this run.

Outputs

Parameter	Type	Description
documents	List[Document]	Matching files as Haystack documents with metadata and optional exported content.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
include_content	bool	False	When True, exports native Google Docs/Sheets/Slides to text and uses the result as document content.
top_k	int	10	Maximum number of documents to return.
query_filter	str | None	None	Optional Drive query clause AND-ed with the search term, for example "mimeType != 'application/vnd.google-apps.folder'".
include_shared_drives	bool	False	When True, searches shared drives as well as My Drive.
order_by	str | None	None	Optional Drive orderBy expression, for example "modifiedTime desc".
fields	List[str] | None	None	File properties to request via the Drive fields selection.
api_base_url	str	https://www.googleapis.com/drive/v3	The Drive API base URL.
timeout	float	30.0	HTTP timeout in seconds for each Drive API request.
max_retries	int	3	Maximum retries on rate-limit or transient server errors.

Run Method Parameters

These are the parameters you can configure for the component's run() method. This means you can pass these parameters at query time through the API, in Playground, or when running a job. For details, see Modify Pipeline Parameters at Query Time.

Parameter	Type	Default	Description
query	str		Search query string.
access_token	str | Secret		Delegated Google OAuth bearer token.
top_k	int | None	None	Maximum number of documents to return. Overrides the init-time value.

Related Information

• GoogleDriveFetcher
• OAuthTokenResolver
• Add Secrets