Skip to main content

⚠️ Note: While we are waiting for Google Verification, folders cannot be selected. Please select all the the files you want ingested to the pipeline.

Google Drive (OAuth)

The Google Drive (OAuth) connector allows you to integrate Google Drive as a data source for your pipelines using OAuth authentication. This guide explains the configuration options available when setting up this connector.

Configure the Connector

To configure a connector to your Google Drive instance using OAuth:

  1. Click Source Connectors from the main menu.

  2. Click New Source Connector from the Source Connectors page.

  3. Select the Google Drive OAuth card.

    Google Drive OAuth Card

  4. Enter a name for your connector.

  5. Click Authorize to begin the OAuth process.

    Google Drive OAuth Parameters

  6. A new window will open, prompting you to sign in to your Google account.

  7. Follow the prompts to grant Vectorize access to your Google Drive.

  8. After authorization, you'll be presented with a file selector showing your Google Drive contents.

  9. Select the files and folders you want to include in your pipeline.

Google Drive File Selector

  1. Click Finish Selection.
  2. Click Create Google Drive OAuth Integration.

Configuring the Google Drive OAuth Connector in a RAG Pipeline

The Google Drive OAuth connector streamlines access to your personal Google Drive without the need for service account configuration.

Configuring Google Drive OAuth for RAG Pipeline

The following table outlines the fields available when configuring a Google Drive OAuth source for use within a Retrieval-Augmented Generation (RAG) pipeline.

FieldDescriptionRequired
File ExtensionsSpecifies the types of files to be included (e.g., PDF, HTML, Markdown, Text, DOCX).Yes
Polling IntervalInterval (in seconds) at which the connector will check Google Drive for updates.Yes

Modifying Selected Files

To add or remove files from your Google Drive OAuth connector:

  1. Navigate to your existing Google Drive OAuth connector.
  2. Click Edit to modify your connector settings.
  3. Click Select Files to reopen the file selector.
  4. Update your file selection as needed.
  5. Click Confirm Selection to save your changes.

Troubleshooting

If your Google Drive OAuth connector is not ingesting files properly, check the following:

  1. Authorization status: Ensure your OAuth authorization hasn't expired. If it has, you'll need to reauthorize the connector.
  2. File access: Verify that you still have access to all selected files in your Google Drive.
  3. File size limits: Files exceeding 10MB may not be processed properly due to Google Drive API limitations.
  4. Supported file types: Confirm that all files match the file extensions you've specified in the configuration.

If you see an error during the OAuth process, try the following:

  1. Clear your browser cookies and cache
  2. Use a private/incognito browser window
  3. Ensure you're signed in to the correct Google account

What's next?

  • If you haven't yet built a connector to your vector database, go to Configuring Vector Database Connectors and select the platform you prefer to use for storing output vectors.

    OR

  • If you're ready to start producing vector embeddings from your input data, head to Pipeline Basics. Select your new connector as the data source to use it in your pipeline.

Was this page helpful?