Google Drive Connector Documentation

If you have already set up a connector, skip to How to Use the Google Drive Connector.

Connect your Google Drive to Abacus.AI

To connect your Google Drive folder to Abacus.AI, follow these steps to set up the connector:

Add New Connector

1. In the Abacus.AI interface, click on your profile picture in the top right corner.

2. Select "Manage Connectors" from the dropdown menu.

3. Choose "Add New Connector", select "Google Drive" as the connector type, enter your Google Drive folder URL, and click "Save".

Service Account Configuration

A service account email address will be automatically generated for you during the setup process. This email is essential for granting folder access.

Grant Folder Access to Service Account

1. With the service account email provided, navigate to your Google Drive and locate the folder you wish to connect.

2. Right-click on the folder and select "Share". Enter the service account email and set the permission to "Viewer".

User-Level Permissions

If the folder is not public, you need to share it with the service account and assign the appropriate permissions:

1. Navigate to your Google Drive and locate the folder you wish to connect.

2. Right-click on the folder and select "Share".

3. Enter the service account email provided in the setup instructions.

4. Assign the permission level of "Viewer".

5. Click "Send" to share the folder.

Finalize Configuration

After sharing your folder with the service account, return to the connector setup page to verify that the connector setup is complete.

How to Use the Google Drive Connector

Once the Google Drive connector is set up, you can fetch data to train models in Abacus.AI.

1. Create a new project and select the use case, then go to the "Datasets" tab and click "Create Dataset".

2. Click on "Create New".

3. Name the dataset, select the data type, and click "Continue".

4. Choose "Read from External Service" and select your Google Drive connector under "Application Connectors".

5. Specify the regex location of the files to fetch. This is a required field, but you can use the application browser to select the file or folder to pull.

6. If you want to include highlighting for documents in the doc viewer, enable the "Extract Bounding Boxes" advanced option.

7. After configuring the data import options, proceed to upload the dataset.

8. Once the dataset is uploaded, configure the schema mapping and train models with the data.