Google Vertex AI

Supported Labeling Types: Row Labeling

We have made it easy for you to connect our system with Vertex AI. If you already have data and training pipelines in Vertex AI, you can use your trained model to improve it.

Extension Menu

To use the Vertex AI model, you must select Google Vertex AI in the Settings option. Once selected, you will see the following menu.

1. Target text: Pick which text to use as input for reference.

2. Target question: Decide which output column to predict.

3. API URL: The endpoint from Google Vertex AI. The format will follow the sample below:

   https://<REGION>-aiplatform.googleapis.com/ui/projects/<PROJECT-ID>/locations/<REGION>/endpoints/<ENDPOINT-ID>:predict

4. Faster prediction speed: Toggle this option to run predictions faster via the backend.

Setup Your Model

You can view the endpoint URL by clicking on the endpoint's name after the successful deployment.

To allow ML-Assisted Labeling to run your model, you need to grant access Datasaur Service Account as Vertex AI Administrator. Below are the steps:

1. Navigate to your selected project where your model is located.

2. Go to “IAM & Admin”.

3. Click on the “IAM” option in the left sidebar.

   
4. Click “Grant Access”.

5. In the New Principals field, fill in the Service Account Email:

   [email protected]

   
6. In the role field, select Vertex AI Administrator.

7. Click “Save” to finish setting up permissions.

Use the Model in ML-Assisted Labeling

After configuring all the settings above, you can copy the endpoint URL and paste it into the API URL field. You can predict the labels and obtain the predicted labels from your own model by clicking “Predict labels”.