Skip to main content

Score Tool (Live Query for Google BigQuery)

Use the Score tool to assign a numeric value to text based on a custom instruction. The tool predicts the score for each row and writes the result to the specified output column.

Use this tool when you want to rate, rank, or compare text using natural language instructions. For example, you can score sentiment, quality, or relevance.

Tool Availability

The Score tool is available in the Google BigQuery tool palette.

Before using this tool...

  1. From a Cloud Native workflow, go to Options.

  2. Verify that Enable LiveQuery is enabled.

  3. Verify that the Selected Connection displays a BigQuery connection.

Tool Configuration

Column to Score

Use the Column to Score dropdown to select the column that contains the text to evaluate.

The selected column must contain string data.

Scoring Instructions

Enter an instruction that describes how to evaluate the data. Write clear and specific instructions to get consistent results. The input is limited to 1000 characters.

For best results, define a clear numeric scale and expected output. For example:

Return a number from 1 to 5, where 1 is very negative and 5 is very positive.

Execute

Select Execute to preview how the model scores your data. If you update the scoring instructions, select Execute again to refresh the results.

Output Column Name

Enter a name for the output column in Output Column Name. If you don't specify a name, the tool appends _score to the input column name.

Output

The tool outputs a new column that contains the generated numeric score for each row.

Permission Required

To use this tool, assign the Vertex AI API permission to the BigQuery project or credentials (service account key or OAuth):