Materialization
Live Query can temporarily store intermediate results so that expensive operations, particularly AI processing, don’t need to run again each time you interact with downstream tools. This process is called materialization.
During workflow design, AI tools process a limited sample of the input data. Live Query reuses the sampled results while the AI tool configuration and its input remain unchanged. The interface indicates when preview results are sampled, and downstream previews are based on the same sample.
Full-data AI processing occurs when you run the workflow, not automatically during preview.
Live Query recalculates a preview when:
You change the tool configuration, prompt, instructions, or selected input column.
An upstream change affects the rows or values sent to the tool.
You change the model, provider, or model version.
You refresh the source data.
You select Workflow Refresh.
Workflow Refresh marks stored preview results as outdated. Live Query recalculates the affected sample the next time it is needed.
The stored preview expires.
重要
Design-time results are previews based on sampled data. Run the workflow to process the complete dataset.
To avoid reprocessing existing AI results during a workflow run, configure the workflow so that populated results bypass the AI tool, and only new or empty rows are processed.
Eligible Tools
These tools support materialization:
Tool | Cloud Data Warehouse | Materialization Sample |
|---|---|---|
Classify | BigQuery | 500 rows. |
Document Extract | BigQuery | 2 rows. |
Score | BigQuery | 500 rows. |
Speech to Text | BigQuery | 2 rows. |
Text Summary | BigQuery | 500 rows. |
Translate | BigQuery | 500 rows. |