Skip to main content

Google Drive Listing Workflow

This workflow fetches a list of files from your Google Drive using a search query and summarizes the results using AI.

Note:
This workflow uses two AI Data Processing nodes, each with a tool, because the output of the first tool (Date/Time Now) is required as input for the second tool (Google Drive Fetch Files).
Current smaller models (≤ 8B parameters) are not able to call the available tools sequentially—they attempt to call both tools at the same time, which leads to incorrect results.
If you use a larger LLM (more than 8B parameters), you can combine both tools in a single AI Data Processing node, as larger models can more reliably call tools one after the other.

Google Drive Listing Workflow


Steps

  1. Provide Input: The workflow starts with a Data Source node that supplies the prompt: "Can you tell me the latest document that was created?"
  2. Add Date/Time Context: The first AI Data Processing node uses the Date/Time Now Tool to obtain the current date and time, then augments the original request with this temporal context.
  3. Fetch Drive Files: The second AI Data Processing node receives the time-augmented request and uses the Google Drive Fetch Files Tool to retrieve the files, then formats the results.
  4. Display Result: The Data Flow Spy node displays the final formatted list of Google Drive files.
  5. (Optional) Inspect Intermediate Data: An additional Data Flow Spy node can be used to inspect the time-augmented request between the two AI processing steps.