HTTP and Knowledge: Google Drive Folder Index Template

A scheduled Spojit workflow that watches a Google Drive folder, pulls in new files, and embeds them into a searchable Knowledge collection for the whole team.

What It Builds

A Schedule trigger runs on a cron you set. On each run, the http connector calls the Google Drive API to list a folder and download any files added since the last pass. A Knowledge node in Embed mode adds those documents to a persistent collection, so AI search stays current across the shared drive. Google Drive has no native connector, so Miraxa researches its API and wires the http calls for you.

The Prompt

Paste this into Miraxa and it builds the workflow, connecting the tools for you:

Build a workflow that runs every morning at 7am, connects to the Google Drive API to list the files in a specific folder, downloads any new files added since the last run, and embeds them into a persistent Knowledge collection called "Team Drive" so the team can search them with AI.

Connectors Used

  • Schedule trigger - runs the indexer on a cron in your time zone.
  • http - calls the Google Drive API to list the folder and download files.
  • Knowledge (Embed mode) - adds documents to a persistent, searchable collection.

Customize It

Change the schedule (for example every 15 minutes), point at a different folder, rename the collection, or restrict to file types like PDFs and Docs. You can also tell Miraxa to skip files already embedded so re-runs stay cheap.

Tips

  • Give your Google Drive credentials read access to the target folder before the first run.
  • Knowledge Embed handles OCR and many document types, so scanned PDFs are searchable too.
  • Use a persistent collection (not Transient) so embedded files stay available for future queries.

Related

Did this answer your question? Thanks for the feedback There was a problem submitting your feedback. Please try again later.