FTP and Knowledge: Contract Library Sync Template

A nightly Spojit workflow that pulls new contract PDFs from an FTP share and embeds them into a persistent Knowledge collection, giving you a queryable contract library that mirrors the file share.

What It Builds

A Schedule trigger runs every night, lists the contracts directory on your FTP server, and downloads any PDFs that have not been seen before. Each new file is passed to a Knowledge node in Embed mode, adding it to a persistent collection. Over time the collection mirrors the file share, so anyone can query contract terms without opening the raw documents.

The Prompt

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

Build a workflow that runs every night at 2am, lists files in the /contracts directory on my FTP server, and for any new PDF that hasn't been processed yet, downloads it and embeds it into a persistent Knowledge collection called "Contract Library" so I can query contract terms later.

Connectors Used

  • Schedule trigger - fires the nightly run on a cron schedule with your timezone.
  • FTP - lists the contracts directory and downloads new PDF files.
  • Knowledge (Embed mode) - adds each PDF to a persistent, reusable collection with OCR for scanned documents.

Customize It

Change /contracts to your own remote path, adjust the 2am run time, and rename the Contract Library collection to match your team. You can also widen the file match beyond PDFs (for example DOCX) or narrow the schedule to weekdays only, all in the same prompt.

Tips

  • Use SFTP credentials with read access to the contracts path; the connection only needs to list and download.
  • Embed into a persistent collection (not Transient) so the library survives across runs and stays queryable.
  • Track processed filenames so re-runs skip files already embedded and avoid duplicate entries.

Related

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