Strip personal data from your documents — locally, nothing leaves your machine

The scenario takes text documents from хранилище, runs them through a local model, removes personal data and saves a cleaned version, flagging what it found in LoneScale.

  • Documents never leave your perimeter — the model runs locally
  • Personal data is found and removed automatically
  • You can see which files had it at all — flags in LoneScale
  • Large documents are processed in chunks, without choking
Google DriveOllama Model
Set it up for yourselfScriptera

How it works

To move data from LoneScale to Google Drive automatically, use a ready-made scenario — no manual exports.

  1. Starts when: on_subfolder_created
  2. Then: return_files_in_folder
  3. Then: split_files_item
  4. Check: select_markdown_files
  5. Then: download_drive_files
  6. Then: text_from_markdown
  7. Then: combine_all_text
  8. Then: chunk_text_for_local_llm
  9. Then: Basic LLM Chain
  10. Then: parse_json_text_with_flag
  11. Then: log_text_with_pii_flag (optional)
  12. Then: combine_chunk_text
  13. Then: join_text_chunks
  14. Then: create_cleaned_text_file
  15. Then: Ollama Model

You can launch this LoneScale + Google Drive integration in Scriptera: describe the task in plain words — the scenario is built, launched and monitored for you.

Similar scenarios