A chat assistant over documents from a folder

The scenario reads documents from a folder, stores them in a search base and answers questions strictly from their contents.

  • Answers from your documents, not made up
  • Just drop a file in the folder
  • Remove a file — it leaves the base too
  • Answers everyone who asks
Google DriveSupabase Vector StoreDefault Data LoaderEmbeddings OpenAISupabasePostgres Chat Memory
Set it upScriptera

How it works

To connect Google Drive and Supabase Vector Store, you don't need a developer: a ready-made scenario links them in minutes.

  1. Starts when: File Updated
  2. Then: Set File ID
  3. Check: Loop Over Items
  4. Then: Delete a row
  5. Then: Download the file
  6. Then: Extract from File
  7. Then: Supabase Vector Store
  8. Then: Default Data Loader
  9. Then: Recursive Character Text Splitter
  10. Starts when: File Created
  11. Then: Embeddings OpenAI
  12. Then: Postgres Chat Memory
  13. Then: OpenAI Chat Model
  14. Starts when: When chat message received
  15. Then: RAG AI Agent
  16. Then: RAG Vector store
  17. Then: Embeddings OpenAI1

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

Similar scenarios