An assistant that answers from all your sources at once

The scenario answers questions in a chat, assembling the answer from your documents in Microsoft OneDrive, your knowledge base and fresh data from the web.

  • An answer from documents, database and the web at once
  • One assistant instead of a dozen tabs
  • Fresh data from the web via perplexity
  • Documents pulled from Microsoft OneDrive
Postgres Chat MemoryEmbeddings OpenAIReranker CoherePostgres ToolSupabase Vector Store
Connect perplexity and launchScriptera

How it works

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

  1. Starts when: When chat message received
  2. Then: Knowledge Agent
  3. Then: Postgres Chat Memory
  4. Then: Embeddings OpenAI
  5. Then: Reranker Cohere
  6. Then: Anthropic Chat Model
  7. Then: structured data
  8. Then: General knowledge
  9. Starts when: When clicking ‘Execute workflow’
  10. Then: Download file
  11. Then: Add to Supabase Vector DB
  12. Then: Default Data Loader1
  13. Then: Recursive Character Text Splitter1
  14. Then: Embeddings OpenAI1
  15. Then: Think
  16. Starts when: When Executed by Another Workflow
  17. Check: Operation
  18. If yes: Download File1
  19. Check: FileType
  20. If yes: Extract from PDF
  21. Then: Get PDF Response
  22. If no: Extract from CSV
  23. Then: Get CSV Response
  24. If no: Analyse Image
  25. If no: Transcribe Audio
  26. Starts when: Google Drive MCP Server
  27. Then: Read File From GDrive
  28. Then: Search Files from Gdrive
  29. Then: search about any doc in google drive
  30. Then: Message a model in Perplexity

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

Similar scenarios