A chat over your documents with answers from the source

The scenario gathers your files into a smart base and answers questions from them — to the point and with a source link.

  • Answers from your documents
  • Files are picked up on their own
  • Many formats: PDF, sheets, texts
  • Questions in plain words
Google DriveSupabase Vector StoreEmbeddings OpenAIDefault Data Loader
Set it upScriptera

How it works

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

  1. Starts when: File Created
  2. Check: Loop Over Items
  3. Then: Set File ID
  4. Check: Validate File
  5. If yes: Check for Duplicates
  6. Check: IF Duplicate Check
  7. If yes: Log Duplicate
  8. Then: Slack Duplicate Notification
  9. If no: Debug File ID
  10. Then: Delete old Doc
  11. Then: Delete Old Data Rows
  12. Then: Insert Metadata
  13. Then: Download File
  14. Check: Switch
  15. If yes: Extract from File PDF
  16. Then: Supabase Vector Store
  17. If no: Extract from TXT
  18. If no: Extract from CSV
  19. Then: Aggregate
  20. Then: Summarize
  21. Then: Set Schema
  22. Then: Schema Document Metadata
  23. Then: Insert Table Rows
  24. If no: Extract from XLSX
  25. If no: Extract from RTF
  26. If no: Extract from DOC
  27. If no: Set Error Type
  28. Then: Error Logger
  29. Then: Error Notification
  30. Starts when: Update to File
  31. Then: Embeddings OpenAI
  32. Then: Default Data Loader
  33. Then: RAG AI Agent
  34. Then: OpenAI Chat Model
  35. Then: Postgres Chat Memory
  36. Then: List Documents
  37. Then: Query Document Rows
  38. Then: Character Text Splitter
  39. Starts when: When chat message received
  40. Then: Edit Fields2
  41. Then: Supabase Vector Store2
  42. Then: Embeddings OpenAI2
  43. Then: Get Full Document Text - Get File Contents

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

Similar scenarios