Automation library · Data collection

AI personal assistant with RAG and Supabase

Started by another system calling it, and works across Postgres, Redis, Supabase and Supabase vectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 64 steps, 5 branches, 1 loop or waits: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAIRetrieval

Download free
64 stepsLarge: read it before trusting it with anything live
5Branches: places the flow splits
1Loop or waits
4Services it connects to

The flow

Starts it 1Model 22Logic 21Service 16

The steps in the order they run, from what starts it. The first 60 of 64.

  1. 1OpenAI Chat ModelLm Chat Open AiModel
  2. 2Message DelayWaitLogic
  3. 3Puxar as MensagensRedisService
  4. 4DatabaseRedisService
  5. 5setar_supabase_tabelas_vectoriaisPostgresService
  6. 6Embeddings OpenAI1Embeddings Open AiModel
  7. 7Recursive Character Text SplitterText Splitter Recursive Character Text SplitterModel
  8. 8Embeddings OpenAIEmbeddings Open AiModel
  9. 9OpenAI Chat Model2Lm Chat Open AiModel
  10. 10agendamentosTool WorkflowModel
  11. 11criar_cerebroPostgresService
  12. 12Postgres Chat MemoryMemory Postgres ChatModel
  13. 13Deletar_todas_as_mensagens1PostgresService
  14. 14base64SetLogic
  15. 15OpenAI Chat Model1Lm Chat Open AiModel
  16. 16Merge Database Data1AggregateLogic
  17. 17criar_rag_controlePostgresService
  18. 18Merge Database Data2AggregateLogic
  19. 19excluir_rag_arquivoTool WorkflowModel
  20. 20emailsTool WorkflowModel
  21. 21adicionar_conhecimentoTool WorkflowModel
  22. 22buscar_conhecimentoTool WorkflowModel
  23. 23WebhookWebhookStarts it
  24. 24Merge Database Data3AggregateLogic
  25. 25excluir_conhecimentoTool WorkflowModel
  26. 26mensagem_clienteSetLogic
  27. 27deletar_arquivoPostgresService
  28. 28Postgres Chat Memory1Memory Postgres ChatModel
  29. 29deletar_conhecimentoPostgresService
  30. 30recepcionistaAgentModel
  31. 31classificador_de_intencaoAgentModel
  32. 32If1IfLogic
  33. 33supabase_vectorstoreVector Store SupabaseModel
  34. 34Default Data LoaderDocument Default Data LoaderModel
  35. 35Supabase Vector StoreVector Store SupabaseModel
  36. 36RAGTool Vector StoreModel
  37. 37convert_to_fileConvert To FileService
  38. 38resumoChain LlmModel
  39. 39MergeMergeLogic
  40. 40configSetLogic
  41. 41puxar_promptPostgresService
  42. 42rag_resumosPostgresService
  43. 43SwitchSwitchLogic
  44. 44Edit Fields2SetLogic
  45. 45tipo_arquivoSwitchLogic
  46. 46atualizar_lista_de_arquivosPostgresService
  47. 47authIfLogic
  48. 48tratamentoSetLogic
  49. 49extrair_pdfExtract From FileService
  50. 50mensagem_tipoSwitchLogic
  51. 51atualizar_promptExecute WorkflowLogic
  52. 52exportar_textoSetLogic
  53. 53arquivo_idSetLogic
  54. 54Convert to FileConvert To FileService
  55. 55baseSetLogic
  56. 56edit2SetLogic
  57. 57deletar_arquivos_antigosSupabaseService
  58. 58OpenAIOpen AiModel
  59. 59Convert to File1Convert To FileService
  60. 60mensagem_cliente_inicialSetLogic

How it's built

Starts on
Another system calling it
Steps
64, with 5 branches, 1 loop or waits
Size
Large: read it before trusting it with anything live
Connects to
Postgres, Redis, Supabase, Supabase vectors
Model
OpenAI
Retrieval
Answers are drawn from documents you supply, not from the model alone

Questions

What does it need to run?

An n8n account, plus your own Postgres, Redis, Supabase and Supabase vectors accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on another system calling it.

Does it use AI?

Yes. It calls OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 64 steps it is large: read it before trusting it with anything live.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

Before you run it

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 64 steps before you point it at anything that matters.