Automation library · Scheduling

Priya AI Virtual Assisstant Version 2 with Gemini and OpenAI

Started by an incoming Telegram message, and works across Gmail, Google Calendar and Telegram. It puts Gemini and OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 40 steps, 2 branches: large, and worth reading before you trust it with anything live.

LargeCalls a model: Gemini, OpenAIRetrieval

Download free
40 stepsLarge: read it before trusting it with anything live
2Branches: places the flow splits
0Loops or waits
3Services it connects to

The flow

Starts it 1Model 7Logic 3Service 29

The steps in the order they run, from what starts it.

  1. 1InboundTelegram triggerStarts it
  2. 2Fetch EmailsGmail ToolService
  3. 3Send EmailGmail ToolService
  4. 4Reply EmailGmail ToolService
  5. 5Delete EmailGmail ToolService
  6. 6Mark ReadGmail ToolService
  7. 7Add LabelGmail ToolService
  8. 8Mark UnreadGmail ToolService
  9. 9Remove LabelGmail ToolService
  10. 10Create EventGoogle Calendar ToolService
  11. 11Fetch EventsGoogle Calendar ToolService
  12. 12Delete EventGoogle Calendar ToolService
  13. 13Update EventGoogle Calendar ToolService
  14. 14Fetch Emails1Gmail ToolService
  15. 15Delete Email1Gmail ToolService
  16. 16Remove Label1Gmail ToolService
  17. 17Send Email1Gmail ToolService
  18. 18Reply Email1Gmail ToolService
  19. 19Mark unread Gmail ToolService
  20. 20Mark ReadGmail ToolService
  21. 21Add label Gmail ToolService
  22. 22Create Event1Google Calendar ToolService
  23. 23Delete event Google Calendar ToolService
  24. 24Fetch EventGoogle Calendar ToolService
  25. 25Update event Google Calendar ToolService
  26. 26Session ContextMemory Buffer WindowModel
  27. 27Session Context1Memory Buffer WindowModel
  28. 28Conversational IntelligenceLm Chat Google GeminiModel
  29. 29Reasoning & Decision EngineLm Chat Open AiModel
  30. 30Knowledge & Research EnginePerplexity ToolService
  31. 31Knowledge & Research Engine1Perplexity ToolService
  32. 32Router | Voice DetectionIfLogic
  33. 33Voice Command ProcessorAgentModel
  34. 34Text Command ProcessorAgentModel
  35. 35Voice | Fetch Audio FileTelegramService
  36. 36Router | Text DetectionIfLogic
  37. 37FormatterMarkdownLogic
  38. 38Outbound TelegramService
  39. 39Voice | Speech-to-TextGoogle GeminiModel
  40. 40OutboundTelegramService

How it's built

Starts on
An incoming Telegram message
Steps
40, with 2 branches
Size
Large: read it before trusting it with anything live
Connects to
Gmail, Google Calendar, Telegram
Model
Gemini, 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 Gmail, Google Calendar and Telegram accounts, and a key for Gemini and OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an incoming Telegram message.

Does it use AI?

Yes. It calls Gemini and 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 40 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 40 steps before you point it at anything that matters.