Automation library · Customer support

Answer internal policy questions from Google Drive with OpenAI

Started by someone opening a chat with it, and works across Google Drive, Qdrant and Slack. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 31 steps, 2 branches: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAIRetrieval

Download free
31 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 4Model 9Logic 8Service 10

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

  1. 1When File Created in DriveGoogle Drive triggerStarts it
  2. 2When File Updated in DriveGoogle Drive triggerStarts it
  3. 3Generate OpenAI EmbeddingsEmbeddings Open AiModel
  4. 4Split Text RecursivelyText Splitter Recursive Character Text SplitterModel
  5. 5Chat Message TriggerChat triggerStarts it
  6. 6Buffer Memory StorageMemory Buffer WindowModel
  7. 7OpenAI GPT-4 Chat ModelLm Chat Open AiModel
  8. 8Query OpenAI EmbeddingsEmbeddings Open AiModel
  9. 9When Slack Event OccursSlack triggerStarts it
  10. 10Download Created FileGoogle DriveService
  11. 11Download Updated FileGoogle DriveService
  12. 12Insert into Qdrant Vector StoreVector Store QdrantModel
  13. 13Load Default DataDocument Default Data LoaderModel
  14. 14Normalize Message DataSetLogic
  15. 15Support AI AgentAgentModel
  16. 16Retrieve from Qdrant Vector StoreVector Store QdrantModel
  17. 17Filter Slack MessagesFilterLogic
  18. 18Merge Files for ProcessingMergeLogic
  19. 19Merge Chat and Slack DataMergeLogic
  20. 20Format Citations for MessagingCodeLogic
  21. 21Route by File TypeSwitchLogic
  22. 22Check If Origin Is SlackIfLogic
  23. 23Extract Text from PDFExtract From FileService
  24. 24Extract Text from Google DocExtract From FileService
  25. 25Convert DOCX to Google DocHttp RequestService
  26. 26Extract Text from TXTExtract From FileService
  27. 27Post Message to SlackSlackService
  28. 28Text Extraction OutputNo OpLogic
  29. 29Export GDoc to TextHttp RequestService
  30. 30Delete Vectors by File IDHttp RequestService
  31. 31Remove Temporary Google DocHttp RequestService

How it's built

Starts on
Someone opening a chat with it
Steps
31, with 2 branches
Size
Large: read it before trusting it with anything live
Connects to
Google Drive, Qdrant, Slack
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 Google Drive, Qdrant and Slack accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone opening a chat with 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 31 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 31 steps before you point it at anything that matters.