Automation library · Content

Maintain RAG embeddings with OpenAI and Postgres

Started by another system calling it, and works across Postgres and in-memory vectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 27 steps, 1 branch: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAIRetrieval

Download free
27 stepsLarge: read it before trusting it with anything live
1Branch: places the flow splits
0Loops or waits
2Services it connects to

The flow

Starts it 2Model 9Logic 7Service 9

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

  1. 1Daily RAG Maintenance ScheduleSchedule triggerStarts it
  2. 2Source Change WebhookWebhookStarts it
  3. 3OpenAI EmbeddingsEmbeddings Open AiModel
  4. 4Recursive Text SplitterText Splitter Recursive Character Text SplitterModel
  5. 5OpenAI Chat ModelLm Chat Open AiModel
  6. 6Workflow ConfigurationSetLogic
  7. 7New Vector Store (Candidate)Vector Store In MemoryModel
  8. 8Query New Vector Store (Tool)Vector Store In MemoryModel
  9. 9Query Old Vector Store (Tool)Vector Store In MemoryModel
  10. 10Document LoaderDocument Default Data LoaderModel
  11. 11Generate Answers (New)AgentModel
  12. 12Generate Answers (Old)AgentModel
  13. 13Fetch Documents from SourceHttp RequestService
  14. 14Fetch Previous Chunk HashesPostgresService
  15. 15Store Embedding MetadataCodeLogic
  16. 16Calculate Quality MetricsCodeLogic
  17. 17Chunk Documents & Compute HashCodeLogic
  18. 18Detect Changed ChunksCompare DatasetsService
  19. 19Save Embedding Version MetadataPostgresService
  20. 20Calculate Embedding DriftCodeLogic
  21. 21Fetch Golden QuestionsPostgresService
  22. 22Fetch Previous EmbeddingsPostgresService
  23. 23Quality Improved?IfLogic
  24. 24Promote New EmbeddingsPostgresService
  25. 25Rollback to Previous EmbeddingsPostgresService
  26. 26Flag for Human ReviewSetLogic
  27. 27Send NotificationHttp RequestService

How it's built

Starts on
Another system calling it
Steps
27, with 1 branch
Size
Large: read it before trusting it with anything live
Connects to
Postgres, in-memory 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 and in-memory 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 27 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 27 steps before you point it at anything that matters.