Automation library · AI assistants

Create a RAG system with Paul Essays and Milvus

Started by someone opening a chat with it. It calls services over plain HTTP rather than through connectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 20 steps: a working afternoon to understand properly.

MediumCalls a model: OpenAIRetrieval

Download free
20 stepsMedium: a working afternoon
0Branches: places the flow splits
0Loops or waits
0Services by connector: it calls them over plain HTTP

The flow

Starts it 2Model 8Logic 8Service 2

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

  1. 1When clicking "Execute Workflow"Manual triggerStarts it
  2. 2Recursive Character Text Splitter1Text Splitter Recursive Character Text SplitterModel
  3. 3Set max chunks to send to modelSetLogic
  4. 4Embeddings OpenAI2Embeddings Open AiModel
  5. 5When chat message receivedChat triggerStarts it
  6. 6Embeddings OpenAIEmbeddings Open AiModel
  7. 7OpenAI Chat ModelLm Chat Open AiModel
  8. 8Fetch Essay ListHttp RequestService
  9. 9Default Data LoaderDocument Default Data LoaderModel
  10. 10Milvus Vector Store in retrievalVector Store MilvusModel
  11. 11Milvus Vector StoreVector Store MilvusModel
  12. 12Answer the query based on chunksInformation ExtractorModel
  13. 13Extract essay namesHtmlLogic
  14. 14Prepare chunksCodeLogic
  15. 15Compose citationsSetLogic
  16. 16Split out into itemsSplit OutLogic
  17. 17Generate responseSetLogic
  18. 18Limit to first 3LimitLogic
  19. 19Fetch essay textsHttp RequestService
  20. 20Extract Text OnlyHtmlLogic

How it's built

Starts on
Someone opening a chat with it
Steps
20
Size
Medium: a working afternoon
Connects to
Nothing by connector; it calls services over plain HTTP
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, 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?

Plan an afternoon. 20 steps is enough that you should read each one before running it.

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 20 steps before you point it at anything that matters.