Automation library · AI assistants

ULTIMATE RAG - vectorization search system with OpenAI

Started by someone opening a chat with it, and works across Qdrant. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 36 steps, 1 branch: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAIRetrieval

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

The flow

Starts it 6Model 19Logic 9Service 2

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

  1. 1Embeddings OpenAIEmbeddings Open AiModel
  2. 2Default Data LoaderDocument Default Data LoaderModel
  3. 3OpenAI Chat ModelLm Chat Open AiModel
  4. 4Embeddings OpenAI1Embeddings Open AiModel
  5. 5Default Data Loader1Document Default Data LoaderModel
  6. 6Embeddings OpenAI2Embeddings Open AiModel
  7. 7MEMORYMemory Buffer WindowModel
  8. 8TRIGGER REQUETEChat triggerStarts it
  9. 9Default Data Loader2Document Default Data LoaderModel
  10. 10Embeddings OpenAI3Embeddings Open AiModel
  11. 11📝 Form SubmitForm triggerStarts it
  12. 12🔗 WebhookWebhookStarts it
  13. 13RequeteWebhookStarts it
  14. 14Respond to Webhook1Respond To WebhookStarts it
  15. 15💾 Qdrant PDF2Vector Store QdrantModel
  16. 16AI AgentAgentModel
  17. 17Qdrant Vector Store1Vector Store QdrantModel
  18. 18💾 Qdrant PDF1Vector Store QdrantModel
  19. 19💾 Qdrant PDFVector Store QdrantModel
  20. 20🔀 PDF ou URL ?CodeLogic
  21. 21Code in JavaScript1CodeLogic
  22. 22Code in JavaScriptCodeLogic
  23. 23🚦 RouterSwitchLogic
  24. 24Respond to WebhookRespond To WebhookStarts it
  25. 25🔍 OCR FichierMistral AiModel
  26. 26📥 Scrap PageHttp RequestService
  27. 27📥 Download PDFHttp RequestService
  28. 28🧠 Analyse FichierOpen AiModel
  29. 29📄 Extract HTMLHtmlLogic
  30. 30🔍 OCR PDFMistral AiModel
  31. 31⚙️ Parse FichierCodeLogic
  32. 32🧹 Clean HTMLCodeLogic
  33. 33🧠 Analyse PDF (notation)Open AiModel
  34. 34WEB analyseOpen AiModel
  35. 35⚙️ Parse PDFCodeLogic
  36. 36⚙️ Parse WebCodeLogic

How it's built

Starts on
Someone opening a chat with it
Steps
36, with 1 branch
Size
Large: read it before trusting it with anything live
Connects to
Qdrant
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 Qdrant 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?

Take your time. At 36 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 36 steps before you point it at anything that matters.