Automation library · AI assistants

Build a WordPress RAG chatbot with OpenAI and Qdrant

Started by another system calling it, and works across Google Cloud Storage, Qdrant and WordPress. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 44 steps, 1 branch: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAIRetrieval

Download free
44 stepsLarge: read it before trusting it with anything live
1Branch: places the flow splits
0Loops or waits
3Services it connects to

The flow

Starts it 3Model 23Logic 14Service 3

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

  1. 1Embeddings OpenAIEmbeddings Open AiModel
  2. 2Recursive Character Text SplitterText Splitter Recursive Character Text SplitterModel
  3. 3Manual IndexingManual triggerStarts it
  4. 4Build context from Qdrant results1CodeLogic
  5. 5WebhookWebhookStarts it
  6. 6Reranker CohereReranker CohereModel
  7. 7Structured Output ParserOutput Parser StructuredModel
  8. 8OpenAI Chat ModelLm Chat Open AiModel
  9. 9Reranker Cohere3Reranker CohereModel
  10. 10Embeddings OpenAI3Embeddings Open AiModel
  11. 11Structured Output Parser3Output Parser StructuredModel
  12. 12OpenAI Chat Model3Lm Chat Open AiModel
  13. 13OpenAI Chat Model1Lm Chat Open AiModel
  14. 14Embeddings OpenAI4Embeddings Open AiModel
  15. 15Embeddings OpenAI5Embeddings Open AiModel
  16. 16Embeddings OpenAI1Embeddings Open AiModel
  17. 17Qdrant Vector Store1Vector Store QdrantModel
  18. 18Default Data LoaderDocument Default Data LoaderModel
  19. 19WP Get all postWordpressService
  20. 20AI AgentAgentModel
  21. 21Code-Request_ParsingCodeLogic
  22. 22Qdrant Search (Collection_name)Vector Store QdrantModel
  23. 23AI Agent3AgentModel
  24. 24AI Agent - SKILLSAgentModel
  25. 25MongoDB Atlas Vector SKILLSVector Store Mongo DBAtlasModel
  26. 26MongoDB Atlas Vector PROFILEVector Store Mongo DBAtlasModel
  27. 27Prepare Documents for IndexingCodeLogic
  28. 28Code-Response_ParsingCodeLogic
  29. 29OpenAI Intent RouterOpen AiModel
  30. 30Build context from Qdrant resultsCodeLogic
  31. 31url_enCodeLogic
  32. 32Code in JavaScriptCodeLogic
  33. 33Code in JavaScript3CodeLogic
  34. 34Code: remove followupCodeLogic
  35. 35SwitchSwitchLogic
  36. 36Respond to WebhookRespond To WebhookStarts it
  37. 37SmallTalk ResponseOpen AiModel
  38. 38Crypto: IP HashCryptoService
  39. 39Code-Smalltalk_responseCodeLogic
  40. 40Set: dateSetLogic
  41. 41set: ObjectName_Date/Folder & dataSetLogic
  42. 42Code: parsingCodeLogic
  43. 43GCS: Object_LogGoogle Cloud StorageService

How it's built

Starts on
Another system calling it
Steps
44, with 1 branch
Size
Large: read it before trusting it with anything live
Connects to
Google Cloud Storage, Qdrant, WordPress
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 Cloud Storage, Qdrant and WordPress 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 44 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 44 steps before you point it at anything that matters.