Automation library · AI assistants

Find the most relevant workflow templates with RAG and Qdrant

Started by someone opening a chat with it, and works across Qdrant. It puts Gemini behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 18 steps, 1 branch: a working afternoon to understand properly.

MediumCalls a model: GeminiRetrieval

Download free
18 stepsMedium: a working afternoon
1Branch: places the flow splits
0Loops or waits
1Service it connects to

The flow

Starts it 2Model 8Logic 7Service 1

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

  1. 1Start Ingestion (Manual Trigger)Manual triggerStarts it
  2. 2Generate EmbeddingsEmbeddings Google GeminiModel
  3. 3Load Documents for EmbeddingDocument Default Data LoaderModel
  4. 4Chat Input TriggerChat triggerStarts it
  5. 5LLM (Gemini Chat Model)Lm Chat Google GeminiModel
  6. 6Conversation MemoryMemory Buffer WindowModel
  7. 7Query Embedding (Gemini)Embeddings Google GeminiModel
  8. 8Generate Search QueriesCodeLogic
  9. 9Store in Vector DB (Qdrant)Vector Store QdrantModel
  10. 10AI AgentAgentModel
  11. 11Retriever (Qdrant)Vector Store QdrantModel
  12. 12Split QueriesSplit OutLogic
  13. 13Prepare Search ParamsSetLogic
  14. 14Fetch Templates from n8n APIHttp RequestService
  15. 15Check If Results ExistIfLogic
  16. 16Split WorkflowsSplit OutLogic
  17. 17Format for Embedding (Content + Metadata)CodeLogic
  18. 18Remove Duplicate TemplatesCodeLogic

How it's built

Starts on
Someone opening a chat with it
Steps
18, with 1 branch
Size
Medium: a working afternoon
Connects to
Qdrant
Model
Gemini
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 Gemini. 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 Gemini. 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. 18 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 18 steps before you point it at anything that matters.