Automation library · AI assistants

Ultimate RAG system (Query data and tables) with Claude

Started by someone opening a chat with it, and works across Pinecone and Supabase vectors. It puts Claude and OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 21 steps: large, and worth reading before you trust it with anything live.

LargeCalls a model: Claude, OpenAIRetrieval

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

The flow

Starts it 2Model 19

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

  1. 1Embeddings HuggingFace InferenceEmbeddings Hugging Face InferenceModel
  2. 2Recursive Character Text Splitter1Text Splitter Recursive Character Text SplitterModel
  3. 3On form submissionForm triggerStarts it
  4. 4Embeddings HuggingFace Inference1Embeddings Hugging Face InferenceModel
  5. 5When chat message receivedChat triggerStarts it
  6. 6OpenAI Chat ModelLm Chat Open AiModel
  7. 7OpenAI Chat Model1Lm Chat Open AiModel
  8. 8Simple MemoryMemory Buffer WindowModel
  9. 9Reranker CohereReranker CohereModel
  10. 10ThinkTool ThinkModel
  11. 11Anthropic Chat ModelLm Chat AnthropicModel
  12. 12Embeddings OpenAI4Embeddings Open AiModel
  13. 13Postgres Chat MemoryMemory Postgres ChatModel
  14. 14OpenAI Chat Model2Lm Chat Open AiModel
  15. 15Pinecone Vector StoreVector Store PineconeModel
  16. 16Default Data Loader1Document Default Data LoaderModel
  17. 17VectorVector Store PineconeModel
  18. 18AI Agent1AgentModel
  19. 19Re-RankerAgent ToolModel
  20. 20Supabase Vector Store5Vector Store SupabaseModel
  21. 21AI AgentAgentModel

How it's built

Starts on
Someone opening a chat with it
Steps
21
Size
Large: read it before trusting it with anything live
Connects to
Pinecone, Supabase vectors
Model
Claude, 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 Pinecone and Supabase vectors accounts, and a key for Claude and 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 Claude and 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 21 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 21 steps before you point it at anything that matters.