Automation library · Content

Create a private document Q&A system with Llama3 and Postgres

Started by someone opening a chat with it, and works across Google Drive and Qdrant. It puts a local model behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 17 steps: a working afternoon to understand properly.

MediumCalls a model: a local modelRetrieval

Download free
17 stepsMedium: a working afternoon
0Branches: places the flow splits
0Loops or waits
2Services it connects to

The flow

Starts it 3Model 11Logic 1Service 2

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

  1. 1When chat message receivedChat triggerStarts it
  2. 2Ollama Chat ModelLm Chat OllamaModel
  3. 3Postgres Chat MemoryMemory Postgres ChatModel
  4. 4Ollama ModelLm OllamaModel
  5. 5Embeddings OllamaEmbeddings OllamaModel
  6. 6File CreatedGoogle Drive triggerStarts it
  7. 7File UpdatedGoogle Drive triggerStarts it
  8. 8Recursive Character Text SplitterText Splitter Recursive Character Text SplitterModel
  9. 9Embeddings Ollama1Embeddings OllamaModel
  10. 10AI AgentAgentModel
  11. 11Answer questions with a vector storeTool Vector StoreModel
  12. 12Qdrant Vector StoreVector Store QdrantModel
  13. 13Set File IDSetLogic
  14. 14Default Data LoaderDocument Default Data LoaderModel
  15. 15Qdrant Vector Store InsertVector Store QdrantModel
  16. 16Download FileGoogle DriveService
  17. 17Extract Document TextExtract From FileService

How it's built

Starts on
Someone opening a chat with it
Steps
17
Size
Medium: a working afternoon
Connects to
Google Drive, Qdrant
Model
a local model
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 Drive and Qdrant accounts, and a key for a local model. 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 a local model. 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. 17 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 17 steps before you point it at anything that matters.