Automation library · AI assistants

Build a RAG knowledge assistant with Google Drive and OpenAI

Started by another system calling it, and works across Google Drive and Pinecone. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 16 steps: a working afternoon to understand properly.

MediumCalls a model: OpenAIRetrieval

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

The flow

Starts it 3Model 11Logic 1Service 1

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

  1. 1Drive File WatcherGoogle Drive triggerStarts it
  2. 2Split Text into ChunksText Splitter Character Text SplitterModel
  3. 3Generate Embeddings (Ingest)Embeddings Open AiModel
  4. 4User Query WebhookWebhookStarts it
  5. 5Primary LLM (Agent Brain)Lm Chat Open AiModel
  6. 6Conversation Memory BufferMemory Buffer WindowModel
  7. 7Generate Embeddings (Query)Embeddings Open AiModel
  8. 8Secondary LLM (Retriever QA)Lm Chat Open AiModel
  9. 9Extract File MetadataSetLogic
  10. 10Parse Document ContentDocument Default Data LoaderModel
  11. 11Ingest into Pinecone Vector DBVector Store PineconeModel
  12. 12AI AgentAgentModel
  13. 13Retrieve Vectors from PineconeVector Store PineconeModel
  14. 14Vector Search QA ToolTool Vector StoreModel
  15. 15Download File from DriveGoogle DriveService
  16. 16Respond to WebhookRespond To WebhookStarts it

How it's built

Starts on
Another system calling it
Steps
16
Size
Medium: a working afternoon
Connects to
Google Drive, Pinecone
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 Drive and Pinecone 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?

Plan an afternoon. 16 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 16 steps before you point it at anything that matters.