Automation library · Documents and files

RAG OCR for PDFs with OpenAI and Google Drive

Started by someone opening a chat with it, and works across Google Drive and in-memory vectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 11 steps: a working afternoon to understand properly.

MediumCalls a model: OpenAIRetrieval

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

The flow

Starts it 2Model 7Logic 1Service 1

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

  1. 1Google Drive TriggerGoogle Drive triggerStarts it
  2. 2Embeddings OpenAIEmbeddings Open AiModel
  3. 3Default Data LoaderDocument Default Data LoaderModel
  4. 4When chat message receivedChat triggerStarts it
  5. 5OpenAI Chat ModelLm Chat Open AiModel
  6. 6Google Drive - DownloadGoogle DriveService
  7. 7Simple Vector StoreVector Store In MemoryModel
  8. 8Query Data ToolVector Store In MemoryModel
  9. 9AI AgentAgentModel
  10. 10Extract textMistral AiModel
  11. 11Code - ChunkCodeLogic

How it's built

Starts on
Someone opening a chat with it
Steps
11
Size
Medium: a working afternoon
Connects to
Google Drive, in-memory vectors
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 in-memory vectors accounts, and a key for 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 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. 11 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 11 steps before you point it at anything that matters.