Build a PDF Document RAG System with Mistral and Qdrant: n8n workflow

Build a PDF Document RAG System with Mistral and Qdrant

Started by someone opening a chat with it, and works across Google Drive and Qdrant. It puts Gemini and OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 29 steps, 3 loops or waits: large, and worth reading before you trust it with anything live.

LargeCalls a model: Gemini, OpenAIRetrieval

The flow

Starts it 3Model 11Logic 8Service 7

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

1When clicking ‘Test workflow’Manual triggerStarts it
2Embeddings OpenAIEmbeddings Open AiModel
3Token SplitterText Splitter Token SplitterModel
4When chat message receivedChat triggerStarts it
5Google Gemini Chat ModelLm Chat Google GeminiModel
6Embeddings OpenAI1Embeddings Open AiModel
7When Executed by Another WorkflowExecute Workflow triggerStarts it
8Create collectionHttp RequestService
9Google Gemini Chat Model1Lm Chat Google GeminiModel
10Refresh collectionHttp RequestService
11Qdrant Vector StoreVector Store QdrantModel
12Default Data LoaderDocument Default Data LoaderModel
13Question and Answer ChainChain Retrieval QaModel
14Qdrant Vector Store1Vector Store QdrantModel
15Get PDFGoogle DriveService
16Summarization ChainChain SummarizationModel
17Search PDFsGoogle DriveService
18WaitWaitLogic
19Vector Store RetrieverRetriever Vector StoreModel
20Mistral UploadHttp RequestService
21Set summarySetLogic
22Loop Over Items1Split In BatchesLogic
23Loop Over ItemsSplit In BatchesLogic
24Mistral Signed URLHttp RequestService
25Edit Fields1SetLogic
26Set pageSetLogic
27Mistral DOC OCRHttp RequestService
28Execute WorkflowExecute WorkflowLogic
29CodeCodeLogic

How it's built

Starts on: Someone opening a chat with it
Steps: 29, 3 loops or waits
Size: Large: read it before trusting it with anything live
Connects to: Google Drive, Qdrant
Model: Gemini, 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 Qdrant accounts, and a key for Gemini 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 Gemini 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 29 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 29 steps before you point it at anything that matters.