# Build a document QA system with RAG and Milvus: n8n workflow

> Started by someone opening a chat with it, and works across Google Drive. It puts OpenAI behind a retrieval step, so answers are drawn from documents you...

Source: https://millionrounds.com/workflow/build-a-document-qa-system-with-rag-and-milvus (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Documents and files](https://millionrounds.com/workflows?category=Documents+and+files#library)

# Build a document QA system with RAG and Milvus

Started by someone opening a chat with it, and works across Google Drive. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 13 steps: a working afternoon to understand properly.

Medium Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-a-document-qa-system-with-rag-and-milvus)

**13 steps** Medium: a working afternoon

**0** Branches: places the flow splits

**0** Loops or waits

**1** Service it connects to

## The flow

Starts it 2 Model 9 Service 2

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

- 1 **Embeddings Cohere** Embeddings Cohere *Model*
- 2 **When chat message received** Chat trigger *Starts it*
- 3 **Watch New Files** Google Drive trigger *Starts it*
- 4 **OpenAI 4o** Lm Chat Open Ai *Model*
- 5 **Memory** Memory Buffer Window *Model*
- 6 **Cohere embeddings** Embeddings Cohere *Model*
- 7 **Set Chunks** Text Splitter Recursive Character Text Splitter *Model*
- 8 **Insert into Milvus** Vector Store Milvus *Model*
- 9 **RAG Agent** Agent *Model*
- 10 **Download New** Google Drive *Service*
- 11 **Retrieve from Milvus** Vector Store Milvus *Model*
- 12 **Default Data Loader** Document Default Data Loader *Model*
- 13 **Extract from File** Extract From File *Service*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 13
- **Size:** Medium: a working afternoon
- **Connects to:** Google Drive
- **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 account, 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. 13 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 13 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-a-document-qa-system-with-rag-and-milvus)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Google Drive](https://millionrounds.com/workflows?service=Google+Drive#library)

## Workflows like it

Also documents and files, with the same services where possible, closest in size first.

- [**Automate multi-language text translation with OpenAI** 13 steps · calls a model · Google Drive](https://millionrounds.com/workflow/automate-multi-language-text-translation-with-openai)
- [**Build a PDF Q&A system with LlamaIndex and OpenAI** 13 steps · calls a model · Google Drive, Pinecone](https://millionrounds.com/workflow/build-a-pdf-q-and-a-system-with-llamaindex-and-openai)
- [**Build a retrieval-based chatbot with Telegram and OpenAI** 13 steps · calls a model · Google Drive, Telegram](https://millionrounds.com/workflow/build-a-retrieval-based-chatbot-with-telegram-and-openai)
- [**Document-based AI chatbot with RAG and OpenAI** 13 steps · calls a model · Google Drive, Supabase vectors](https://millionrounds.com/workflow/document-based-ai-chatbot-with-rag-and-openai)
- [**Google Drive AI Document Classifier with DeepSeek** 13 steps · calls a model · Google Drive](https://millionrounds.com/workflow/google-drive-ai-document-classifier-with-deepseek)
- [**Google Drive AI documents classifier with DeepSeek** 13 steps · calls a model · Google Drive](https://millionrounds.com/workflow/google-drive-ai-documents-classifier-with-deepseek)