# Create a private document Q&A system with Llama3 and Postgres: n8n workflow

> 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...

Source: https://millionrounds.com/workflow/create-a-private-document-q-and-a-system-with-llama3-and-pos (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Content](https://millionrounds.com/workflows?category=Content#library)

# 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.

Medium Calls a model: a local model Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fcreate-a-private-document-q-and-a-system-with-llama3-and-pos)

**17 steps** Medium: a working afternoon

**0** Branches: places the flow splits

**0** Loops or waits

**2** Services it connects to

## The flow

Starts it 3 Model 11 Logic 1 Service 2

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

- 1 **When chat message received** Chat trigger *Starts it*
- 2 **Ollama Chat Model** Lm Chat Ollama *Model*
- 3 **Postgres Chat Memory** Memory Postgres Chat *Model*
- 4 **Ollama Model** Lm Ollama *Model*
- 5 **Embeddings Ollama** Embeddings Ollama *Model*
- 6 **File Created** Google Drive trigger *Starts it*
- 7 **File Updated** Google Drive trigger *Starts it*
- 8 **Recursive Character Text Splitter** Text Splitter Recursive Character Text Splitter *Model*
- 9 **Embeddings Ollama1** Embeddings Ollama *Model*
- 10 **AI Agent** Agent *Model*
- 11 **Answer questions with a vector store** Tool Vector Store *Model*
- 12 **Qdrant Vector Store** Vector Store Qdrant *Model*
- 13 **Set File ID** Set *Logic*
- 14 **Default Data Loader** Document Default Data Loader *Model*
- 15 **Qdrant Vector Store Insert** Vector Store Qdrant *Model*
- 16 **Download File** Google Drive *Service*
- 17 **Extract Document Text** Extract From File *Service*

## 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.

## 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%2Fcreate-a-private-document-q-and-a-system-with-llama3-and-pos)
- **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)[Qdrant](https://millionrounds.com/workflows?service=Qdrant#library)

## Workflows like it

Also content, with the same services where possible, closest in size first.

- [**Auto-generate LinkedIn content with Gemini** 17 steps · calls a model · Google Drive, Google Sheets](https://millionrounds.com/workflow/auto-generate-linkedin-content-with-gemini)
- [**Create YouTube videos with OpenAI and ElevenLabs** 17 steps · calls a model · Google Drive](https://millionrounds.com/workflow/create-youtube-videos-with-openai-and-elevenlabs)
- [**Create daily AI and blockchain social posts with SerpAPI** 17 steps · calls a model · Google Drive, Google Sheets](https://millionrounds.com/workflow/create-daily-ai-and-blockchain-social-posts-with-serpapi)
- [**Daily space image gallery with Google Drive** 17 steps · calls a model · Google Drive, Slack](https://millionrounds.com/workflow/daily-space-image-gallery-with-google-drive)
- [**Generate multilingual audio content with OpenAI and ElevenLabs** 17 steps · calls a model · Google Drive, Slack](https://millionrounds.com/workflow/generate-multilingual-audio-content-with-openai-and-elevenla)
- [**Google Sheets to AI Image Generation with Drive Storage** 17 steps · calls a model · Google Drive, Google Sheets](https://millionrounds.com/workflow/google-sheets-to-ai-image-generation-with-drive-storage)