# Build an All-Source Knowledge Assistant with Claude and RAG: n8n workflow

> Started by someone opening a chat with it, and works across Google Drive and Supabase vectors.

Source: https://millionrounds.com/workflow/build-an-all-source-knowledge-assistant-with-claude-and-rag (Millionrounds; every figure on the page links to its filing or article)

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

# Build an All-Source Knowledge Assistant with Claude and RAG

Started by someone opening a chat with it, and works across Google Drive and Supabase vectors. It puts Claude and OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 30 steps, 2 branches: large, and worth reading before you trust it with anything live.

Large Calls a model: Claude, OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-an-all-source-knowledge-assistant-with-claude-and-rag)

**30 steps** Large: read it before trusting it with anything live

**2** Branches: places the flow splits

**0** Loops or waits

**2** Services it connects to

## The flow

Starts it 4 Model 15 Logic 4 Service 7

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

- 1 **When chat message received** Chat trigger *Starts it*
- 2 **Postgres Chat Memory** Memory Postgres Chat *Model*
- 3 **Embeddings OpenAI** Embeddings Open Ai *Model*
- 4 **Reranker Cohere** Reranker Cohere *Model*
- 5 **Anthropic Chat Model** Lm Chat Anthropic *Model*
- 6 **structured data** Postgres Tool *Service*
- 7 **When clicking ‘Execute workflow’** Manual trigger *Starts it*
- 8 **Recursive Character Text Splitter1** Text Splitter Recursive Character Text Splitter *Model*
- 9 **Embeddings OpenAI1** Embeddings Open Ai *Model*
- 10 **Think** Tool Think *Model*
- 11 **When Executed by Another Workflow** Execute Workflow trigger *Starts it*
- 12 **Read File From GDrive** Tool Workflow *Model*
- 13 **Search Files from Gdrive** Google Drive Tool *Service*
- 14 **search about any doc in google drive** Mcp Client Tool *Model*
- 15 **Message a model in Perplexity** Perplexity Tool *Service*
- 16 **Knowledge Agent** Agent *Model*
- 17 **General knowledge** Vector Store Supabase *Model*
- 18 **Download file** Google Drive *Service*
- 19 **Default Data Loader1** Document Default Data Loader *Model*
- 20 **Add to Supabase Vector DB** Vector Store Supabase *Model*
- 21 **Operation** Switch *Logic*
- 22 **Google Drive MCP Server** Mcp trigger *Starts it*
- 23 **Download File1** Google Drive *Service*
- 24 **FileType** Switch *Logic*
- 25 **Extract from PDF** Extract From File *Service*
- 26 **Extract from CSV** Extract From File *Service*
- 27 **Analyse Image** Open Ai *Model*
- 28 **Transcribe Audio** Open Ai *Model*
- 29 **Get PDF Response** Set *Logic*
- 30 **Get CSV Response** Set *Logic*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 30, with 2 branches
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Google Drive, Supabase vectors
- **Model:** Claude, 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 Supabase vectors accounts, and a key for Claude 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 Claude 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 30 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 30 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-an-all-source-knowledge-assistant-with-claude-and-rag)
- **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)[Supabase vectors](https://millionrounds.com/workflows?service=Supabase+vectors#library)

## Workflows like it

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

- [**Voice memos into daily journals & tasks with Gemini** 29 steps · calls a model · Google Drive](https://millionrounds.com/workflow/voice-memos-into-daily-journals-and-tasks-with-gemini)
- [**AI voice & text note-taking with LINE Messaging** 27 steps · calls a model · Gmail, Supabase vectors](https://millionrounds.com/workflow/ai-voice-and-text-note-taking-with-line-messaging)
- [**Build a dual-stage RAG chat assistant with Google Drive** 27 steps · calls a model · Google Drive, Pinecone](https://millionrounds.com/workflow/build-a-dual-stage-rag-chat-assistant-with-google-drive)
- [**Place products on AI generated backgrounds with Google Imagen** 27 steps · calls a model · Google Drive](https://millionrounds.com/workflow/place-products-on-ai-generated-backgrounds-with-google-image)
- [**Voice AI chatbot with OpenAI and RAG** 27 steps · calls a model · Google Drive, Qdrant](https://millionrounds.com/workflow/voice-ai-chatbot-with-openai-and-rag)
- [**Generate LinkedIn carousel images from text with Mistral** 26 steps · calls a model · Google Drive, S3](https://millionrounds.com/workflow/generate-linkedin-carousel-images-from-text-with-mistral)