# My solution for the "Agentic Arena Community Contest" with RAG: n8n workflow

> Started by an event in a connected app, and works across Google Drive and Qdrant. It puts OpenAI behind a retrieval step, so answers are drawn from...

Source: https://millionrounds.com/workflow/my-solution-for-the-agentic-arena-community-contest-with-rag (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)

# My solution for the "Agentic Arena Community Contest" with RAG

Started by an event in a connected app, and works across Google Drive and Qdrant. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 34 steps, 3 loops or waits: large, and worth reading before you trust it with anything live.

Large Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fmy-solution-for-the-agentic-arena-community-contest-with-rag)

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

**0** Branches: places the flow splits

**3** Loops or waits

**2** Services it connects to

## The flow

Starts it 3 Model 12 Logic 9 Service 10

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

- 1 **Eval Set** Evaluation trigger *Starts it*
- 2 **LLM as a Judge** Lm Chat Open Ai *Model*
- 3 **When clicking ‘Execute workflow’** Manual trigger *Starts it*
- 4 **Embeddings OpenAI** Embeddings Open Ai *Model*
- 5 **When Executed by Another Workflow** Execute Workflow trigger *Starts it*
- 6 **Create collection** Http Request *Service*
- 7 **Character Text Splitter** Text Splitter Character Text Splitter *Model*
- 8 **Simple Memory** Memory Buffer Window *Model*
- 9 **Reranker Cohere** Reranker Cohere *Model*
- 10 **Embeddings OpenAI1** Embeddings Open Ai *Model*
- 11 **OpenAI Chat Model** Lm Chat Open Ai *Model*
- 12 **Eval Input** Set *Logic*
- 13 **Run Evaluation** Evaluation *Service*
- 14 **Refresh collection** Http Request *Service*
- 15 **Qdrant Vector Store** Vector Store Qdrant *Model*
- 16 **Get PDF** Google Drive *Service*
- 17 **Default Data Loader** Document Default Data Loader *Model*
- 18 **AI Agent** Agent *Model*
- 19 **RAG** Vector Store Qdrant *Model*
- 20 **Filter Empty Rows** Filter *Logic*
- 21 **Save Eval** Evaluation *Service*
- 22 **Search PDFs** Google Drive *Service*
- 23 **Wait** Wait *Logic*
- 24 **Mistral Upload** Http Request *Service*
- 25 **Only if we are evaluating** Evaluation *Service*
- 26 **Loop Over Items1** Split In Batches *Logic*
- 27 **Loop Over Items** Split In Batches *Logic*
- 28 **Mistral Signed URL** Http Request *Service*
- 29 **Respond to Chat** Chat *Model*
- 30 **Get File ID** Set *Logic*
- 31 **Set page** Set *Logic*
- 32 **Mistral DOC OCR** Http Request *Service*
- 33 **Call 'Agent Arena'** Execute Workflow *Logic*
- 34 **Code** Code *Logic*

## How it's built

- **Starts on:** An event in a connected app
- **Steps:** 34, 3 loops or waits
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Google Drive, Qdrant
- **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 Qdrant accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an event in a connected app.

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?

Take your time. At 34 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 34 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%2Fmy-solution-for-the-agentic-arena-community-contest-with-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)[Qdrant](https://millionrounds.com/workflows?service=Qdrant#library)

## Workflows like it

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

- [**Breakdown documents into study notes with Qdrant** 35 steps · calls a model · Qdrant](https://millionrounds.com/workflow/breakdown-documents-into-study-notes-with-qdrant)
- [**Send, chase, and e-signature with Airtable and TurboDocx** 33 steps · Airtable, Gmail](https://millionrounds.com/workflow/send-chase-and-e-signature-with-airtable-and-turbodocx)
- [**AI knowledge assistant with Gemini and OpenAI** 32 steps · calls a model · Google Drive, Pinecone](https://millionrounds.com/workflow/ai-knowledge-assistant-with-gemini-and-openai)
- [**Document-based RAG chat assistant with Google Drive** 32 steps · calls a model · Google Drive, Supabase](https://millionrounds.com/workflow/document-based-rag-chat-assistant-with-google-drive)
- [**PDF RAG agent with Telegram** 32 steps · calls a model · Google Drive, Telegram](https://millionrounds.com/workflow/pdf-rag-agent-with-telegram)
- [**Sync Google Drive documents to Pinecone RAG with Gemini** 32 steps · calls a model · Google Drive, Google Sheets](https://millionrounds.com/workflow/sync-google-drive-documents-to-pinecone-rag-with-gemini)