# Evaluation metric example: RAG document relevance with OpenAI: n8n workflow

> Started by someone opening a chat with it, and works across Google Sheets and in-memory vectors.

Source: https://millionrounds.com/workflow/evaluation-metric-example-rag-document-relevance-with-openai (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)

# Evaluation metric example: RAG document relevance with OpenAI

Started by someone opening a chat with it, and works across Google Sheets and in-memory vectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 19 steps: a working afternoon to understand properly.

Medium Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fevaluation-metric-example-rag-document-relevance-with-openai)

**19 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 9 Logic 4 Service 3

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

- 1 **When fetching a dataset row** Evaluation trigger *Starts it*
- 2 **When chat message received** Chat trigger *Starts it*
- 3 **Embeddings OpenAI** Embeddings Open Ai *Model*
- 4 **Recursive Character Text Splitter** Text Splitter Recursive Character Text Splitter *Model*
- 5 **When clicking ‘Execute workflow’** Manual trigger *Starts it*
- 6 **OpenAI Chat Model** Lm Chat Open Ai *Model*
- 7 **Embeddings OpenAI1** Embeddings Open Ai *Model*
- 8 **Match chat format** Set *Logic*
- 9 **AI Agent** Agent *Model*
- 10 **Simple Vector Store** Vector Store In Memory *Model*
- 11 **Default Data Loader** Document Default Data Loader *Model*
- 12 **Get dataset** Google Sheets *Service*
- 13 **Simple Vector Store1** Vector Store In Memory *Model*
- 14 **Evaluating?** Evaluation *Service*
- 15 **Remove Duplicates** Remove Duplicates *Logic*
- 16 **Extract documents** Set *Logic*
- 17 **Return chat response** No Op *Logic*
- 18 **Calculate doc relevance metric** Open Ai *Model*
- 19 **Set metrics** Evaluation *Service*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 19
- **Size:** Medium: a working afternoon
- **Connects to:** Google Sheets, in-memory vectors
- **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 Sheets and in-memory vectors accounts, 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. 19 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 19 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%2Fevaluation-metric-example-rag-document-relevance-with-openai)
- **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 Sheets](https://millionrounds.com/workflows?service=Google+Sheets#library)[in-memory vectors](https://millionrounds.com/workflows?service=in-memory+vectors#library)

## Workflows like it

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

- [**Scrape detailed GitHub profiles to Google Sheets** 19 steps · Google Sheets, Slack](https://millionrounds.com/workflow/scrape-detailed-github-profiles-to-google-sheets)
- [**Answer product queries with WhatsApp and OpenAI** 18 steps · calls a model · WhatsApp, in-memory vectors](https://millionrounds.com/workflow/answer-product-queries-with-whatsapp-and-openai)
- [**Build a Reels swipe file from Instagram with Apify and Groq** 18 steps · calls a model · Google Sheets, Telegram](https://millionrounds.com/workflow/build-a-reels-swipe-file-from-instagram-with-apify-and-groq)
- [**Financial document extraction from Gmail to Google Sheets** 20 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/financial-document-extraction-from-gmail-to-google-sheets)
- [**Generate DOCX documents from Gmail with OpenAI** 20 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/generate-docx-documents-from-gmail-with-openai)
- [**Organize handwritten memos from LINE with Gemini and Drive** 20 steps · calls a model · Google Drive, Google Sheets](https://millionrounds.com/workflow/organize-handwritten-memos-from-line-with-gemini-and-drive)