# Gmail assistant with OpenAI: n8n workflow template

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

Source: https://millionrounds.com/workflow/gmail-assistant-with-openai (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)

# Gmail assistant with OpenAI

Started by someone opening a chat with it, and works across Gmail and Qdrant. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 20 steps, 1 loop or waits: a working afternoon to understand properly.

Medium Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fgmail-assistant-with-openai)

**20 steps** Medium: a working afternoon

**0** Branches: places the flow splits

**1** Loop or waits

**2** Services it connects to

## The flow

Starts it 3 Model 13 Logic 2 Service 2

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

- 1 **OpenAI Chat Model** Lm Chat Open Ai *Model*
- 2 **When clicking ‘Test workflow’** Manual trigger *Starts it*
- 3 **Embeddings OpenAI5** Embeddings Open Ai *Model*
- 4 **Embeddings OpenAI11** Embeddings Open Ai *Model*
- 5 **When chat message received** Chat trigger *Starts it*
- 6 **Simple Memory** Memory Buffer Window *Model*
- 7 **New Email** Gmail trigger *Starts it*
- 8 **Split emails** Text Splitter Character Text Splitter *Model*
- 9 **Split emails1** Text Splitter Character Text Splitter *Model*
- 10 **Embeddings OpenAI** Embeddings Open Ai *Model*
- 11 **RAG Agent** Agent *Model*
- 12 **Get all emails** Gmail *Service*
- 13 **Store Emails in Vector DB** Vector Store Qdrant *Model*
- 14 **Store Emails in Vector DB1** Vector Store Qdrant *Model*
- 15 **Get new Email Body** Gmail *Service*
- 16 **Set proper metadata** Document Default Data Loader *Model*
- 17 **Set proper metadata1** Document Default Data Loader *Model*
- 18 **Qdrant Email Vector Store** Vector Store Qdrant *Model*
- 19 **Refactor Email Body data** Code *Logic*
- 20 **Loop over all emails** Split In Batches *Logic*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 20, 1 loop or waits
- **Size:** Medium: a working afternoon
- **Connects to:** Gmail, 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 Gmail 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 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. 20 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 20 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%2Fgmail-assistant-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.

[Gmail](https://millionrounds.com/workflows?service=Gmail#library)[Qdrant](https://millionrounds.com/workflows?service=Qdrant#library)

## Workflows like it

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

- [**Draft customer-facing changelogs from merged GitHub PRs** 20 steps · calls a model · GitHub, Gmail](https://millionrounds.com/workflow/draft-customer-facing-changelogs-from-merged-github-prs)
- [**Send an AI news digest email daily from RSS feeds with Gemini** 20 steps · calls a model · Gmail, RSS](https://millionrounds.com/workflow/send-an-ai-news-digest-email-daily-from-rss-feeds-with-gemin)
- [**Agile project generator with ClickUp and OpenAI** 21 steps · calls a model · ClickUp, Gmail](https://millionrounds.com/workflow/agile-project-generator-with-clickup-and-openai)
- [**Build an on-premises AI Kaggle competition assistant** 21 steps · calls a model · Qdrant](https://millionrounds.com/workflow/build-an-on-premises-ai-kaggle-competition-assistant)
- [**Design and apply Gmail label systems with OpenAI** 21 steps · calls a model · Gmail](https://millionrounds.com/workflow/design-and-apply-gmail-label-systems-with-openai)
- [**Parse Gmail inbox and transform into Todoist tasks with OpenAI** 21 steps · calls a model · Email, Gmail](https://millionrounds.com/workflow/parse-gmail-inbox-and-transform-into-todoist-tasks-with-open)