# Run Bunker Guard NPC chat and RAG lore checks with Gemini: n8n workflow

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

Source: https://millionrounds.com/workflow/run-bunker-guard-npc-chat-and-rag-lore-checks-with-gemini (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)

# Run Bunker Guard NPC chat and RAG lore checks with Gemini

Started by someone opening a chat with it, and works across Google Drive and in-memory vectors. It puts Gemini behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 19 steps, 1 branch: a working afternoon to understand properly.

Medium Calls a model: Gemini Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Frun-bunker-guard-npc-chat-and-rag-lore-checks-with-gemini)

**19 steps** Medium: a working afternoon

**1** Branch: places the flow splits

**0** Loops or waits

**2** Services it connects to

## The flow

Starts it 4 Model 13 Logic 1 Service 1

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

- 1 **Webhook** Webhook *Starts it*
- 2 **Google Gemini Chat Model** Lm Chat Google Gemini *Model*
- 3 **Simple Memory** Memory Buffer Window *Model*
- 4 **Recursive Character Text Splitter** Text Splitter Recursive Character Text Splitter *Model*
- 5 **Embeddings Google Gemini** Embeddings Google Gemini *Model*
- 6 **When chat message received** Chat trigger *Starts it*
- 7 **When clicking ‘Execute workflow’** Manual trigger *Starts it*
- 8 **Window Buffer Memory** Memory Buffer Window *Model*
- 9 **Switch** Switch *Logic*
- 10 **npc creator** Agent *Model*
- 11 **DayClue creator** Agent *Model*
- 12 **Chat Generator** Agent *Model*
- 13 **Database_Bunker** Tool Vector Store *Model*
- 14 **AI Agent** Agent *Model*
- 15 **Default Data Loader** Document Default Data Loader *Model*
- 16 **Simple Vector Store1** Vector Store In Memory *Model*
- 17 **Simple Vector Store** Vector Store In Memory *Model*
- 18 **Download File From Google Drive** Google Drive *Service*
- 19 **Respond to Webhook** Respond To Webhook *Starts it*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 19, with 1 branch
- **Size:** Medium: a working afternoon
- **Connects to:** Google Drive, in-memory vectors
- **Model:** Gemini
- **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 in-memory vectors accounts, and a key for Gemini. 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 Gemini. 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%2Frun-bunker-guard-npc-chat-and-rag-lore-checks-with-gemini)
- **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)[in-memory vectors](https://millionrounds.com/workflows?service=in-memory+vectors#library)

## Workflows like it

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

- [**Generate 100+ ad variations from one image** 19 steps · calls a model · Google Drive](https://millionrounds.com/workflow/generate-100-ad-variations-from-one-image)
- [**Generate Instagram news carousels from RSS feeds with OpenAI** 19 steps · calls a model · Google Drive, RSS](https://millionrounds.com/workflow/generate-instagram-news-carousels-from-rss-feeds-with-openai)
- [**Music Producer Chatbot with Gemini and Suno** 19 steps · calls a model · Google Drive](https://millionrounds.com/workflow/music-producer-chatbot-with-gemini-and-suno)
- [**Score inspection defects and draft repair packets with OpenAI** 19 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/score-inspection-defects-and-draft-repair-packets-with-opena)
- [**Answer restaurant voice queries with ElevenLabs and OpenAI** 18 steps · calls a model · Google Drive, Qdrant](https://millionrounds.com/workflow/answer-restaurant-voice-queries-with-elevenlabs-and-openai)
- [**Create AI-generated books with OpenAI and DALL-E** 18 steps · calls a model · Google Drive, S3](https://millionrounds.com/workflow/create-ai-generated-books-with-openai-and-dall-e)