# Run a RAG support copilot with Claude and OpenAI: n8n workflow

> Started by someone opening a chat with it, and works across Gmail, in-memory vectors and n8n data table.

Source: https://millionrounds.com/workflow/run-a-rag-support-copilot-with-claude-and-openai (Millionrounds; every figure on the page links to its filing or article)

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

# Run a RAG support copilot with Claude and OpenAI

Started by someone opening a chat with it, and works across Gmail, in-memory vectors and n8n data table. It puts Claude and OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 13 steps: a working afternoon to understand properly.

Medium Calls a model: Claude, OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Frun-a-rag-support-copilot-with-claude-and-openai)

**13 steps** Medium: a working afternoon

**0** Branches: places the flow splits

**0** Loops or waits

**3** Services it connects to

## The flow

Starts it 2 Model 9 Service 2

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

- 1 **Knowledge Ingest Form** Form trigger *Starts it*
- 2 **Ingest Embeddings** Embeddings Open Ai *Model*
- 3 **Chunk Splitter** Text Splitter Recursive Character Text Splitter *Model*
- 4 **Support Chat** Chat trigger *Starts it*
- 5 **Claude Sonnet 4.6** Lm Chat Anthropic *Model*
- 6 **Conversation Memory** Memory Buffer Window *Model*
- 7 **Retrieve Embeddings** Embeddings Open Ai *Model*
- 8 **Escalate to Human** Gmail Tool *Service*
- 9 **Company Knowledge Base** Vector Store In Memory *Model*
- 10 **Document Loader** Document Default Data Loader *Model*
- 11 **AI Support Agent** Agent *Model*
- 12 **Knowledge Base Search** Vector Store In Memory *Model*
- 13 **Log Q&A** Data Table *Service*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 13
- **Size:** Medium: a working afternoon
- **Connects to:** Gmail, in-memory vectors, n8n data table
- **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 Gmail and in-memory 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?

Plan an afternoon. 13 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 13 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-a-rag-support-copilot-with-claude-and-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)[in-memory vectors](https://millionrounds.com/workflows?service=in-memory+vectors#library)[n8n data table](https://millionrounds.com/workflows?service=n8n+data+table#library)

## Workflows like it

Also customer support, with the same services where possible, closest in size first.

- [**AI-powered support automation with Outlook and OpenAI** 13 steps · calls a model · Gmail, Jira](https://millionrounds.com/workflow/ai-powered-support-automation-with-outlook-and-openai)
- [**Answer support chat questions from uploaded documents** 13 steps · calls a model · in-memory vectors](https://millionrounds.com/workflow/answer-support-chat-questions-from-uploaded-documents)
- [**Escalate VIP Zendesk tickets with OpenAI and Slack** 13 steps · calls a model · Airtable, Gmail](https://millionrounds.com/workflow/escalate-vip-zendesk-tickets-with-openai-and-slack)
- [**Turn support emails into FAQ drafts with Gmail and OpenAI** 13 steps · calls a model · Gmail, Google Docs](https://millionrounds.com/workflow/turn-support-emails-into-faq-drafts-with-gmail-and-openai)
- [**Triage customer support emails with Groq AI and ClickUp** 13 steps · ClickUp, Gmail](https://millionrounds.com/workflow/triage-customer-support-emails-with-groq-ai-and-clickup)
- [**AI-Powered LINE Bot: Automate Customer Support & Task Automation** 12 steps · calls a model · Airtable, Gmail](https://millionrounds.com/workflow/ai-powered-line-bot-automate-customer-support-and-task-autom)