# Answer support questions from a knowledge base with OpenAI: n8n workflow

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

Source: https://millionrounds.com/workflow/answer-support-questions-from-a-knowledge-base-with-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)

# Answer support questions from a knowledge base with OpenAI

Started by someone opening a chat with it, and works across in-memory vectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 12 steps: a working afternoon to understand properly.

Medium Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fanswer-support-questions-from-a-knowledge-base-with-openai)

**12 steps** Medium: a working afternoon

**0** Branches: places the flow splits

**0** Loops or waits

**1** Service it connects to

## The flow

Starts it 2 Model 9 Service 1

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

- 1 **When Chat Message Received** Chat trigger *Starts it*
- 2 **OpenAI Chat GPT-4o-Mini** Lm Chat Open Ai *Model*
- 3 **Manage Conversation Memory** Memory Buffer Window *Model*
- 4 **Generate Query Embeddings** Embeddings Open Ai *Model*
- 5 **Manual Document Ingestion** Manual trigger *Starts it*
- 6 **Create Insert Embeddings** Embeddings Open Ai *Model*
- 7 **Split Text for Processing** Text Splitter Recursive Character Text Splitter *Model*
- 8 **AI Support Assistant** Agent *Model*
- 9 **Load Knowledge Base Data** Vector Store In Memory *Model*
- 10 **Fetch FAQ Documents** Http Request *Service*
- 11 **Add Data to Knowledge Base** Vector Store In Memory *Model*
- 12 **Load Documents** Document Default Data Loader *Model*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 12
- **Size:** Medium: a working afternoon
- **Connects to:** 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 in-memory vectors account, 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. 12 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 12 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%2Fanswer-support-questions-from-a-knowledge-base-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.

[in-memory vectors](https://millionrounds.com/workflows?service=in-memory+vectors#library)

## Workflows like it

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

- [**WhatsApp support bot with Gemini and in-memory vectors** 12 steps · calls a model · in-memory vectors](https://millionrounds.com/workflow/whatsapp-support-bot-with-gemini-and-in-memory-vectors)
- [**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)
- [**Run a RAG support copilot with Claude and OpenAI** 13 steps · calls a model · Gmail, in-memory vectors](https://millionrounds.com/workflow/run-a-rag-support-copilot-with-claude-and-openai)
- [**Answer code of conduct questions in Slack with OpenAI and RAG** 14 steps · calls a model · Google Drive, Slack](https://millionrounds.com/workflow/answer-code-of-conduct-questions-in-slack-with-openai-and-ra)
- [**Dual-path customer support system with Google Sheets** 15 steps · calls a model · Google Sheets, in-memory vectors](https://millionrounds.com/workflow/dual-path-customer-support-system-with-google-sheets)
- [**Answer customer questions and book jobs with OpenAI RAG** 16 steps · calls a model · Gmail, Google Calendar](https://millionrounds.com/workflow/answer-customer-questions-and-book-jobs-with-openai-rag-2)