# Build an in-memory RAG knowledge base chat 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/build-an-in-memory-rag-knowledge-base-chat-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)

# Build an in-memory RAG knowledge base chat 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%2Fbuild-an-in-memory-rag-knowledge-base-chat-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 **Run ingestion** Manual trigger *Starts it*
- 2 **Embeddings (ingest)** Embeddings Open Ai *Model*
- 3 **Recursive text splitter** Text Splitter Recursive Character Text Splitter *Model*
- 4 **Ask a question** Chat trigger *Starts it*
- 5 **OpenAI Chat Model** Lm Chat Open Ai *Model*
- 6 **Embeddings (query)** Embeddings Open Ai *Model*
- 7 **Conversation memory** Memory Buffer Window *Model*
- 8 **Download demo document** Http Request *Service*
- 9 **Insert into vector store** Vector Store In Memory *Model*
- 10 **Document loader** Document Default Data Loader *Model*
- 11 **RAG agent** Agent *Model*
- 12 **Knowledge base retriever** Vector Store In Memory *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%2Fbuild-an-in-memory-rag-knowledge-base-chat-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 ai assistants, with the same services where possible, closest in size first.

- [**Basic RAG chat with Groq and in-memory vectors** 12 steps · calls a model · in-memory vectors](https://millionrounds.com/workflow/basic-rag-chat-with-groq-and-in-memory-vectors)
- [**IPL cricket rules Q&A chat bot with RAG and Gemini** 12 steps · calls a model · in-memory vectors](https://millionrounds.com/workflow/ipl-cricket-rules-q-and-a-chat-bot-with-rag-and-gemini)
- [**Simple RAG chatbot with Gemini and Google Drive** 11 steps · calls a model · Google Drive, in-memory vectors](https://millionrounds.com/workflow/simple-rag-chatbot-with-gemini-and-google-drive)
- [**Build a RAG demo with EcoHash and BGE** 10 steps · calls a model · in-memory vectors](https://millionrounds.com/workflow/build-a-rag-demo-with-ecohash-and-bge)
- [**Save Costs In RAG Workflows with Tool** 10 steps · calls a model · in-memory vectors](https://millionrounds.com/workflow/save-costs-in-rag-workflows-with-tool)
- [**Optimize unstructured data for RAG with Blockify IdeaBlocks** 15 steps · calls a model · Google Drive, in-memory vectors](https://millionrounds.com/workflow/optimize-unstructured-data-for-rag-with-blockify-ideablocks)