# Create a Paul Graham essay Q&A system with OpenAI and Milvus: n8n workflow

> Started by someone opening a chat with it. It calls services over plain HTTP rather than through connectors.

Source: https://millionrounds.com/workflow/create-a-paul-graham-essay-q-and-a-system-with-openai-and-mi (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)

# Create a Paul Graham essay Q&A system with OpenAI and Milvus

Started by someone opening a chat with it. It calls services over plain HTTP rather than through connectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 17 steps: a working afternoon to understand properly.

Medium Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fcreate-a-paul-graham-essay-q-and-a-system-with-openai-and-mi)

**17 steps** Medium: a working afternoon

**0** Branches: places the flow splits

**0** Loops or waits

**0** Services by connector: it calls them over plain HTTP

## The flow

Starts it 2 Model 9 Logic 4 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 "Execute Workflow"** Manual trigger *Starts it*
- 3 **When chat message received** Chat trigger *Starts it*
- 4 **Embeddings OpenAI** Embeddings Open Ai *Model*
- 5 **Recursive Character Text Splitter** Text Splitter Recursive Character Text Splitter *Model*
- 6 **Embeddings OpenAI1** Embeddings Open Ai *Model*
- 7 **Q&A Chain to Retrieve from Milvus and Answer Question** Chain Retrieval Qa *Model*
- 8 **Fetch Essay List** Http Request *Service*
- 9 **Milvus Vector Store** Vector Store Milvus *Model*
- 10 **Default Data Loader** Document Default Data Loader *Model*
- 11 **Milvus Vector Store1** Vector Store Milvus *Model*
- 12 **Extract essay names** Html *Logic*
- 13 **Milvus Vector Store Retriever** Retriever Vector Store *Model*
- 14 **Split out into items** Split Out *Logic*
- 15 **Limit to first 3** Limit *Logic*
- 16 **Fetch essay texts** Http Request *Service*
- 17 **Extract Text Only** Html *Logic*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 17
- **Size:** Medium: a working afternoon
- **Connects to:** Nothing by connector; it calls services over plain HTTP
- **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, 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. 17 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 17 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%2Fcreate-a-paul-graham-essay-q-and-a-system-with-openai-and-mi)
- **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.

## Workflows like it

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

- [**Auto-reply to Telegram messages with BrowserAct and Gemini** 17 steps · calls a model](https://millionrounds.com/workflow/auto-reply-to-telegram-messages-with-browseract-and-gemini)
- [**Automated Twitter following with Phantombuster and OpenAI** 17 steps · calls a model](https://millionrounds.com/workflow/automated-twitter-following-with-phantombuster-and-openai)
- [**Baby Photoshop AI Workflow with Gemini** 17 steps · calls a model](https://millionrounds.com/workflow/baby-photoshop-ai-workflow-with-gemini)
- [**Collect AI news via local deployment and send to Feishu with DeepSeek** 17 steps · calls a model · RSS](https://millionrounds.com/workflow/ai-with-deepseek)
- [**Compare LLM token costs across 350+ models with OpenRouter** 17 steps · calls a model](https://millionrounds.com/workflow/compare-llm-token-costs-across-350-models-with-openrouter)
- [**Compare shipping rates with FedEx and DHL** 17 steps · calls a model](https://millionrounds.com/workflow/compare-shipping-rates-with-fedex-and-dhl)