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

by Cheney Zhang ✓ · 1,262 views · created 2025-04-16 · Engineering, AI RAG

What this workflow does

This AI workflow has 17 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects OpenAI Chat Model, Milvus Vector Store and Embeddings OpenAI. It also calls paulgraham.com over HTTP.

How it runs

Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).

1. Fetch Essay List (HTTP Request): calls paulgraham.com
2. Q&A Chain to Retrieve from Milvus and Answer Question (Question and Answer Chain): answers questions over your documents (RAG), with model: OpenAI Chat Model; retriever: Milvus Vector Store Retriever
3. Extract essay names (HTML): parses or builds HTML
4. Split Out: splits a list into separate items
5. Limit: keeps the first few items
6. Fetch essay texts (HTTP Request): calls an HTTP API
7. Extract Text Only (HTML): parses or builds HTML
8. Milvus Vector Store: stores documents in the Milvus vector store, with embeddings: Embeddings OpenAI; document loader: Default Data Loader

Services it uses

OpenAI Chat ModelMilvus Vector StoreEmbeddings OpenAI

HTTP calls to: paulgraham.com

Scraping pages by hand? Firecrawl is a simpler option (10% off for new users).

Before you upgrade to n8n 3.0

Nodes used (13)

• OpenAI Chat Model@n8n/n8n-nodes-langchain.lmChatOpenAi
• Manual Triggern8n-nodes-base.manualTrigger
• HTTP Requestn8n-nodes-base.httpRequest
• HTMLn8n-nodes-base.html
• Split Outn8n-nodes-base.splitOut
• Limitn8n-nodes-base.limit
• Chat Trigger@n8n/n8n-nodes-langchain.chatTrigger
• Milvus Vector Store@n8n/n8n-nodes-langchain.vectorStoreMilvus
• Default Data Loader@n8n/n8n-nodes-langchain.documentDefaultDataLoader
• Embeddings OpenAI@n8n/n8n-nodes-langchain.embeddingsOpenAi
• Recursive Character Text Splitter@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter
• Question and Answer Chain@n8n/n8n-nodes-langchain.chainRetrievalQa
• Vector Store Retriever@n8n/n8n-nodes-langchain.retrieverVectorStore

From the author

Create a Paul Graham Essay Q&A System with OpenAI and Milvus Vector Database How It Works This workflow creates a question-answering system based on Paul Graham essays. It has two main steps: 1. Data Collection & Processing: - Scrapes Paul Graham essays -…

View the original on n8n.io → Check your own copy