Create a RAG system with Paul Essays, Milvus, and OpenAI for cited answers

by Cheney Zhang ✓ · 2,349 views · created 2025-04-16 · Internal Wiki, AI RAG

What this workflow does

This AI workflow has 20 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects Embeddings OpenAI, Milvus Vector Store and OpenAI Chat Model. 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. Extract essay names (HTML): parses or builds HTML
3. Split Out: splits a list into separate items
4. Limit: keeps the first few items
5. Fetch essay texts (HTTP Request): calls an HTTP API
6. Extract Text Only (HTML): parses or builds HTML
7. Milvus Vector Store: stores documents in the Milvus vector store, with embeddings: Embeddings OpenAI; document loader: Default Data Loader
8. Set max chunks to send to model (Edit Fields (Set)): sets 1 field: chunks
9. Milvus Vector Store: searches the Milvus vector store, with embeddings: Embeddings OpenAI
10. Prepare chunks (Code): runs custom JavaScript code

…plus 3 more steps. See the full node list below.

Services it uses

Embeddings OpenAIMilvus Vector StoreOpenAI Chat Model

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 (14)

• Manual Triggern8n-nodes-base.manualTrigger
• HTTP Requestn8n-nodes-base.httpRequest
• HTMLn8n-nodes-base.html
• Split Outn8n-nodes-base.splitOut
• Limitn8n-nodes-base.limit
• Recursive Character Text Splitter@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter
• Edit Fields (Set)n8n-nodes-base.set
• Information Extractor@n8n/n8n-nodes-langchain.informationExtractor
• Coden8n-nodes-base.code
• Embeddings OpenAI@n8n/n8n-nodes-langchain.embeddingsOpenAi
• Chat Trigger@n8n/n8n-nodes-langchain.chatTrigger
• Milvus Vector Store@n8n/n8n-nodes-langchain.vectorStoreMilvus
• Default Data Loader@n8n/n8n-nodes-langchain.documentDefaultDataLoader
• OpenAI Chat Model@n8n/n8n-nodes-langchain.lmChatOpenAi

From the author

Create a RAG System with Paul Essays, Milvus, and OpenAI for Cited Answers This workflow automates the process of creating a document-based AI retrieval system using Milvus, an open-source vector database. It consists of two main steps: 1. Data…

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