Hey n8n community!
Just published two community nodes that make building AI/RAG workflows easier:
-–
n8n-nodes-rag-architect
**Transform any website into AI-ready knowledge chunks**
```
npm install n8n-nodes-rag-architect
```
Features:
- Structure-aware chunking (respects headers, code blocks, tables)
- Automatic PII scrubbing (emails, phones)
- Optional Q&A pair generation
- Multiple output formats: n8n, LangChain, LlamaIndex
**Use case:** Feed websites directly into vector stores for RAG pipelines.
-–
n8n-nodes-hyper-reader
**Agent-ready web scraper optimized for Claude, GPT-4, and Gemini**
```
npm install n8n-nodes-hyper-reader
```
Features:
- Agent presets (Claude, GPT-4, Gemini, SearchGPT)
- 85% noise reduction (strips ads, navbars, tracking)
- Elite stealth mode for protected sites
- Vision support (screenshot capture)
- Deep Read - follows internal links
**Use case:** Get clean, LLM-optimized content from any URL in seconds.
-–
Installation
1. Go to **Settings** → **Community Nodes**
2. Click **Install**
3. Enter `n8n-nodes-rag-architect` or `n8n-nodes-hyper-reader`
4. Click **Install**
Both nodes use Apify under the hood - you’ll need an Apify API token (free tier available).
-–
Example Workflow
```
[Webhook] → [Hyper-Reader] → [RAG-Architect] → [Vector Store] → [AI Agent]
```
Scrape clean content → Chunk for RAG → Store embeddings → Query with AI
-–
Links
- npm: npmjs.com/package/n8n-nodes-rag-architect
- npm: npmjs.com/package/n8n-nodes-hyper-reader
- Apify: Rag Architect · Apify
- Apify: Hyper-Reader: LLM-Optimized Web Scraper · Apify
Let me know if you have questions or feature requests! Happy to help with workflow examples.