Turn a YouTube channel into a second brain with Neo4j GraphRAG and GPT-4o-mini
UnknownWhat this workflow does
This AI workflow has 19 nodes and runs when a chat message arrives (plus 1 other trigger). Along the way it connects OpenRouter Chat Model, HTTP Request and Apify (community). It also calls 4b095dfe.databases.neo4j.io over HTTP.
How it runs
Trigger: When a chat message arrives (plus 1 other trigger).
- AI Agent: runs an AI agent, with model: 4o, sonnet 4.; 1 tool (neo4j_query); memory: Simple Memory
- Get channel videos URLs (Apify): run actor and get dataset
- Respond to Chat (Chat): uses Chat
- loop each video (Loop Over Items (Split in Batches)): loops over the items in batches
- Results (n8n Form): shows the next form page
- Scraping of each URLs (Apify): run actor and get dataset
- If: checks a condition and branches into true / false
- Catégorie définition Agent (AI Agent): runs an AI agent, with model: 4o mini, sonnet 3.; output parser: Parseur
- Vers Neo4j (HTTP Request): calls 4b095dfe.databases.neo4j.io (POST)
Services it uses
HTTP calls to: 4b095dfe.databases.neo4j.io
Before you upgrade to n8n 3.0
We can't fully verify this one: it relies on 1 community package, and n8n 3.0 turns unverified community packages off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
- Check that @apify/n8n-nodes-apify is verified or supports 3.0 (used in Get channel videos URLs, Scraping of each URLs).
Nodes used (13)
- OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter - AI Agent
@n8n/n8n-nodes-langchain.agent - If
n8n-nodes-base.if - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Chat
@n8n/n8n-nodes-langchain.chat - Http Request Tool
n8n-nodes-base.httpRequestTool - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - HTTP Request
n8n-nodes-base.httpRequest - n8n Form Trigger
n8n-nodes-base.formTrigger - Apify
@apify/n8n-nodes-apify.apify - n8n Form
n8n-nodes-base.form - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches
From the author
AI-powered "Second Brain" that can answer questions about any YouTube channel's content using Neo4j Graph Database and RAG. Turn any YouTube channel into a searchable knowledge base. The AI agent understands relationships between videos, topics, tools, and…