Turn a YouTube channel into a second brain with Neo4j GraphRAG and GPT-4o-mini

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 concepts - enabling powerful queries like "Which videos talk about automation AND mention n8n?" or "What are the most discussed topics?".

Good to know

Neo4j Aura Free Tier is sufficient for most channels (up to 200k nodes) Apify credits are required for YouTube scraping (~$5 for 500 videos) LLM costs are minimal (~$0.01 per video for entity extraction)

How it works

Ingestion Flow**: Scrapes YouTube videos via Apify, including titles, descriptions, and transcripts. Entity Extraction**: GPT-4o-mini analyzes each video and extracts Topics, Tools, and Concepts mentioned. Graph Storage**: Data is stored in Neo4j with relationships: Video → COVERS → Topic, Video → USES → Tool, Video → EXPLAINS → Concept. AI Agent**: Receives user questions, generates Cypher queries to search the graph, and returns natural language responses with relevant video links.

How to use

Set up a free Neo4j Aura instance and save credentials Convert your Neo4j username:password to Base64 for authentication Configure Apify with your target YouTube channel URL Run the ingestion workflow to populate the database Chat with the AI agent to query your video knowledge base

Requirements

Neo4j Aura account (free tier available) Apify account for YouTube scraping OpenAI API key (GPT-4o-mini) for entity extraction Anthropic API key (Claude) or OpenAI for the AI agent

Customization

Modify the system prompt to change response style or language Add more entity types (e.g., People, Companies, Frameworks) Connect multiple YouTube channels into one knowledge base Extend to other content sources (blogs, podcasts, Notion docs)