The Best RAG System On YouTube (Steal This!)

The Best RAG System On YouTube (Steal This!)

by Nate Herk

Applied Sciences & Engineering AI — Models & Research UYQArtificial intelligence (AI)UYQMMachine learning
🎙 Nate Herk 👥 964K 📅 December 7, 2024 ⏱ 18 min 👁 51K 📄 tutorial 🧭 2026-08-28
Available in: English (current) Français

Keywords

RAGn8nSupabasePostgresvector database

Summary

This video presents a comprehensive tutorial on building a Retrieval-Augmented Generation (RAG) system using n8n, Supabase, and Postgres. The system automatically monitors a Google Drive folder, detects new or updated files, extracts text based on file type, and stores embeddings in a vector database with rich metadata. The workflow includes a RAG agent for querying the knowledge base, a trigger for file creation, and another for file updates, which deletes the old vector records and re-uploads with incremented version numbers. The creator demonstrates the system with a Google Doc, showing how it handles text extraction, metadata storage, and versioning. He also tests with a PDF to show file-type routing. The video includes practical tips like using an AI model to increment version numbers instead of a code node, and discusses future improvements like handling file deletions. The tutorial is aimed at users familiar with n8n and AI automation, and the workflow is available for download in the creator’s community.

159 words

Critical Evaluation

Value of the Information & Strength of the Argument

The video provides a practical, step-by-step guide to implementing a RAG system, which is valuable for practitioners. The argumentation is based on live demonstrations and clear explanations of each node’s function. The creator’s approach to solving the version increment problem with an AI model is a creative and effective solution. However, the video lacks a critical evaluation of the system’s limitations, such as scalability, cost, or accuracy, and does not compare with alternative approaches.

Scientific Rigor, Source Quality, Title Accuracy

The tutorial is well-structured and the creator demonstrates a working system, which adds credibility. However, no external sources are cited, and the only references are to the creator’s own community and previous videos. The title is somewhat sensational but the content does deliver a comprehensive RAG system tutorial. The description includes affiliate links and community promotions, but these do not affect the technical content.

153 words

Title / Content Match

The title is somewhat clickbait but the content does deliver a comprehensive RAG system tutorial, so it is mostly accurate.

Quality & Reliability

7/10

The tutorial is practical and demonstrates a working RAG system, but it lacks rigorous scientific validation, relies on anecdotal evidence, and does not cite external sources.

Chapters

Cited Sources

  • n8n Partner Link — Affiliate link to sign up for n8n, the automation platform used in the tutorial.
  • Free Skool Community — Community where the workflow can be downloaded.
  • Paid Skool Community — Paid community for deeper learning on n8n and AI automations.
  • Background Music — Background music used in the video.
  • Watch Next Video — Suggested next video from the creator.

Concurring Sources

  • n8n Documentation — Official documentation for n8n, which supports the workflow described.

Contribution & Novelties

The video offers a practical, no-code approach to building a RAG system with automatic file ingestion and versioning, which is a common need in AI applications. The use of n8n for orchestration and Supabase for vector storage is a modern stack. The creator’s solution to increment version numbers using an AI model is a novel workaround.

Pour aller plus loin :

92 words

Radar Profile

The radar profile shows high scores in information quantity and technical level, indicating a detailed tutorial. The lower score in reliability reflects the lack of external sources and scientific rigor.

Reliability 6/10