How to Set up Supabase and Postgres for RAG Agent with Memory in n8n (2025)

How to Set up Supabase and Postgres for RAG Agent with Memory in n8n (2025)

by Nate Herk

Applied Sciences & Engineering AI — Models & Research UYQArtificial intelligence (AI)UYQMMachine learning
🎙 Nate Herk 👥 964K 📅 February 22, 2025 ⏱ 10 min 👁 166K 📄 tutorial 🧭 2026-08-28
Available in: English (current) Français

Keywords

SupabasePostgresn8nRAGvector database

Summary

This tutorial by Nate Herk demonstrates how to connect Supabase and Postgres to n8n for building a RAG agent with memory. The video begins by explaining the roles of Postgres (as chat memory) and Supabase (as a vector database). The creator walks through signing up for Supabase, creating a project, and retrieving the necessary credentials. He then shows how to configure the Postgres chat memory node in n8n, using the transaction pooler details from Supabase. Next, he sets up the Supabase vector store node, using the project URL and service role secret. He creates a vector store table by running a SQL script from the Supabase documentation. To demonstrate the setup, he uploads a Google Doc into the vector store and tests the agent with a query about brake services. The agent successfully retrieves relevant information and stores the conversation in the Postgres chat memory. The video concludes with tips on prompting the agent and mentions the scalability and security options of Supabase.

163 words

Critical Evaluation

Value of the Information & Strength of the Argument

The video provides a practical, step-by-step guide that is easy to follow, with clear visual demonstrations. The argumentation is straightforward, focusing on the ‘how-to’ rather than deep theoretical explanations. The value lies in its actionable instructions, which save time for viewers. However, the lack of discussion on alternative configurations or potential pitfalls limits its depth.

Scientific Rigor, Source Quality, Title Accuracy

The tutorial is methodical and accurate, with each step verified by testing connections and querying data. The creator does not cite external sources beyond his own promotional links, which reduces the scientific rigor. The title accurately reflects the content, and the video is well-structured with chapters. The comments indicate that viewers find the tutorial helpful, though some note that Supabase’s interface has changed, suggesting the video may become outdated.

139 words

Title / Content Match

The title accurately describes the content: a tutorial on setting up Supabase and Postgres for a RAG agent with memory in n8n.

Quality & Reliability

7/10

The tutorial is clear and practical, with step-by-step instructions and visual verification of each step. However, it lacks in-depth explanation of underlying concepts and does not cite external sources beyond promotional links.

Chapters

Cited Sources

Concurring Sources

  • Supabase Documentation — Official documentation for Supabase, which the video references for setting up the vector store.
  • n8n Documentation — Official documentation for n8n, which the video uses for node configuration.

Contribution & Novelties

The video offers a clear, practical guide to integrating Supabase and Postgres with n8n for RAG agents, which is valuable for practitioners. It demonstrates the entire workflow from setup to testing, filling a gap for those needing a step-by-step tutorial. The approach is straightforward and accessible.

Pour aller plus loin :

83 words

Radar Profile

The radar profile shows a balanced performance with moderate scores across all dimensions. The tutorial is informative and reliable, but lacks deep technical depth and external sourcing, which is typical for a practical tutorial.

Reliability 7/10

💬 Très positif. Sur les 30 commentaires analysés, la grande majorité exprime des remerciements et des éloges pour la clarté et l'utilité du tutoriel, avec quelques demandes de contenu supplémentaire.