Build an Al RAG Agent in n8n (quickest way) | COMPLETE n8n crash course [Part 5]

Author: DigitalOcean - Bewertung: 0x - Views:8

PROMO CODE 🚀

The first 50 people to redeem the promo code DO20YT will get $20 in free credits!

https://cloud.digitalocean.com/registrations/new?utm_source=youtube&utm_medium=organic_video&utm_campaign=digitalocean&utm_content=-PrhgxaBZG0



Here's how you can redeem the code: https://docs.digitalocean.com/platform/billing/promo-codes/



Build a powerful RAG (Retrieval Augmented Generation) agent in n8n in just 10 minutes. In this lesson, we show you the easiest way to create an AI agent that can learn from your website's documentation and automatically answer customer product questions.



We'll use DigitalOcean's Agent Builder to create a knowledge base by automatically crawling a documentation site. Then, we'll integrate this custom AI agent into our n8n workflow's support branch. When a product question comes in, the RAG agent will provide a factual, grounded answer, which we'll format into a professional email and send to the user automatically.



👇 WHAT YOU'LL LEARN IN THIS VIDEO 👇



🤖 What RAG is: Understand how Retrieval Augmented Generation makes AI agents more accurate and truthful.

🌐 DigitalOcean Agent Builder: A step-by-step guide to creating an agent and a knowledge base.

🕸️ Automated Web Crawling: Build a knowledge base by simply providing a URL to your documentation.

🔌 Calling External APIs: Use the n8n HTTP Request node to communicate with your custom RAG agent.

🔐 API Authentication: Securely connect to your agent using a Bearer Token and generic credentials.

✉️ Formatting AI Responses: Use a second LLM call to transform the RAG agent's raw output into a polished, customer-facing email.

⚙️ Full Integration: Wire the new RAG agent into the "Support Inquiry" branch of our main workflow.



🔗 Get the full lesson's code from GitHub: https://github.com/do-community/n8n-crash-course/tree/main/lessons/lesson_5



►► New to n8n? Watch our "Getting Started" video first: https://www.youtube.com/watch?v=uCe0IzejSBU

►► WATCH NEXT: https://www.youtube.com/watch?v=g2bhGPaDUw0&list=PLseEp7p6EwibcvBe7cOWqDmN99zA1YFL2&index=7

►► FULL N8N CRASH COURSE PLAYLIST: https://www.youtube.com/watch?v=BLG9kpUCnww&list=PLseEp7p6EwibcvBe7cOWqDmN99zA1YFL2



🚀 Join the Developer Cloud (use promo code DO20YT for $20 in credits for the first 50 devs who join):

https://cloud.digitalocean.com/registrations/new?utm_source=youtube&utm_medium=organic_video&utm_campaign=digitalocean&utm_content=-PrhgxaBZG0



// STAY CONNECTED

🌏 Follow our blog for the latest updates: https://www.digitalocean.com/blog

🦈 Join our Developer Community on Discord: https://discord.com/invite/digitalocean

🐥 Follow us on X/Twitter: https://x.com/digitalocean

👩‍💻 We're Hiring! See open roles: http://grnh.se/aicoph1



------------------



TIMESTAMPS



0:00 - What we're going to build (simple RAG agent)

0:59 - Step 1: Create your agent

2:02 - Step 2: Build a knowledge base via web crawling

4:20 - Step 3: Connect the knowledge base to the agent

4:47 - Step 4: Call the agent from n8n

5:15 - Step 5: Handle authentication

6:19 - Step 6: Structure the API request body (JSON)

7:00 - Step 7: Integrate the RAG agent into the workflow

8:18 - Step 8: Submit a real product question

10:35 - Step 9: Format the Agent's response into a final email

11:45 - Step 10: Send the automated support email

12:10 - Recap & what's next