Proxmox AI Agent with n8n and Generative AI Integration n8n Workflow Template

n8n workflow template · 27 nodes · Google Gemini

Proxmox AI Agent with n8n and Generative AI Integration is a free n8n workflow template that starts when a chat message is received and works with Google Gemini, Telegram and Gmail. It has 27 nodes, 11 of them AI nodes (HTTP Request Tool, Auto-fixing Output Parser, Google Gemini Chat Model and Structured Output Parser). The notes inside the workflow say: “Thank you for using this workflow template. It has taken me countless hours of hard work, research, and dedication to develop, and I sincerely hope it adds value to your work.” To run it, you add your own credentials for Gmail OAuth2, Google Gemini (PaLM) API, HTTP Header Auth and Telegram Bot API.

Download JSON How to import into n8n

At a glance

Trigger
Chat Trigger (When chat message received)
Nodes
27
Apps
Google Gemini, Telegram and Gmail
AI nodes
11
Credentials
4 types
Category
Chatbots and messaging

Apps and integrations

  • Google Gemini
  • Telegram
  • Gmail

Node types used

  • HTTP Request
  • HTTP Request Tool
  • Auto-fixing Output Parser
  • Google Gemini Chat Model
  • Structured Output Parser
  • Chat Trigger
  • Telegram Trigger
  • Gmail Trigger
  • Webhook
  • Code
  • If
  • Merge
  • AI Agent
  • Switch

How it works

The text below comes from the sticky notes inside the workflow. We removed links, code samples and anything that looks like a key or token.

Developed by Amjid Ali

Thank you for using this workflow template. It has taken me countless hours of hard work, research, and dedication to develop, and I sincerely hope it adds value to your work.

If you find this template helpful, I kindly ask you to consider supporting my efforts. Your support will help me continue improving and creating more valuable resources.

You can contribute via PayPal here

Additionally, when sharing this template, I would greatly appreciate it if you include my original information to ensure proper credit is given.

Thank you for your generosity and support! Email

Trigger

You can use any trigger as input, a chat, telegram, email etc

Trigger

You can use any trigger as input, a chat, telegram, email etc

You can think of any input, even it could be from your cloud platform, your own Web Applicaiton, etc.

Possibilities are limitless.

Chat is shown just as example.

Porxmox Custom AI Agent

It uses the intelligence provided to it including the Proxmox API Wiki, Proxmox Cluster Linked and Proxmox API Documentation.

The AI Model connected with this is Gemini, you can connect any AI Model by Ollama, OpenAI, Claude etc.

Output Parser is used to ensure the fixed output structure that can be used for API URL

Porxmox Custom AI Agent (Get)

This agent will convert the response from proxmox to meaningful explanation

Created or triggered an action on the server.

Response will come back here

Setup notes

The text below comes from the sticky notes inside the workflow. We removed links, code samples and anything that looks like a key or token.

HTTP methods

GET Retrieve resources Fetch VM status, list nodes, get logs.

POST Create or trigger actions Start/stop VMs, create backups.

PUT Update/replace entire resource configuration Modify VM configurations.

DELETE Delete resources Remove VMs, delete users, remove files.

OPTIONS Fetch supported methods for an endpoint Check available operations for an API.

PATCH Apply partial updates Update specific fields in VM settings.

API Key for Proxmox

Create Credentails ensure to create credentials in Proxmox Data Center as API Key and then create credentails. Add Credentials to n8n Click on Credentails, add new Credentails and Chose Header Auth In Header Auth Below will be used Name: Authorization Value: PVEAPIToken= @! =

Suppose my token id is n8n and key is 1234 so value will be as below

Value: PVEAPIToken=root@pam!n8n=1234

Nodes in this workflow

The 27 nodes in file order (sticky notes excluded). Branches and connections determine execution order in n8n:

  1. HTTP Request1 (HTTP Request)
  2. Proxmox API Documentation (HTTP Request Tool)
  3. Auto-fixing Output Parser (Auto-fixing Output Parser)
  4. Google Gemini Chat Model1 (Google Gemini Chat Model)
  5. Structured Output Parser (Structured Output Parser)
  6. Proxmox (HTTP Request Tool)
  7. HTTP Request (HTTP Request)
  8. Google Gemini Chat Model2 (Google Gemini Chat Model)
  9. When chat message received (Chat Trigger)
  10. Telegram Trigger (Telegram Trigger)
  11. Gmail Trigger (Gmail Trigger)
  12. Webhook (Webhook)
  13. Proxmox API Wiki (HTTP Request Tool)
  14. Structure Response (Code)
  15. Structgure Response from Proxmox (Code)
  16. Format Response and Hide Sensitive Data (Code)
  17. If (If)
  18. HTTP Request2 (HTTP Request)
  19. Merge (Merge)
  20. HTTP Request3 (HTTP Request)
  21. Google Gemini Chat Model (Google Gemini Chat Model)
  22. AI Agent1 (AI Agent)
  23. If1 (If)
  24. HTTP Request4 (HTTP Request)
  25. Merge1 (Merge)
  26. AI Agent (AI Agent)
  27. Switch (Switch)

Credentials you need

  • Gmail OAuth2 – used by Gmail Trigger
  • Google Gemini (PaLM) API – used by Google Gemini Chat Model, Google Gemini Chat Model1 and Google Gemini Chat Model2
  • HTTP Header Auth – used by HTTP Request, HTTP Request1, HTTP Request2 and HTTP Request3 and others
  • Telegram Bot API – used by Telegram Trigger

Configure your own credentials after importing. Create each credential in n8n, then select it in the node.

How to import into n8n

  1. Download the JSON file with the button above.
  2. In n8n, open a new workflow, select the ... menu and choose Import from File. You can also paste the JSON straight into the editor canvas.
  3. Open each node that shows a warning and select or create its credential.
  4. Read the notes on the canvas, test the workflow with sample data, then activate it.

Do you need somewhere to run it? Read our guide to self-hosted n8n.

Need this customised?

We can adapt this workflow to your apps, data and process, then deploy and support it.

Contact Us