AI Agents

Automated workflow

15 nodes 291 163 Automatic trigger
Download

Workflow Description

Intelligent workflow combining AI agents with multiple language models. Receives queries through live chat, processes them via OpenAI agent while maintaining conversation memory, and supports local Ollama processing. Delivers context-aware responses in unified interface.

How it works

  1. 1.Receive user query through real-time chat trigger interface
  2. 2.Route message to intelligent agent for multi-model processing
  3. 3.Store conversation context in sliding window memory buffer
  4. 4.Execute query through LLM chain with OpenAI or Ollama model
  5. 5.Return complete response to user with full context

Use cases

  • Automated customer support systems maintaining conversation history and continuity
  • Hybrid AI assistants combining cloud OpenAI with local Ollama models for flexibility
  • Complex query processing requiring conversation memory and contextual understanding

Requirements

  • Valid OpenAI API key configured for language model operations
  • Local Ollama installation if using local models instead of cloud API
  • Properly configured memory buffer settings to retain conversation history effectively

Service Value

Ideal as a smart automation service combining integrations and AI to produce ready-to-use results.

Apps Used

Chat Trigger AI Agent OpenAI Memory LLM Chain Lm Chat Ollama

Details

Trigger Automatic trigger
Nodes 15
Apps 6
Views 291
Downloads 163

How to Use

  1. 1.Click "Download Template"
  2. 2.Open your n8n dashboard
  3. 3.Go to Workflows > Import from File
  4. 4.Select downloaded file and configure credentials

Nodes Used (15)

/

When chat message received

Chat Trigger

#1

AI Agent

Agent

#2

DeepSeek

OpenAI

#3

Window Buffer Memory

Memory Buffer Window

#4

Basic LLM Chain2

LLM Chain

#5

Sticky Note

Sticky Note

#6

Sticky Note1

Sticky Note

#7

Ollama DeepSeek

Lm Chat Ollama

#8

Sticky Note2

Sticky Note

#9

Sticky Note3

Sticky Note

#10

DeepSeek JSON Body

HTTP Request

#11

DeepSeek Raw Body

HTTP Request

#12

Sticky Note4

Sticky Note

#13

Sticky Note5

Sticky Note

#14

Sticky Note6

Sticky Note

#15