N8N Workflows

This guide shows you how to integrate UniCraft with N8N workflows to automate AI-powered processes.

Overview

N8N is a powerful workflow automation tool that can be integrated with UniCraft to create sophisticated AI-powered automations. This integration allows you to:

Automate AI model selection and routing
Process data through AI models in workflows
Create intelligent decision-making processes
Build AI-powered business processes

Prerequisites

Before setting up N8N workflows with UniCraft:

N8N Instance: Have N8N running (self-hosted or cloud)
UniCraft Account: Active UniCraft account with API access
API Keys: UniCraft API key and configured providers
N8N Custom Nodes: Install UniCraft custom nodes (if available)

Basic Setup

1. Install UniCraft Custom Nodes

If UniCraft provides custom N8N nodes:

# Install via N8N CLI
n8n install @cloudcraftlabs/unicraft-nodes

# Or install via N8N interface
# Go to Settings > Community Nodes > Install
# Add: @cloudcraftlabs/unicraft-nodes

2. Configure UniCraft Credentials

Set up UniCraft credentials in N8N:

Go to Credentials in N8N
Click Add Credential
Select UniCraft API
Enter your UniCraft API key
Test the connection

3. Basic Workflow Example

Create a simple workflow that uses UniCraft:

{
  "name": "UniCraft Chat Completion",
  "nodes": [
    {
      "name": "Start",
      "type": "n8n-nodes-base.start",
      "position": [240, 300]
    },
    {
      "name": "UniCraft Chat",
      "type": "@cloudcraftlabs/unicraft-nodes.chatCompletion",
      "position": [460, 300],
      "parameters": {
        "messages": [
          {
            "role": "user",
            "content": "{{ $json.prompt }}"
          }
        ],
        "model": "auto",
        "max_tokens": 100
      }
    },
    {
      "name": "Process Response",
      "type": "n8n-nodes-base.function",
      "position": [680, 300],
      "parameters": {
        "functionCode": "return { response: $input.first().json.choices[0].message.content };"
      }
    }
  ],
  "connections": {
    "Start": {
      "main": [["UniCraft Chat"]]
    },
    "UniCraft Chat": {
      "main": [["Process Response"]]
    }
  }
}

Advanced Workflow Examples

1. Content Generation Workflow

Automate content generation with quality checks:

{
  "name": "Content Generation Pipeline",
  "nodes": [
    {
      "name": "Content Request",
      "type": "n8n-nodes-base.webhook",
      "parameters": {
        "path": "content-request",
        "httpMethod": "POST"
      }
    },
    {
      "name": "Generate Content",
      "type": "@cloudcraftlabs/unicraft-nodes.chatCompletion",
      "parameters": {
        "messages": [
          {
            "role": "system",
            "content": "You are a professional content writer."
          },
          {
            "role": "user",
            "content": "Write a blog post about: {{ $json.topic }}"
          }
        ],
        "model": "gpt-4",
        "max_tokens": 1000,
        "temperature": 0.7
      }
    },
    {
      "name": "Quality Check",
      "type": "@cloudcraftlabs/unicraft-nodes.chatCompletion",
      "parameters": {
        "messages": [
          {
            "role": "system",
            "content": "You are a content quality reviewer."
          },
          {
            "role": "user",
            "content": "Rate the quality of this content (1-10): {{ $json.choices[0].message.content }}"
          }
        ],
        "model": "gpt-3.5-turbo",
        "max_tokens": 50
      }
    },
    {
      "name": "Conditional Processing",
      "type": "n8n-nodes-base.if",
      "parameters": {
        "conditions": {
          "number": [
            {
              "value1": "{{ $json.choices[0].message.content }}",
              "operation": "larger",
              "value2": 7
            }
          ]
        }
      }
    },
    {
      "name": "Save Content",
      "type": "n8n-nodes-base.googleSheets",
      "parameters": {
        "operation": "append",
        "sheetId": "your-sheet-id",
        "columns": {
          "mappingMode": "defineBelow",
          "value": {
            "topic": "={{ $('Content Request').item.json.topic }}",
            "content": "={{ $('Generate Content').item.json.choices[0].message.content }}",
            "quality_score": "={{ $('Quality Check').item.json.choices[0].message.content }}"
          }
        }
      }
    }
  ]
}

2. Customer Support Automation

Automate customer support with AI:

{
  "name": "Customer Support Bot",
  "nodes": [
    {
      "name": "Support Request",
      "type": "n8n-nodes-base.webhook",
      "parameters": {
        "path": "support-request",
        "httpMethod": "POST"
      }
    },
    {
      "name": "Classify Request",
      "type": "@cloudcraftlabs/unicraft-nodes.chatCompletion",
      "parameters": {
        "messages": [
          {
            "role": "system",
            "content": "Classify this customer support request into categories: billing, technical, general, complaint"
          },
          {
            "role": "user",
            "content": "{{ $json.message }}"
          }
        ],
        "model": "gpt-3.5-turbo",
        "max_tokens": 50
      }
    },
    {
      "name": "Route by Category",
      "type": "n8n-nodes-base.switch",
      "parameters": {
        "rules": {
          "rules": [
            {
              "value1": "={{ $json.choices[0].message.content }}",
              "operation": "contains",
              "value2": "billing"
            },
            {
              "value1": "={{ $json.choices[0].message.content }}",
              "operation": "contains",
              "value2": "technical"
            },
            {
              "value1": "={{ $json.choices[0].message.content }}",
              "operation": "contains",
              "value2": "complaint"
            }
          ]
        }
      }
    },
    {
      "name": "Generate Response",
      "type": "@cloudcraftlabs/unicraft-nodes.chatCompletion",
      "parameters": {
        "messages": [
          {
            "role": "system",
            "content": "You are a helpful customer support agent. Provide a professional and helpful response."
          },
          {
            "role": "user",
            "content": "Customer message: {{ $('Support Request').item.json.message }}\nCategory: {{ $('Classify Request').item.json.choices[0].message.content }}"
          }
        ],
        "model": "gpt-3.5-turbo",
        "max_tokens": 200
      }
    },
    {
      "name": "Send Response",
      "type": "n8n-nodes-base.emailSend",
      "parameters": {
        "toEmail": "={{ $('Support Request').item.json.email }}",
        "subject": "Re: {{ $('Support Request').item.json.subject }}",
        "message": "={{ $json.choices[0].message.content }}"
      }
    }
  ]
}

3. Data Analysis Workflow

Automate data analysis with AI:

{
  "name": "Data Analysis Pipeline",
  "nodes": [
    {
      "name": "Data Source",
      "type": "n8n-nodes-base.googleSheets",
      "parameters": {
        "operation": "read",
        "sheetId": "your-data-sheet-id"
      }
    },
    {
      "name": "Analyze Data",
      "type": "@cloudcraftlabs/unicraft-nodes.chatCompletion",
      "parameters": {
        "messages": [
          {
            "role": "system",
            "content": "You are a data analyst. Analyze the provided data and provide insights."
          },
          {
            "role": "user",
            "content": "Analyze this data: {{ JSON.stringify($json) }}"
          }
        ],
        "model": "gpt-4",
        "max_tokens": 500
      }
    },
    {
      "name": "Generate Report",
      "type": "@cloudcraftlabs/unicraft-nodes.chatCompletion",
      "parameters": {
        "messages": [
          {
            "role": "system",
            "content": "You are a business analyst. Create a professional report based on the analysis."
          },
          {
            "role": "user",
            "content": "Create a report based on this analysis: {{ $json.choices[0].message.content }}"
          }
        ],
        "model": "gpt-4",
        "max_tokens": 1000
      }
    },
    {
      "name": "Save Report",
      "type": "n8n-nodes-base.googleDocs",
      "parameters": {
        "operation": "create",
        "title": "Data Analysis Report - {{ new Date().toISOString().split('T')[0] }}",
        "content": "={{ $json.choices[0].message.content }}"
      }
    }
  ]
}

Using HTTP Request Node

If custom nodes aren’t available, use the HTTP Request node:

Basic HTTP Request to UniCraft

{
  "name": "UniCraft HTTP Request",
  "type": "n8n-nodes-base.httpRequest",
  "parameters": {
    "url": "https://api.unicraft.com/v1/chat/completions",
    "method": "POST",
    "headers": {
      "Authorization": "Bearer {{ $credentials.unicraftApi.apiKey }}",
      "Content-Type": "application/json"
    },
    "body": {
      "messages": [
        {
          "role": "user",
          "content": "{{ $json.prompt }}"
        }
      ],
      "model": "auto",
      "max_tokens": 100
    }
  }
}

Advanced HTTP Request with Error Handling

{
  "name": "UniCraft with Error Handling",
  "type": "n8n-nodes-base.httpRequest",
  "parameters": {
    "url": "https://api.unicraft.com/v1/chat/completions",
    "method": "POST",
    "headers": {
      "Authorization": "Bearer {{ $credentials.unicraftApi.apiKey }}",
      "Content-Type": "application/json"
    },
    "body": {
      "messages": [
        {
          "role": "user",
          "content": "{{ $json.prompt }}"
        }
      ],
      "model": "auto",
      "max_tokens": 100
    },
    "options": {
      "retry": {
        "enabled": true,
        "maxRetries": 3
      },
      "timeout": 30000
    }
  }
}

Workflow Best Practices

1. Error Handling

Always implement error handling in your workflows:

{
  "name": "Error Handler",
  "type": "n8n-nodes-base.function",
  "parameters": {
    "functionCode": "if ($input.first().json.error) { throw new Error($input.first().json.error.message); } return $input.all();"
  }
}

2. Rate Limiting

Implement rate limiting to avoid hitting API limits:

{
  "name": "Rate Limiter",
  "type": "n8n-nodes-base.wait",
  "parameters": {
    "amount": 1,
    "unit": "seconds"
  }
}

3. Data Validation

Validate input data before processing:

{
  "name": "Validate Input",
  "type": "n8n-nodes-base.function",
  "parameters": {
    "functionCode": "const input = $input.first().json; if (!input.prompt || input.prompt.length < 10) { throw new Error('Prompt too short'); } return $input.all();"
  }
}

4. Logging and Monitoring

Add logging for debugging and monitoring:

{
  "name": "Log Response",
  "type": "n8n-nodes-base.function",
  "parameters": {
    "functionCode": "console.log('UniCraft Response:', JSON.stringify($input.first().json, null, 2)); return $input.all();"
  }
}

Testing Workflows

1. Manual Testing

Test workflows manually using the N8N interface:

Click Execute Workflow
Provide test data
Monitor execution
Check results

2. Automated Testing

Set up automated testing for your workflows:

{
  "name": "Test Workflow",
  "nodes": [
    {
      "name": "Test Data",
      "type": "n8n-nodes-base.function",
      "parameters": {
        "functionCode": "return [{ json: { prompt: 'Test prompt', expected: 'Test response' } }];"
      }
    },
    {
      "name": "UniCraft Request",
      "type": "@cloudcraftlabs/unicraft-nodes.chatCompletion",
      "parameters": {
        "messages": [
          {
            "role": "user",
            "content": "{{ $json.prompt }}"
          }
        ],
        "model": "gpt-3.5-turbo",
        "max_tokens": 50
      }
    },
    {
      "name": "Validate Response",
      "type": "n8n-nodes-base.function",
      "parameters": {
        "functionCode": "const response = $input.first().json.choices[0].message.content; if (!response || response.length < 10) { throw new Error('Invalid response'); } return $input.all();"
      }
    }
  ]
}

Deployment and Production

1. Environment Configuration

Set up different environments for development and production:

{
  "development": {
    "unicraft_api_url": "https://api-dev.unicraft.com",
    "model": "gpt-3.5-turbo",
    "max_tokens": 100
  },
  "production": {
    "unicraft_api_url": "https://api.unicraft.com",
    "model": "auto",
    "max_tokens": 500
  }
}

2. Security Considerations

Use environment variables for API keys
Implement proper authentication
Validate all inputs
Monitor for unusual activity

3. Performance Optimization

Use appropriate models for tasks
Implement caching where possible
Batch requests when appropriate
Monitor response times

Troubleshooting

Common Issues

Authentication Errors: Check API key configuration
Rate Limiting: Implement proper rate limiting
Model Selection: Ensure models are available
Data Format: Validate input data format

Debug Tips

Use the N8N execution log
Add logging nodes to workflows
Test with simple requests first
Check UniCraft API documentation

Next Steps

After setting up N8N workflows with UniCraft:

Test Thoroughly: Test all workflows with various inputs
Monitor Performance: Set up monitoring for workflow execution
Optimize Costs: Monitor and optimize AI usage costs
Scale Gradually: Start with simple workflows and add complexity
Document Processes: Document your workflows for team use