N8N Custom Nodes

N8N Custom Nodes

UniCraft provides custom N8N nodes that make it easy to integrate AI model routing into your N8N workflows.

Overview

N8N is a powerful workflow automation tool that allows you to connect different services and automate processes. UniCraft’s custom N8N nodes provide:

• Chat Completions: Generate text using AI models
• Model Selection: Automatically choose the best model for your task
• Cost Optimization: Route requests to the most cost-effective models
• Provider Management: Handle multiple AI providers seamlessly

Installation

Method 1: N8N CLI

# Install the UniCraft custom nodes
n8n install @cloudcraftlabs/unicraft-nodes

Method 2: N8N Interface

1. Open your N8N instance
2. Go to Settings → Community Nodes
3. Click Install a community node
4. Enter: @cloudcraftlabs/unicraft-nodes
5. Click Install

Method 3: Manual Installation

# Clone the repository
git clone https://github.com/cloudcraftlabs/unicraft-n8n-nodes.git

# Install dependencies
cd unicraft-n8n-nodes
npm install

# Build the nodes
npm run build

# Copy to N8N nodes directory
cp -r dist/* /path/to/n8n/nodes/

Configuration

1. Set Up Credentials

1. Go to Credentials in N8N
2. Click Add Credential
3. Select UniCraft API
4. Enter your UniCraft API key
5. Test the connection

2. Configure Providers

Set up your AI providers in the UniCraft dashboard:

// Example provider configuration
const providers = [
  {
    name: "OpenAI Production",
    type: "openai",
    api_key: process.env.OPENAI_API_KEY,
    models: ["gpt-4", "gpt-3.5-turbo"],
    priority: 1,
  },
  {
    name: "Anthropic Production",
    type: "anthropic",
    api_key: process.env.ANTHROPIC_API_KEY,
    models: ["claude-3-sonnet", "claude-3-haiku"],
    priority: 2,
  },
];

Available Nodes

1. Chat Completion Node

The Chat Completion node allows you to generate text using AI models.

Parameters

• Messages: Array of message objects
• Model: AI model to use (or “auto” for smart routing)
• Max Tokens: Maximum number of tokens to generate
• Temperature: Controls randomness (0.0 to 1.0)
• Top P: Controls diversity (0.0 to 1.0)
• Frequency Penalty: Reduces repetition (-2.0 to 2.0)
• Presence Penalty: Encourages new topics (-2.0 to 2.0)

Example Usage

{
  "name": "Chat Completion",
  "type": "@cloudcraftlabs/unicraft-nodes.chatCompletion",
  "parameters": {
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "{{ $json.prompt }}"
      }
    ],
    "model": "auto",
    "max_tokens": 100,
    "temperature": 0.7
  }
}

2. Model Selection Node

The Model Selection node helps you choose the best model for your task.

Parameters

• Task Type: Type of task (text, code, analysis, etc.)
• Quality Requirement: Quality level needed (low, medium, high)
• Cost Preference: Cost preference (low, medium, high)
• Response Time: Maximum acceptable response time

Example Usage

{
  "name": "Model Selection",
  "type": "@cloudcraftlabs/unicraft-nodes.modelSelection",
  "parameters": {
    "task_type": "text_generation",
    "quality_requirement": "high",
    "cost_preference": "medium",
    "response_time": 5000
  }
}

3. Provider Status Node

The Provider Status node checks the status of your AI providers.

Parameters

• Provider: Specific provider to check (optional)
• Include Models: Whether to include model information

Example Usage

{
  "name": "Provider Status",
  "type": "@cloudcraftlabs/unicraft-nodes.providerStatus",
  "parameters": {
    "provider": "openai",
    "include_models": true
  }
}

Workflow Examples

1. Content Generation Workflow

{
  "name": "Content Generation",
  "nodes": [
    {
      "name": "Webhook",
      "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": "auto",
        "max_tokens": 1000,
        "temperature": 0.7
      }
    },
    {
      "name": "Save to Google Docs",
      "type": "n8n-nodes-base.googleDocs",
      "parameters": {
        "operation": "create",
        "title": "{{ $json.topic }} - Blog Post",
        "content": "{{ $json.choices[0].message.content }}"
      }
    }
  ]
}

2. Customer Support Automation

{
  "name": "Customer Support",
  "nodes": [
    {
      "name": "Support Request",
      "type": "n8n-nodes-base.webhook",
      "parameters": {
        "path": "support",
        "httpMethod": "POST"
      }
    },
    {
      "name": "Classify Request",
      "type": "@cloudcraftlabs/unicraft-nodes.chatCompletion",
      "parameters": {
        "messages": [
          {
            "role": "system",
            "content": "Classify this support request: billing, technical, general, complaint"
          },
          {
            "role": "user",
            "content": "{{ $json.message }}"
          }
        ],
        "model": "gpt-3.5-turbo",
        "max_tokens": 50
      }
    },
    {
      "name": "Generate Response",
      "type": "@cloudcraftlabs/unicraft-nodes.chatCompletion",
      "parameters": {
        "messages": [
          {
            "role": "system",
            "content": "You are a helpful customer support agent."
          },
          {
            "role": "user",
            "content": "Respond to this {{ $json.choices[0].message.content }} request: {{ $('Support Request').item.json.message }}"
          }
        ],
        "model": "auto",
        "max_tokens": 200
      }
    },
    {
      "name": "Send Email",
      "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

{
  "name": "Data Analysis",
  "nodes": [
    {
      "name": "Data Source",
      "type": "n8n-nodes-base.googleSheets",
      "parameters": {
        "operation": "read",
        "sheetId": "your-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."
          },
          {
            "role": "user",
            "content": "Create a report based on: {{ $json.choices[0].message.content }}"
          }
        ],
        "model": "gpt-4",
        "max_tokens": 1000
      }
    }
  ]
}

Advanced Features

1. Smart Routing

Use smart routing to automatically select the best model:

{
  "name": "Smart Routing",
  "type": "@cloudcraftlabs/unicraft-nodes.chatCompletion",
  "parameters": {
    "messages": [
      {
        "role": "user",
        "content": "{{ $json.prompt }}"
      }
    ],
    "model": "auto",
    "routing_strategy": "cost_optimized",
    "max_cost_per_request": 0.01,
    "quality_threshold": 0.8
  }
}

2. Batch Processing

Process multiple requests together:

{
  "name": "Batch Processing",
  "type": "@cloudcraftlabs/unicraft-nodes.batchCompletion",
  "parameters": {
    "requests": [
      {
        "messages": [
          {
            "role": "user",
            "content": "{{ $json.prompt1 }}"
          }
        ]
      },
      {
        "messages": [
          {
            "role": "user",
            "content": "{{ $json.prompt2 }}"
          }
        ]
      }
    ],
    "model": "auto",
    "max_tokens": 100
  }
}

3. Cost Monitoring

Monitor costs in real-time:

{
  "name": "Cost Monitor",
  "type": "@cloudcraftlabs/unicraft-nodes.costMonitor",
  "parameters": {
    "time_range": "1h",
    "alert_threshold": 10.0,
    "alert_channels": ["email", "slack"]
  }
}

Error Handling

1. Retry Logic

Implement retry logic for failed requests:

{
  "name": "Retry Logic",
  "type": "n8n-nodes-base.function",
  "parameters": {
    "functionCode": "const maxRetries = 3; let retries = 0; while (retries < maxRetries) { try { return $input.all(); } catch (error) { retries++; if (retries >= maxRetries) throw error; await new Promise(resolve => setTimeout(resolve, 1000 * retries)); } }"
  }
}

2. Fallback Handling

Set up fallback providers:

{
  "name": "Fallback Handler",
  "type": "@cloudcraftlabs/unicraft-nodes.chatCompletion",
  "parameters": {
    "messages": [
      {
        "role": "user",
        "content": "{{ $json.prompt }}"
      }
    ],
    "model": "auto",
    "fallback_enabled": true,
    "fallback_providers": ["anthropic", "google"]
  }
}

Best Practices

1. Model Selection

• Use “auto” for most cases to leverage smart routing
• Specify models only when you need specific capabilities
• Consider cost vs. quality trade-offs

2. Error Handling

• Always implement error handling
• Use retry logic for transient failures
• Set up fallback providers

3. Performance

• Use appropriate max_tokens values
• Implement caching where possible
• Monitor response times

4. Security

• Store API keys securely
• Validate input data
• Monitor for unusual activity

Troubleshooting

Common Issues

1. Authentication Errors

   • Check API key configuration
   • Verify credentials in N8N
   • Test connection

2. Model Not Available

   • Check provider configuration
   • Verify model availability
   • Use “auto” for smart routing

3. Rate Limiting

   • Implement rate limiting
   • Use batch processing
   • Monitor usage

4. High Costs

   • Use cost-optimized routing
   • Set cost limits
   • Monitor spending

Debug Tips

1. Use N8N execution log
2. Add logging nodes
3. Test with simple requests
4. Check UniCraft dashboard

Support

For support with UniCraft N8N nodes:

• Documentation: UniCraft Docs
• GitHub: UniCraft N8N Nodes
• Community: UniCraft Community
• Support: support@unicraft.com

Next Steps

After setting up UniCraft N8N nodes:

1. Test Workflows: Test your workflows with various inputs
2. Monitor Performance: Set up monitoring for workflow execution
3. Optimize Costs: Monitor and optimize AI usage costs
4. Scale Gradually: Start with simple workflows and add complexity
5. Document Processes: Document your workflows for team use