Skip to content

n8n community node for Latitude.so. Enables LLM prompt integration with auto-parameter detection, conversation continuity, and token cost tracking.

License

Notifications You must be signed in to change notification settings

yigitkonur/n8n-nodes-latitude

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 

History

21 Commits
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 

Repository files navigation

๐Ÿš€ n8n-nodes-latitude ๐Ÿš€

Stop hardcoding AI prompts. Start shipping smarter workflows.

The ultimate n8n integration for Latitude.so โ€” the AI prompt management platform. Execute prompts, continue conversations, and log everything with zero JSON wrestling.

npm node ย ย โ€ขย ย  license n8n

zero config ai agent ready


n8n-nodes-latitude is the prompt manager your n8n workflows wish they had. Stop embedding AI prompts directly in your automation and praying they still work next week. This node connects directly to Latitude.so, letting you manage prompts centrally, hot-reload changes, and execute with auto-detected parameters โ€” all without touching your workflow.

๐ŸŽฏ

Dynamic Parameters
Auto-detects {{ variables }}

๐Ÿ’ฌ

Conversation Memory
Continue multi-turn chats

๐Ÿค–

AI Agent Ready
Use as tool in AI workflows

๐Ÿ“Š

Full Observability
Logs, costs, token tracking

How it slaps:

  • You: Drag Latitude node into n8n workflow
  • Node: Fetches prompts, shows parameters, handles auth
  • You: Map your data โ†’ Execute
  • Latitude: Returns response with usage stats, costs, and conversation UUID
  • Result: Ship production AI features. Zero prompt maintenance headaches.

๐Ÿ’ฅ Why This Slaps Hardcoded Prompts

Embedding prompts in workflows is a vibe-killer. n8n-nodes-latitude makes hardcoding look ancient.

โŒ The Old Way (Pain) โœ… The Latitude Way (Glory)
  1. Hardcode prompt in n8n HTTP node.
  2. Manually build JSON payload.
  3. Change prompt โ†’ Redeploy workflow.
  4. No version history. No rollback.
  5. Debug blind with no observability.
  1. Select prompt from dropdown.
  2. Parameters auto-populate.
  3. Change prompt in Latitude โ†’ Live instantly.
  4. Version control + cost tracking.
  5. Full conversation logs in dashboard. โ˜•

We're not just calling an API. We're giving you centralized prompt management with dynamic parameter extraction, conversation continuity, and automatic SDK integration that handles all the complexity.


๐Ÿš€ Get Started in 60 Seconds

Community Nodes (Recommended)

The fastest way to get started. No terminal required.

  1. Go to Settings โ†’ Community Nodes
  2. Click Install
  3. Enter n8n-nodes-latitude
  4. Confirm installation

That's it. The node appears in your node palette.

Manual Installation

For self-hosted n8n or custom setups:

# Navigate to your n8n installation
cd ~/.n8n/nodes

# Install the package
npm install n8n-nodes-latitude

# Restart n8n

โœจ Zero Config: After installation, add your Latitude credentials and start building. The node handles SDK initialization, auth, and API versioning automatically.


โœจ Feature Breakdown: The Secret Sauce

Feature What It Does Why You Care
๐ŸŽฏ Auto Parameter Detection
No JSON wrestling
Extracts {{ variables }} from prompt content automatically Select prompt โ†’ Parameters appear. Done.
๐Ÿ’ฌ Conversation Continuity
Multi-turn chats
Continue conversations using UUID from previous runs Build chatbots and agents with memory
๐Ÿค– AI Agent Support
usableAsTool: true
Works as a tool in n8n AI workflows Plug into AI Agent node directly
๐Ÿ“Š Token & Cost Tracking
Full observability
Returns usage, cost, and toolCalls from each run Know exactly what you're spending
๐Ÿ  Self-Hosted Support
Custom gateway URL
Point to your own Latitude instance Enterprise-ready, air-gapped deployments
๐Ÿ“ External Logging
Create log entries
Log conversations from external AI calls to Latitude Unified analytics across all AI touchpoints
โšก Hot Reload
No redeploy needed
Change prompts in Latitude, live instantly in n8n Iterate on prompts without workflow changes
๐Ÿ”’ Secure by Default
Credentials encrypted
API keys never exposed, errors sanitized Production-ready security

๐ŸŽฎ Operations Reference

โ–ถ๏ธ

Run Prompt
Execute AI prompts

๐Ÿ’ฌ

Chat
Continue conversations

๐Ÿ“

Create Log
Log external AI calls

Run Prompt โ–ถ๏ธ

Execute an AI prompt from your Latitude project with automatic parameter detection.

Parameter Type Required Description
Prompt Path Dropdown Yes Select from your Latitude prompts โ€” shows required parameters
Parameters Key-Value No Map values to {{ variables }}. Supports n8n expressions
Simplify Output Boolean No Return clean data or full conversation history
Custom Identifier String No Tag runs for filtering in Latitude dashboard
Version UUID String No Use specific version instead of live

Example Configuration:

Prompt Path: "marketing/personalized-email"
Parameters:
  - customer_name: {{ $json.name }}
  - product: {{ $json.product }}
  - tone: "professional"

Simplified Output:

{
  "uuid": "conv_abc123-def456",
  "text": "Dear John, thank you for your interest in...",
  "usage": {
    "promptTokens": 150,
    "completionTokens": 200,
    "totalTokens": 350
  },
  "cost": 0.0035
}

Chat ๐Ÿ’ฌ

Continue a conversation using the UUID from a previous prompt run.

Parameter Type Required Description
Conversation UUID String Yes UUID from a previous Run Prompt response
Messages Collection Yes New messages to add to the conversation
Simplify Output Boolean No Return clean data or full conversation history

Example โ€” Building a Chatbot:

// First node: Run Prompt (initial)
// Returns: { uuid: "conv_abc123", text: "How can I help?" }

// Second node: Chat (continue)
Conversation UUID: {{ $('Latitude').item.json.uuid }}
Messages:
  - Role: user
    Content: "What's the weather like?"

Create Log ๐Ÿ“

Log conversations from external AI calls (OpenAI, Anthropic, etc.) to your Latitude project for unified analytics.

Parameter Type Required Description
Prompt Path Dropdown Yes The prompt to associate this log with
Messages Collection Yes The conversation messages to log
Response String No The AI-generated response text

Use Case: You're calling OpenAI directly but want all your AI usage visible in Latitude's dashboard:

Prompt Path: "support/ticket-classifier"
Messages:
  - Role: user
    Content: {{ $json.ticket_body }}
Response: {{ $json.openai_response }}

โš™๏ธ Credentials Setup

You need a Latitude.so account with API access.

Field Description Where to Find
API Key Your Latitude API key Dashboard โ†’ Settings โ†’ API Keys (format: lat_...)
Project ID Numeric project identifier Dashboard โ†’ Project Settings or URL
Gateway URL Optional โ€” Custom gateway for self-hosted Your instance URL (e.g., https://latitude.yourcompany.com)

Setting Up Credentials

  1. Go to Credentials in n8n
  2. Click New Credential
  3. Search for Latitude API
  4. Fill in your API Key and Project ID
  5. (Optional) Add Gateway URL for self-hosted instances
  6. Click Save โ€” Credentials are automatically validated

๐Ÿ”’ Security Note: Your API key is encrypted at rest and never exposed in logs or error messages.


๐Ÿ”ฅ Workflow Examples

Basic: Webhook โ†’ AI Response

Webhook โ†’ Latitude (Run Prompt) โ†’ Respond to Webhook

Perfect for: Slack bots, API endpoints, form processing.

Advanced: Multi-Turn Chatbot

Webhook โ†’ Latitude (Run) โ†’ Set UUID โ†’ Loop โ†’ Latitude (Chat) โ†’ Respond

Perfect for: Customer support bots, interactive assistants.

Hybrid: External AI + Latitude Logging

Webhook โ†’ OpenAI โ†’ Latitude (Create Log) โ†’ Respond

Perfect for: Using other providers but want Latitude's analytics.

AI Agent Integration

AI Agent โ†’ Latitude Tool โ†’ Agent Output

Perfect for: ReAct agents, function calling, tool use.


๐Ÿ”ง Compatibility

Requirement Version
n8n 1.0.0+
Node.js 18.0.0+
Latitude SDK 5.2.2+

๐Ÿ”ฅ Common Issues & Quick Fixes

Expand for troubleshooting tips
Problem Solution
Authentication failed Verify API key format (lat_...) and Project ID in Latitude dashboard. Keys are project-specific.
Prompt not found Refresh the dropdown. Verify the prompt exists and is published (not draft).
Parameters not loading Check credentials are valid. Run credential test. Ensure prompt has {{ variables }}.
Empty response Prompt might be in draft mode. Check Latitude dashboard for prompt status.
Chat fails Verify conversationUuid is from a recent run. UUIDs may expire based on project settings.
Self-hosted connection issues Ensure Gateway URL includes protocol (https://). Check firewall rules.
Rate limiting Latitude has usage limits. Check your plan in the dashboard.

๐Ÿ› ๏ธ Development

Want to contribute or customize?

# Clone the repo
git clone https://github.com/yigitkonur/n8n-nodes-latitude.git
cd n8n-nodes-latitude

# Install dependencies
npm install

# Development mode (watch for changes)
npm run dev

# Build for production
npm run build

# Lint and format
npm run lint:fix
npm run format

Project Structure

โ”œโ”€โ”€ credentials/          # Latitude API credential definition
โ”œโ”€โ”€ nodes/Latitude/
โ”‚   โ”œโ”€โ”€ actions/          # Operation implementations
โ”‚   โ”‚   โ”œโ”€โ”€ runPrompt.operation.ts
โ”‚   โ”‚   โ”œโ”€โ”€ chat.operation.ts
โ”‚   โ”‚   โ””โ”€โ”€ createLog.operation.ts
โ”‚   โ”œโ”€โ”€ methods/          # Dynamic dropdown loaders
โ”‚   โ”œโ”€โ”€ shared/           # Types, utils, transport
โ”‚   โ””โ”€โ”€ Latitude.node.ts  # Main node definition
โ””โ”€โ”€ icons/                # Light/dark mode icons

๐Ÿ“š Resources


๐Ÿค Contributing

Contributions are welcome! This is how we make it better together.

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

Built with ๐Ÿ”ฅ because hardcoding AI prompts in workflows is a soul-crushing waste of time.

MIT ยฉ YiฤŸit Konur

GitHub โ€ข npm โ€ข Latitude.so โ€ข n8n.io

About

n8n community node for Latitude.so. Enables LLM prompt integration with auto-parameter detection, conversation continuity, and token cost tracking.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published