n8n-nodes-ai-langfuse

n8n community nodes for AI LLM providers with Langfuse observability

This project is proudly developed and maintained by Wistron DXLab.

Supported Providers:

• OpenAI (GPT-4, GPT-4o, etc.)
• Google Gemini (Gemini 2.5, Gemini 1.5, etc.)

npm package: https://www.npmjs.com/package/n8n-nodes-openai-langfuse

Features

• OpenAI Chat Node (lmChatOpenAiLangfuse)

  • Support for OpenAI-compatible chat models (e.g., gpt-4.1-mini, gpt-4o)
  • Automatic Langfuse tracing for every request and response
  • Custom metadata injection: sessionId, userId, and structured JSON

• Google Gemini Chat Node (lmChatGoogleGeminiLangfuse)

  • Support for Google Gemini models (e.g., gemini-2.5-flash, gemini-1.5-pro)
  • Automatic Langfuse tracing for every request and response
  • Safety settings configuration
  • Custom metadata injection: sessionId, userId, and structured JSON

n8n is a fair-code licensed workflow automation platform.

Installation Credentials Operations Compatibility Resources

Installation

Follow the installation guide in the official n8n documentation for community nodes.

Community Nodes (Recommended)

For n8n v0.187+, install directly from the UI:

1. Go to Settings → Community Nodes
2. Click Install
3. Enter n8n-nodes-openai-langfuse in Enter npm package name
4. Agree to the risks of using community nodes
5. Select Install

Manual Installation

For a standard installation:

# Go to your n8n installation directory
cd ~/.n8n
# Install the node
npm install n8n-nodes-openai-langfuse
# Restart n8n to apply the node
n8n start

Credentials

OpenAI + Langfuse Credentials

|Field Name|Description|Example| |-----|-----|-----| |OpenAI API Key|Your API key for accessing the OpenAI-compatible endpoint|sk-abc123...| |OpenAI Organization ID|(Optional) Your OpenAI organization ID|org-xyz789| |OpenAI Base URL|Full URL to your OpenAI-compatible endpoint|default: https://api.openai.com/v1| |Langfuse Base URL|The base URL of your Langfuse instance|https://cloud.langfuse.com| |Langfuse Public Key|Langfuse public key for tracing|pk-xxx| |Langfuse Secret Key|Langfuse secret key for tracing|sk-xxx|

Google Gemini + Langfuse Credentials

|Field Name|Description|Example| |-----|-----|-----| |Google API Key|Your Google AI Studio API key|AIza...| |Langfuse Base URL|The base URL of your Langfuse instance|https://cloud.langfuse.com| |Langfuse Public Key|Langfuse public key for tracing|pk-xxx| |Langfuse Secret Key|Langfuse secret key for tracing|sk-xxx|

🔑 How to find your Langfuse keys: Log in to your Langfuse dashboard, then go to: Settings → Projects → [Your Project] to retrieve publicKey and secretKey.

🔑 How to get a Google API Key: Go to Google AI Studio to create an API key.

Operations

Both nodes let you inject Langfuse-compatible metadata into your LLM requests. You can trace every run with context such as sessionId, userId, and any custom metadata.

Supported Fields

| Field | Type | Description | |----------|----------|----------| | sessionId | string | Logical session ID to group related runs | | userId | string | ID representing the end user making the request | | metadata | object | Custom JSON object with additional context (e.g., workflowId, env) |

Google Gemini Additional Options

| Option | Type | Description | |----------|----------|----------| | temperature | number | Controls randomness (0-2) | | topP | number | Nucleus sampling (0-1) | | topK | number | Top-k token selection (1-100) | | maxOutputTokens | number | Maximum tokens to generate | | safetySettings | object | Content filtering configuration |

Available Gemini Models

• Gemini 2.5 Series: gemini-2.5-flash, gemini-2.5-pro
• Gemini 2.0 Series: gemini-2.0-flash-thinking-exp, gemini-2.0-flash-exp
• Gemini 1.5 Series: gemini-1.5-pro, gemini-1.5-flash, gemini-1.5-flash-8b
• Gemini 1.0 Series: gemini-1.0-pro, gemini-pro

Compatibility

• Requires n8n version 1.0.0 or later
• Compatible with:
  • OpenAI official API (https://api.openai.com)
  • Any OpenAI-compatible LLM (e.g. via LiteLLM, LocalAI, Azure OpenAI)
  • Google Generative AI API (https://generativelanguage.googleapis.com)
  • Langfuse Cloud and self-hosted instances

Resources

• n8n Community Node Docs
• Langfuse Documentation
• Google AI Studio
• n8n Community Forum

Version History

• v0.2.0 – Added Google Gemini chat node with Langfuse integration
• v0.1.x – OpenAI + Langfuse integration

License

MIT © 2025 Wistron DXLab