Langfuse is an open-source LLM observability platform that helps you monitor, debug, and analyze your LLM applications. When combined with Portkey, you get the best of both worlds: Langfuse’s detailed observability and Portkey’s advanced AI gateway features.

This integration allows you to:

  • Track all LLM requests in Langfuse while routing through Portkey
  • Use Portkey’s 250+ LLM providers with Langfuse observability
  • Implement advanced features like caching, fallbacks, and load balancing
  • Maintain detailed traces and analytics in both platforms

​
Quick Start Integration

Since Portkey provides an OpenAI-compatible API, integrating with Langfuse is straightforward using Langfuse’s OpenAI wrapper.

​
Installation

pip install portkey-ai langfuse openai

​
Basic Setup

import os
from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL

# Set your Langfuse credentials
os.environ["LANGFUSE_PUBLIC_KEY"] = "YOUR_LANGFUSE_PUBLIC_KEY"
os.environ["LANGFUSE_SECRET_KEY"] = "YOUR_LANGFUSE_SECRET_KEY"

# Import OpenAI from langfuse
from langfuse.openai import OpenAI

# Initialize the client
client = OpenAI(
    api_key="YOUR_OPENAI_API_KEY",  # Your LLM provider API key
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        api_key="YOUR_PORTKEY_API_KEY",
        provider="@YOUR_PROVIDER",
        # config="YOUR_CONFIG_ID",        # Optional: Use saved configs
        # trace_id="YOUR_TRACE_ID",       # Optional: Custom trace ID
    )
)

# Make a request
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello, world!"}],
)

print(response.choices[0].message.content)

This integration automatically logs requests to both Langfuse and Portkey, giving you observability data in both platforms.

​
Using Portkey Features with Langfuse

​
1. LLM Integrations

LLM Integrations in Portkey allow you to securely manage API keys and set usage limits. Use them with Langfuse for better security:

from langfuse.openai import OpenAI
from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL

client = OpenAI(
    api_key="PORTKEY_API_KEY",
    base_url=PORTKEY_GATEWAY_URL
)

response = client.chat.completions.create(
    model="@openai/gpt-4o",
    messages=[{"role": "user", "content": "Explain quantum computing"}]
)

​
2. Multiple Providers

Switch between 250+ LLM providers while maintaining Langfuse observability:

client = OpenAI(
    api_key="YOUR_OPENAI_KEY",
    base_url=PORTKEY_GATEWAY_URL
)

​
3. Advanced Routing with Configs

Use Portkey’s config system for advanced features while tracking in Langfuse:

# Create a config in Portkey dashboard first, then reference it
client = OpenAI(
    api_key="PORTKEY_API_KEY",
    base_url=PORTKEY_GATEWAY_URL
)

Example config for fallback between providers:

{
  "strategy": {
    "mode": "fallback"
  },
  "targets": [
    {
      "provider":"@openai-key",
      "override_params": {"model": "gpt-4o"}
    },
    {
      "provider":"@anthropic-key",
      "override_params": {"model": "claude-3-opus-20240229"}
    }
  ]
}

​
4. Caching for Cost Optimization

Enable caching to reduce costs while maintaining full observability:

config = {
    "cache": {
        "mode": "semantic",
        "max_age": 3600
    },
    "provider":"@YOUR_PROVIDER"
}

client = OpenAI(
    api_key="PORTKEY_API_KEY",
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        config=config
    )
)

​
5. Custom Metadata and Tracing

Add custom metadata visible in both Langfuse and Portkey:

client = OpenAI(
    api_key="PORTKEY_API_KEY",
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        metadata={
            "user_id": "user_123",
            "session_id": "session_456",
            "environment": "production"
        },
        trace_id="langfuse-trace-001"
    )
)

Fallbacks

Automatically switch to backup targets if the primary target fails.

Conditional Routing

Route requests to different targets based on specified conditions.

Load Balancing

Distribute requests across multiple targets based on defined weights.

Caching

Enable caching of responses to improve performance and reduce costs.

Smart Retries

Automatic retry handling with exponential backoff for failed requests

Budget Limits

Set and manage budget limits across teams and departments. Control costs with granular budget limits and usage tracking.

​
Observability Features

With this integration, you get:

​
In Langfuse:

  • request/response logging
  • Latency tracking
  • Token usage analytics
  • Cost calculation
  • Trace visualization

​
In Portkey:

  • Request logs with provider details
  • Advanced analytics across providers
  • Cost tracking and budgets
  • Performance metrics
  • Custom dashboards
  • Token usage analytics

​
Migration Guide

If you’re already using Langfuse with OpenAI, migrating to use Portkey is simple:

from langfuse.openai import OpenAI

client = OpenAI(
    api_key="YOUR_OPENAI_KEY"
)

​
Next Steps

​
Resources

For enterprise support and custom features, contact our enterprise team.