Langfuse Integration - Helicone OSS LLM Observability

Introduction#

Langfuse is an open-source LLM observability and analytics platform that provides tracing, monitoring, and analytics for LLM applications.

Note

This integration requires only two changes to your existing Langfuse code - updating the base URL and API key.

Integration Steps#

Create an account and generate an API key

Log into Helicone or create an account. Once you have an account, you can generate an API key here.

Create a .env file in your project:

HELICONE_API_KEY=sk-helicone-...

Install Langfuse packages

pip install langfuse python-dotenv

Create a Langfuse OpenAI client using Helicone

Use Langfuse's OpenAI client wrapper with Helicone's base URL:

import osfrom dotenv import load_dotenvfrom langfuse.openai import openai# Load environment variablesload_dotenv()# Create an OpenAI client with Helicone's base URLclient = openai.OpenAI(    api_key=os.getenv("HELICONE_API_KEY"),    base_url="https://ai-gateway.helicone.ai/")

Make requests with Langfuse tracing

Your existing Langfuse code continues to work without any changes:

# Make a chat completion requestresponse = client.chat.completions.create(    model="gpt-4o",    messages=[        {"role": "system", "content": "You are a helpful assistant."},        {"role": "user", "content": "Tell me a fun fact about space."}    ],    name="fun-fact-request"  # Optional: Name of the generation in Langfuse)# Print the assistant's replyprint(response.choices[0].message.content)

You can find all 100+ supported models at helicone.ai/models.

View requests in the Helicone dashboard

All your Langfuse requests are now visible in your Helicone dashboard.

Request/response bodies
Latency metrics
Token usage and costs
Model performance analytics
Error tracking
LLM traces and spans in Langfuse
Session tracking

Tip

While you're here, why not give us a star on GitHub? It helps us a lot!

Complete Working Example#

#!/usr/bin/env python3import osfrom dotenv import load_dotenvfrom langfuse.openai import openai# Load environment variablesload_dotenv()# Create an OpenAI client with Helicone's base URLclient = openai.OpenAI(    api_key=os.getenv("HELICONE_API_KEY"),    base_url="https://ai-gateway.helicone.ai/")# Make a chat completion requestresponse = client.chat.completions.create(    model="gpt-4o",    messages=[        {"role": "system", "content": "You are a helpful assistant."},        {"role": "user", "content": "Tell me a fun fact about space."}    ],    name="fun-fact-request"  # Optional: Name of the generation in Langfuse)# Print the assistant's replyprint(response.choices[0].message.content)

Streaming Responses#

Langfuse supports streaming responses with full observability:

# Streaming examplestream = client.chat.completions.create(    model="gpt-4o",    messages=[        {"role": "user", "content": "Write a short story about a robot learning to code."}    ],    stream=True,    name="streaming-story")print("🤖 Assistant (streaming):")for chunk in stream:    if chunk.choices[0].delta.content is not None:        print(chunk.choices[0].delta.content, end="", flush=True)print("\n")

Nested Example#

import osfrom dotenv import load_dotenvfrom langfuse import observefrom langfuse.openai import openaiload_dotenv()client = openai.OpenAI(    base_url="https://ai-gateway.helicone.ai/",    api_key=os.getenv("HELICONE_API_KEY"),)@observe()  # This decorator enables tracing of the functiondef analyze_text(text: str):    # First LLM call: Summarize the text    summary_response = summarize_text(text)    summary = summary_response.choices[0].message.content    # Second LLM call: Analyze the sentiment of the summary    sentiment_response = analyze_sentiment(summary)    sentiment = sentiment_response.choices[0].message.content    return {        "summary": summary,        "sentiment": sentiment    }@observe()  # Nested function to be traceddef summarize_text(text: str):    return client.chat.completions.create(        model="gpt-4o",        messages=[            {"role": "system", "content": "You summarize texts in a concise manner."},            {"role": "user", "content": f"Summarize the following text:\n{text}"}        ],        name="summarize-text"    )@observe()  # Nested function to be traceddef analyze_sentiment(summary: str):    return client.chat.completions.create(        model="gpt-4o",        messages=[            {"role": "system", "content": "You analyze the sentiment of texts."},            {"role": "user", "content": f"Analyze the sentiment of the following summary:\n{summary}"}        ],        name="analyze-sentiment"    )# Example usagetext_to_analyze = "OpenAI's GPT-4 model has significantly advanced the field of AI, setting new standards for language generation."analyze_text(text_to_analyze)