Getting Started

Langfuse Integration

Langfuse provides observability and tracing for LLM applications.

Installation

pip install langfuse openai

Configuration

import os

# Langfuse configuration
os.environ["LANGFUSE_SECRET_KEY"] = "sk-lf-..."
os.environ["LANGFUSE_PUBLIC_KEY"] = "pk-lf-..."
os.environ["LANGFUSE_HOST"] = "https://cloud.langfuse.com"

# LangMart configuration
os.environ["OPENAI_API_KEY"] = "your-langmart-api-key"

Basic Usage

from langfuse.openai import openai

client = openai.OpenAI(
    base_url="https://api.langmart.ai/v1",
)

# Requests are automatically logged to Langfuse
response = client.chat.completions.create(
    model="anthropic/claude-opus-4.5",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Tell me a fun fact about space."},
    ],
    name="fun-fact-request",
)

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

Advanced Tracing

from langfuse import observe
from langfuse.openai import openai

client = openai.OpenAI(base_url="https://api.langmart.ai/v1")

@observe()
def analyze_text(text: str):
    summary = summarize_text(text)
    sentiment = analyze_sentiment(summary)
    return {"summary": summary, "sentiment": sentiment}

@observe()
def summarize_text(text: str) -> str:
    response = client.chat.completions.create(
        model="openai/gpt-5.2",
        messages=[
            {"role": "system", "content": "Summarize concisely."},
            {"role": "user", "content": f"Summarize: {text}"},
        ],
        name="summarize-text",
    )
    return response.choices[0].message.content

@observe()
def analyze_sentiment(text: str) -> str:
    response = client.chat.completions.create(
        model="openai/gpt-5.2",
        messages=[
            {"role": "system", "content": "Analyze sentiment."},
            {"role": "user", "content": f"Sentiment: {text}"},
        ],
        name="analyze-sentiment",
    )
    return response.choices[0].message.content

Learn More