Langfuse

Using Infron AI with Langfuse

Langfuse provides observability and analytics for LLM applications. Since Infron AI uses the OpenAI API schema, you can utilize Langfuse's native integration with the OpenAI SDK to automatically trace and monitor your Infron AI API calls.

Installation

pip install langfuse openai

Configuration

Set up your environment variables:

import os

# Set your Langfuse API keys
LANGFUSE_SECRET_KEY="sk-lf-..."
LANGFUSE_PUBLIC_KEY="pk-lf-..."
# EU region
LANGFUSE_HOST="https://cloud.langfuse.com"
# US region
# LANGFUSE_HOST="https://us.cloud.langfuse.com"

# Set your Infron AI API key
os.environ["OPENAI_API_KEY"] = "${API_KEY}"

Simple LLM Call

Since Infron AI provides an OpenAI-compatible API, you can use the Langfuse OpenAI SDK wrapper to automatically log Infron AI calls as generations in Langfuse:

# Import the Langfuse OpenAI SDK wrapper
from langfuse.openai import openai

# Create an OpenAI client with Infron AI's base URL
client = openai.OpenAI(
    base_url="https://llm.onerouter.pro/v1"
)

# Make a chat completion request
response = client.chat.completions.create(
    model="{{MODEL}}",
    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 reply
print(response.choices[0].message.content)

Advanced Tracing with Nested Calls

Use the @observe() decorator to capture execution details of functions with nested LLM calls:

from langfuse import observe
from langfuse.openai import openai

# Create an OpenAI client with Infron AI's base URL
client = openai.OpenAI(
    base_url="https://llm.onerouter.pro/v1",
)

@observe()  # This decorator enables tracing of the function
def 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 traced
def summarize_text(text: str):
    return client.chat.completions.create(
        model="{{MODEL}}",
        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 traced
def analyze_sentiment(summary: str):
    return client.chat.completions.create(
        model="{{MODEL}}",
        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 usage
text_to_analyze = "OneRouter's unified API has significantly advanced the field of AI development, setting new standards for model accessibility."
result = analyze_text(text_to_analyze)
print(result)