LiteLLM Integration with OpenLLmetry

Easily log your LiteLLM API calls to Helicone using OpenLLmetry.

Overview

Helicone’s OpenLLmetry integration allows you to log your LiteLLM API calls to Helicone without modifying your code.

• Python

1

Install Helicone Async

pip install helicone-async

2

Initialize Logger

from helicone_async import HeliconeAsyncLogger
from openai import OpenAI
from litellm import completion

logger = HeliconeAsyncLogger(
    api_key=HELICONE_API_KEY,
)

logger.init()

client = OpenAI(api_key=OPENAI_API_KEY)

#openai call
response = completion(
  model="gpt-3.5-turbo",
  messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}],
  metadata={
    "Helicone-Property-Hello": "World"
  }
)

#cohere call
response = completion(
  model="command-r",
  messages=[{"role": "user", "content": "Hi 👋 - i'm cohere"}],
  metadata={
    "Helicone-Property-Hello": "World"
  }
)
print(response.choices[0])

Read more about OpenLLmetry