Skip to main content
LiteLLM allows developers to call all LLM APIs using the OpenAI format. LiteLLM Proxy is a proxy server to call 100+ LLMs in OpenAI format. Both are supported by this OpenInference auto-instrumentation, and traces can be viewed in Arize. Any calls made to the following functions will be automatically captured by this integration:
  • completion()
  • acompletion()
  • completion_with_retries()
  • embedding()
  • aembedding()
  • image_generation()
  • aimage_generation()

​
Launch Arize

To get started, sign up for a free Arize account and get your Space ID and API Key.

​
Install

pip install openinference-instrumentation-litellm litellm arize-otel

​
Setup

Use the register function to connect your application to Arize and instrument LiteLLM. 
# Import open-telemetry dependencies
from arize.otel import register

# Setup OTel via our convenience function
tracer_provider = register(
    space_id = "your-space-id", # in app space settings page
    api_key = "your-api-key", # in app space settings page
    project_name = "your-project-name", # name this to whatever you would like
)

# Import the instrumentor from OpenInference
from openinference.instrumentation.litellm import LiteLLMInstrumentor

# Instrument LiteLLM
LiteLLMInstrumentor().instrument(tracer_provider=tracer_provider)
Add any API keys needed by the models you are using with LiteLLM. For example, if using an OpenAI model: 
import os
os.environ["OPENAI_API_KEY"] = "PASTE_YOUR_API_KEY_HERE"

​
Run LiteLLM

You can now use LiteLLM as normal and calls will be traced in Arize. 
import litellm

# Ensure the required API key (e.g., OPENAI_API_KEY) is set in your environment
completion_response = litellm.completion(
    model="gpt-3.5-turbo",
    messages=[{"content": "What's the capital of China?", "role": "user"}]
)
print(completion_response)

​
Observe

Traces should now be visible in your Arize account!

​
Resources