LiteLLM

Arize has first-class support for instrumenting LiteLLM. Traces are fully OpenTelemetry compatible and can be sent to any OpenTelemetry collector for viewing.

Google Colab

Follow our colab guide

tutorials/python/llm/tracing/litellm/litellm-tracing.ipynb at main · Arize-ai/tutorialsGitHub

See the source code in our repo

Python

In this example we will instrument generate_content calls.

pip install openinference-instrumentation-litellm arize-otel litellm

Set up LiteLLMInstrumentor to trace your application and sends the traces to Phoenix at the endpoint defined below.

# 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
)

from openinference.instrumentation.litellm import LiteLLMInstrumentor
LiteLLMInstrumentor().instrument(tracer_provider=tracer_provider)

Now, all calls by litellm are instrumented!

import litellm
litellm.completion(
    model="gpt-3.5-turbo", 
    messages=[{"content": "What's the capital of China?", "role": "user"}]
)