​
Overview

LiteLLM is a framework/library for building LLM applications that simplifies accessing many models across different providers.

​
Default configuration

LiteLLM is well integrated with OpenTelemetry, so you only need to specify the configuration through the environment variables.

1

Install the opentelemetry packages

First, install the opentelemetry packages:

pip install opentelemetry-api opentelemetry-sdk\
  opentelemetry-exporter-otlp
2

install LiteLLM

For opentelemetry callback to work, you need to install LiteLLM with the proxy extra of the LiteLLM package.

pip install litellm[proxy]
3

Set the environment variables

LMNR_PROJECT_API_KEY="<your-project-api-key>"
OTEL_EXPORTER="otlp_grpc"
OTEL_ENDPOINT="https://api.lmnr.ai:8443"
OTEL_HEADERS="authorization=Bearer $LMNR_PROJECT_API_KEY"

authorization must start with a lowercase a. This is different from common HTTP headers convention.

4

Enable otel callback in the code

litellm.callbacks = ['otel']
5

Run your code and see traces in Laminar

​
Using Laminar’s features

If you want to use Laminar’s features, such as sessions, manual spans, observe decorator, you will need to install and initialize Laminar.

1

Install Laminar

pip install lmnr
2

Initialize Laminar

from lmnr import Laminar
Laminar.initialize(project_api_key="LMNR_PROJECT_API_KEY")

This, however, will most likely result in your LLM calls being double-traced – once by LiteLLM and once by Laminar. To avoid this, you can disable automatic Laminar instruments at initialization.

Laminar.initialize(project_api_key="LMNR_PROJECT_API_KEY", instruments=set())