LLM Observability for LiteLLM

Overview

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

Default configuration

1. Ensure you have the latest version of Laminar

   pip install -U lmnr[all]
   
2. Initialize Laminar

   Laminar auto-instruments LiteLLM. No callback is required.

   import litellm
   from lmnr import Laminar
   
   Laminar.initialize(project_api_key="LMNR_PROJECT_API_KEY")
   
3. LaminarLiteLLMCallback is deprecated and does nothing. Remove it if you already use it.

4. Run your code and see traces in Laminar

   Example code:

   import litellm
   from lmnr import Laminar
   
   Laminar.initialize(project_api_key="LMNR_PROJECT_API_KEY")
   
   response = litellm.completion(
       model="gpt-4.1-nano",
       messages=[
         {"role": "user", "content": "What is the capital of France?"}
       ],
   )