AgentOps requires a minor adjustment to how you call LiteLLM. This is because of other existing integrations that use the completion function.
import agentopsimport litellmagentops.init(<INSERT YOUR API KEY HERE>)# Some code here...response = litellm.completion(model="gpt-4o", messages=messages)# Some code here...agentops.end_session('Success')
Set your API key as an .env variable for easy access.
