# Global settings for the litellm module
litellm_settings:
  drop_params: True
  # failure_callbacks: ["sentry"]

# Model-specific settings
model_list: # refer to https://docs.litellm.ai/docs/routing
  - model_name: gpt-3.5-turbo
    litellm_params:  # parameters for litellm.completion() 
      model: azure/chatgpt-v-2 # azure/<your-deployment-name>
      api_key: your_azure_api_key
      api_version: your_azure_api_version
      api_base: your_azure_api_base
    tpm: 240000 # [OPTIONAL] To load balance between multiple deployments
    rpm: 1800 # [OPTIONAL] To load balance between multiple deployments
  - model_name: mistral
    litellm_params:
      model: ollama/mistral
      api_base: my_ollama_api_base
  - model_name: gpt-3.5-turbo
    litellm_params:
      model: gpt-3.5-turbo
      api_key: your_openai_api_key
    tpm: 1000000 # [OPTIONAL] REPLACE with your openai tpm
    rpm: 9000 # [OPTIONAL] REPLACE with your openai rpm

environment_variables:
  REDIS_HOST: your_redis_host
  REDIS_PASSWORD: your_redis_password
  REDIS_PORT: your_redis_port