litellm_config.yaml

model_list:
  # "openai-model" is the alias the app requests (backend LLMModel Literal +
  # frontend). It is a GROUP of two interchangeable chat backends — Azure OpenAI
  # and hosted OpenAI. Provide a key for EITHER (or both); LiteLLM routes to
  # whichever authenticates and cools down one that fails. This gives deploy-time
  # flexibility without committing to a provider up front.
  #
  # NOTE: knowledge-base *embeddings* still use Azure directly (backend), so the
  # RAG features specifically require an Azure key regardless of the above.
  - model_name: openai-model
    litellm_params:
      model: os.environ/AZURE_MODEL          # e.g. azure/<chat-deployment-name>
      api_base: os.environ/AZURE_ENDPOINT    # same value the backend uses for embeddings
      api_key: os.environ/AZURE_API_KEY
      api_version: os.environ/AZURE_API_VERSION
  - model_name: openai-model
    litellm_params:
      model: os.environ/OPENAI_MODEL
      api_key: os.environ/OPENAI_API_KEY

  - model_name: local-model
    litellm_params:
      model: os.environ/LOCAL_LLM_MODEL
      api_base: os.environ/LOCAL_LLM_API_BASE

litellm_settings:
  success_callback: ["langfuse"]
  fallbacks:
    - openai-model: ["local-model"]

general_settings:
  master_key: os.environ/LITELLM_MASTER_KEY
  database_url: os.environ/DATABASE_URL