settings.yaml

llm:
  api_key: "3bf18984-b4df-49ba-a30b-6cbae3964b08"
  type: openai_chat
  model_supports_json: true
  model: "claude-3-5-sonnet-20240620"
  api_base: "http://localhost:30012/v1"
  # max_tokens: 10000 # Adjusted based on Claude 3 Haiku's typical context window
  request_timeout: 30
  tokens_per_minute: 100000
  requests_per_minute: 1000
  max_retry_wait: 5
  temperature: 0.1
  
  embeddings:
  async_mode: threaded
  llm:
    type: openai_embedding
    model: "mixedbread-ai/mxbai-embed-large-v1"
    api_base: "http://localhost:7997"