version: v0.1
listener:
  address: 127.0.0.1
  port: 8080 #If you configure port 443, you'll need to update the listener with tls_certificates
  message_format: huggingface

# Centralized way to manage LLMs, manage keys, retry logic, failover and limits in a central way
llm_providers:
  - name: OpenAI
    provider: openai
    access_key: OPENAI_API_KEY
    model: gpt-4o
    default: true

# default system prompt used by all prompt targets
system_prompt: |
  You are a network assistant that just offers facts; not advice on manufacturers or purchasing decisions.

prompt_targets:
    - name: reboot_devices
      description: Reboot specific devices or device groups
      endpoint:
        name: app_server
        path: /agent/device_reboot
      parameters:
        - name: device_ids
          type: list
          description: A list of device identifiers (IDs) to reboot.
          required: true
        - name: time_range
          type: int
          description: Optional time range in days for reboot operations. Defaults to 7.
    - name: network_qa
      endpoint:
        name: app_server
        path: /agent/network_summary
      description: Handle general Q/A related to networking.
      default: true
    - name: device_summary
      description: Retrieve statistics for specific devices within a time range
      endpoint:
        name: app_server
        path: /agent/device_summary
      parameters:
        - name: device_ids
          type: list
          description: A list of device identifiers (IDs) to retrieve statistics for.
          required: true  # device_ids are required to get device statistics
        - name: time_range
          type: int
          description: Time range in days for which to gather device statistics. Defaults to 7.
          default: "7"

# Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.
endpoints:
  app_server:
    # value could be ip address or a hostname with port
    # this could also be a list of endpoints for load balancing
    # for example endpoint: [ ip1:port, ip2:port ]
    endpoint: host.docker.internal:18083
    # max time to wait for a connection to be established
    connect_timeout: 0.005s

ratelimits:
  - model: gpt-4
    selector:
      key: selector-key
      value: selector-value
    limit:
      tokens: 1
      unit: minute