services:
  ollama-piha:
    image: ollama/ollama:latest
    container_name: ollama-piha
    restart: unless-stopped
    ports:
      # Loopback: healthcheck.sh curls localhost directly on the node. LAN IP: kb-query@PIHA
      # reaches this over the host's LAN interface -- kb-query runs in its own Docker network
      # (separate compose project), same reasoning as kb-query's KB_DSN reaching kb-postgres.
      # Requires .env (from env.example) next to this file at deploy.
      - "127.0.0.1:11434:11434"
      - "${LAN_BIND_IP}:11434:11434"
    environment:
      # Module 5 phase 4 plan §2 decision 2 / §5 requirement: the model is loaded only for the
      # duration of a request and released immediately after -- RPi5 has no GPU and limited RAM
      # (hosts/piha/capabilities.yaml: arm64, 4 cores, no acceleration), so this is a short burst
      # spike (idle Ollama binary ~100 MB) rather than a permanent ~1.5-2 GB resident cost. This
      # is a fallback-only path (kb-query only reaches this when SOLARIA is down/times out), not
      # the default hot path, so paying a cold-load per request here is the correct trade-off.
      - OLLAMA_KEEP_ALIVE=0
    volumes:
      - /opt/homelab/data/ollama-piha:/root/.ollama
    # No GPU reservation -- PIHA is arm64 with no acceleration (hosts/piha/capabilities.yaml),
    # unlike services/ollama@SOLARIA. CPU-only inference here is expected to be slower; that is
    # exactly what the plan §5 live calibration step measures before this is trusted as a
    # default fallback (see README.md "Calibration status").