# Managed by Ansible — do not edit manually
services:
  ollama:
    image: ollama/ollama:{{ ollama_version }}
    container_name: ollama
    restart: unless-stopped
    environment:
      OLLAMA_CONTEXT_LENGTH: "{{ ollama_context_length }}"
      OLLAMA_FLASH_ATTENTION: "1"
      OLLAMA_KV_CACHE_TYPE: "q8_0"
      # One model, one request at a time — keeps RAM use predictable on the shared VPS
      OLLAMA_MAX_LOADED_MODELS: "1"
      OLLAMA_NUM_PARALLEL: "1"
      # Unload the model after this idle time to free RAM for the other services
      OLLAMA_KEEP_ALIVE: "{{ ollama_keep_alive }}"
    volumes:
      - {{ ollama_data_dir }}/models:/root/.ollama
    mem_limit: {{ ollama_mem_limit }}
    networks:
      - ollama_internal

# Not exposed via Traefik. Containers that need the API join this network
# (declared as external there) and reach it at http://ollama:11434.
networks:
  ollama_internal:
    name: ollama_internal