version: '3.8'

services:
  # Vector Database - Long-term semantic memory
  qdrant:
    image: qdrant/qdrant:latest
    container_name: qdrant-memory
    ports:
      - "6333:6333"
      - "6334:6334"
    volumes:
      - qdrant-storage:/qdrant/storage
    environment:
      - QDRANT__SERVICE__HTTP_PORT=6333
    restart: unless-stopped
    # qdrant image does not ship with curl/wget; disable container-level healthcheck.
    # Host-level checks (curl to localhost:6333) are sufficient.
    # healthcheck:
    #   test: ["CMD", "sh", "-lc", ": </dev/tcp/127.0.0.1/6333" ]
    #   interval: 30s
    #   timeout: 10s
    #   retries: 3

  # Fast Buffer - Short-term memory accumulation
  redis:
    image: redis:7-alpine
    container_name: redis-memory
    ports:
      - "6379:6379"
    volumes:
      - redis-data:/data
    command: redis-server --appendonly yes
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 3s
      retries: 5

  # Embeddings - Generate vectors for semantic search
  ollama:
    image: ollama/ollama:latest
    container_name: ollama-embeddings
    ports:
      - "11434:11434"
    volumes:
      - ollama-models:/root/.ollama
    environment:
      - OLLAMA_HOST=0.0.0.0
    restart: unless-stopped
    # Pull the embedding model on first start
    entrypoint: >
      sh -c "
        ollama serve &
        sleep 5
        ollama pull snowflake-arctic-embed2
        wait
      "

volumes:
  qdrant-storage:
    driver: local
  redis-data:
    driver: local
  ollama-models:
    driver: local

networks:
  default:
    name: memory-system
    driver: bridge