docker-compose.yml

# Gleann Docker Compose — example with Ollama sidecar
#
# Usage:
#   docker compose up -d
#
# This starts gleann in server mode with a local Ollama instance
# for embedding computation.

services:
  gleann:
    build:
      context: .
      dockerfile: Dockerfile
      args:
        VERSION: ${VERSION:-dev}
    ports:
      - "8080:8080"
    volumes:
      - gleann-data:/data/indexes
    environment:
      GLEANN_INDEX_DIR: /data/indexes
      OLLAMA_HOST: http://ollama:11434
      EMBEDDING_MODEL: bge-m3:latest
      EMBEDDING_PROVIDER: ollama
    depends_on:
      ollama:
        condition: service_healthy
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 2G
        reservations:
          memory: 512M

  ollama:
    image: ollama/ollama:latest
    ports:
      - "11434:11434"
    volumes:
      - ollama-data:/root/.ollama
    healthcheck:
      test: ["CMD-SHELL", "curl -sf http://localhost:11434/api/tags || exit 1"]
      interval: 30s
      timeout: 10s
      start_period: 30s
      retries: 3
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 8G
        reservations:
          memory: 2G
    # Uncomment the following for GPU support:
    # deploy:
    #   resources:
    #     reservations:
    #       devices:
    #         - driver: nvidia
    #           count: 1
    #           capabilities: [gpu]

volumes:
  gleann-data:
  ollama-data: