docker-compose.yml

version: "3.9"

services:
  redis:
    image: redis
    restart: always
    container_name: chatglm-api-redis
    hostname: chatglm-api-redis
    volumes:
    - ./redis:/data
    - /etc/timezone:/etc/timezone
    - /etc/localtime:/etc/localtime
    environment:
    - TZ=Asia/Shanghai
    command: redis-server --bind 0.0.0.0 --requirepass 123 --appendonly yes --appendfsync always

  chatglm-api:
    image: chatglm2:openai-api-beta-0.0.1
    build: .
    restart: always
    container_name: chatglm-api
    hostname: chatglm-api
    ports:
    - 8000:8000
    volumes:
    - ./.env:/chatglm-api/.env
    - ./model:/model
    command: uvicorn app:api --host 0.0.0.0 --port 8000 --log-config log.json
    deploy:
      resources:
        reservations:
          devices:
          - driver: nvidia
            device_ids: ["0","1","2","3"]
            capabilities: [gpu]
    healthcheck:
      test:
        [
          "CMD-SHELL",
          "curl -s -I http://127.0.0.1:8000/docs | grep '200 OK'",
        ]
      interval: 30s
      timeout: 60s
      retries: 180