docker利用docker-compose-gpu.yml启动RAGFLOW，文档解析出错【亲测已解决】

0.问题说明

想要让RAGFLOW利用GPU资源跑起来，可以选择docker-compose-gpu.yml启动。（但是官网启动案例是×86平台的不是NVIDIA GPU的，docker-compose-gpu.yml又是第三方维护，所以稍有问题）

1.问题

docker利用docker-compose-gpu.yml启动RAGFLOW，文档解析出错
报错：

18:10:23 [ERROR][Exception]: NCCL Error 2: unhandled system error (run with NCCL_DEBUG=INFO for details)

2.解决方案

（1）修改docker-compose-gpu.yml文件（稍作改动）

下面是修改后的完整docker-compose-gpu.yml文件，可以直接复制。

# The RAGFlow team do not actively maintain docker-compose-gpu.yml, so use them at your own risk.
# However, you are welcome to file a pull request to improve it.
include:
  - ./docker-compose-base.yml
 
services:
  ragflow:
    depends_on:
      mysql:
        condition: service_healthy
    image: ${RAGFLOW_IMAGE}
    container_name: ragflow-server
    ports:
      - ${SVR_HTTP_PORT}:9380
      - 80:80
      - 443:443
    volumes:
      - ./ragflow-logs:/ragflow/logs
      - ./nginx/ragflow.conf:/etc/nginx/conf.d/ragflow.conf
      - ./nginx/proxy.conf:/etc/nginx/proxy.conf
      - ./nginx/nginx.conf:/etc/nginx/nginx.conf
    env_file: .env
    ipc: host
    shm_size: 8g
    environment:
      - TZ=${TIMEZONE}
      - HF_ENDPOINT=${HF_ENDPOINT}
      - MACOS=${MACOS}
      - NCCL_DEBUG=INFO
    networks:
      - ragflow
    restart: on-failure
    # https://docs.docker.com/engine/daemon/prometheus/#create-a-prometheus-configuration
    # If you're using Docker Desktop, the --add-host flag is optional. This flag makes sure that the host's internal IP gets exposed to the Prometheus container.
    extra_hosts:
      - "host.docker.internal:host-gateway"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

参数解释：
ipc: host：允许容器共享主机的IPC命名空间，解决NCCL多卡通信问题
shm_size: 8g：增大共享内存容量（默认64MB不足）

（2）通过docker-compose-gpu.yml重新启动RAGFLOW

docker compose -f docker-compose-gpu.yml up -d

（3）运行ragflow-server服务器

docker logs -f ragflow-server

（4）检查是否成功进行文档解析

成功解析如下结果：

到此，问题解决！