环境
- Windows 11系统，使用
wls - Windows 开启Clash VPN连接外网
- docker 版本：26.1.4
- docker-compose ：v2.27.1
设备名称 win11
处理器 13th Gen Intel(R) Core(TM) i7-13700KF 3.40 GHz
机带 RAM 32.0 GB (31.8 GB 可用)
设备 ID 84550625-3CC6-40FD-B602-9899F3FBBB92
产品 ID 00330-80000-00000-AA842
系统类型 64 位操作系统, 基于 x64 的处理器
笔和触控 没有可用于此显示器的笔或触控输入
PS C:\Users\scien> docker --version
Docker version 26.1.4, build 5650f9b
PS C:\Users\scien> docker-compose --version
Docker Compose version v2.27.1-desktop.1
PS C:\Users\scien> wsl --version
WSL 版本： 2.2.4.0
内核版本： 5.15.153.1-2
WSLg 版本： 1.0.61
MSRDC 版本： 1.2.5326
Direct3D 版本： 1.611.1-81528511
DXCore 版本： 10.0.26091.1-240325-1447.ge-release
Windows 版本： 10.0.22631.3880
PS C:\Users\scien> nvidia-smi
Sat Jul 20 23:20:18 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 555.99 Driver Version: 555.99 CUDA Version: 12.5 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Driver-Model | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 4070 Ti WDDM | 00000000:01:00.0 On | N/A |
| 0% 37C P2 35W / 285W | 11582MiB / 12282MiB | 1% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
lvxinliang@win11:/mnt/d/workspace/docker$ nvidia-smi
Sat Jul 20 23:20:05 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 555.52.01 Driver Version: 555.99 CUDA Version: 12.5 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 4070 Ti On | 00000000:01:00.0 On | N/A |
| 0% 35C P8 4W / 285W | 11609MiB / 12282MiB | 1% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 1 C /python3.11 N/A |
| 0 N/A N/A 27 C /ollama_llama_server N/A |
+-----------------------------------------------------------------------------------------+
单独搭建ollama 与 open-webui
docker network create my_custom_network
docker run -d --gpus=all -v ollama:/root/.ollama -p 11434:11434 --name ollama --hostname ollama --network my_custom_network ollama/ollama
docker run -d -p 3000:8080 --gpus all --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --network my_custom_network --restart always ghcr.io/open-webui/open-webui:cuda
配置
搭建ragflow +ollama + open-webui
运行ragflow
按照https://github.com/infiniflow/ragflow/blob/main/README_zh.md中的快速开始
docker compose -f docker-compose-CN.yml up -d
查看docker内网络信息
lvxinliang@win11:/mnt/d/workspace/docker$ docker network ls
NETWORK ID NAME DRIVER SCOPE
5741ae3858b7 bridge bridge local
0a607a9761fb docker_ragflow bridge local
95d9ff87fd11 host host local
affe05591fd6 my_custom_network bridge local
b25daea68bd3 none null local
docker运行镜像并指定网络
docker run -d --gpus=all -v ollama:/root/.ollama -p 11434:11434 --name ollama --hostname ollama --network docker_ragflow ollama/ollama
docker run -d -p 3000:8080 --gpus all --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --network docker_ragflow --restart always ghcr.io/open-webui/open-webui:cuda
