本地WSL/Docker Desktop部署：RAGFlow-CFANZ编程社区

1、一共5个镜像：2024/6/13

$ git clone https://github.com/infiniflow/ragflow.git
$ cd ragflow/docker
$ chmod +x ./entrypoint.sh
$ docker compose up -d      #老失败，以下单独拉取
docker pull infiniflow/ragflow:dev      【RAGFLOW_VERSION=dev  10.1GB】
docker pull docker.elastic.co/elasticsearch/elasticsearch:8.11.3  【STACK_VERSION=8.11.3】
docker pull mysql:5.7.18
docker pull quay.io/minio/minio:RELEASE.2023-12-20T01-00-02Z
docker pull redis:7.2.4

docker compose up命令（-d：表示以守护进程（后台）模式运行）会根据 docker-compose.yml 文件中定义的服务配置，创建并启动相关的容器，自动下载 RAGFlow 的“开发版本 ”docker 镜像。如果你想下载并运行特定版本的 docker 镜像，在 docker/.env 文件中找到 RAGFLOW_VERSION 变量，将其改为对应版本。例如 RAGFLOW_VERSION=v0.7.0

atc@WIN11-Room208:~$ docker images
REPOSITORY                                            TAG                            IMAGE ID       CREATED        SIZE
infiniflow/ragflow                                    dev                            9fa1045436e3   26 hours ago   29.4GB
swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow   dev                            9fa1045436e3   26 hours ago   29.4GB
redis                                                 7.2.4                          5a93f6b2e391   2 months ago   173MB
quay.io/minio/minio                                   RELEASE.2023-12-20T01-00-02Z   5702ea361420   5 months ago   206MB
docker.elastic.co/elasticsearch/elasticsearch         8.11.3                         2892d2363c3c   6 months ago   2.19GB
mysql                                                 5.7.18                         d178dffba8d8   6 years ago    575MB

运行后：

atc@WIN11-Room208:~$ docker ps                                                                                                                                                                                               
CONTAINER ID   IMAGE                                                     COMMAND                  CREATED       STATUS                 PORTS                                                              NAMES              
bd77411ab716   swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:dev   "./entrypoint.sh"        4 hours ago   Up 4 hours             0.0.0.0:80->80/tcp, 0.0.0.0:443->443/tcp, 0.0.0.0:9380->9380/tcp   ragflow-server     
8ca697b33948   redis:7.2.4                                               "docker-entrypoint.s…"   4 hours ago   Up 4 hours             0.0.0.0:6379->6379/tcp                                             ragflow-redis      
b57e6da21132   quay.io/minio/minio:RELEASE.2023-12-20T01-00-02Z          "/usr/bin/docker-ent…"   4 hours ago   Up 4 hours             0.0.0.0:9000-9001->9000-9001/tcp                                   ragflow-minio      
eb7df0b4d1f9   docker.elastic.co/elasticsearch/elasticsearch:8.11.3      "/bin/tini -- /usr/l…"   4 hours ago   Up 4 hours (healthy)   9300/tcp, 0.0.0.0:1200->9200/tcp                                   ragflow-es-01      
abaeb3b121e0   mysql:5.7.18                                              "docker-entrypoint.s…"   4 hours ago   Up 4 hours (healthy)   0.0.0.0:5455->3306/tcp                                             ragflow-mysql

2、访问： enter http://IP_OF_YOUR_MACHINE， default HTTP serving port 80，随便注册一个账户即可。

http://192.168.1.16:80

3、RAGFlow中模型提供商设置：

添加ollama：
宿主机运行Ollama，添加用户环境变量 OLLAMA_HOST：0.0.0.0【Ollama binds 127.0.0.1 port 11434 by default. Change the bind address with the OLLAMA_HOST environment variable.】
在模型提供商添加 LLM页面，基础 Url处输入：192.168.1.16:11434/api，模型名称：qwen2:7b

4、