ragflow搭建笔记学习笔记

ragflow搭建笔记学习笔记

1.确保 vm.max_map_count >= 262144

• (1) 查看 vm.max_map_count值

>> sysctl vm.max_map_count
vm.max_map_count = 65530

• (2) 手动设置 vm.max_map_count值为262144

>> sudo sysctl -w vm.max_map_count=262144

​ 或者直接修改配置：/etc/sysctl.conf

# 1.修改配置
>> sudo vim /etc/sysctl.conf
vm.max_map_count=262144
# 2.打印配置使之生效
>> sudo sysctl -p
vm.overcommit_memory = 1
vm.max_map_count = 262144
kernel.core_pattern = ./core.%t

2.下载源码

>> $ git clone https://github.com/infiniflow/ragflow.git

3.使用预编译的docker镜像来启动服务

# 1.进入ragflow的docker路径
>> cd ragflow/docker
# 2.使用docker compose启动服务，可以使用CPU或GPU两种模式
## 2.1 使用CPU运行embedding和DeepDoc任务
# >> sudo docker compose -p ragflow -f docker-compose.yml up -d
## 2.2 使用GPU加速embedding和DeepDoc任务
>> sudo docker compose -p ragflow -f docker-compose-gpu.yml up -d
# 3.查看日志
>> sudo docker logs -f ragflow-server
        ____   ___    ______ ______ __
       / __ \ /   |  / ____// ____// /____  _      __
      / /_/ // /| | / / __ / /_   / // __ \| | /| / /
     / _, _// ___ |/ /_/ // __/  / // /_/ /| |/ |/ /
    /_/ |_|/_/  |_|\____//_/    /_/ \____/ |__/|__/

​ 

4.登录RAGFlow管理页面

# 1.查询ip
>> ifconfig
eth0: flags=4163<UP,BROADCAST,RUNNING,MULTICAST>  mtu 1500
        inet 192.168.89.64  netmask 255.255.240.0  broadcast 192.168.95.255
        inet6 fe80::215:5dff:fefc:a70c  prefixlen 64  scopeid 0x20<link>
        ether 00:15:5d:fc:a7:0c  txqueuelen 1000  (Ethernet)
        RX packets 135625  bytes 191103112 (191.1 MB)
        RX errors 0  dropped 0  overruns 0  frame 0
        TX packets 72590  bytes 5389967 (5.3 MB)
        TX errors 0  dropped 0 overruns 0  carrier 0  collisions 0

lo: flags=73<UP,LOOPBACK,RUNNING>  mtu 65536
        inet 127.0.0.1  netmask 255.0.0.0
        inet6 ::1  prefixlen 128  scopeid 0x10<host>
        loop  txqueuelen 1000  (Local Loopback)
        RX packets 81  bytes 8003 (8.0 KB)
        RX errors 0  dropped 0  overruns 0  frame 0
        TX packets 81  bytes 8003 (8.0 KB)
        TX errors 0  dropped 0 overruns 0  carrier 0  collisions 0
# 2.web登录
http://192.168.89.64:80

5.配置 Model provider

​ 右键单击右上角角色图标 -> "Model provider" -> 配置模型：

6.创建知识库

​ Knowledge Base -> Create Knowledge base -> 输入知识库名 -> Configuration -> 按需配置模型参数 -> Dataset-> Add file添加知识库文件 -> Pasing Status对上传文件解析

7.参考资料

• [1] ragflow