FAQ#

Q1: text2vec-large-chinese not found#

按照正确的姿势下载text2vec-large-chinese模型#

centos:yum install git-lfs
ubuntu:apt-get install git-lfs -y
macos:brew install git-lfs

cd models
git lfs clone https://huggingface.co/GanymedeNil/text2vec-large-chinese

执行pip install -r requirements.txt报错#

修改pip源#

# pypi
$ pip install -r requirements.txt -i https://pypi.python.org/simple

或

# tsinghua
$ pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple/

或

# aliyun
$ pip install -r requirements.txt -i http://mirrors.aliyun.com/pypi/simple/

或#

按照正确姿势安装mysql#

Docker:

docker run --name=mysql -p 3306:3306 -e MYSQL_ROOT_PASSWORD=aa12345678 -dit mysql:latest

download mysql instance

使用openai-chatgpt模型时(MODEL_SERVER=proxyllm)#

确认openapi API_KEY是否可用#

Chat Data and Chat Meta Data报如下错#

需要创建自己的数据库#

1.先创建数据库

mysql> create database {$your_name}
mysql> use {$your_name}

然后创建数据表，模拟数据

mysql>CREATE TABLE `users` (
  `id` int NOT NULL AUTO_INCREMENT,
  `username` varchar(50) NOT NULL COMMENT '用户名',
  `password` varchar(50) NOT NULL COMMENT '密码',
  `email` varchar(50) NOT NULL COMMENT '邮箱',
  `phone` varchar(20) DEFAULT NULL COMMENT '电话',
  PRIMARY KEY (`id`),
  KEY `idx_username` (`username`) COMMENT '索引：按用户名查询'
) ENGINE=InnoDB AUTO_INCREMENT=101 DEFAULT CHARSET=utf8mb4 COMMENT='聊天用户表'

使用vicuna-13b，知识库问答出现乱码#

将KNOWLEDGE_SEARCH_TOP_SIZE和KNOWLEDGE_CHUNK_SIZE设置小点然后重启#