Metadata-Version: 2.4
Name: rag
Version: 0.0.1
Summary: rag
Home-page: https://github.com/yumoqing/rag
Author: yumoqing
Author-email: yumoqing@gmail.com
Platform: any
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Description-Content-Type: text/markdown
Requires-Dist: chromadb
Requires-Dist: langchain
Requires-Dist: langchain_community
Requires-Dist: unstructured
Requires-Dist: langchain-text-splitters
Requires-Dist: unstructured[all-docs]
Requires-Dist: langchain_milvus
Requires-Dist: langchain_huggingface
Requires-Dist: transformers
Requires-Dist: openai
Requires-Dist: torch
Requires-Dist: torchvision
Requires-Dist: pymilvus
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: platform
Dynamic: requires-dist
Dynamic: summary

# 知识库服务器
本系统为不同的客户提供自我管理的知识库，并在知识库基础上提供知识检索

本系统提供API形式，为注册的服务器提供知识服支持，不面向最终客户

## 依赖
依赖[这些模块](requirements.txt)

## 安装部署
1. 创建rag用户
2. 登录rag用户
3. 执行以下命令
```
git clone git@git.kaiyuancloud.cn:yumoqing/rag
cd rag/script
./install.sh

```

将项目在用户根目录checkout
3. 
## 功能
管理client系统的客户知识库，并提供知识查询

每个客户可以创建一到多个独立的知识库，为不同的业务场景提供知识库知识

知识库之间数据相互独立，互不干扰。

## http API

### add
增加知识库文档

#### path
/api/add
#### method
POST
#### 输入
name: authentication
value: Bears ${apikey}
score: headers

name: file_name
value: path of uploaded file
score: data

name: userid
value: userid of client system
score: data

name: kdbname
value: rag kdb name
score: data

#### 输出

### query
查询知识库

#### path
/api/query
#### method
POST

#### 输入
name: authentication
value: Bears ${apikey}
score: headers

name: prompt
value: ${prompt} 
score: data

name: userid
value: ${userid}
score: data

name: kdbname
value: ${kdbname}
score: data


#### 输出
```
{
    total:返回记录条数,
    rows：返回记录内容
}
rows有以下属性
content：文本内容
distances：距离
source：文档path
```