diff --git a/README.en.md b/README.en.md index b2e4c5d6f..97fcb373b 100644 --- a/README.en.md +++ b/README.en.md @@ -2,96 +2,105 @@ --- +[中文版](README.md) + A Open Database-GPT Experiment, interact your data and environment using the local GPT, no data leaks, 100% privately, 100% security. -![GitHub Repo stars](https://img.shields.io/github/stars/csunny/db-gpt?style=social) +## Features -一个数据库相关的GPT实验项目, 模型与数据全部本地化部署, 绝对保障数据的隐私安全。 同时此GPT项目可以直接本地部署连接到私有数据库, 进行私有数据处理。 +- SQL Project + - SQL Generate + - SQL-diagnosis +- Database-QA Based Knowledge -[DB-GPT](https://github.com/csunny/DB-GPT) 是一个实验性的开源应用，它基于[FastChat](https://github.com/lm-sys/FastChat)，并使用[vicuna-13b](https://huggingface.co/Tribbiani/vicuna-13b)作为基础模型。此外，此程序结合了[langchain](https://github.com/hwchase17/langchain)和[llama-index](https://github.com/jerryjliu/llama_index)基于现有知识库进行[In-Context Learning](https://arxiv.org/abs/2301.00234)来对其进行数据库相关知识的增强。它可以进行SQL生成、SQL诊断、数据库知识问答、数据处理等一系列的工作。 +## Architecture Design - -## 项目方案 - +

+ +

[DB-GPT](https://github.com/csunny/DB-GPT) is an experimental open-source application that builds upon the [FastChat](https://github.com/lm-sys/FastChat) model and uses vicuna as its base model. Additionally, it looks like this application incorporates langchain and llama-index embedding knowledge to improve Database-QA capabilities. Overall, it appears to be a sophisticated and innovative tool for working with databases. If you have any specific questions about how to use or implement DB-GPT in your work, please let me know and I'll do my best to assist you. +## Demo -## 运行效果演示 Run on an RTX 4090 GPU (The origin mov not sped up!, [YouTube地址](https://www.youtube.com/watch?v=1PWI6F89LPo)) -- 运行演示 -![](https://github.com/csunny/DB-GPT/blob/main/asserts/演示.gif) +### Run +

+ +

-- SQL生成示例 -首先选择对应的数据库, 然后模型即可根据对应的数据库Schema信息生成SQL +### SQL Generate - +First, select the DataBase, you can use Schema to generate the SQL.。 -The Generated SQL is runable. +

+ +

- +

+ +

-- 数据库QA示例 +### Database-QA - +

+ +

-基于默认内置知识库QA +

+ +

- +## Deployment -# Dependencies -1. First you need to install python requirements. -``` -python>=3.9 -pip install -r requirements.txt +### 1. Python Requirement + +```bash +$ python>=3.9 +$ pip install -r requirements.txt ``` + or if you use conda envirenment, you can use this command -``` -cd DB-GPT -conda env create -f environment.yml + +```bash +$ conda env create -f environment.yml ``` -2. MySQL Install +### 2. MySQL In this project examples, we connect mysql and run SQL-Generate. so you need install mysql local for test. recommand docker -``` -docker run --name=mysql -p 3306:3306 -e MYSQL_ROOT_PASSWORD=aa12345678 -dit mysql:latest -``` -The password just for test, you can change this if necessary -# Install -1. 基础模型下载 -关于基础模型, 可以根据[vicuna](https://github.com/lm-sys/FastChat/blob/main/README.md#model-weights)合成教程进行合成。 -如果此步有困难的同学，也可以直接使用[Hugging Face](https://huggingface.co/)上的模型进行替代. [替代模型](https://huggingface.co/Tribbiani/vicuna-7b) - -2. Run model server -``` -cd pilot/server -python vicuna_server.py +```bash +$ docker run --name=mysql -p 3306:3306 -e MYSQL_ROOT_PASSWORD=aa12345678 -dit mysql:latest ``` -3. Run gradio webui -``` -python webserver.py +### 3. LLM + +- [vicuna](https://github.com/lm-sys/FastChat/blob/main/README.md#model-weights) +- [Hugging Face](https://huggingface.co/Tribbiani/vicuna-7b) + +```bash +$ cd pilot/server +$ python vicuna_server.py ``` -4. 基于阿里云部署指南 -[阿里云部署指南](https://open.oceanbase.com/blog/3278046208) +Run gradio webui -# Featurs -- SQL-Generate -- Database-QA Based Knowledge -- SQL-diagnosis +```bash +$ python webserver.py +``` -总的来说，它是一个用于数据库的复杂且创新的AI工具。如果您对如何在工作中使用或实施DB-GPT有任何具体问题，请联系我, 我会尽力提供帮助, 同时也欢迎大家参与到项目建设中, 做一些有趣的事情。 +## Thanks - +- [FastChat](https://github.com/lm-sys/FastChat) +- [vicuna-13b](https://huggingface.co/Tribbiani/vicuna-13b) +- [langchain](https://github.com/hwchase17/langchain) +- [llama-index](https://github.com/jerryjliu/llama_index) and [In-Context Learning](https://arxiv.org/abs/2301.00234) -# Contribute -[Contribute](https://github.com/csunny/DB-GPT/blob/main/CONTRIBUTING) -# Licence -[MIT](https://github.com/csunny/DB-GPT/blob/main/LICENSE) +## Licence + +The MIT License (MIT) diff --git a/README.md b/README.md index 02e5c060e..dda524665 100644 --- a/README.md +++ b/README.md @@ -18,7 +18,7 @@ ## 架构方案

- +

DB-GPT 基于[FastChat](https://github.com/lm-sys/FastChat) 构建大模型运行环境，并提供 vicuna 作为基础的大语言模型。此外，我们通过 langchain 和 llama-index 提供私域知识库问答能力。 @@ -29,7 +29,7 @@ DB-GPT 基于[FastChat](https://github.com/lm-sys/FastChat) 构建大模型运 ### 运行环境演示

- +

### SQL 生成 @@ -37,30 +37,30 @@ DB-GPT 基于[FastChat](https://github.com/lm-sys/FastChat) 构建大模型运 首先选择对应的数据库, 然后模型即可根据对应的数据库 Schema 信息生成 SQL。

- +

运行成功的效果如下面的演示：

- +

### 数据库问答

- +

基于默认内置知识库。

- +

## 部署 -### 1. 安装 Python 依赖的模块。 +### 1. 安装 Python ```bash $ python>=3.9 @@ -109,16 +109,23 @@ $ python webserver.py - [llama-index](https://github.com/jerryjliu/llama_index) 基于现有知识库进行[In-Context Learning](https://arxiv.org/abs/2301.00234)来对其进行数据库相关知识的增强。 + ## Contributors -|[
csunny](https://github.com/csunny)
| +|[
csunny](https://github.com/csunny)
|[
xudafeng](https://github.com/xudafeng)
| | :---: | :---: | -This project follows the git-contributor [spec](https://github.com/xudafeng/git-contributor), auto updated at `Sun May 14 2023 22:37:46 GMT+0800`. +This project follows the git-contributor [spec](https://github.com/xudafeng/git-contributor), auto updated at `Sun May 14 2023 23:02:43 GMT+0800`. +这是一个用于数据库的复杂且创新的工具，如有任何具体问题，请联系如下微信，我会尽力提供帮助，同时也欢迎参与到项目建设中。 + +

+ +

+ ## Licence The MIT License (MIT) diff --git a/asserts/DB-GPT.png b/asserts/DB-GPT.png deleted file mode 100644 index 1c9bee139..000000000 Binary files a/asserts/DB-GPT.png and /dev/null differ diff --git a/asserts/DB_QA.png b/asserts/DB_QA.png deleted file mode 100644 index 46bd327d0..000000000 Binary files a/asserts/DB_QA.png and /dev/null differ diff --git a/asserts/SQLGEN.png b/asserts/SQLGEN.png deleted file mode 100644 index cac479364..000000000 Binary files a/asserts/SQLGEN.png and /dev/null differ diff --git a/asserts/VectorDBQA.png b/asserts/VectorDBQA.png deleted file mode 100644 index 05279002e..000000000 Binary files a/asserts/VectorDBQA.png and /dev/null differ diff --git a/asserts/exeable.png b/asserts/exeable.png deleted file mode 100644 index 47ee94f7d..000000000 Binary files a/asserts/exeable.png and /dev/null differ diff --git a/asserts/pilot.png b/asserts/pilot.png deleted file mode 100644 index 41bd01207..000000000 Binary files a/asserts/pilot.png and /dev/null differ diff --git a/asserts/sql_generate.png b/asserts/sql_generate.png deleted file mode 100644 index 13fb44af0..000000000 Binary files a/asserts/sql_generate.png and /dev/null differ diff --git a/asserts/wechat.jpg b/asserts/wechat.jpg deleted file mode 100644 index 77ddbc89a..000000000 Binary files a/asserts/wechat.jpg and /dev/null differ diff --git a/asserts/演示.gif b/asserts/演示.gif deleted file mode 100644 index 22bab31ab..000000000 Binary files a/asserts/演示.gif and /dev/null differ