Interact your data and environment using the local GPT, no data leaks, 100% privately, 100% security
Go to file
2023-05-15 14:40:29 +08:00
.github/workflows Create python-publish.yml 2023-04-29 23:30:55 +08:00
assets asserts renamed to assets 2023-05-14 11:38:11 +05:30
docs add file 2023-04-28 22:50:44 +08:00
examples fix:unusual file 2023-05-15 00:18:06 +08:00
pilot fix:unusual file 2023-05-15 00:18:06 +08:00
plugins fix:unusual file 2023-05-15 00:18:06 +08:00
tests fix:unusual file 2023-05-15 00:18:06 +08:00
.env.template Add: config 2023-05-09 11:18:06 +08:00
.gitignore Merge remote-tracking branch 'origin/plugin_init' into source_embedding 2023-05-12 21:06:00 +08:00
CONTRIBUTING.md rm oceanbase document 2023-05-08 23:01:52 +08:00
docker-compose.yml docker deployment 2023-05-14 12:00:37 +05:30
Dockerfile docker deployment 2023-05-14 12:00:37 +05:30
environment.yml fix 2023-05-12 18:23:49 +08:00
LICENSE Initial commit 2023-04-13 22:52:44 +08:00
README.en.md docs: update english docs 2023-05-14 23:20:52 +08:00
README.md add project vision 2023-05-15 14:40:29 +08:00
requirements.txt fix 2023-05-12 18:23:49 +08:00
run.sh rm oceanbase document 2023-05-08 23:01:52 +08:00
SECURITY.md Create SECURITY.md 2023-05-13 15:59:34 +08:00

DB-GPT


中文版

A Open Database-GPT Experiment, interact your data and environment using the local GPT, no data leaks, 100% privately, 100% security.

Features

  • SQL Project
    • SQL Generate
    • SQL-diagnosis
  • Database-QA Based Knowledge

Architecture Design

DB-GPT is an experimental open-source application that builds upon the 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

Run on an RTX 4090 GPU (The origin mov not sped up!, YouTube地址)

Run

SQL Generate

First, select the DataBase, you can use Schema to generate the SQL.。

Database-QA

Deployment

1. Python Requirement

$ python>=3.9
$ pip install -r requirements.txt

or if you use conda envirenment, you can use this command

$ conda env create -f environment.yml

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

3. LLM

$ cd pilot/server
$ python vicuna_server.py

Run gradio webui

$ python webserver.py 

Thanks

Licence

The MIT License (MIT)