Interact your data and environment using the local GPT, no data leaks, 100% privately, 100% security
Go to file
2023-05-01 02:04:02 +08:00
.vscode run a demo 2023-04-29 15:17:48 +08:00
asserts update 2023-05-01 01:34:22 +08:00
docs add file 2023-04-28 22:50:44 +08:00
examples add vicuna embedding 2023-04-29 18:28:42 +08:00
pilot add prompt 2023-05-01 00:12:03 +08:00
.gitignore add asserts 2023-05-01 00:51:27 +08:00
environment.yml fix problem 2023-04-30 23:58:32 +08:00
LICENSE Initial commit 2023-04-13 22:52:44 +08:00
README.md update 2023-05-01 02:04:02 +08:00
requirements.txt fix problem 2023-04-30 23:58:32 +08:00

DB-GPT

A Open Database-GPT Experiment

GitHub Repo stars

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.

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

Install

  1. Run model server
cd pilot/server
python vicuna_server.py
  1. Run gradio webui
python webserver.py 

Featurs

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