A Open Database-GPT Experiment
DB-GPT 是一个实验性的开源应用程序,它基于FastChat,并使用vicuna-13b作为基础模型。此外,此程序结合了langchain和llama-index基于现有知识库进行In-Context Learning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、数据库知识问答等一系列的工作。
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)
- 运行演示
- 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
- 数据库QA示例
-
基础模型下载 关于基础模型, 可以根据vicuna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上的模型进行替代。 替代模型: vicuna-13b
-
Run model server
cd pilot/server
python vicuna_server.py
- Run gradio webui
python webserver.py
- SQL-Generate
- Database-QA Based Knowledge
- SQL-diagnosis
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。