数据交互的本地化GPT模型：DB-GPT

# DB-GPT: Revolutionizing Database Interactions with Private LLM Technology <p align="left"> <img src="./assets/LOGO.png" width="100%" /> </p> <div align="center"> <p> <a href="https://github.com/eosphoros-ai/DB-GPT"> <img alt="stars" src="https://img.shields.io/github/stars/eosphoros-ai/db-gpt?style=social" /> </a> <a href="https://github.com/eosphoros-ai/DB-GPT"> <img alt="forks" src="https://img.shields.io/github/forks/eosphoros-ai/db-gpt?style=social" /> </a> <a href="https://opensource.org/licenses/MIT"> <img alt="License: MIT" src="https://img.shields.io/badge/License-MIT-yellow.svg" /> </a> <a href="https://github.com/eosphoros-ai/DB-GPT/releases"> <img alt="Release Notes" src="https://img.shields.io/github/release/eosphoros-ai/DB-GPT" /> </a> <a href="https://github.com/eosphoros-ai/DB-GPT/issues"> <img alt="Open Issues" src="https://img.shields.io/github/issues-raw/eosphoros-ai/DB-GPT" /> </a> <a href="https://discord.gg/7uQnPuveTY"> <img alt="Discord" src="https://dcbadge.vercel.app/api/server/7uQnPuveTY?compact=true&style=flat" /> </a> <a href="https://join.slack.com/t/slack-inu2564/shared_invite/zt-29rcnyw2b-N~ubOD9kFc7b7MDOAM1otA"> <img alt="Slack" src="https://badgen.net/badge/Slack/Join%20DB-GPT/0abd59?icon=slack" /> </a> <a href="https://codespaces.new/eosphoros-ai/DB-GPT"> <img alt="Open in GitHub Codespaces" src="https://github.com/codespaces/badge.svg" /> </a> </p> [**简体中文**](README.zh.md) | [**Discord**](https://discord.gg/7uQnPuveTY) | [**Documents**](https://docs.dbgpt.site) | [**微信**](https://github.com/eosphoros-ai/DB-GPT/blob/main/README.zh.md#%E8%81%94%E7%B3%BB%E6%88%91%E4%BB%AC) | [**Community**](https://github.com/eosphoros-ai/community) | [**Paper**](https://arxiv.org/pdf/2312.17449.pdf) </div> ## What is DB-GPT? DB-GPT is an open-source, data-domain large model framework. Its purpose is to build the infrastructure for the large model domain by developing a variety of technical capabilities, including multi-model management, Text2SQL performance optimization, RAG framework and optimization, and Multi-Agents framework collaboration. These capabilities aim to simplify and facilitate the construction of large model applications around databases. In the Data 3.0 era, based on models and databases, enterprises and developers can build their own bespoke applications with less code. ### Data Agents   ## Contents - [Introduction](#introduction) - [Install](#install) - [Features](#features) - [Contribution](#contribution) - [Contact](#contact-information) ## Introduction The architecture of DB-GPT is shown in the following figure: <p align="center"> <img src="./assets/dbgpt.png" width="800" /> </p> The core capabilities include the following parts: - **RAG (Retrieval Augmented Generation)**: RAG is currently the most practically implemented and urgently needed domain. DB-GPT has already implemented a framework based on RAG, allowing users to build knowledge-based applications using the RAG capabilities of DB-GPT. - **GBI (Generative Business Intelligence)**: Generative BI is one of the core capabilities of the DB-GPT project, providing the foundational data intelligence technology to build enterprise report analysis and business insights. - **Fine-tuning Framework**: Model fine-tuning is an indispensable capability for any enterprise to implement in vertical and niche domains. DB-GPT provides a complete fine-tuning framework that integrates seamlessly with the DB-GPT project. In recent fine-tuning efforts, an accuracy rate based on the Spider dataset has been achieved at 82.5%. - **Data-Driven Multi-Agents Framework**: DB-GPT offers a data-driven self-evolving fine-tuning framework, aiming to continuously make decisions and execute based on data. - **Data Factory**: The Data Factory is mainly about cleaning and processing trustworthy knowledge and data in the era of large models. - **Data Sources**: Integrating various data sources to seamlessly connect production business data to the core capabilities of DB-GPT. ### SubModule - [DB-GPT-Hub](https://github.com/eosphoros-ai/DB-GPT-Hub) Text-to-SQL workflow with high performance by applying Supervised Fine-Tuning (SFT) on Large Language Models (LLMs). #### Text2SQL Finetune - support llms - [x] LLaMA - [x] LLaMA-2 - [x] BLOOM - [x] BLOOMZ - [x] Falcon - [x] Baichuan - [x] Baichuan2 - [x] InternLM - [x] Qwen - [x] XVERSE - [x] ChatGLM2 - SFT Accuracy As of October 10, 2023, through the fine-tuning of an open-source model with 13 billion parameters using this project, we have achieved execution accuracy on the Spider dataset that surpasses even GPT-4! [More Information about Text2SQL finetune](https://github.com/eosphoros-ai/DB-GPT-Hub) - [DB-GPT-Plugins](https://github.com/eosphoros-ai/DB-GPT-Plugins) DB-GPT Plugins that can run Auto-GPT plugin directly - [GPT-Vis](https://github.com/eosphoros-ai/GPT-Vis) Visualization protocol ## Install     [**Usage Tutorial**](http://docs.dbgpt.site/docs/overview) - [**Install**](http://docs.dbgpt.site/docs/installation) - [**Quickstart**](http://docs.dbgpt.site/docs/quickstart) - [**Application**](http://docs.dbgpt.site/docs/operation_manual) - [**Debugging**](http://docs.dbgpt.site/docs/operation_manual/advanced_tutorial/debugging) ## Features At present, we have introduced several key features to showcase our current capabilities: - **Private Domain Q&A & Data Processing** The DB-GPT project offers a range of functionalities designed to improve knowledge base construction and enable efficient storage and retrieval of both structured and unstructured data. These functionalities include built-in support for uploading multiple file formats, the ability to integrate custom data extraction plug-ins, and unified vector storage and retrieval capabilities for effectively managing large volumes of information. - **Multi-Data Source & GBI(Generative Business intelligence)** The DB-GPT project facilitates seamless natural language interaction with diverse data sources, including Excel, databases, and data warehouses. It simplifies the process of querying and retrieving information from these sources, empowering users to engage in intuitive conversations and gain insights. Moreover, DB-GPT supports the generation of analytical reports, providing users with valuable data summaries and interpretations. - **Multi-Agents&Plugins** It offers support for custom plug-ins to perform various tasks and natively integrates the Auto-GPT plug-in model. The Agents protocol adheres to the Agent Protocol standard. - **Automated Fine-tuning text2SQL** We've also developed an automated fine-tuning lightweight framework centred on large language models (LLMs), Text2SQL datasets, LoRA/QLoRA/Pturning, and other fine-tuning methods. This framework simplifies Text-to-SQL fine-tuning, making it as straightforward as an assembly line process. [DB-GPT-Hub](https://github.com/eosphoros-ai/DB-GPT-Hub) - **SMMF(Service-oriented Multi-model Management Framework)** We offer extensive model support, including dozens of large language models (LLMs) from both open-source and API agents, such as LLaMA/LLaMA2, Baichuan, ChatGLM, Wenxin, Tongyi, Zhipu, and many more.