docs: update readme (#2760)

This commit is contained in:
alanchen 2025-06-10 16:07:51 +08:00 committed by GitHub
parent 569770e47d
commit e7c8c3e1b1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
6 changed files with 178 additions and 156 deletions

View File

@ -1,10 +1,11 @@
# DB-GPT: データベースとの対話を革新するプライベートLLM技術 # <img src="./assets/LOGO_SMALL.png" alt="Logo" style="vertical-align: middle; height: 24px;" /> DB-GPT: データベースとの対話を革新するプライベートLLM技術
<p align="left">
<img src="./assets/LOGO.png" width="100%" /> <p style="text-align: left;">
<img src="./assets/Twitter_LOGO.png" width="100%" />
</p> </p>
<div align="center"> <div style="text-align: center;">
<p> <p>
<a href="https://github.com/eosphoros-ai/DB-GPT"> <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" /> <img alt="stars" src="https://img.shields.io/github/stars/eosphoros-ai/db-gpt?style=social" />
@ -21,18 +22,30 @@
<a href="https://github.com/eosphoros-ai/DB-GPT/issues"> <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" /> <img alt="Open Issues" src="https://img.shields.io/github/issues-raw/eosphoros-ai/DB-GPT" />
</a> </a>
<a href="https://discord.gg/7uQnPuveTY"> <a href="https://x.com/DBGPT_AI">
<img alt="Discord" src="https://dcbadge.vercel.app/api/server/7uQnPuveTY?compact=true&style=flat" /> <img alt="X (formerly Twitter) Follow" src="https://img.shields.io/twitter/follow/DBGPT_AI" />
</a>
<a href="https://medium.com/@dbgpt0506">
<img alt="Medium Follow" src="https://badgen.net/badge/Medium/Dbgpt/orange?icon=medium" />
</a>
<a href="https://space.bilibili.com/3537113070963392">
<img alt="Bilibili Space" src="https://img.shields.io/badge/Bilibili-DB--GPT-blue?style=plastic&logo=bilibili&link=https%3A%2F%2Fspace.bilibili.com%2F3537113070963392" />
</a> </a>
<a href="https://join.slack.com/t/slack-inu2564/shared_invite/zt-29rcnyw2b-N~ubOD9kFc7b7MDOAM1otA"> <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" /> <img alt="Slack" src="https://badgen.net/badge/Slack/Join%20DB-GPT/0abd59?icon=slack" />
</a> </a>
<br/>
<a href="https://codespaces.new/eosphoros-ai/DB-GPT"> <a href="https://codespaces.new/eosphoros-ai/DB-GPT">
<img alt="Open in GitHub Codespaces" src="https://github.com/codespaces/badge.svg" /> <img alt="Open in GitHub Codespaces" src="https://github.com/codespaces/badge.svg" />
</a> </a>
</p> </p>
[**英語**](README.md) | [**中国語**](README.zh.md) | [**Discord**](https://discord.gg/7uQnPuveTY) | [**ドキュメント**](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) | [**コミュニティ**](https://github.com/eosphoros-ai/community) | [**論文**](https://arxiv.org/pdf/2312.17449.pdf) [![英語](https://img.shields.io/badge/英語-gray?style=flat-square)](README.md)
[![中国語](https://img.shields.io/badge/中国語-gray?style=flat-square)](README.zh.md)
[![日本語](https://img.shields.io/badge/日本語-gray?style=flat-square)](README.ja.md)
[**ドキュメント**](http://docs.dbgpt.cn/docs/overview/) | [**チームに連絡します**](https://github.com/eosphoros-ai/DB-GPT/blob/main/README.zh.md#%E8%81%94%E7%B3%BB%E6%88%91%E4%BB%AC) | [**コミュニティ**](https://github.com/eosphoros-ai/community) | [**論文**](https://arxiv.org/pdf/2312.17449.pdf)
</div> </div>
@ -44,33 +57,7 @@
🚀 **データ3.0時代には、モデルとデータベースを基盤として、企業や開発者がより少ないコードで独自のアプリケーションを構築できます。** 🚀 **データ3.0時代には、モデルとデータベースを基盤として、企業や開発者がより少ないコードで独自のアプリケーションを構築できます。**
### AIネイティブデータアプリ ### 紹介
- 🔥🔥🔥 [V0.7.0 リリース | 重要なアップグレードのセット](http://docs.dbgpt.cn/blog/db-gpt-v070-release)
- [サポート MCP Protocol](https://github.com/eosphoros-ai/DB-GPT/pull/2497)
- [サポート DeepSeek R1](https://github.com/deepseek-ai/DeepSeek-R1)
- [サポート QwQ-32B](https://huggingface.co/Qwen/QwQ-32B)
- [基本モジュールをリファクタリングする]()
- [dbgpt-app](./packages/dbgpt-app)
- [dbgpt-core](./packages/dbgpt-core)
- [dbgpt-serve](./packages/dbgpt-serve)
- [dbgpt-client](./packages/dbgpt-client)
- [dbgpt-accelerator](./packages/dbgpt-accelerator)
- [dbgpt-ext](./packages/dbgpt-ext)
![Data-awels](https://github.com/eosphoros-ai/DB-GPT/assets/17919400/37d116fc-d9dd-4efa-b4df-9ab02b22541c)
![Data-Apps](https://github.com/eosphoros-ai/DB-GPT/assets/17919400/a7bf6d65-92d1-4f0e-aaf0-259ccdde22fd)
![dashboard-images](https://github.com/eosphoros-ai/DB-GPT/assets/17919400/1849a79a-f7fd-40cf-bc9c-b117a041dd6a)
## 目次
- [紹介](#紹介)
- [インストール](#インストール)
- [特徴](#特徴)
- [貢献](#貢献)
- [連絡先](#連絡先情報)
## 紹介
DB-GPTのアーキテクチャは以下の図に示されています DB-GPTのアーキテクチャは以下の図に示されています
<p align="center"> <p align="center">
@ -91,7 +78,7 @@ DB-GPTのアーキテクチャは以下の図に示されています
- **データソース**DB-GPTのコア機能に生産ビジネスデータをシームレスに接続するために、さまざまなデータソースを統合します。 - **データソース**DB-GPTのコア機能に生産ビジネスデータをシームレスに接続するために、さまざまなデータソースを統合します。
### サブモジュール #### サブモジュール
- [DB-GPT-Hub](https://github.com/eosphoros-ai/DB-GPT-Hub) 大規模言語モデルLLM上での教師ありファインチューニングSFTを適用することにより、高性能なText-to-SQLワークフロー。 - [DB-GPT-Hub](https://github.com/eosphoros-ai/DB-GPT-Hub) 大規模言語モデルLLM上での教師ありファインチューニングSFTを適用することにより、高性能なText-to-SQLワークフロー。
- [dbgpts](https://github.com/eosphoros-ai/dbgpts) dbgptsは、DB-GPT上で構築されたいくつかのデータアプリ、AWELオペレータ、AWELワークフローテンプレート、およびエージェントを含む公式リポジトリです。 - [dbgpts](https://github.com/eosphoros-ai/dbgpts) dbgptsは、DB-GPT上で構築されたいくつかのデータアプリ、AWELオペレータ、AWELワークフローテンプレート、およびエージェントを含む公式リポジトリです。
@ -118,6 +105,31 @@ DB-GPTのアーキテクチャは以下の図に示されています
- [DB-GPT-Plugins](https://github.com/eosphoros-ai/DB-GPT-Plugins) Auto-GPTプラグインを直接実行できるDB-GPTプラグイン - [DB-GPT-Plugins](https://github.com/eosphoros-ai/DB-GPT-Plugins) Auto-GPTプラグインを直接実行できるDB-GPTプラグイン
- [GPT-Vis](https://github.com/eosphoros-ai/GPT-Vis) 可視化プロトコル - [GPT-Vis](https://github.com/eosphoros-ai/GPT-Vis) 可視化プロトコル
### AIネイティブデータアプリ
- 🔥🔥🔥 [V0.7.0 リリース | 重要なアップグレードのセット](http://docs.dbgpt.cn/blog/db-gpt-v070-release)
- [サポート MCP Protocol](https://github.com/eosphoros-ai/DB-GPT/pull/2497)
- [サポート DeepSeek R1](https://github.com/deepseek-ai/DeepSeek-R1)
- [サポート QwQ-32B](https://huggingface.co/Qwen/QwQ-32B)
- [基本モジュールをリファクタリングする]()
- [dbgpt-app](./packages/dbgpt-app)
- [dbgpt-core](./packages/dbgpt-core)
- [dbgpt-serve](./packages/dbgpt-serve)
- [dbgpt-client](./packages/dbgpt-client)
- [dbgpt-accelerator](./packages/dbgpt-accelerator)
- [dbgpt-ext](./packages/dbgpt-ext)
---
![app_chat_v0 6](https://github.com/user-attachments/assets/a2f0a875-df8c-4f0d-89a3-eed321c02113)
![app_manage_chat_data_v0 6](https://github.com/user-attachments/assets/c8cc85bb-e3c2-4fab-8fb9-7b4b469d0611)
![chat_dashboard_display_v0 6](https://github.com/user-attachments/assets/b15d6ebe-54c4-4527-a16d-02fbbaf20dc9)
![agent_prompt_awel_v0 6](https://github.com/user-attachments/assets/40761507-a1e1-49d4-b49a-3dd9a5ea41cc)
## インストール ## インストール
![Docker](https://img.shields.io/badge/docker-%230db7ed.svg?style=for-the-badge&logo=docker&logoColor=white) ![Docker](https://img.shields.io/badge/docker-%230db7ed.svg?style=for-the-badge&logo=docker&logoColor=white)
![Linux](https://img.shields.io/badge/Linux-FCC624?style=for-the-badge&logo=linux&logoColor=black) ![Linux](https://img.shields.io/badge/Linux-FCC624?style=for-the-badge&logo=linux&logoColor=black)
@ -232,9 +244,6 @@ DB-GPTのアーキテクチャは以下の図に示されています
## 画像 ## 画像
🌐 [AutoDLイメージ](https://www.codewithgpu.com/i/eosphoros-ai/DB-GPT/dbgpt) 🌐 [AutoDLイメージ](https://www.codewithgpu.com/i/eosphoros-ai/DB-GPT/dbgpt)
### 言語切り替え
.env設定ファイルでLANGUAGEパラメータを変更して、異なる言語に切り替えることができます。デフォルトは英語です中国語zh、英語en、他の言語は後で追加されます
## 貢献 ## 貢献
- 新しい貢献のための詳細なガイドラインを確認するには、[貢献方法](https://github.com/eosphoros-ai/DB-GPT/blob/main/CONTRIBUTING.md)を参照してください。 - 新しい貢献のための詳細なガイドラインを確認するには、[貢献方法](https://github.com/eosphoros-ai/DB-GPT/blob/main/CONTRIBUTING.md)を参照してください。

144
README.md
View File

@ -1,10 +1,10 @@
# DB-GPT: AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents # <img src="./assets/LOGO_SMALL.png" alt="Logo" style="vertical-align: middle; height: 24px;" /> DB-GPT: AI Native Data App Development framework with AWEL and Agents
<p align="left"> <p style="text-align: left;">
<img src="./assets/LOGO.png" width="100%" /> <img src="./assets/Twitter_LOGO.png" width="100%" />
</p> </p>
<div align="center"> <div style="text-align: center;">
<p> <p>
<a href="https://github.com/eosphoros-ai/DB-GPT"> <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" /> <img alt="stars" src="https://img.shields.io/github/stars/eosphoros-ai/db-gpt?style=social" />
@ -21,19 +21,30 @@
<a href="https://github.com/eosphoros-ai/DB-GPT/issues"> <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" /> <img alt="Open Issues" src="https://img.shields.io/github/issues-raw/eosphoros-ai/DB-GPT" />
</a> </a>
<a href="https://discord.gg/7uQnPuveTY"> <a href="https://x.com/DBGPT_AI">
<img alt="Discord" src="https://dcbadge.vercel.app/api/server/7uQnPuveTY?compact=true&style=flat" /> <img alt="X (formerly Twitter) Follow" src="https://img.shields.io/twitter/follow/DBGPT_AI" />
</a>
<a href="https://medium.com/@dbgpt0506">
<img alt="Medium Follow" src="https://badgen.net/badge/Medium/Dbgpt/orange?icon=medium" />
</a>
<a href="https://space.bilibili.com/3537113070963392">
<img alt="Bilibili Space" src="https://img.shields.io/badge/Bilibili-DB--GPT-blue?style=plastic&logo=bilibili&link=https%3A%2F%2Fspace.bilibili.com%2F3537113070963392" />
</a> </a>
<a href="https://join.slack.com/t/slack-inu2564/shared_invite/zt-29rcnyw2b-N~ubOD9kFc7b7MDOAM1otA"> <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" /> <img alt="Slack" src="https://badgen.net/badge/Slack/Join%20DB-GPT/0abd59?icon=slack" />
</a> </a>
<br/>
<a href="https://codespaces.new/eosphoros-ai/DB-GPT"> <a href="https://codespaces.new/eosphoros-ai/DB-GPT">
<img alt="Open in GitHub Codespaces" src="https://github.com/codespaces/badge.svg" /> <img alt="Open in GitHub Codespaces" src="https://github.com/codespaces/badge.svg" />
</a> </a>
</p> </p>
[**简体中文**](README.zh.md) | [**日本語**](README.ja.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) [![English](https://img.shields.io/badge/English-gray?style=flat-square)](README.md)
[![简体中文](https://img.shields.io/badge/简体中文-gray?style=flat-square)](README.zh.md)
[![日本語](https://img.shields.io/badge/日本語-gray?style=flat-square)](README.ja.md)
[**Documents**](http://docs.dbgpt.cn/docs/overview/) | [**Concat**](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> </div>
@ -45,8 +56,50 @@ The purpose is to build infrastructure in the field of large models, through the
🚀 **In the Data 3.0 era, based on models and databases, enterprises and developers can build their own bespoke applications with less code.** 🚀 **In the Data 3.0 era, based on models and databases, enterprises and developers can build their own bespoke applications with less code.**
### DISCKAIMER ### Introduction
- [disckaimer](./DISCKAIMER.md) 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 multi-agents 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).
- [dbgpts](https://github.com/eosphoros-ai/dbgpts) dbgpts is the official repository which contains some data apps、AWEL operators、AWEL workflow templates and agents which build upon DB-GPT.
#### 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
[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
### AI-Native Data App ### AI-Native Data App
--- ---
@ -71,59 +124,8 @@ The purpose is to build infrastructure in the field of large models, through the
![agent_prompt_awel_v0 6](https://github.com/user-attachments/assets/40761507-a1e1-49d4-b49a-3dd9a5ea41cc) ![agent_prompt_awel_v0 6](https://github.com/user-attachments/assets/40761507-a1e1-49d4-b49a-3dd9a5ea41cc)
## Contents
- [Introduction](#introduction)
- [Install](#install)
- [Features](#features)
- [Contribution](#contribution)
- [Contact](#contact-information)
## Introduction ## Installation / Quick Start
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 multi-agents 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).
- [dbgpts](https://github.com/eosphoros-ai/dbgpts) dbgpts is the official repository which contains some data apps、AWEL operators、AWEL workflow templates and agents which build upon DB-GPT.
#### 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
[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
![Docker](https://img.shields.io/badge/docker-%230db7ed.svg?style=for-the-badge&logo=docker&logoColor=white) ![Docker](https://img.shields.io/badge/docker-%230db7ed.svg?style=for-the-badge&logo=docker&logoColor=white)
![Linux](https://img.shields.io/badge/Linux-FCC624?style=for-the-badge&logo=linux&logoColor=black) ![Linux](https://img.shields.io/badge/Linux-FCC624?style=for-the-badge&logo=linux&logoColor=black)
![macOS](https://img.shields.io/badge/mac%20os-000000?style=for-the-badge&logo=macos&logoColor=F0F0F0) ![macOS](https://img.shields.io/badge/mac%20os-000000?style=for-the-badge&logo=macos&logoColor=F0F0F0)
@ -239,8 +241,6 @@ At present, we have introduced several key features to showcase our current capa
🌐 [AutoDL Image](https://www.codewithgpu.com/i/eosphoros-ai/DB-GPT/dbgpt) 🌐 [AutoDL Image](https://www.codewithgpu.com/i/eosphoros-ai/DB-GPT/dbgpt)
### Language Switching
In the .env configuration file, modify the LANGUAGE parameter to switch to different languages. The default is English (Chinese: zh, English: en, other languages to be added later).
## Contribution ## Contribution
@ -255,10 +255,13 @@ At present, we have introduced several key features to showcase our current capa
## Licence ## Licence
The MIT License (MIT) The MIT License (MIT)
## Citation ## DISCKAIMER
If you want to understand the overall architecture of DB-GPT, please cite <a href="https://arxiv.org/abs/2312.17449" target="_blank">paper</a> and <a href="https:// arxiv.org/abs/2404.10209" target="_blank">Paper</a> - [disckaimer](./DISCKAIMER.md)
If you want to learn about using DB-GPT for Agent development, please cite the <a href="https://arxiv.org/abs/2412.13520" target="_blank">paper</a> ## Citation
If you want to understand the overall architecture of DB-GPT, please cite <a href="https://arxiv.org/abs/2312.17449" target="_blank">Paper</a> and <a href="https://arxiv.org/abs/2404.10209" target="_blank">Paper</a>
If you want to learn about using DB-GPT for Agent development, please cite the <a href="https://arxiv.org/abs/2412.13520" target="_blank">Paper</a>
```bibtex ```bibtex
@article{xue2023dbgpt, @article{xue2023dbgpt,
title={DB-GPT: Empowering Database Interactions with Private Large Language Models}, title={DB-GPT: Empowering Database Interactions with Private Large Language Models},
@ -287,7 +290,12 @@ If you want to learn about using DB-GPT for Agent development, please cite the <
## Contact Information ## Contact Information
We are working on building a community, if you have any ideas for building the community, feel free to contact us. Thanks to everyone who has contributed to DB-GPT! Your ideas, code, comments, and even sharing them at events and on social platforms can make DB-GPT better.
[![](https://dcbadge.vercel.app/api/server/7uQnPuveTY?compact=true&style=flat)](https://discord.gg/7uQnPuveTY) We are working on building a community, if you have any ideas for building the community, feel free to contact us.
- [Github Issues](https://github.com/eosphoros-ai/DB-GPT/issues) ⭐For questions about using GB-DPT, see the CONTRIBUTING.
- [Github Discussions](https://github.com/orgs/eosphoros-ai/discussions) ⭐Share your experience or unique apps.
- [Twitter](https://x.com/DBGPT_AI) ⭐Please feel free to talk to us.
[![Star History Chart](https://api.star-history.com/svg?repos=csunny/DB-GPT&type=Date)](https://star-history.com/#csunny/DB-GPT) [![Star History Chart](https://api.star-history.com/svg?repos=csunny/DB-GPT&type=Date)](https://star-history.com/#csunny/DB-GPT)

View File

@ -1,11 +1,11 @@
# DB-GPT: AI原生数据应用开发框架 # <img src="./assets/LOGO_SMALL.png" alt="Logo" style="vertical-align: middle; height: 24px;" /> DB-GPT: AI原生数据应用开发框架
<p align="left"> <p style="text-align: left;">
<img src="./assets/LOGO.png" width="100%" /> <img src="./assets/Twitter_LOGO.png" width="100%" />
</p> </p>
<div align="center"> <div style="text-align: center;">
<p> <p>
<a href="https://github.com/eosphoros-ai/DB-GPT"> <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" /> <img alt="stars" src="https://img.shields.io/github/stars/eosphoros-ai/db-gpt?style=social" />
@ -22,18 +22,30 @@
<a href="https://github.com/eosphoros-ai/DB-GPT/issues"> <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" /> <img alt="Open Issues" src="https://img.shields.io/github/issues-raw/eosphoros-ai/DB-GPT" />
</a> </a>
<a href="https://discord.gg/7uQnPuveTY"> <a href="https://x.com/DBGPT_AI">
<img alt="Discord" src="https://dcbadge.vercel.app/api/server/7uQnPuveTY?compact=true&style=flat" /> <img alt="X (formerly Twitter) Follow" src="https://img.shields.io/twitter/follow/DBGPT_AI" />
</a>
<a href="https://medium.com/@dbgpt0506">
<img alt="Medium Follow" src="https://badgen.net/badge/Medium/Dbgpt/orange?icon=medium" />
</a>
<a href="https://space.bilibili.com/3537113070963392">
<img alt="Bilibili Space" src="https://img.shields.io/badge/Bilibili-DB--GPT-blue?style=plastic&logo=bilibili&link=https%3A%2F%2Fspace.bilibili.com%2F3537113070963392" />
</a> </a>
<a href="https://join.slack.com/t/slack-inu2564/shared_invite/zt-29rcnyw2b-N~ubOD9kFc7b7MDOAM1otA"> <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" /> <img alt="Slack" src="https://badgen.net/badge/Slack/Join%20DB-GPT/0abd59?icon=slack" />
</a> </a>
<br/>
<a href="https://codespaces.new/eosphoros-ai/DB-GPT"> <a href="https://codespaces.new/eosphoros-ai/DB-GPT">
<img alt="Open in GitHub Codespaces" src="https://github.com/codespaces/badge.svg" /> <img alt="Open in GitHub Codespaces" src="https://github.com/codespaces/badge.svg" />
</a> </a>
</p> </p>
[**English**](README.md) | [**Discord**](https://discord.gg/7uQnPuveTY) | [**文档**](https://www.yuque.com/eosphoros/dbgpt-docs/bex30nsv60ru0fmx) | [**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) | [**社区**](https://github.com/eosphoros-ai/community) | [**Paper**](https://arxiv.org/pdf/2312.17449.pdf) [![English](https://img.shields.io/badge/English-gray?style=flat-square)](README.md)
[![简体中文](https://img.shields.io/badge/简体中文-gray?style=flat-square)](README.zh.md)
[![日本語](https://img.shields.io/badge/日本語-gray?style=flat-square)](README.ja.md)
[**文档**](http://docs.dbgpt.cn/docs/overview/) | [**联系团队**](https://github.com/eosphoros-ai/DB-GPT/blob/main/README.zh.md#%E8%81%94%E7%B3%BB%E6%88%91%E4%BB%AC) | [**社区**](https://github.com/eosphoros-ai/community) | [**Paper**](https://arxiv.org/pdf/2312.17449.pdf)
</div> </div>
## DB-GPT 是什么? ## DB-GPT 是什么?
@ -44,6 +56,38 @@
🚀 **数据3.0 时代,基于模型、数据库,企业/开发者可以用更少的代码搭建自己的专属应用。** 🚀 **数据3.0 时代,基于模型、数据库,企业/开发者可以用更少的代码搭建自己的专属应用。**
### 架构方案
<p align="center">
<img src="./assets/dbgpt.png" width="800px" />
</p>
核心能力主要有以下几个部分:
- **RAG(Retrieval Augmented Generation)**RAG是当下落地实践最多也是最迫切的领域DB-GPT目前已经实现了一套基于RAG的框架用户可以基于DB-GPT的RAG能力构建知识类应用。
- **GBI**生成式BI是DB-GPT项目的核心能力之一为构建企业报表分析、业务洞察提供基础的数智化技术保障。
- **微调框架**: 模型微调是任何一个企业在垂直、细分领域落地不可或缺的能力DB-GPT提供了完整的微调框架实现与DB-GPT项目的无缝打通在最近的微调中基于spider的准确率已经做到了82.5%
- **数据驱动的Multi-Agents框架**: DB-GPT提供了数据驱动的自进化Multi-Agents框架目标是可以持续基于数据做决策与执行。
- **数据工厂**: 数据工厂主要是在大模型时代,做可信知识、数据的清洗加工。
- **数据源**: 对接各类数据源实现生产业务数据无缝对接到DB-GPT核心能力。
#### 子模块
- [DB-GPT-Hub](https://github.com/eosphoros-ai/DB-GPT-Hub) 通过微调来持续提升Text2SQL效果
- [DB-GPT-Plugins](https://github.com/eosphoros-ai/DB-GPT-Plugins) DB-GPT 插件仓库, 兼容Auto-GPT
- [GPT-Vis](https://github.com/eosphoros-ai/DB-GPT-Web) 可视化协议
- [dbgpts](https://github.com/eosphoros-ai/dbgpts) dbgpts 是官方提供的数据应用仓库, 包含数据智能应用, 智能体编排流程模版, 通用算子等构建在DB-GPT之上的资源。
#### RAG生产落地实践架构
<p align="center">
<img src="./assets/RAG-IN-ACTION.jpg" width="800px" />
</p>
## 效果演示 ## 效果演示
### AI原生数据智能应用 ### AI原生数据智能应用
@ -69,45 +113,6 @@
![agent_prompt_awel_v0 6](https://github.com/user-attachments/assets/40761507-a1e1-49d4-b49a-3dd9a5ea41cc) ![agent_prompt_awel_v0 6](https://github.com/user-attachments/assets/40761507-a1e1-49d4-b49a-3dd9a5ea41cc)
## 目录
- [架构方案](#架构方案)
- [安装](#安装)
- [特性简介](#特性一览)
- [贡献](#贡献)
- [路线图](#路线图)
- [联系我们](#联系我们)
## 架构方案
<p align="center">
<img src="./assets/dbgpt.png" width="800px" />
</p>
核心能力主要有以下几个部分:
- **RAG(Retrieval Augmented Generation)**RAG是当下落地实践最多也是最迫切的领域DB-GPT目前已经实现了一套基于RAG的框架用户可以基于DB-GPT的RAG能力构建知识类应用。
- **GBI**生成式BI是DB-GPT项目的核心能力之一为构建企业报表分析、业务洞察提供基础的数智化技术保障。
- **微调框架**: 模型微调是任何一个企业在垂直、细分领域落地不可或缺的能力DB-GPT提供了完整的微调框架实现与DB-GPT项目的无缝打通在最近的微调中基于spider的准确率已经做到了82.5%
- **数据驱动的Multi-Agents框架**: DB-GPT提供了数据驱动的自进化Multi-Agents框架目标是可以持续基于数据做决策与执行。
- **数据工厂**: 数据工厂主要是在大模型时代,做可信知识、数据的清洗加工。
- **数据源**: 对接各类数据源实现生产业务数据无缝对接到DB-GPT核心能力。
### RAG生产落地实践架构
<p align="center">
<img src="./assets/RAG-IN-ACTION.jpg" width="800px" />
</p>
### 子模块
- [DB-GPT-Hub](https://github.com/eosphoros-ai/DB-GPT-Hub) 通过微调来持续提升Text2SQL效果
- [DB-GPT-Plugins](https://github.com/eosphoros-ai/DB-GPT-Plugins) DB-GPT 插件仓库, 兼容Auto-GPT
- [GPT-Vis](https://github.com/eosphoros-ai/DB-GPT-Web) 可视化协议
- [dbgpts](https://github.com/eosphoros-ai/dbgpts) dbgpts 是官方提供的数据应用仓库, 包含数据智能应用, 智能体编排流程模版, 通用算子等构建在DB-GPT之上的资源。
## 安装 ## 安装
![Docker](https://img.shields.io/badge/docker-%230db7ed.svg?style=for-the-badge&logo=docker&logoColor=white) ![Docker](https://img.shields.io/badge/docker-%230db7ed.svg?style=for-the-badge&logo=docker&logoColor=white)
@ -251,10 +256,6 @@
🌐 [小程序云部署](https://www.yuque.com/eosphoros/dbgpt-docs/ek12ly8k661tbyn8) 🌐 [小程序云部署](https://www.yuque.com/eosphoros/dbgpt-docs/ek12ly8k661tbyn8)
### 多语言切换
在.env 配置文件当中修改LANGUAGE参数来切换使用不同的语言默认是英文(中文zh, 英文en, 其他语言待补充)
## 使用说明 ## 使用说明
### 多模型使用 ### 多模型使用
@ -281,6 +282,10 @@
The MIT License (MIT) The MIT License (MIT)
### 免责声明
- [免责声明](./DISCKAIMER.md)
## 引用 ## 引用
如果您发现`DB-GPT`对您的研究或开发有用,请引用以下论文,其中: 如果您发现`DB-GPT`对您的研究或开发有用,请引用以下论文,其中:

BIN
assets/LOGO_SMALL.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 14 KiB

BIN
assets/Twitter_LOGO.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 620 KiB

BIN
assets/Youtube_LOGO.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.2 MiB