diff --git a/README.ja.md b/README.ja.md index 61561ec21..898d4bbda 100644 --- a/README.ja.md +++ b/README.ja.md @@ -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 +# Logo 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 -

- + +

+

-
+

stars @@ -21,18 +22,30 @@ Open Issues - - Discord + + X (formerly Twitter) Follow + + + Medium Follow + + + Bilibili Space Slack +
Open in GitHub Codespaces

-[**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) +
@@ -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。** -### 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) - -![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 +### 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：

@@ -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。 -### 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。 - [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 - [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 ![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) @@ -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 🌐 [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 - 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。 diff --git a/README.md b/README.md index be27a42b9..7c2bf7e53 100644 --- a/README.md +++ b/README.md @@ -1,10 +1,10 @@ -# DB-GPT: AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents +# Logo DB-GPT: AI Native Data App Development framework with AWEL and Agents -

- +

+

-
+

stars @@ -21,19 +21,30 @@ Open Issues - - Discord + + X (formerly Twitter) Follow + + + Medium Follow + + + Bilibili Space Slack +
Open in GitHub Codespaces

-[**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)
@@ -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.** -### DISCKAIMER -- [disckaimer](./DISCKAIMER.md) +### Introduction +The architecture of DB-GPT is shown in the following figure: + +

+ +

+ +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 --- @@ -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) -## Contents -- [Introduction](#introduction) -- [Install](#install) -- [Features](#features) -- [Contribution](#contribution) -- [Contact](#contact-information) -## Introduction -The architecture of DB-GPT is shown in the following figure: - -

- -

- -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 +## Installation / Quick Start ![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) ![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) -### 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 @@ -255,10 +255,13 @@ At present, we have introduced several key features to showcase our current capa ## Licence The MIT License (MIT) -## Citation -If you want to understand the overall architecture of DB-GPT, please cite paper and Paper +## DISCKAIMER +- [disckaimer](./DISCKAIMER.md) -If you want to learn about using DB-GPT for Agent development, please cite the paper +## Citation +If you want to understand the overall architecture of DB-GPT, please cite Paper and Paper + +If you want to learn about using DB-GPT for Agent development, please cite the Paper ```bibtex @article{xue2023dbgpt, 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 -We are working on building a community, if you have any ideas for building the community, feel free to contact us. -[![](https://dcbadge.vercel.app/api/server/7uQnPuveTY?compact=true&style=flat)](https://discord.gg/7uQnPuveTY) +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. +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) diff --git a/README.zh.md b/README.zh.md index 3410c6225..c692d7b51 100644 --- a/README.zh.md +++ b/README.zh.md @@ -1,11 +1,11 @@ -# DB-GPT: AI原生数据应用开发框架 +# Logo DB-GPT: AI原生数据应用开发框架 -

- +

+

-
+

stars @@ -22,18 +22,30 @@ Open Issues - - Discord + + X (formerly Twitter) Follow + + + Medium Follow + + + Bilibili Space Slack +
Open in GitHub Codespaces

-[**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) +
## 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。** +### 架构方案 + +

+ +

+ +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 +

+ +

+ + ## 效果演示 ### 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) -## 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 - -

- -

- -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 -

- -

- -### 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 ![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) -### 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 ### 多模型使用 @@ -281,6 +282,10 @@ The MIT License (MIT) +### 免责声明 + +- [免责声明](./DISCKAIMER.md) + ## 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： diff --git a/assets/LOGO_SMALL.png b/assets/LOGO_SMALL.png new file mode 100644 index 000000000..40eeb962a Binary files /dev/null and b/assets/LOGO_SMALL.png differ diff --git a/assets/Twitter_LOGO.png b/assets/Twitter_LOGO.png new file mode 100644 index 000000000..e78967506 Binary files /dev/null and b/assets/Twitter_LOGO.png differ diff --git a/assets/Youtube_LOGO.png b/assets/Youtube_LOGO.png new file mode 100644 index 000000000..62b0059a4 Binary files /dev/null and b/assets/Youtube_LOGO.png differ