From dd3a3aeffd3b7cdb246c028e0ffeb6a426c8b443 Mon Sep 17 00:00:00 2001 From: aries_ckt <916701291@qq.com> Date: Sun, 15 Mar 2026 21:30:40 +0800 Subject: [PATCH] docs: quick-start installation --- README.md | 201 +++++++++++++++++++++++++++++++-------------------- README.zh.md | 198 ++++++++++++++++++++++++++++++-------------------- 2 files changed, 244 insertions(+), 155 deletions(-) diff --git a/README.md b/README.md index 5272cac8a..763fb61d9 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,4 @@ -# Logo DB-GPT: AI Native Data App Development framework with AWEL and Agents +# Logo DB-GPT: Open-Source Agentic AI Data Assistant

@@ -50,82 +50,62 @@ +> **Connect to databases, files, and knowledge bases. Let AI autonomously write SQL and code, use skills, run in sandboxed environments, and generate charts, reports, and decisions.** + ## What is DB-GPT? -🤖 **DB-GPT is an open source AI native data app development framework with AWEL(Agentic Workflow Expression Language) and agents**. +DB-GPT is an open-source **agentic AI data assistant** built for the next generation of **AI + Data** products. -The purpose is to build infrastructure in the field of large models, through the development of multiple technical capabilities such as multi-model management (SMMF), Text2SQL effect optimization, RAG framework and optimization, Multi-Agents framework collaboration, AWEL (agent workflow orchestration), etc. Which makes large model applications with data simpler and more convenient. +It helps users and teams: +- connect to **multiple data sources** such as databases, CSV / Excel files, warehouses, and knowledge bases +- ask questions in natural language and let AI **autonomously write SQL** +- run **Python and code-based analysis** workflows +- load and execute reusable **skills** for domain-specific tasks +- generate **charts, dashboards, HTML reports, and analysis summaries** +- safely execute tasks in **sandboxed environments** -🚀 **In the Data 3.0 era, based on models and databases, enterprises and developers can build their own bespoke applications with less code.** +DB-GPT is also a platform for building **AI-native data agents, workflows, and applications** with agents, AWEL, RAG, and multi-model support. -### Introduction -The architecture of DB-GPT is shown in the following figure: +## Why DB-GPT? -

- -

+### 1. Agentic data analysis +DB-GPT can plan tasks, break work into steps, call tools, and iteratively complete analysis workflows. -The core capabilities include the following parts: +### 2. Autonomous SQL + code execution +DB-GPT can automatically write SQL and code to query data, clean datasets, compute metrics, and generate outputs. -- **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. +### 3. Multi-source data access +DB-GPT works across structured and unstructured sources, including databases, spreadsheets, documents, and knowledge bases. -- **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. +### 4. Skills-driven extensibility +DB-GPT supports reusable skills that encapsulate domain knowledge, analysis methods, and execution workflows. -- **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%. +### 5. Sandboxed execution +DB-GPT can safely run code and tools in isolated environments for more reliable and controllable analysis. -- **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. +## What you can do with DB-GPT -- **Data Factory**: The Data Factory is mainly about cleaning and processing trustworthy knowledge and data in the era of large models. +- **Analyze CSV / Excel files** and generate visual reports +- **Connect to databases** and produce profiling reports +- Ask business questions in natural language and let AI **write SQL automatically** +- Perform **financial report analysis** with code, charts, and narrative summaries +- Create and reuse **SQL analysis skills** and domain workflows +- Combine **code, SQL, retrieval, and tools** in one agentic workflow +- Build next-generation **AI + Data assistants** for your team or product -- **Data Sources**: Integrating various data sources to seamlessly connect production business data to the core capabilities of DB-GPT. +## Product Workflow -#### 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). +### Explore data +Connect files, databases, and knowledge bases in one workspace. -- [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. +### Plan and execute +Let AI reason through the task, write SQL and code, and execute step by step. -#### DeepWiki -- [DB-GPT](https://deepwiki.com/eosphoros-ai/DB-GPT) -- [DB-GPT-HUB](https://deepwiki.com/eosphoros-ai/DB-GPT-Hub) -- [dbgpts](https://deepwiki.com/eosphoros-ai/dbgpts) +### Use skills +Load reusable skills for repeatable business analysis workflows. - -#### Text2SQL Finetune - - | LLM | Supported | - |:-----------:|:-----------:| - | LLaMA | ✅ | - | LLaMA-2 | ✅ | - | BLOOM | ✅ | - | BLOOMZ | ✅ | - | Falcon | ✅ | - | Baichuan | ✅ | - | Baichuan2 | ✅ | - | InternLM | ✅ | - | Qwen | ✅ | - | XVERSE | ✅ | - | 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 ---- -- 🔥🔥🔥 [Released V0.7.0 | A set of significant upgrades](http://docs.dbgpt.cn/blog/db-gpt-v070-release) - - [Support MCP Protocol](https://github.com/eosphoros-ai/DB-GPT/pull/2497) - - [Support DeepSeek R1](https://github.com/deepseek-ai/DeepSeek-R1) - - [Support QwQ-32B](https://huggingface.co/Qwen/QwQ-32B) - - [Refactor the basic modules]() - - [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) ---- +### Generate reports +Produce charts, dashboards, HTML reports, and decision-ready outputs. ![app_chat_v0 6](https://github.com/user-attachments/assets/a2f0a875-df8c-4f0d-89a3-eed321c02113) @@ -225,30 +205,81 @@ For Docker, local GPU models (vLLM, llama.cpp), or manual source-code setup, see - [AWEL](http://docs.dbgpt.cn/docs/awel/tutorial) -## Features +## Core Capabilities -At present, we have introduced several key features to showcase our current capabilities: -- **Private Domain Q&A & Data Processing** +### Agentic Analysis +- task planning +- step-by-step execution +- tool use +- iterative reasoning - 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. +### SQL + Code Execution +- natural language to SQL +- Python-based analysis and transformation +- metric calculation +- chart generation -- **Multi-Data Source & GBI(Generative Business intelligence)** +### Multi-Source Data Access +- relational databases +- CSV / Excel +- documents +- knowledge bases +- mixed-source workflows - 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. +### Skills and Agents +- reusable skills +- domain workflows +- agent orchestration +- customizable execution flows -- **Multi-Agents&Plugins** +### Reporting and Decision Support +- database profiling reports +- financial analysis reports +- visual reports and dashboards +- summaries and business insights - 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. +### Safe Execution +- sandboxed code execution +- controlled tool use +- reproducible outputs and artifacts -- **Automated Fine-tuning text2SQL** +## Platform & Ecosystem - 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) +DB-GPT is also a platform for building AI-native data systems. - - **SMMF(Service-oriented Multi-model Management Framework)** +- **AWEL** for agentic workflow orchestration +- **Agents** for autonomous task execution +- **RAG** for knowledge-enhanced reasoning +- **SMMF** for multi-model management +- **DB-GPT-Hub** for Text2SQL and finetuning workflows +- **dbgpts** for apps, workflows, operators, and templates +- [DB-GPT-Plugins](https://github.com/eosphoros-ai/DB-GPT-Plugins) for plugin-based extension +- [GPT-Vis](https://github.com/eosphoros-ai/GPT-Vis) for visualization protocols - 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. +#### DeepWiki +- [DB-GPT](https://deepwiki.com/eosphoros-ai/DB-GPT) +- [DB-GPT-HUB](https://deepwiki.com/eosphoros-ai/DB-GPT-Hub) +- [dbgpts](https://deepwiki.com/eosphoros-ai/dbgpts) - - News +#### Text2SQL Finetune + + | LLM | Supported | + |:-----------:|:-----------:| + | LLaMA | ✅ | + | LLaMA-2 | ✅ | + | BLOOM | ✅ | + | BLOOMZ | ✅ | + | Falcon | ✅ | + | Baichuan | ✅ | + | Baichuan2 | ✅ | + | InternLM | ✅ | + | Qwen | ✅ | + | XVERSE | ✅ | + | ChatGLM2 | ✅ | + +[More Information about Text2SQL finetune](https://github.com/eosphoros-ai/DB-GPT-Hub) + +### Supported Models @@ -358,12 +389,26 @@ At present, we have introduced several key features to showcase our current capa - [More Supported LLMs](http://docs.dbgpt.site/docs/modules/smmf) -- **Privacy and Security** - - We ensure the privacy and security of data through the implementation of various technologies, including privatized large models and proxy desensitization. +### Privacy and Security -- Support Datasources - - [Datasources](http://docs.dbgpt.cn/docs/modules/connections) +We protect data privacy and execution safety through private model deployment, proxy desensitization, and sandboxed execution mechanisms. + +### Data Sources +- [Datasources](http://docs.dbgpt.cn/docs/modules/connections) + +## Vision + +We believe the future of data products is not dashboards alone. + +The next generation of **AI + Data** products will be: +- **agentic** +- **multi-source** +- **skill-driven** +- **sandboxed** +- capable of writing **SQL and code** +- able to turn analysis into **reports, decisions, and action** + +DB-GPT aims to help developers and enterprises build that future. ## Image 🌐 [AutoDL Image](https://www.codewithgpu.com/i/eosphoros-ai/DB-GPT/dbgpt) diff --git a/README.zh.md b/README.zh.md index 931f5b8e4..5f7748f31 100644 --- a/README.zh.md +++ b/README.zh.md @@ -1,4 +1,4 @@ -# Logo DB-GPT: AI原生数据应用开发框架 +# Logo DB-GPT：开源 Agentic AI 数据分析智能助手

@@ -50,84 +50,62 @@ +> **连接数据库、文件和知识库，让 AI 自主写 SQL、自主写代码、调用 skills、在沙箱环境中执行任务，并生成图表、报告与决策结论。** + ## DB-GPT 是什么？ -🤖️ **DB-GPT是一个开源的AI原生数据应用开发框架(AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents)。** +DB-GPT 是一个开源的 **Agentic AI 数据分析智能助手**，面向下一代 **AI + Data** 产品形态。 -目的是构建大模型领域的基础设施，通过开发多模型管理(SMMF)、Text2SQL效果优化、RAG框架以及优化、Multi-Agents框架协作、AWEL(智能体工作流编排)等多种技术能力，让围绕数据库构建大模型应用更简单，更方便。 +它可以帮助用户和团队： +- 连接 **多种数据源**，包括数据库、CSV / Excel、数仓、知识库与文档 +- 使用自然语言提问，并让 AI **自主编写 SQL** +- 执行 **Python 与代码分析** 流程 +- 加载并执行可复用的 **skills** +- 自动生成 **图表、Dashboard、HTML 报告和分析总结** +- 在 **沙箱环境** 中安全执行分析任务 -🚀 **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。** +DB-GPT 不只是一个助手界面，它同时也是一个平台，用于构建 **AI Native 数据智能体、工作流与应用**，底层支持 agents、AWEL、RAG 与多模型能力。 -### 架构方案 +## 为什么选择 DB-GPT？ -

- -

+### 1. Agentic 数据分析 +DB-GPT 不只是回答问题，它会进行任务规划、步骤拆解、工具调用和迭代式分析。 -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。 +### 2. 自主 SQL + 自主代码执行 +DB-GPT 能自动编写 SQL 和代码，用于查询数据、处理数据、计算指标和生成结果。 -- **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。 +### 3. 多数据源分析 +DB-GPT 可同时处理结构化与非结构化数据，包括数据库、表格文件、文档和知识库。 -- **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% +### 4. Skills 驱动的可扩展能力 +DB-GPT 支持将领域知识、分析方法和执行流程沉淀为 skills，实现复用与扩展。 -- **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。 +### 5. 沙箱安全执行 +DB-GPT 可以在隔离环境中运行代码和工具，使分析过程更安全、更可控。 -- **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。 +## 你可以用 DB-GPT 做什么？ -- **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。 +- **分析 CSV / Excel 文件** 并生成可视化报告 +- **连接数据库** 自动生成数据库画像与分析报告 +- 用自然语言提问，让 AI **自动写 SQL** +- 进行 **财报深度分析**，生成图表、分析结论与总结 +- 创建和复用 **SQL 分析技能** +- 将 **代码、SQL、检索和工具调用** 组合成完整的 agentic 分析流程 +- 构建面向团队或产品的下一代 **AI + Data 智能助手** -#### 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。 +## 产品工作流 +### 数据探索 +连接文件、数据库和知识库，在统一入口开始分析任务。 -#### DeepWiki -- [DB-GPT](https://deepwiki.com/eosphoros-ai/DB-GPT) -- [DB-GPT-HUB](https://deepwiki.com/eosphoros-ai/DB-GPT-Hub) -- [dbgpts](https://deepwiki.com/eosphoros-ai/dbgpts) +### 规划与执行 +让 AI 进行任务推理、生成 SQL / 代码，并逐步完成分析。 +### 使用 Skills +加载可复用的业务分析技能与领域工作流。 - -#### Text2SQL 微调模型 - - | LLM | Supported | - |:-----------:|:-----------:| - | LLaMA | ✅ | - | LLaMA-2 | ✅ | - | BLOOM | ✅ | - | BLOOMZ | ✅ | - | Falcon | ✅ | - | Baichuan | ✅ | - | Baichuan2 | ✅ | - | InternLM | ✅ | - | Qwen | ✅ | - | XVERSE | ✅ | - | ChatGLM2 | ✅ | - -#### RAG生产落地实践架构 -

- -

- - -## 效果演示 - -### AI原生数据智能应用 ---- -- [V0.7.0发布——一系列重大功能更新](https://www.yuque.com/eosphoros/dbgpt-docs/asweou4i9rhnwchm) - - [支持MCP协议](https://github.com/eosphoros-ai/DB-GPT/pull/2497) - - 支持DeepSeek-R1、QwQ-32B等推理模型 - - 重构基础模块 - - [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 Agents +### 生成报告 +自动输出图表、Dashboard、HTML 报告和决策结论。 ![app_chat_v0 6](https://github.com/user-attachments/assets/a2f0a875-df8c-4f0d-89a3-eed321c02113) @@ -138,7 +116,7 @@ ![agent_prompt_awel_v0 6](https://github.com/user-attachments/assets/40761507-a1e1-49d4-b49a-3dd9a5ea41cc) -## 安装 +## 快速开始 你可以通过一键安装脚本在几分钟内启动 DB-GPT（macOS / Linux）： @@ -234,28 +212,79 @@ cd ~/.dbgpt/DB-GPT && uv run dbgpt start webserver --config ~/.dbgpt/configs/ @@ -379,12 +408,27 @@ cd ~/.dbgpt/DB-GPT && uv run dbgpt start webserver --config ~/.dbgpt/configs/