mirror of
https://github.com/csunny/DB-GPT.git
synced 2026-07-16 17:15:22 +00:00
docs: readme
This commit is contained in:
26
README.md
26
README.md
@@ -50,38 +50,38 @@
|
||||
|
||||
</div>
|
||||
|
||||
> **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.**
|
||||
> **An open-source AI data assistant that connects to your data, writes SQL and code, runs skills in sandboxed environments, and turns analysis into reports, insights, and action.**
|
||||
|
||||
## What is DB-GPT?
|
||||
|
||||
DB-GPT is an open-source **agentic AI data assistant** built for the next generation of **AI + Data** products.
|
||||
DB-GPT is an open-source **agentic AI data assistant** for the next generation of **AI + Data** products.
|
||||
|
||||
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
|
||||
- connect to **databases, CSV / Excel files, warehouses, and knowledge bases**
|
||||
- ask questions in natural language and let AI **write SQL autonomously**
|
||||
- run **Python- and code-driven 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**
|
||||
- execute tasks safely in **sandboxed environments**
|
||||
|
||||
DB-GPT is also a platform for building **AI-native data agents, workflows, and applications** with agents, AWEL, RAG, and multi-model support.
|
||||
|
||||
## Why DB-GPT?
|
||||
|
||||
### 1. Agentic data analysis
|
||||
DB-GPT can plan tasks, break work into steps, call tools, and iteratively complete analysis workflows.
|
||||
Plan tasks, break work into steps, call tools, and complete analysis workflows end to end.
|
||||
|
||||
### 2. Autonomous SQL + code execution
|
||||
DB-GPT can automatically write SQL and code to query data, clean datasets, compute metrics, and generate outputs.
|
||||
Generate SQL and code to query data, clean datasets, compute metrics, and produce outputs.
|
||||
|
||||
### 3. Multi-source data access
|
||||
DB-GPT works across structured and unstructured sources, including databases, spreadsheets, documents, and knowledge bases.
|
||||
Work across structured and unstructured sources, including databases, spreadsheets, documents, and knowledge bases.
|
||||
|
||||
### 4. Skills-driven extensibility
|
||||
DB-GPT supports reusable skills that encapsulate domain knowledge, analysis methods, and execution workflows.
|
||||
Package domain knowledge, analysis methods, and execution workflows into reusable skills.
|
||||
|
||||
### 5. Sandboxed execution
|
||||
DB-GPT can safely run code and tools in isolated environments for more reliable and controllable analysis.
|
||||
Run code and tools in isolated environments for safer, more reliable analysis.
|
||||
|
||||
## What you can do with DB-GPT
|
||||
|
||||
@@ -90,7 +90,7 @@ DB-GPT can safely run code and tools in isolated environments for more reliable
|
||||
- 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
|
||||
- Combine **code, SQL, retrieval, and tools** in a single agentic workflow
|
||||
- Build next-generation **AI + Data assistants** for your team or product
|
||||
|
||||
## Product Workflow
|
||||
@@ -398,7 +398,7 @@ We protect data privacy and execution safety through private model deployment, p
|
||||
|
||||
## Vision
|
||||
|
||||
We believe the future of data products is not dashboards alone.
|
||||
We believe the future of data products goes beyond dashboards.
|
||||
|
||||
The next generation of **AI + Data** products will be:
|
||||
- **agentic**
|
||||
|
||||
18
README.zh.md
18
README.zh.md
@@ -50,16 +50,16 @@
|
||||
|
||||
</div>
|
||||
|
||||
> **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。**
|
||||
> **一个开源的 AI 数据分析智能助手:连接你的数据,自主编写 SQL 与代码,在沙箱环境中运行 skills,把分析转化为报告、洞察与行动。**
|
||||
|
||||
## DB-GPT 是什么?
|
||||
|
||||
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。
|
||||
|
||||
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
|
||||
- 连接 **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
|
||||
- 执行 **Python 与代码驱动的数据分析流程**
|
||||
- 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
|
||||
@@ -69,19 +69,19 @@ DB-GPT 不只是一个助手界面,它同时也是一个平台,用于构建
|
||||
## 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。
|
||||
它不只是回答问题,而是会进行任务规划、步骤拆解、工具调用和迭代式分析。
|
||||
|
||||
### 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。
|
||||
自动编写 SQL 和代码,用于查询数据、处理数据、计算指标并生成结果。
|
||||
|
||||
### 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。
|
||||
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。
|
||||
|
||||
### 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。
|
||||
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。
|
||||
|
||||
### 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。
|
||||
在隔离环境中运行代码和工具,让分析过程更安全、更可控。
|
||||
|
||||
## 你可以用 DB-GPT 做什么?
|
||||
|
||||
@@ -417,7 +417,7 @@ DB-GPT 同时也是一个构建 AI Native 数据产品的平台,提供:
|
||||
|
||||
## 愿景
|
||||
|
||||
我们相信,未来的数据产品不应只是 Dashboard。
|
||||
我们相信,未来的数据产品不应止于 Dashboard。
|
||||
|
||||
下一代 **AI + Data** 产品将是:
|
||||
- **agentic**
|
||||
|
||||
Reference in New Issue
Block a user