doc:v0.8.0 docs i18n

This commit is contained in:
aries_ckt
2026-03-23 00:00:35 +08:00
parent 3c34f50134
commit 3b0be9d740
8 changed files with 812 additions and 57 deletions

View File

@@ -26,7 +26,7 @@ The default installation includes the **core framework** (CLI, FastAPI, SQLAlche
**OpenAI-compatible LLM support** (also works with Kimi, Qwen, MiniMax, Z.AI),
**DashScope / Tongyi** support, **RAG document parsing**, and **ChromaDB** vector store.
Need additional providers or data sources? See [Optional Modules](#optional-modules).
Need additional providers or data sources? See [Optional Modules](#7-optional-modules).
:::
After installation the `dbgpt` command is available in your terminal.

View File

@@ -0,0 +1,56 @@
---
sidebar_position: 0
title: Install
summary: "Choose the fastest way to install DB-GPT: quick install, CLI install, or source install"
read_when:
- You want to decide which installation path fits your environment
- You want the shortest route to a working DB-GPT setup
---
# Install
DB-GPT offers three recommended installation paths. Pick the one that matches how you want to run and manage the project.
## Choose an installation path
| Method | Best for | What you get |
|---|---|---|
| [Quick Install](/docs/installation/quick-install) | Fastest first run on macOS / Linux | One-line installer, generated profile config, ready-to-start webserver |
| [CLI Install](/docs/getting-started/cli-quickstart) | Users who prefer installing from PyPI | `dbgpt` CLI, interactive setup wizard, profile management |
| [Source Install](/docs/getting-started/deploy/source-code) | Developers and custom deployments | Full repo checkout, editable configs, maximum flexibility |
## Recommended path
For most users, start with **Quick Install**. It gives you the fastest path from zero to a running DB-GPT web UI.
```bash
curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh | bash
```
After installation, start the generated profile config:
```bash
cd ~/.dbgpt/DB-GPT && uv run dbgpt start webserver --config ~/.dbgpt/configs/<profile>.toml
```
Then open [http://localhost:5670](http://localhost:5670).
## When to choose each method
### Quick Install
Choose this if you want the simplest install flow and do not need to manage the repository manually.
### CLI Install
Choose this if you want to install DB-GPT directly from PyPI and use the `dbgpt` command to set up profiles interactively.
### Source Install
Choose this if you want full access to the repository for development, debugging, or custom integrations.
## Next steps
- [Quick Install](/docs/installation/quick-install)
- [CLI Install](/docs/getting-started/cli-quickstart)
- [Source Install](/docs/getting-started/deploy/source-code)

View File

@@ -0,0 +1,127 @@
---
sidebar_position: 1
title: Quick Install
summary: "The fastest way to install DB-GPT with the installer script from the README"
read_when:
- You want the shortest path to a working DB-GPT web UI
- You prefer the installer script over a manual source setup
---
import CommandCopyCard from "@site/src/components/mdx/CommandCopyCard";
# Quick Install
The fastest way to get DB-GPT running. The installer script prepares a local DB-GPT workspace, generates a provider profile, and gives you a ready-to-run webserver command.
## Recommended: installer script
Use the installer script if you want the shortest path from zero to a working DB-GPT web UI.
<CommandCopyCard command={`curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh | bash`} />
## System requirements
This quick-install flow is designed for:
- **macOS** or **Linux**
- a shell environment that can run `bash`
- network access to download dependencies
- an API key if you plan to use a hosted model provider immediately
:::tip Best fit
Choose this path if you want to try DB-GPT quickly without managing the repository structure yourself.
:::
## Install with a provider profile
If you already know which provider you want, pass the profile and API key directly during installation.
### OpenAI-compatible profile
<CommandCopyCard command={`curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh \
| OPENAI_API_KEY=sk-xxx bash -s -- --profile openai`} />
### Kimi 2.5 via Moonshot API
<CommandCopyCard command={`curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh \
| MOONSHOT_API_KEY=sk-xxx bash -s -- --profile kimi`} />
### MiniMax via an OpenAI-compatible API
<CommandCopyCard command={`curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh \
| MINIMAX_API_KEY=sk-xxx bash -s -- --profile minimax`} />
## Reuse an existing local checkout
Already have a local DB-GPT repository? Reuse it instead of cloning into `~/.dbgpt/DB-GPT`.
### Reuse local repo with OpenAI
<CommandCopyCard command={`OPENAI_API_KEY=sk-xxx \
bash scripts/install/install.sh --profile openai --repo-dir "$(pwd)" --yes`} />
### Reuse local repo with Kimi
<CommandCopyCard command={`MOONSHOT_API_KEY=sk-xxx \
bash scripts/install/install.sh --profile kimi --repo-dir "$(pwd)" --yes`} />
### Reuse local repo with MiniMax
<CommandCopyCard command={`MINIMAX_API_KEY=sk-xxx \
bash scripts/install/install.sh --profile minimax --repo-dir "$(pwd)" --yes`} />
## What the installer prepares
The installer script sets up the common runtime layout for you:
- a DB-GPT checkout under `~/.dbgpt/DB-GPT` unless `--repo-dir` is used
- generated provider configs under `~/.dbgpt/configs/`
- the DB-GPT home directory under `~/.dbgpt/`
- a ready-to-run webserver command using the generated profile
## Start DB-GPT after installation
After installation completes, start the webserver with the generated profile config:
<CommandCopyCard command={`cd ~/.dbgpt/DB-GPT && uv run dbgpt start webserver --config ~/.dbgpt/configs/<profile>.toml`} />
Then open [http://localhost:5670](http://localhost:5670).
## Verify the install
Your install is working if:
- the webserver starts without configuration errors
- the Web UI opens at `http://localhost:5670`
- you can start a chat in the browser
## Review the script first
If you prefer to inspect the installer before running it:
```bash
curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh -o install.sh
less install.sh
bash install.sh --profile openai
```
## Alternative install methods
If the installer script is not the right fit for your environment:
- use [CLI Install](/docs/getting-started/cli-quickstart) for a PyPI-based install with the `dbgpt` command
- use [Source Install](/docs/getting-started/deploy/source-code) for development, debugging, and customization
## Troubleshooting
### The installer script does not match my shell or platform
Use [CLI Install](/docs/getting-started/cli-quickstart) or [Source Install](/docs/getting-started/deploy/source-code) instead.
### I want more control over dependencies and configuration
Use [Source Install](/docs/getting-started/deploy/source-code). It exposes the full repository layout and `uv sync` workflow.
### The install completed, but DB-GPT does not start cleanly
Check the generated config under `~/.dbgpt/configs/`, then see [Installation Issues](/docs/getting-started/troubleshooting/installation).

View File

@@ -15,6 +15,18 @@
"message": "安装部署",
"description": "The label for category Installation in sidebar docsSidebar"
},
"sidebar.docsSidebar.doc.Quick Install": {
"message": "快速安装",
"description": "The label for the doc item Quick Install in sidebar docsSidebar, linking to the doc installation/quick-install"
},
"sidebar.docsSidebar.doc.CLI Install": {
"message": "CLI 安装",
"description": "The label for the doc item CLI Install in sidebar docsSidebar, linking to the doc getting-started/cli-quickstart"
},
"sidebar.docsSidebar.doc.Source Install": {
"message": "源码安装",
"description": "The label for the doc item Source Install in sidebar docsSidebar, linking to the doc getting-started/deploy/source-code"
},
"sidebar.docsSidebar.category.Model Service Deployment": {
"message": "模型服务部署",
"description": "The label for category Model Service Deployment in sidebar docsSidebar"

View File

@@ -0,0 +1,429 @@
---
sidebar_position: 1
title: CLI 安装
summary: "通过 PyPI 安装 DB-GPT并用单条命令启动它无需源码 checkout"
read_when:
- 你想直接从 PyPI 安装 DB-GPT
- 你希望通过 `dbgpt` CLI 完成交互式配置
---
# CLI 安装
通过 PyPI 安装 DB-GPT并使用单条命令启动它 —— 无需检出源码仓库。
:::tip 前置条件
- Python **3.10** 或更高版本
- 推荐使用 [uv](https://docs.astral.sh/uv/getting-started/installation/) 包管理器,也支持 pip
:::
## 1. 安装
```bash
# 推荐:使用 uv
uv pip install dbgpt-app
# 或者使用 pip
pip install dbgpt-app
```
:::info 默认包含内容
默认安装会包含 **核心框架**CLI、FastAPI、SQLAlchemy、Agent、**OpenAI 兼容 LLM 支持**(也适用于 Kimi、Qwen、MiniMax、Z.AI、**DashScope / Tongyi** 支持、**RAG 文档解析** 和 **ChromaDB** 向量存储。
如果你需要更多 provider 或数据源,可参考 [可选模块](#7-可选模块)。
:::
安装完成后,终端中就可以直接使用 `dbgpt` 命令。
## 2. 启动 DB-GPT
```bash
dbgpt start
```
首次运行时DB-GPT 会自动启动一个 **交互式配置向导**,帮助你:
1. 选择 LLM providerOpenAI、Kimi、Qwen、MiniMax、Z.AI 或自定义 endpoint
2. 输入 API Key或改用环境变量
3. 确认模型名称和 API Base URL
完成后,系统会把 TOML 配置写入 `~/.dbgpt/configs/<profile>.toml`,并自动启动 webserver。然后打开浏览器访问 `http://localhost:5670`
### 启动后的样子
```
____ ____ ____ ____ _____
| _ \| __ ) / ___| _ \_ _|
| | | | _ \ ____| | _| |_) || |
| |_| | |_) |____| |_| | __/ | |
|____/|____/ \____|_| |_|
🚀 DB-GPT Quick Start
+- - - - - - - - - - - - - - - - - - - - - - - -+
: Profile: openai :
: Config: /Users/you/.dbgpt/configs/openai.toml:
: Workspace: /Users/you/.dbgpt/workspace :
+- - - - - - - - - - - - - - - - - - - - - - - -+
```
---
## 3. 命令参考
### 总览
```
dbgpt [OPTIONS] COMMAND [ARGS]...
Options:
--log-level TEXT Log level (default: warn)
--version Show version and exit
--help Show help message
Commands:
start Start the DB-GPT server
stop Stop a running server
setup Configure LLM provider (interactive wizard or CI mode)
profile Manage configuration profiles
knowledge Knowledge base operations
model Manage model serving
db Database management and migration
...
```
---
### `dbgpt start`
启动 DB-GPT web server。直接运行 `dbgpt start` 等价于 `dbgpt start web`
#### 子命令
| 子命令 | 说明 |
|---|---|
| `web`(或 `webserver` | 启动 web server默认 |
| `none` | 仅 API 模式 —— *未来版本计划支持* |
| `controller` | 启动模型 controller |
| `worker` | 启动模型 worker |
| `apiserver` | 启动 API server |
#### `dbgpt start web` 参数
| 参数 | Short | 类型 | 默认值 | 说明 |
|---|---|---|---|---|
| `--config` | `-c` | PATH | *auto* | TOML 配置文件路径。若未提供,则使用当前 active profile或自动启动配置向导。 |
| `--profile` | `-p` | TEXT | *active* | Provider profile 名称(`openai``kimi``qwen``minimax``glm``custom`)。会覆盖当前 active profile。 |
| `--yes` | `-y` | FLAG | false | 非交互模式:跳过向导,直接使用默认值 / 环境变量,适合 CI/CD。 |
| `--api-key` | | TEXT | *env* | 指定 provider 的 API key也可通过对应环境变量提供。 |
| `--daemon` | `-d` | FLAG | false | 后台守护进程方式运行。可通过 `dbgpt stop webserver` 停止。 |
#### 示例
```bash
# 首次运行,使用交互式向导
dbgpt start
# 使用现有 profile
dbgpt start web --profile openai
# 非交互方式并显式传入 API key
dbgpt start web --profile kimi --api-key sk-xxx --yes
# 使用指定配置文件
dbgpt start web --config /path/to/my-config.toml
# 以 daemon 方式运行
dbgpt start web --daemon
```
#### 配置解析优先级
启动 web server 时,配置文件的解析顺序如下:
1. **`--config` 参数** —— 如果提供,直接使用这个文件
2. **`--profile` 参数** —— 查找 `~/.dbgpt/configs/<profile>.toml`
3. **Active profile** —— 从 `~/.dbgpt/config.toml` 中读取
4. **配置向导** —— 如果还没有配置,则自动启动交互式向导
---
### `dbgpt stop`
停止正在运行的 DB-GPT 服务进程。
```bash
# 停止 web server
dbgpt stop webserver
# 停止指定端口上的 web server
dbgpt stop webserver --port 5670
# 停止所有服务
dbgpt stop all
```
---
### `dbgpt setup`
交互式配置 LLM provider或用于非交互 / CI 模式配置。这个命令会把 TOML 配置写入 `~/.dbgpt/configs/<profile>.toml`,并将它标记为 active profile。
#### 参数
| 参数 | Short | 类型 | 默认值 | 说明 |
|---|---|---|---|---|
| `--profile` | `-p` | TEXT | *interactive* | 要配置的 provider profile。若省略则显示交互菜单。 |
| `--yes` | `-y` | FLAG | false | 非交互模式:跳过向导并使用默认值。 |
| `--api-key` | | TEXT | *env* | API key也会读取 `DBGPT_API_KEY` 环境变量。 |
| `--show` | | FLAG | false | 显示当前 active profile 和配置路径后退出。 |
#### 示例
```bash
# 交互式向导
dbgpt setup
# 非交互:使用 OpenAI + 环境变量
export OPENAI_API_KEY=sk-xxx
dbgpt setup --profile openai --yes
# 非交互:显式传入 key
dbgpt setup --profile kimi --api-key sk-xxx
# 查看当前配置
dbgpt setup --show
```
---
### `dbgpt profile`
管理多个配置 profile。每个 profile 都是 `~/.dbgpt/configs/` 下的一个 TOML 文件。
#### 子命令
| 子命令 | 说明 |
|---|---|
| `list` | 列出所有 profileactive 的会用 `*` 标记 |
| `show <name>` | 显示某个 profile 的 TOML 内容 |
| `create <name>` | 使用配置向导创建(或重新配置)一个 profile |
| `switch <name>` | 将某个 profile 设为当前默认 |
| `delete <name>` | 删除某个 profile 配置文件 |
#### 示例
```bash
# 列出所有 profile
dbgpt profile list
# openai ← no asterisk
# * kimi ← active
# 查看 profile 内容
dbgpt profile show openai
# 创建新 profile
dbgpt profile create qwen
# 切换 active profile
dbgpt profile switch openai
# 删除 profile
dbgpt profile delete minimax
dbgpt profile delete minimax --yes # 跳过确认
```
---
## 4. 支持的 Providers
配置向导和 `--profile` 参数支持以下 provider
| Profile 名称 | 显示名称 | LLM 模型 | Embedding 模型 | API Key 环境变量 |
|---|---|---|---|---|
| `openai` | OpenAI | gpt-4o | text-embedding-3-small | `OPENAI_API_KEY` |
| `kimi` | Kimi | kimi-k2 | text-embedding-v3 | `MOONSHOT_API_KEY`embedding 同时需要 `DASHSCOPE_API_KEY` |
| `qwen` | Qwen | qwen-plus | text-embedding-v3 | `DASHSCOPE_API_KEY` |
| `minimax` | MiniMax | abab6.5s-chat | embo-01 | `MINIMAX_API_KEY` |
| `glm` | Z.AI | glm-4-plus | embedding-3 | `ZHIPUAI_API_KEY` |
| `custom` | Custom | gpt-4o | text-embedding-3-small | `OPENAI_API_KEY` |
:::info
**Custom** profile 可以连接任意 OpenAI 兼容 API endpoint。在向导中你会被要求输入 API Base URL。
:::
---
## 5. 目录结构
首次运行后DB-GPT 会在用户目录下创建如下结构:
```
~/.dbgpt/
├── config.toml # 记录当前 active profile 名称
├── configs/
│ ├── openai.toml # OpenAI profile
│ ├── kimi.toml # Kimi profile
│ └── ... # 每个 profile 对应一个文件
└── workspace/
└── pilot/ # 运行时工作区(数据库、数据文件等)
├── meta_data/
│ └── dbgpt.db # SQLite 元数据库
└── data/ # 向量数据存储
```
### 环境变量
| 变量 | 默认值 | 说明 |
|---|---|---|
| `DBGPT_HOME` | `~/.dbgpt` | 覆盖 DB-GPT home 目录 |
| `OPENAI_API_KEY` | — | OpenAI API key也用于 `openai``custom` profile |
| `MOONSHOT_API_KEY` | — | Kimi / Moonshot API key |
| `DASHSCOPE_API_KEY` | — | Qwen / DashScope API key也用于 Kimi embedding |
| `MINIMAX_API_KEY` | — | MiniMax API key |
| `ZHIPUAI_API_KEY` | — | Z.AI / Zhipu API key |
| `DBGPT_API_KEY` | — | 通用 API key`--api-key` 的 fallback |
| `DBGPT_LANG` | `en` | UI 语言(`en``zh` |
---
## 6. 常见工作流
### 首次安装
```bash
pip install dbgpt-app
dbgpt start
# Follow the wizard → choose provider → enter API key → server starts
```
### 在不同 provider 间切换
```bash
# 创建一个 Kimi profile
dbgpt profile create kimi
# 切换到它
dbgpt profile switch kimi
# 使用新 profile 启动
dbgpt start
```
### CI/CD 部署
```bash
export OPENAI_API_KEY=sk-xxx
dbgpt setup --profile openai --yes
dbgpt start web --daemon
```
### 自定义 endpoint例如 Azure OpenAI、local vLLM
```bash
dbgpt setup --profile custom
# Wizard will ask for:
# - API base URL (e.g. http://localhost:8000/v1)
# - API key
# - Model names
```
---
## 7. 可选模块
默认 `pip install dbgpt-app` 会包含核心框架。你也可以通过 extras 为 LLM provider、vector store、data source 等增加能力。
### LLM Providers
| Extra | Provider | 关键包 |
|-------|----------|-------------|
| `proxy_openai` | OpenAI、Kimi、Qwen、MiniMax、Z.AI 以及任意 OpenAI-compatible API | `openai`, `tiktoken` |
| `proxy_ollama` | Ollama本地模型 | `ollama` |
| `proxy_zhipuai` | Zhipu AIGLM | `openai` |
| `proxy_tongyi` | Tongyi Qianwen | `openai`, `dashscope` |
| `proxy_qianfan` | 百度千帆 | `qianfan` |
| `proxy_anthropic` | Anthropic Claude | `anthropic` |
### Vector Stores
| Extra | 存储 | 关键包 |
|-------|---------|-------------|
| `storage_chromadb` | ChromaDB | `chromadb`, `onnxruntime` |
| `storage_milvus` | Milvus | `pymilvus` |
| `storage_weaviate` | Weaviate | `weaviate-client` |
| `storage_elasticsearch` | Elasticsearch | `elasticsearch` |
| `storage_obvector` | OBVector | `pyobvector` |
### Knowledge & RAG
| Extra | 增加能力 | 关键包 |
|-------|-------------|-------------|
| `rag` | 文档解析PDF、DOCX、PPTX、Markdown、HTML | `spacy`, `pypdf`, `python-docx`, `python-pptx` |
| `graph_rag` | 基于 TuGraph / Neo4j 的 Graph RAG | `networkx`, `neo4j` |
### Data Sources
| Extra | 数据库 | 关键包 |
|-------|----------|-------------|
| `datasource_mysql` | MySQL | `mysqlclient` |
| `datasource_postgres` | PostgreSQL | `psycopg2-binary` |
| `datasource_clickhouse` | ClickHouse | `clickhouse-connect` |
| `datasource_oracle` | Oracle | `oracledb` |
| `datasource_mssql` | SQL Server | `pymssql` |
| `datasource_spark` | Apache Spark | `pyspark` |
| `datasource_hive` | Hive | `pyhive` |
| `datasource_vertica` | Vertica | `vertica-python` |
### 组合多个 extras 的示例
```bash
# OpenAI + ChromaDB + RAG + MySQL
pip install "dbgpt-app[proxy_openai,storage_chromadb,rag,datasource_mysql]"
```
:::tip 最小安装
如果你只需要核心框架而不需要任何 LLM 或存储支持:
```bash
pip install dbgpt-app
```
这会提供 CLI、FastAPI server 和 agent framework但要真正使用它至少还需要安装一个 LLM provider extra。
:::
---
## 8. 故障排查
### 端口已被占用
```bash
# 停止已有 web server
dbgpt stop webserver --port 5670
# 或改配置文件换端口
# [service.web]
# port = 5671
```
### 提示 “No config file found”
这说明当前还没有配置任何 profile请运行
```bash
dbgpt setup
```
### 更换 API Key
重新对同一个 profile 运行 setup 向导即可覆盖原配置:
```bash
dbgpt setup --profile openai
# 或者直接编辑 ~/.dbgpt/configs/openai.toml
```
### 查看当前配置
```bash
dbgpt setup --show
dbgpt profile show openai
```

View File

@@ -0,0 +1,56 @@
---
sidebar_position: 0
title: 安装
summary: "选择最适合你的 DB-GPT 安装方式快速安装、CLI 安装或源码安装"
read_when:
- 你想判断哪种安装路径最适合当前环境
- 你希望以最短路径完成可用的 DB-GPT 安装
---
# 安装
DB-GPT 提供三种推荐安装方式。你可以根据自己的使用方式和环境选择最合适的路径。
## 选择安装方式
| 方式 | 适合人群 | 你会得到什么 |
|---|---|---|
| [快速安装](/docs/installation/quick-install) | 希望在 macOS / Linux 上最快完成首次启动的用户 | 一行安装脚本、自动生成的 provider 配置、可直接启动的 webserver |
| [CLI 安装](/docs/getting-started/cli-quickstart) | 希望通过 PyPI 安装并使用命令行的用户 | `dbgpt` CLI、交互式向导、profile 管理能力 |
| [源码安装](/docs/getting-started/deploy/source-code) | 开发者或需要自定义部署的用户 | 完整仓库、可编辑配置、最大灵活性 |
## 推荐路径
对于大多数用户,建议先使用 **快速安装**。这是从零开始到跑通 DB-GPT Web UI 的最快路径。
```bash
curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh | bash
```
安装完成后,使用生成好的 profile 配置启动:
```bash
cd ~/.dbgpt/DB-GPT && uv run dbgpt start webserver --config ~/.dbgpt/configs/<profile>.toml
```
然后打开 [http://localhost:5670](http://localhost:5670)。
## 什么时候选择哪种方式
### 快速安装
如果你想以最少步骤完成安装,并且不打算手动管理仓库结构,选择这种方式。
### CLI 安装
如果你想直接通过 PyPI 安装 DB-GPT并用 `dbgpt` 命令交互式配置 provider profile选择这种方式。
### 源码安装
如果你需要完整仓库用于开发、调试或自定义集成,选择这种方式。
## 下一步
- [快速安装](/docs/installation/quick-install)
- [CLI 安装](/docs/getting-started/cli-quickstart)
- [源码安装](/docs/getting-started/deploy/source-code)

View File

@@ -0,0 +1,127 @@
---
sidebar_position: 1
title: 快速安装
summary: "使用 README 中的安装脚本,以最快方式安装 DB-GPT"
read_when:
- 你希望以最短路径跑通 DB-GPT Web UI
- 你希望优先使用安装脚本而不是手动源码部署
---
import CommandCopyCard from "@site/src/components/mdx/CommandCopyCard";
# 快速安装
这是让 DB-GPT 跑起来的最快方式。安装脚本会帮你准备本地 DB-GPT 工作目录、生成 provider profile并给出可直接运行的 webserver 启动命令。
## 推荐:安装脚本
如果你想从零开始,以最短路径获得一个可用的 DB-GPT Web UI推荐直接使用安装脚本。
<CommandCopyCard command={`curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh | bash`} />
## 系统要求
这个快速安装流程主要面向以下环境:
- **macOS** 或 **Linux**
- 可运行 `bash` 的 shell 环境
- 可以联网下载依赖
- 如果你要直接使用托管模型 provider需要提前准备好 API Key
:::tip 适用场景
如果你想快速体验 DB-GPT而不是手动管理仓库结构和依赖细节这条路径最合适。
:::
## 使用 provider profile 安装
如果你已经明确要使用哪个 provider可以在安装时直接传入 profile 和 API Key。
### OpenAI 兼容 profile
<CommandCopyCard command={`curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh \
| OPENAI_API_KEY=sk-xxx bash -s -- --profile openai`} />
### 通过 Moonshot API 使用 Kimi 2.5
<CommandCopyCard command={`curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh \
| MOONSHOT_API_KEY=sk-xxx bash -s -- --profile kimi`} />
### 通过 OpenAI 兼容接口使用 MiniMax
<CommandCopyCard command={`curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh \
| MINIMAX_API_KEY=sk-xxx bash -s -- --profile minimax`} />
## 复用已有本地仓库
如果你已经有一个本地 DB-GPT 仓库,可以直接复用,而不是重新克隆到 `~/.dbgpt/DB-GPT`
### 使用本地仓库 + OpenAI
<CommandCopyCard command={`OPENAI_API_KEY=sk-xxx \
bash scripts/install/install.sh --profile openai --repo-dir "$(pwd)" --yes`} />
### 使用本地仓库 + Kimi
<CommandCopyCard command={`MOONSHOT_API_KEY=sk-xxx \
bash scripts/install/install.sh --profile kimi --repo-dir "$(pwd)" --yes`} />
### 使用本地仓库 + MiniMax
<CommandCopyCard command={`MINIMAX_API_KEY=sk-xxx \
bash scripts/install/install.sh --profile minimax --repo-dir "$(pwd)" --yes`} />
## 安装脚本会准备什么
安装脚本会帮你准备一套通用运行布局:
-`~/.dbgpt/DB-GPT` 下放置一个 DB-GPT checkout如果没有使用 `--repo-dir`
-`~/.dbgpt/configs/` 下生成 provider 配置文件
-`~/.dbgpt/` 下准备 DB-GPT home 目录
- 给出一个基于生成 profile 的 webserver 启动命令
## 安装完成后启动 DB-GPT
安装完成后,使用生成的 profile 配置启动 webserver
<CommandCopyCard command={`cd ~/.dbgpt/DB-GPT && uv run dbgpt start webserver --config ~/.dbgpt/configs/<profile>.toml`} />
然后打开 [http://localhost:5670](http://localhost:5670)。
## 验证安装是否成功
如果满足以下条件,就说明安装成功:
- webserver 启动时没有配置错误
- Web UI 能在 `http://localhost:5670` 打开
- 你可以在浏览器中发起聊天
## 先查看安装脚本
如果你希望先审查脚本内容,再决定是否执行:
```bash
curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh -o install.sh
less install.sh
bash install.sh --profile openai
```
## 其他安装方式
如果安装脚本不适合你的环境:
- 使用 [CLI 安装](/docs/getting-started/cli-quickstart),通过 PyPI 安装并使用 `dbgpt` 命令
- 使用 [源码安装](/docs/getting-started/deploy/source-code),用于开发、调试和自定义部署
## 故障排查
### 安装脚本不适合我的 shell 或平台
请改用 [CLI 安装](/docs/getting-started/cli-quickstart) 或 [源码安装](/docs/getting-started/deploy/source-code)。
### 我想更细粒度地控制依赖和配置
请使用 [源码安装](/docs/getting-started/deploy/source-code)。它会暴露完整仓库结构和 `uv sync` 安装流程。
### 安装完成了,但 DB-GPT 启动不正常
先检查 `~/.dbgpt/configs/` 下生成的配置文件,然后参考 [安装问题排查](/docs/getting-started/troubleshooting/installation)。

View File

@@ -521,63 +521,11 @@ const sidebars = {
label: "Installation",
collapsed: false,
collapsible: false,
link: {
type: "generated-index",
description: "DB-GPT supports source code, Docker, and cluster deployment modes.",
slug: "installation",
},
link: { type: "doc", id: "installation/index" },
items: [
{ type: "doc", id: "installation/sourcecode" },
{ type: "doc", id: "installation/docker" },
{ type: "doc", id: "installation/docker_compose" },
{ type: "doc", id: "installation/docker-build-guide" },
{
type: "category",
label: "Model Service Deployment",
items: [
{ type: "doc", id: "installation/model_service/stand_alone" },
{ type: "doc", id: "installation/model_service/cluster" },
{ type: "doc", id: "installation/model_service/cluster_ha" },
],
},
{
type: "category",
label: "Other Integrations",
collapsed: true,
collapsible: true,
items: [
{ type: "doc", id: "installation/integrations" },
{
type: "category",
label: "Datasource Integrations",
items: [
{ type: "doc", id: "installation/integrations/mysql_install" },
{ type: "doc", id: "installation/integrations/sqlite_install" },
{ type: "doc", id: "installation/integrations/clickhouse_install" },
{ type: "doc", id: "installation/integrations/postgres_install" },
{ type: "doc", id: "installation/integrations/duckdb_install" },
{ type: "doc", id: "installation/integrations/hive_install" },
{ type: "doc", id: "installation/integrations/mssql_install" },
{ type: "doc", id: "installation/integrations/oracle_install" },
{ type: "doc", id: "installation/integrations/oceanbase_install" },
{ type: "doc", id: "installation/integrations/gaussdb_install" },
{ type: "doc", id: "installation/integrations/doris_install" },
{ type: "doc", id: "installation/integrations/starrocks_install" },
{ type: "doc", id: "installation/integrations/vertica_install" },
],
},
{
type: "category",
label: "RAG Integrations",
items: [
{ type: "doc", id: "installation/integrations/graph_rag_install" },
{ type: "doc", id: "installation/integrations/oceanbase_rag_install" },
{ type: "doc", id: "installation/integrations/bm25_rag_install" },
{ type: "doc", id: "installation/integrations/milvus_rag_install" },
],
},
],
},
{ type: "doc", id: "installation/quick-install", label: "Quick Install" },
{ type: "doc", id: "getting-started/cli-quickstart", label: "CLI Install" },
{ type: "doc", id: "getting-started/deploy/source-code", label: "Source Install" },
],
},
],